IPTV AND VOD NETWORK ARCHITECTURES. Diogo Miguel Mateus Farinha

Size: px
Start display at page:

Download "IPTV AND VOD NETWORK ARCHITECTURES. Diogo Miguel Mateus Farinha"

Transcription

1 IPTV AND VOD NETWORK ARCHITECTURES Diogo Miguel Mateus Farinha Instituto Superior Técnico Av. Rovisco Pais, Lisboa, Portugal ABSTRACT IPTV and Video on Demand are, nowadays, two promissory services, capable of helping operators to support the loss of profit in fix phone market. The major problem of the Video on Demand is how it can be delivered to clients. A real Video on Demand system, where each client can watch the video he wants and whenever he wants, requires huge bandwidth resources. At this context, operators try to develop some solutions to make their networks more scalable. This work proposes a new architecture to organize video servers in the network, based on peer-to-peer models. This architecture will be tested in a network simulator, as well as the operator s solution. Tests done in this work demonstrate that P2P distributed architecture can reduce the utilization of bandwidth in the IP/MPLS core, keeping or reducing time needed to satisfy requests. Key-words: IPTV, Video on Demand, architectures of networks, peer-to-peer, simulation 1. INTRODUCTION Although the video digitalization isn t recent, the existent networks weren t reliable to support this kind of services. With the great advances in technology, concerning the video codification and access networks, these services become attractive to operators and clients. Services like IPTV and VoD require huge amounts of bandwidth to operators network. Nowadays, operators are evolving their network to a new generation network using access technologies like Fiber-To-The-Home/Building/Curb (FTTx). But current network need to be adapted to assure that these services can be delivery now. There are several architectures to accomplish this goal. In this work there will be analyzed 2 types, centralized and distributed based on P2P topologies. The operator, whose network serves as a base to this work, adopted a centralized solution. In this work it will be proposed and simulated a distributed alternative 2. STATE OF ART In this chapter it will be presented the results of the survey made in terms of networks architectures for providing the services referred. This survey was made in terms of centralized and distributed architectures Centralized Solutions In terms of centralized solutions, this paper will present two different solutions. The first is Content Distribution Network (CDN) and the second is Multicast Content Distribution Network CDN are used since several years in Internet for content distribution, to reduce the time for content acquisition from clients [1]. To do this some strategically edge servers are placed in the network and clients get their contents from these instead from central server. There are some central servers somewhere in the network where in first time contents are placed. Then these contents are replicated to distributed servers according to some policies. Client s requests are then forwarded to these edge servers where the contents they want are allocated Multicasting Multicast is the major technique for IPTV delivery. It can deliver efficiently in the network some data streaming from a sender to multiple receivers. There are some different approaches in multicast [2], one-to-all unicast, Applicationlevel multicast and explicit multicast. 2.2 Distributed Solutions Centralized solutions present some limitations, in terms of scalability, especially in operator s networks where bandwidth is an extremely value resource. In order to improve bandwidth usage it can be used a peer-to-peer network topology. A peer-to-peer network is a distributed network that combines a group of distributed, heterogenic 1

2 and independent peers who share between then resources like storage capability or objects [3] Plaxton In a Plaxtron [4] network, videos and servers have identifiers independents of their location and semantic properties. These identifiers are random and have a dimension of 160 bits. It is assumed in this topology that identifiers are uniformly distributed thru the servers and videos identifiers space. Each server has a neighborhood table where it has the IDs of the closest servers. There is another table in each server where are identified the known servers and theirs videos. In terms of organization the videos are organized in trees. When a server S wants to publish a video O, this server sends a message to the root server of video O. During the path to the root server all servers where the message pass update their tables with the information that the video O is in the server S. When a server is looking for a video it sends a message to the root of that video, but if that message passes in a server where the information is already available the request is satisfied Tapestry Tapestry [5][6], is a self-organized and scalable topology to object location and request routing. This topology allows routing a request to the nearest copy of a given object, balancing at same time requests. The routing mechanisms of Tapestry are based on Plaxton, disposing of some other to improve scalability and availability and fail resistance. Like in Plaxton, each server in tapestry has a table with his neighbors. The difference is that beside this each server has a reference to all servers that reference him as a neighbor. The videos in this topology are organized as trees, but there is a great diference to Plaxton. In Plaxton a video can only have a root for his tree, and in Tapestry it can have several. The location mechanism is similar to the one in Plaxton. There is a diference in terms of video location. In both topologies we can have multiple copies of a video in the network, but in Plaxton a server has only the location of the closest video in the network, while tapestry stores all locations of the video. Not always the closest copy of the video is the best to get, for example the server that has it can be overloaded with requests, so its better to get a copy of the video that is in a far but free server Pastry In a Pastry network [7], each server has an identifiers with 128 bits created randomly and distributed uniformly in the server s identifier space. Once again like in some other topologies it uses a hash function on server IP or public key. Each server has a routing table with the others server in the network s IP. This routing table organizes the servers in layers. In the layer n are the servers, which share n bits in the identifiers with the server who own the table, and so on. In this topology all the videos have and identifiers just like the servers. When a request for a video V is made, it is sent to the server which identifiers is closer to V Chord In Chord [8], each server has an identifier that results from the application of a hash function to his IP. Videos have and identifier too resulting from the application of a hash function to it s key. It is pretended to distribute uniformly the identifiers of the videos and server thru the identifiers space. Server s identifiers are ordered increasingly and placed in a ring. Videos are then placed in the server whose ID is equal or immediately higher then his ID. Each server has a routing table with the information of the next server in the ring. This means that each server has only a part of the routing information and don t know all network. When a server receives a request for a video it looks in his routing table for the next server in the ring and re-sends the request to him until it reaches his destination. The video requested is then sent back thru this route Content Addressable Network Content Addressable Network (CAN) [9] is a distributed peer-to-peer topology organized in a multidimensional cartesian space. This space is divided between all servers. Each of these servers is represented by his IP address, and has a routing table with all his neighbors and their location on the cartesian space. All keys of videos in this topology are mapped in the cartesian space using an hash function. When a server wants to locate a video, it uses this hash function in that video key. Then searches in his routing table for which neighbor he should send the message. The neighbor who receives the messages does exactly the same thing until the message reaches its destination Kademlia Kademlia [10] topology follows the same approach as previous topologies concerning the attribution of identifiers. Each server and video in the network has an identifier. Videos are stored in the server who has the closest identifiers. To locate the server, it is used a metric based on XOR between servers IDs. Each server has a list with the servers that have a determined distance from him. These lists are identified as k-buckets and are used to route the request to its destination. 2

3 2.2.7 Viceroy Viceroy [11] is decentralized peer-to-peer topology used to find and locate objects. It uses consistent hash functions [29] to distribute videos for a group of servers uniformly. Like is chord, servers are aligned in a ring ordered by their identifiers. Videos have keys too, and each of these videos is stored in the server that has the same or immediately higher identifier. The difference to Chord is those servers are in more then one ring. This allows a server to send a message not only to the next server but also to a distance server that is in another ring. These rings are known as levels Distributed Models Comparison and Evaluation Is the section it will be done a summary comparison between all models referred above. The location and routing system presented by Plaxton topology has several advantages, but also some disadvantages [6]. It can handle fails either from connections or from servers, since the routing mechanism only needs that the next server shares a few bits with this server. In case a server or connection is down the topology can use another way out. All routing is based on information present locally on the server. This can be good but when there is a great amount of routing information on servers, managing these can be inefficient and difficult. The distance that a message travels is proportional to the physical distance of the network in this topology. In other hand since the routing is done based on information on each server it means, as referred before, that each server must have all topology of network represented in his routing tables. Since there is no update algorithm this topology doesn t allow new nodes to join the network. This problem also means that some other information about the network like temporally congestion points can t be used to help routing. Tapestry and Pastry topologies are based in the Plaxton topology, principally in the routing mechanism. Therefore they share the same advantages adding some features to solve Plaxton problems. Both these topologies allow new servers to join the network and some others to leave, increasing this way the system scalability, availability and resilience to faults. Beside this, there are some differences between both approaches. They use the locality concept in the network. Logical path that a message travels is proportional to the physical one. But the way they use to arrive this concept is different, and it is less complex in Pastry [7]. In Chord, the main difference to topologies like Tapestry and Pastry consists in the way that the logical network topology is related to the physical. In a Chord topology there isn t a concept like network locality. Because servers have and identifiers created using and hash function and then are mapped in a ring, this means that close servers in a ring can be distant in the reality. Another advantage is that each server has only a part of the routing information, and doesn t need to know the entire network. This means that the routing system is less complex, and so Chord is probably the simplest topology to implement [8]. In a CAN topology the routing is done only to neighbors servers. This means that each server only has to now few other servers in the network. For large networks this mean that the routing tables in CAN are much less heavier then the ones in a topology like Tapestry or Pastry. Kademlia gets his advantages from the use of the metric XOR to determine the distance between servers [10]. This metric is simetric, so when a server receives a request he can use the information in this request to determine the distance to the server that sent the message. This way, servers get information from network topology quickly then in other solutions. Viceroy approach is influenced by Chord. Both use identifiers for servers, and then place then in a ring to route the messages. The big difference is that Viceroy has more then one ring, or level, and so can route messages quickly then Chord. 3. SYSTEM ARCHITECTURE In this section of the paper it will be detailed all the developing process of system architecture. In the previous sections were isolated two families of solutions, centralized and distributed based on peer-to-peer models. It will be based on these that the following work will be centered, especially with the proposed architecture based on the distributed models discussed above. 3.1 Goals and Requirements The goal of this work is to propose an alternative architecture to deliver video services. Looking for the solutions detected in the survey, and analyzing the services, IPTV and VoD, it can be concluded that the Multicast is a good option to use to deliver IPTV. It is efficient for delivering a stream of data from a sender to multiple receivers and that is basically the objective of this service. In other hand there is the VoD service. This service has a different nature from IPTV. It is a unicast service, meaning that it will have a different stream for each client. So it is much more exigent in terms of resources from the network. Taking this into count, from now on this work will focus on proposing and distributed architecture for the VoD service. In terms of requirements, it is important to have a network prototype as close as possible to network operators. This will help to get results as close as the ones got in a real network. 3

4 3.2 Operator s Network 12/+& '/4& '/0& The network from a telecommunication operator presents topically and hierarchic topology. It is divided in levels, Core, Service Routing 1 and Service Routing 2. To deliver a service like VoD, operator uses some video servers organized in clusters. Each cluster must have enough servers so that in case of fail in some the other can handle the service. In figure 3.1 there is a generic scheme of architecture from a telecommunication operator. 12/+& '/4& '/0&.2/3+& *+,-+.-& 5"67%8& 9(78:8& ;%:8& 1$:<(%& ;%:8&'=>& D-SERVERS IP/MPLS.2/3+& V-SERVERS REGIONAL CENTER Figure 3-2 Architecture after first decentralization phase *+,-+.-& 5"67%8& 9(78:8& ;%:8& 1$:<(%& ;%:8&'=>& IP/MPLS Figure 3-1 Generic architecture from a telecommunication operator to deliver VoD service. Looking to figure 3.1, it is possible to see that in a earlier phase the VoD service will be delivered from the core level to all clients. This has some advantages as: Low costs of Operation and Maintenance; Easy to implement and capable of supporting and early phase of the service; But as some disadvantages as: Extremely high costs to scale; Requires extremely high resources to core network, like bandwidth; Excessively centralized; The problem is that when the number of clients increases greatly this solution wont be efficient. So the operator will distribute the video server thru the Service Routing 1 (SR1) level, figure 3-2. This decentralization minimizes the resources required from core level and is more scalable, but has bigger Operation and Maintenance costs. The problem once again is when the number of clients increases as before. When it happens, this solution will suffer from same problems as previous. So operator proceeds to another decentralization, this time placing video servers in SR2, figure /3+& *+,-+.-& 5"67%8& 9(78:8& ;%:8& 1$:<(%& ;%:8&'=>& D-SERVERS V-SERVERS 12/+& REGIONAL CENTER Figure 3-3 Last decentralization phase with installation of server in SR2 level. This is the last decentralization phase possible for now cause SR2 is the last routing level, and after this level there is only DSLAMs which don t work on IP level for now, on this operator network, and the client house. But for legal reasons it isn t possible to store videos on client s house. 3.3 Network Architectures IP/MPLS Considering the evolution strategy of the operator, it will be proposed in this work a different architecture for the video servers placed on SR2 level. This is because the operator already has servers installed in level SR1, so these must be re-used to reduce the investment. This architecture will be simulated and compared with the one adopted by the operator for SR2 level. '/4& D-SERVERS V-SERVERS REGIONAL CENTER '/0& 4

5 3.3.1 Centralized The architecture for video server on SR2 level adopted by the operator is a centralized architecture. Since there are already servers installed on SR1 level these will work as server and the one in SR2 level will work as clients to these, figure 3-4. In this case each of the video servers cluster in the SR2 routers is responsible for a group of videos, which are available not only to the clients hierarchically dependent of it but to the clients from other clusters. When a server responsible for a video receives a request for that video and doesn t have it in cache, it is responsible for getting it from the superior level. When a request is made to some server in SR2 level, it cooperates with other servers in same level to satisfy this request reducing the resources consumed from superior levels. To perform this all the topologies studied in the state of art chapter where analyzed. The topology chosen was Chord, because it can be adjusted to the topology of operator network and it is simple and easy to implement. Chord Figure 3-4 Scheme of centralized architecture in SR1 and SR2 level Although this topology was explained in a previous chapter, there were some adaptations to it made in this work. In this topology all servers and videos have and identifiers. In each SR2 router is installed a cluster of servers. These servers are responsible to satisfy all clients from the zone served by that router. When a cluster hasn t the video requested, it does a request to the SR1 cluster for that video. If this SR1 server doesn t have that video, the request will have to travel to the core Distributed The alternative proposed in this work is a distributed approach base on a peer-to-peer topology. In this approach all servers in SR2 level work as a server besides being clients from SR1, figure 3.5. There are groups of SR2 servers that work together to satisfy the client s requests from those servers. Figure 3-6 Chord architecture scheme In order to choose the identifiers of servers, it is needed to know the number of clients in each cluster s router. The clusters that serve a bigger number of clients have more resources, in terms of bandwidth. The more bandwidth the server has, the more clients it can serve simultaneously. So server with more resources will store more videos. To assure that the servers with more resources have more videos, the identifiers space is splited among servers from a peer-topeer group proportionally to the resources they have. Servers are then place in a ring, and videos are stored in the server that has the same or immediately higher identifier, figure 3.6. Figure 3-5 Scheme of distributed architecture in SR1 and SR2 level 5

6 3.3.3 Network prototype In order to simulate both types of solution explained above a network prototype is required. This must be similar to the real network of the operator. Video Servers In the operator s network there are different types of servers, depending of the type of service supplied. Since in this work it will only be considered VoD service, only servers for this server will be considered. These servers have a capacity of storing 1000 hours of videos, and allow an 800 Mbps streaming rate. In this work the streaming rate used in each cluster will depend of the number of clients each cluster has to serve. Core Network The Core network of the operator, and adapted to the prototype created consists of four routing locations connect between then. These locations will then aggregate all router from SR1 level. Service Routing 1 The next level in the network is SR1. Is has a number of routers aggregated by core. It has 20 routers, placed in several locations of the network. Each of these routers connects to 2 different core routers, so there is redundancy. Service Routing 2 This is the last routing level. There are 80 routers in this level, aggregated by SR1 level. Each of these routers is connected to 2 different routers in SR1 level. 3.4 System Components In previous chapter were defined the architectures to simulate and the network prototype were these will be simulated. Now it will be present the system components that implements these architectures and theirs functions Overview The components of the system are represented in figure 3.7. The principal modules are the video servers management module, the clients/request generator and the cache module. Figure 3-7 Generic system architecture component model Simulator The Simulator used in this work wasn t developed, but instead chosen from a group of existent simulators. The criteria and justification for this choice is presented in the chapter Video Servers Management Module As referred before, it s at the level of video servers architectures that this work is concentrated. Since servers in all levels of network have different functions, it was chosen to develop different modules according to these functions. Basic Concepts There are some considerations that must be presented before detailing the modules. It was initially planed to simulate the architectures using real video streams, but with the great number of nodes of this network this options was abandoned. So to simulate the requests and video streaming they are used some packet that include information about the type of video requested and name. A server that receives these packets reserves resources to serve the request, and that server that sends this packet will receive later an ok pack and then reserves the resources required for the streaming. The other consideration is that the number of servers and locations is always the same during the simulations and doesn t change. All servers know the topology and position of all other servers in the network. This was introduced to simplify the simulation. Core SR1 Module Video servers at levels Core and SR1 execute this module. These receive requests, seek on their caches for the requested video and stream it. The only difference is that not always servers at level SR1 have the requested videos. In 6

7 other hand Core servers always have all contents so they only receive requests, while SR1 servers may perform some requests to Core. The use of this module is equal for centralized architecture in operator s architecture and for the one distributed proposed in this work. This happens because as referred before, the architecture proposed is only for level SR2. Chord SR2 Module The topology chord was already detailed in this paper, so only implementations details will be referred. Servers in SR2 are combined in peer-to-peer groups, to serve client s requests without sending requests to superior network levels. In this network prototype, a chord group is constituted by the clusters in SR2, which are aggregated by the same SR1 router. When a server S receives a request it checks if it is the responsible server for that video in the group. If it is and has the video in cache streams the video otherwise makes a request to the SR1 server for that video. If a serves S that receives a video request isn t the responsible for it in the groups, it calculates who is this server R and re-sends the request to it. The server R is now responsible to stream the video to client. It was developed a second version of this module. In this version when a server S receives a request for a video V that isn t of his responsibility, it finds who is the server R responsible. Then this server R instead of streaming the video directly to client streams it to server S who stores it in cache, streaming it to the client simultaneously. This second version needs obviously more resources then the first one. SERVER SR2 Module The functions this module implements are similar to Core SR1 Module. It receives requests, from the module that simulates the clients, search in his cache for the video requested and streams it in case it is available. Otherwise send a request to the superior servers requesting it. will response to client in behalf of server S. So in this version, video servers only store in cache the video that they are responsible for. If in the second version the server S hasn t the video requested in cache, it finds the server R in the group responsible for that video and sends a request to it. This server R now instead of streaming directly to the client, streams the video to the server S. This server S stores the video in cache streaming it at same time to the client. So in this second version server have two kinds of videos in cache. Those who are of its responsibility in the group, and those not from its responsibility but that had been requested from a client of its SR2 router. The first ones stay always in cache, if possible. The last ones have the same popularity model between then, that is used in the centralize model Clients Simulation When specifying network prototype the last hierarchical level specified was SR2. But this level is only responsible for aggregating DSLAMs, and these for aggregating clients. So in this work client simulation is done on SR2 level, to reduce complexity Request Generator Module Each client in the network realizes a number of requests for videos along simulation time. The telecommunication operator estimates that there will be a maximum simultaneity rate of 10%. This means that at top of simulation there will 10% of clients being served. The requests number depends on the time of day and, this percentage is represented on figure Cache/ Storage Module All video servers in all levels of the network have a cache model. The model used in a centralized architecture is based in a popularity model. When a video is requested to a server S it checks its cache for that video. If it is there its popularity is increased and is streamed to the client. If not, server S resends the request to the hierarchically higher server H. In a distributed architecture there are two version of cache model, one for each version considered in the Chord SR2 module. In the first version a client sends a request to the server S. If this server S is responsible for the video checks its cache and streams the video if available. If not, finds the responsible server R in the peer-to-peer group for that video and re-sends the request to it. These servers R Figure 3-8 Percentage of requests during a day When a request is generated there are several options that must be made. These are based in percentages, and concern the type of content and video. The options are schematized in figure

8 J-Sim [16] The last simulator analyzed is J-Sim. It is very similar to SSFNET so is a good option for this work. It allows to easily add the developed modules. In terms of network creation, it is even simpler then in SSFNET. For all these reason J-Sim was the chosen network simulator in this work. Figure 3-9 Options this module has to do when generating a new content. The time between consecutive request are simulate with base on Poisson model [12]. 3.5 Simulator In order to simulate architectures it was done a survey for existent network simulators. There were defined some criteria to select a group of simulators and then to chose the best among then. These criteria were: Support for adding extra modules that allow simulating the topologies and protocols required; Support the construction of hierarchical network topologies; Easiness to add and integrate extra modules; Based on these tree requirements there were chosen four simulators. OPNET [13] This commercial simulator has a good interface and allows the construction of hierarchical networks. The problem with this server is that it s hard to develop and integrate news modules in it, so after trying, it was discarded for this work. NS2 [14] Network Simulator-2 is one of the must used network simulator in network investigation. The problem with this simulator is that it s hard to construct the kind of networks requires and to integrate some extra modules developed externally. SSFNET [15] This simulator can fulfill all the requirements referred before. It s not complex to create the networks required and to add, and integrate some external modules. 3.6 Evaluation Metrics To evaluate the results of the simulation some metrics must be defined to compare the architectures. There were defined tree types of metrics. The first one concerns the evaluation of video servers occupation. The second pretend to evaluate the occupation of the different network level, Core, SR1 and SR2. The third and last is a temporal metric that evaluates the time necessary to find a video in each of the architectures. 4.1 Test Scenarios 4. TESTS AND RESULTS The tests were realized with a population of Clients and 5000 hours of contents, representing 2500 videos considering each video taking 2 hours. They were considered six solutions, with and without previous distribution of more popular contents: - Centralized architecture; (Centralized) - Distributed based on Chord, first version, where servers only store the videos that they are its responsibility; (Chord V1) - Distributed based on Chord, second version, where each serve stores not only the videos they are responsible for but the ones asked for clients they are responsible for; (Chord V2) 4.2 Results Figure 4-1 Median server occupations of all servers during the 10 days simulation. In terms of bandwidth occupation the results in the figure 4-2 show that centralized architecture without previous distribution of more popular contents is the worst solution. 8

9 Figure 4-4 Temporal sequence of median occupation in servers of level SR1 level for the 10 days simulation time, in a centralized architecture. Figure 4-2 Median occupations of all servers in five best solutions for the 10 hours simulation time. To get a better view of server s occupation it is presented the same results of figure 4-3, but this time with only the 5 best solutions. Between these 5 solutions, distributed P2P based architectures have the best results. Between these 2, Chord V1 has less bandwidth occupation. This corroborates the bases concerning the development of distributed architectures were developed. In first version the server S that receives the request from client, re-sends this request to the server R responsible for the video, which responds to client. In second version this server R streams the video to the server S, and this streams the video to the client. So there is more band consumption in this second architecture. Figure 4-5 Temporal sequence of median occupation in servers of level SR1 level for the 10 days simulation time, in a distributed architecture. Analyzing both temporal sequences we concluded that in a distributed architecture after fifth day videos are distributed in P2P levels so there are almost no accesses to SR1 servers. In the centralized architecture, it is easy to see that the access to SR1 servers continue during all simulation time because the videos aren t totally distributed to all servers. Figure 4-3 Median occupation percentages of servers of level SR1 in the network for the 10 days simulation time. Looking now for median occupation of SR1 network level, it is quick to analyze that centralized solutions occupies much more bandwidth the decentralized solutions. This happens because in distributed architectures once videos are distributed thru all P2P groups the access to servers in upper levels is residual. In the next figure it is visible the temporal sequence of occupation in SR1 servers during the total simulation time (10 days). Figure 4-6 Median percentage of occupation of IP/MPLS core servers, during total simulation time (240 hours). Figure 4-7 Median percentage of occupation of IP/MPLS core servers for the 5 best solutions, during all simulation time (240 hours). These last results, occupation of Core IP/MPLS level, corroborate the reduction in the bandwidth consumed for the core IP/MPLS level in a distributed architecture. It happens 9

10 the same as in the SR1 servers. With the reduction in these, the access to core level is reduced too. Figure 4-8 Median percentage times of requests satisfaction Last results (Figure 4-8) allows a comparison between all solutions in terms if mean time to response to a client request. This is the time that architectures need to find videos requested by clients. 5. CONCLUSIONS Tests made and results presented in this work allows to take some conclusion in terms of comparison between the operator s solution and the one proposed in this work. The centralized architecture has a reduced time in terms of client s response, but has an expensive utilization of bandwidth in SR1 and Core IP/MPLS. The distributed architectures based on P2P topologies present a reduction of the bandwidth required in SR1 and Core IP/MPLS. This happens because videos are distributed among groups and so the traffic that travels to upper level is reduce, becoming residual once almost all videos are among servers in SR2 level. There is a difference between both distributed architectures. The first version Chord V1 has a drawback in terms of time to serve clients. To solve this limitation a second version was created, Chord V2. It is present in the results that the Chord V1 as indeed low bandwidth utilization, but in other hand has a great delay serving clients. Chord V2 has almost the same bandwidth utilization, but in its favor is the time requested to serve clients requests, that is almost the same as in the centralized architecture. To summarize, it is possible to say that the P2P centralized architecture proposed in this work achieves the objectives of saving bandwidth to SR1 and Core IP/MPLS level and has a good time in terms of response to clients request. 7. REFERENCES [1] Peng G, CDN: Content Distribution Network, State University of New York at Stony Brook, New York [2] Kurose, J. F., K. W. Ross, Computer Networking a Top-Down Approach Featuring the Internet, second edition, chapter 4, pages [3] Pourebrahimi B., K. Bertels, S. Vassiliadis, A survey of peer-to-peer Networks, Computer Engineering Laboratory, ITS, TU Delft, The Netherlands 2002 [4] Plaxton C., R. Rajaraman, A. Richa, Accessing nearby copies of replicated objects in a distributed environment, in Proceedings of the 9th Annual ACM Symposium on Parallel Algorithms and Architectures, [5] Zhao B. Y., L. Huang, J. Stribling, S. C. Rhea, A. D. Joseph, J. D. Kubiatowicz, Tapestry: A resilient global-scale overlay for service deployment, IEEE Journal on Selected Areas in Communications, vol. 22, no. 1, pp , January [6] Zhao B. Y., J. Kubiatowicz, A. D. Joseph, Tapestry: An Infrastructure for fault-tolerant Wide-area Location and Routing Report UCB/CSD , April [7] A. Rowstron, P. Druschel, Pastry: Scalable, distributed object location and routing for large-scale peer-to-peer systems, in Proceedings of the Middleware, [8] Stoica I., R. Morris, D. Karger, M. F. Kaashoek, and H. Balakrishnan, Chord: A scalable peer-to-peer lookup protocol for internet applications, IEEE/ACM Transactions on Networking, vol. 11, no. 1, pp , [9] Ratnasamy S., P. Francis, M. Handley, R. Karp, and S. Shenker, A scalable content addressable network, in Processings of the ACM SIGCOMM, pp , [10] Maymounkov P., D. Mazieres, Kademlia: A peer-topeer information system based on the xor metric, in Processings of the IPTPS, Cambridge, MA, USA, pp , February [11] Malkhi D., M. Naor, D. Ratajczak, Viceroy: a scalable and dynamic emulation of the butterfly, in Processings of the ACM PODC 02, Monterey, CA, USA, pp , July [12] Becchi Michela, From Poisson Processes to Self- Similarity: a survey of Network Traffic Models [Online] last accessed on 19 September 2008 [13] OPNET, Network Simulator, [Online] last accessed on 19 September 2008 [14] Network Simulator 2, Network Simulator, [Online] last accessed on 19 September 2008 [15] SSFNet, Network Simulator [Online] last accessed on 19 September 2008 [16] J-Sim, Network Simulator [Online] last accessed on 19 September

Join and Leave in Peer-to-Peer Systems: The DASIS Approach

Join and Leave in Peer-to-Peer Systems: The DASIS Approach Join and Leave in Peer-to-Peer Systems: The DASIS Approach Keno Albrecht, Ruedi Arnold, Michael Gähwiler, Roger Wattenhofer {kenoa@inf, rarnold@inf, mgaehwil@student, wattenhofer@inf}.ethz.ch Department

More information

Distributed Hash Tables in P2P Systems - A literary survey

Distributed Hash Tables in P2P Systems - A literary survey Distributed Hash Tables in P2P Systems - A literary survey Timo Tanner Helsinki University of Technology tstanner@cc.hut.fi Abstract Distributed Hash Tables (DHT) are algorithms used in modern peer-to-peer

More information

Varalakshmi.T #1, Arul Murugan.R #2 # Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam

Varalakshmi.T #1, Arul Murugan.R #2 # Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam A Survey on P2P File Sharing Systems Using Proximity-aware interest Clustering Varalakshmi.T #1, Arul Murugan.R #2 # Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam

More information

LOOKING UP DATA IN P2P SYSTEMS

LOOKING UP DATA IN P2P SYSTEMS LOOKING UP DATA IN P2P SYSTEMS Hari Balakrishnan, M. Frans Kaashoek, David Karger, Robert Morris, Ion Stoica MIT Laboratory for Computer Science 1. Introduction The recent success of some widely deployed

More information

International Journal of Scientific & Engineering Research, Volume 4, Issue 11, November-2013 349 ISSN 2229-5518

International Journal of Scientific & Engineering Research, Volume 4, Issue 11, November-2013 349 ISSN 2229-5518 International Journal of Scientific & Engineering Research, Volume 4, Issue 11, November-2013 349 Load Balancing Heterogeneous Request in DHT-based P2P Systems Mrs. Yogita A. Dalvi Dr. R. Shankar Mr. Atesh

More information

A PROXIMITY-AWARE INTEREST-CLUSTERED P2P FILE SHARING SYSTEM

A PROXIMITY-AWARE INTEREST-CLUSTERED P2P FILE SHARING SYSTEM A PROXIMITY-AWARE INTEREST-CLUSTERED P2P FILE SHARING SYSTEM Dr.S. DHANALAKSHMI 1, R. ANUPRIYA 2 1 Prof & Head, 2 Research Scholar Computer Science and Applications, Vivekanandha College of Arts and Sciences

More information

GISP: Global Information Sharing Protocol a distributed index for peer-to-peer systems

GISP: Global Information Sharing Protocol a distributed index for peer-to-peer systems GISP: Global Information Sharing Protocol a distributed index for peer-to-peer systems Daishi Kato Computer Science Department, Stanford University Visiting from NEC Corporation Abstract This paper proposes

More information

New Structured P2P Network with Dynamic Load Balancing Scheme

New Structured P2P Network with Dynamic Load Balancing Scheme New Structured P2P Network with Dynamic Load Balancing Scheme Atushi TAKEDA, Takuma OIDE and Akiko TAKAHASHI Department of Information Science, Tohoku Gakuin University Department of Information Engineering,

More information

Discovery and Routing in the HEN Heterogeneous Peer-to-Peer Network

Discovery and Routing in the HEN Heterogeneous Peer-to-Peer Network Discovery and Routing in the HEN Heterogeneous Peer-to-Peer Network Tim Schattkowsky Paderborn University, C-LAB, D-33102 Paderborn, Germany tim@c-lab.de Abstract. Network infrastructures are nowadays

More information

Improving Availability with Adaptive Roaming Replicas in Presence of Determined DoS Attacks

Improving Availability with Adaptive Roaming Replicas in Presence of Determined DoS Attacks Improving Availability with Adaptive Roaming Replicas in Presence of Determined DoS Attacks Chin-Tser Huang, Prasanth Kalakota, Alexander B. Alexandrov Department of Computer Science and Engineering University

More information

Tornado: A Capability-Aware Peer-to-Peer Storage Network

Tornado: A Capability-Aware Peer-to-Peer Storage Network Tornado: A Capability-Aware Peer-to-Peer Storage Network Hung-Chang Hsiao hsiao@pads1.cs.nthu.edu.tw Chung-Ta King* king@cs.nthu.edu.tw Department of Computer Science National Tsing Hua University Hsinchu,

More information

Load Balancing in Structured Overlay Networks. Tallat M. Shafaat tallat(@)kth.se

Load Balancing in Structured Overlay Networks. Tallat M. Shafaat tallat(@)kth.se Load Balancing in Structured Overlay Networks Tallat M. Shafaat tallat(@)kth.se Overview Background The problem : load imbalance Causes of load imbalance Solutions But first, some slides from previous

More information

A P2P SERVICE DISCOVERY STRATEGY BASED ON CONTENT

A P2P SERVICE DISCOVERY STRATEGY BASED ON CONTENT A P2P SERVICE DISCOVERY STRATEGY BASED ON CONTENT CATALOGUES Lican Huang Institute of Network & Distributed Computing, Zhejiang Sci-Tech University, No.5, St.2, Xiasha Higher Education Zone, Hangzhou,

More information

An Efficient Load Balancing Technology in CDN

An Efficient Load Balancing Technology in CDN Issue 2, Volume 1, 2007 92 An Efficient Load Balancing Technology in CDN YUN BAI 1, BO JIA 2, JIXIANG ZHANG 3, QIANGGUO PU 1, NIKOS MASTORAKIS 4 1 College of Information and Electronic Engineering, University

More information

Are Virtualized Overlay Networks Too Much of a Good Thing?

Are Virtualized Overlay Networks Too Much of a Good Thing? Are Virtualized Overlay Networks Too Much of a Good Thing? Pete Keleher, Bobby Bhattacharjee, Bujor Silaghi Department of Computer Science University of Maryland, College Park keleher@cs.umd.edu 1 Introduction

More information

Research on P2P-SIP based VoIP system enhanced by UPnP technology

Research on P2P-SIP based VoIP system enhanced by UPnP technology December 2010, 17(Suppl. 2): 36 40 www.sciencedirect.com/science/journal/10058885 The Journal of China Universities of Posts and Telecommunications http://www.jcupt.com Research on P2P-SIP based VoIP system

More information

Object Request Reduction in Home Nodes and Load Balancing of Object Request in Hybrid Decentralized Web Caching

Object Request Reduction in Home Nodes and Load Balancing of Object Request in Hybrid Decentralized Web Caching 2012 2 nd International Conference on Information Communication and Management (ICICM 2012) IPCSIT vol. 55 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V55.5 Object Request Reduction

More information

A Topology-Aware Relay Lookup Scheme for P2P VoIP System

A Topology-Aware Relay Lookup Scheme for P2P VoIP System Int. J. Communications, Network and System Sciences, 2010, 3, 119-125 doi:10.4236/ijcns.2010.32018 Published Online February 2010 (http://www.scirp.org/journal/ijcns/). A Topology-Aware Relay Lookup Scheme

More information

Krunal Patel Department of Information Technology A.D.I.T. Engineering College (G.T.U.) India. Fig. 1 P2P Network

Krunal Patel Department of Information Technology A.D.I.T. Engineering College (G.T.U.) India. Fig. 1 P2P Network Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Secure Peer-to-Peer

More information

A Performance Comparison of Native IP Multicast and IP Multicast Tunneled through a Peer-to-Peer Overlay Network

A Performance Comparison of Native IP Multicast and IP Multicast Tunneled through a Peer-to-Peer Overlay Network A Performance Comparison of Native IP Multicast and IP Multicast Tunneled through a Peer-to-Peer Overlay Network Marc Brogle, Dragan Milic, Luca Bettosini, Torsten Braun Institute for Computer Science

More information

Load Balancing in Distributed Systems: A survey

Load Balancing in Distributed Systems: A survey Load Balancing in Distributed Systems: A survey Amit S Hanamakkanavar * and Prof. Vidya S.Handur # * (amitsh2190@gmail.com) Dept of Computer Science & Engg, B.V.B.College of Engg. & Tech, Hubli # (vidya_handur@bvb.edu)

More information

A Self-Managing SIP-based IP Telephony System based on a P2P approach using Kademlia

A Self-Managing SIP-based IP Telephony System based on a P2P approach using Kademlia A Self-Managing SIP-based IP Telephony System based on a P2P approach using Kademlia Felipe de Castro Louback Rocha 1, Linnyer Beatriz 1 Programa de Pós Graduação em Engenharia Elétrica, Universidade Federal

More information

Peer-to-Peer Replication

Peer-to-Peer Replication Peer-to-Peer Replication Matthieu Weber September 13, 2002 Contents 1 Introduction 1 2 Database Replication 2 2.1 Synchronous Replication..................... 2 2.2 Asynchronous Replication....................

More information

SCALABLE RANGE QUERY PROCESSING FOR LARGE-SCALE DISTRIBUTED DATABASE APPLICATIONS *

SCALABLE RANGE QUERY PROCESSING FOR LARGE-SCALE DISTRIBUTED DATABASE APPLICATIONS * SCALABLE RANGE QUERY PROCESSING FOR LARGE-SCALE DISTRIBUTED DATABASE APPLICATIONS * Maha Abdallah LIP6, Université Paris 6, rue du Capitaine Scott 75015 Paris, France Maha.Abdallah@lip6.fr Hung Cuong Le

More information

DUP: Dynamic-tree Based Update Propagation in Peer-to-Peer Networks

DUP: Dynamic-tree Based Update Propagation in Peer-to-Peer Networks : Dynamic-tree Based Update Propagation in Peer-to-Peer Networks Liangzhong Yin and Guohong Cao Department of Computer Science & Engineering The Pennsylvania State University University Park, PA 16802

More information

New Algorithms for Load Balancing in Peer-to-Peer Systems

New Algorithms for Load Balancing in Peer-to-Peer Systems New Algorithms for Load Balancing in Peer-to-Peer Systems David R. Karger Matthias Ruhl MIT Laboratory for Computer Science Cambridge, MA 02139, USA {karger, ruhl}@theory.lcs.mit.edu Abstract Load balancing

More information

Exploring the Design Space of Distributed and Peer-to-Peer Systems: Comparing the Web, TRIAD, and Chord/CFS

Exploring the Design Space of Distributed and Peer-to-Peer Systems: Comparing the Web, TRIAD, and Chord/CFS Exploring the Design Space of Distributed and Peer-to-Peer Systems: Comparing the Web, TRIAD, and Chord/CFS Stefan Saroiu, P. Krishna Gummadi, Steven D. Gribble University of Washington Abstract: Despite

More information

Optimizing and Balancing Load in Fully Distributed P2P File Sharing Systems

Optimizing and Balancing Load in Fully Distributed P2P File Sharing Systems Optimizing and Balancing Load in Fully Distributed P2P File Sharing Systems (Scalable and Efficient Keyword Searching) Anh-Tuan Gai INRIA Rocquencourt anh-tuan.gai@inria.fr Laurent Viennot INRIA Rocquencourt

More information

PROPOSAL AND EVALUATION OF A COOPERATIVE MECHANISM FOR HYBRID P2P FILE-SHARING NETWORKS

PROPOSAL AND EVALUATION OF A COOPERATIVE MECHANISM FOR HYBRID P2P FILE-SHARING NETWORKS PROPOSAL AND EVALUATION OF A COOPERATIVE MECHANISM FOR HYBRID P2P FILE-SHARING NETWORKS Hongye Fu, Naoki Wakamiya, Masayuki Murata Graduate School of Information Science and Technology Osaka University

More information

LOAD BALANCING WITH PARTIAL KNOWLEDGE OF SYSTEM

LOAD BALANCING WITH PARTIAL KNOWLEDGE OF SYSTEM LOAD BALANCING WITH PARTIAL KNOWLEDGE OF SYSTEM IN PEER TO PEER NETWORKS R. Vijayalakshmi and S. Muthu Kumarasamy Dept. of Computer Science & Engineering, S.A. Engineering College Anna University, Chennai,

More information

Identity Theft Protection in Structured Overlays

Identity Theft Protection in Structured Overlays Identity Theft Protection in Structured Overlays Lakshmi Ganesh and Ben Y. Zhao Computer Science Department, U. C. Santa Barbara {lakshmi, ravenben}@cs.ucsb.edu Abstract Structured peer-to-peer (P2P) overlays

More information

A Survey and Comparison of Peer-to-Peer Overlay Network Schemes

A Survey and Comparison of Peer-to-Peer Overlay Network Schemes % " #$! IEEE COMMUNICATIONS SURVEY AND TUTORIAL, MARCH 2004 1 A Survey and Comparison of Peer-to-Peer Overlay Network Schemes Eng Keong Lua, Jon Crowcroft, Marcelo Pias, Ravi Sharma and Steven Lim Abstract

More information

Motivation for peer-to-peer

Motivation for peer-to-peer Peer-to-peer systems INF 5040 autumn 2007 lecturer: Roman Vitenberg INF5040, Frank Eliassen & Roman Vitenberg 1 Motivation for peer-to-peer Inherent restrictions of the standard client/server model Centralised

More information

8 Conclusion and Future Work

8 Conclusion and Future Work 8 Conclusion and Future Work This chapter concludes this thesis and provides an outlook on future work in the area of mobile ad hoc networks and peer-to-peer overlay networks 8.1 Conclusion Due to the

More information

Identity Theft Protection in Structured Overlays

Identity Theft Protection in Structured Overlays Appears in Proceedings of the 1st Workshop on Secure Network Protocols (NPSec 5) Identity Theft Protection in Structured Overlays Lakshmi Ganesh and Ben Y. Zhao Computer Science Department, U. C. Santa

More information

A Load Balancing Method in SiCo Hierarchical DHT-based P2P Network

A Load Balancing Method in SiCo Hierarchical DHT-based P2P Network 1 Shuang Kai, 2 Qu Zheng *1, Shuang Kai Beijing University of Posts and Telecommunications, shuangk@bupt.edu.cn 2, Qu Zheng Beijing University of Posts and Telecommunications, buptquzheng@gmail.com Abstract

More information

Towards a scalable ad hoc network infrastructure

Towards a scalable ad hoc network infrastructure Towards a scalable ad hoc network infrastructure Ansley Post abpost@rice.edu Rice University, Houston, TX, USA Abstract As wirelessly networked devices become more pervasive, large scale mobile ad hoc

More information

Peer-to-Peer Networks. Chapter 6: P2P Content Distribution

Peer-to-Peer Networks. Chapter 6: P2P Content Distribution Peer-to-Peer Networks Chapter 6: P2P Content Distribution Chapter Outline Content distribution overview Why P2P content distribution? Network coding Peer-to-peer multicast Kangasharju: Peer-to-Peer Networks

More information

Locality-Aware Randomized Load Balancing Algorithms for DHT Networks

Locality-Aware Randomized Load Balancing Algorithms for DHT Networks Locality-Aware ized Load Balancing Algorithms for DHT Networks Haiying Shen and Cheng-Zhong Xu Department of Electrical & Computer Engineering Wayne State University, Detroit, MI 4822 {shy,czxu}@ece.eng.wayne.edu

More information

SUITABLE ROUTING PATH FOR PEER TO PEER FILE TRANSFER

SUITABLE ROUTING PATH FOR PEER TO PEER FILE TRANSFER SUITABLE ROUTING PATH FOR PEER TO PEER FILE TRANSFER R. Naga Priyadarsini, S. Suma and V. Dhanakoti Department of Computer Science Engineering, Valliammai Engineering College, Kanchipuram, India ABSTRACT

More information

1.1. Abstract. 1.2. VPN Overview

1.1. Abstract. 1.2. VPN Overview 1.1. Abstract Traditionally organizations have designed their VPN networks using layer 2 WANs that provide emulated leased lines. In the last years a great variety of VPN technologies has appeared, making

More information

International journal of Engineering Research-Online A Peer Reviewed International Journal Articles available online http://www.ijoer.

International journal of Engineering Research-Online A Peer Reviewed International Journal Articles available online http://www.ijoer. RESEARCH ARTICLE ISSN: 2321-7758 GLOBAL LOAD DISTRIBUTION USING SKIP GRAPH, BATON AND CHORD J.K.JEEVITHA, B.KARTHIKA* Information Technology,PSNA College of Engineering & Technology, Dindigul, India Article

More information

Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network

Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network Jian Ni, Danny H. K. Tsang, Ivan S. H. Yeung, Xiaojun Hei Department of Electrical & Electronic Engineering Hong Kong University

More information

Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities

Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities Kavitha Ranganathan, Adriana Iamnitchi, Ian Foster Department of Computer Science, The University

More information

File sharing using IP-Multicast

File sharing using IP-Multicast File sharing using IP-Multicast Kai Trojahner, Peter Sobe University of Luebeck, Germany Institute of Computer Engineering email: sobe@iti.uni-luebeck.de Abstract: File sharing systems cause a huge portion

More information

Content Distribution over IP: Developments and Challenges

Content Distribution over IP: Developments and Challenges Content Distribution over IP: Developments and Challenges Adrian Popescu, Blekinge Inst of Technology, Sweden Markus Fiedler, Blekinge Inst of Technology, Sweden Demetres D. Kouvatsos, University of Bradford,

More information

Multicast vs. P2P for content distribution

Multicast vs. P2P for content distribution Multicast vs. P2P for content distribution Abstract Many different service architectures, ranging from centralized client-server to fully distributed are available in today s world for Content Distribution

More information

P2P VoIP for Today s Premium Voice Service 1

P2P VoIP for Today s Premium Voice Service 1 1 P2P VoIP for Today s Premium Voice Service 1 Ayaskant Rath, Stevan Leiden, Yong Liu, Shivendra S. Panwar, Keith W. Ross ARath01@students.poly.edu, {YongLiu, Panwar, Ross}@poly.edu, Steve.Leiden@verizon.com

More information

Load Balancing in Structured P2P Systems

Load Balancing in Structured P2P Systems 1 Load Balancing in Structured P2P Systems Ananth Rao Karthik Lakshminarayanan Sonesh Surana Richard Karp Ion Stoica ananthar, karthik, sonesh, karp, istoica @cs.berkeley.edu Abstract Most P2P systems

More information

Chord - A Distributed Hash Table

Chord - A Distributed Hash Table Kurt Tutschku Vertretung - Professur Rechnernetze und verteilte Systeme Chord - A Distributed Hash Table Outline Lookup problem in Peer-to-Peer systems and Solutions Chord Algorithm Consistent Hashing

More information

CHAPTER 6. VOICE COMMUNICATION OVER HYBRID MANETs

CHAPTER 6. VOICE COMMUNICATION OVER HYBRID MANETs CHAPTER 6 VOICE COMMUNICATION OVER HYBRID MANETs Multimedia real-time session services such as voice and videoconferencing with Quality of Service support is challenging task on Mobile Ad hoc Network (MANETs).

More information

Approximate Object Location and Spam Filtering on Peer-to-Peer Systems

Approximate Object Location and Spam Filtering on Peer-to-Peer Systems Approximate Object Location and Spam Filtering on Peer-to-Peer Systems Feng Zhou, Li Zhuang, Ben Y. Zhao, Ling Huang, Anthony D. Joseph and John D. Kubiatowicz University of California, Berkeley The Problem

More information

IMPACT OF DISTRIBUTED SYSTEMS IN MANAGING CLOUD APPLICATION

IMPACT OF DISTRIBUTED SYSTEMS IN MANAGING CLOUD APPLICATION INTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN ENGINEERING AND SCIENCE IMPACT OF DISTRIBUTED SYSTEMS IN MANAGING CLOUD APPLICATION N.Vijaya Sunder Sagar 1, M.Dileep Kumar 2, M.Nagesh 3, Lunavath Gandhi

More information

David R. McIntyre CS Department, Cleveland State University Cleveland, Ohio 44101

David R. McIntyre CS Department, Cleveland State University Cleveland, Ohio 44101 Data Distribution in a Wireless Environment with Migrating Nodes David A. Johnston EECS Department, Case Western Reserve University Cleveland, Ohio 44106 David R. McIntyre CS Department, Cleveland State

More information

Cooperative Monitoring for Internet Data Centers

Cooperative Monitoring for Internet Data Centers Cooperative Monitoring for Internet Data Centers Kuai Xu Feng Wang Arizona State University Division of Mathematical and Natural Sciences New College of Interdisciplinary Arts & Sciences P.O. Box 371,

More information

RESEARCH ISSUES IN PEER-TO-PEER DATA MANAGEMENT

RESEARCH ISSUES IN PEER-TO-PEER DATA MANAGEMENT RESEARCH ISSUES IN PEER-TO-PEER DATA MANAGEMENT Bilkent University 1 OUTLINE P2P computing systems Representative P2P systems P2P data management Incentive mechanisms Concluding remarks Bilkent University

More information

A Peer-to-Peer File Sharing System for Wireless Ad-Hoc Networks

A Peer-to-Peer File Sharing System for Wireless Ad-Hoc Networks 1 A Peer-to-Peer File Sharing System for Wireless Ad-Hoc Networks Hasan Sözer, Metin Tekkalmaz, and İbrahim Körpeoğlu Abstract File sharing in wireless ad-hoc networks in a peerto-peer manner imposes many

More information

Applying ID-Based Encryption to Anonymous Communication

Applying ID-Based Encryption to Anonymous Communication ID 466-8555 DHT ID Applying ID-Based Encryption to Anonymous Communication Hiroyuki Tanaka Shoichi Saito Hiroshi Matsuo Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-shi Aichi 466-8555 Japan

More information

A NEW FULLY DECENTRALIZED SCALABLE PEER-TO-PEER GIS ARCHITECTURE

A NEW FULLY DECENTRALIZED SCALABLE PEER-TO-PEER GIS ARCHITECTURE A NEW FULLY DECENTRALIZED SCALABLE PEER-TO-PEER GIS ARCHITECTURE S.H.L. Liang Department of Geomatics Engineering, University of Calgary, Calgary, Alberta, CANADA T2N 1N4 steve.liang@ucalgary.ca Commission

More information

2. Research and Development on the Autonomic Operation. Control Infrastructure Technologies in the Cloud Computing Environment

2. Research and Development on the Autonomic Operation. Control Infrastructure Technologies in the Cloud Computing Environment R&D supporting future cloud computing infrastructure technologies Research and Development on Autonomic Operation Control Infrastructure Technologies in the Cloud Computing Environment DEMPO Hiroshi, KAMI

More information

A SURVEY OF P2P OVERLAYS IN VARIOUS NETWORKS

A SURVEY OF P2P OVERLAYS IN VARIOUS NETWORKS A SURVEY OF P2P OVERLAYS IN VARIOUS Mrs. A. Anitha Dr. J. JayaKumari Department of computer science & engineering Department of Electronics & communication Engineering anidathi@yahoo.co.in jkumaribharat@yahoo.com

More information

Adapting Distributed Hash Tables for Mobile Ad Hoc Networks

Adapting Distributed Hash Tables for Mobile Ad Hoc Networks University of Tübingen Chair for Computer Networks and Internet Adapting Distributed Hash Tables for Mobile Ad Hoc Networks Tobias Heer, Stefan Götz, Simon Rieche, Klaus Wehrle Protocol Engineering and

More information

Definition. A Historical Example

Definition. A Historical Example Overlay Networks This lecture contains slides created by Ion Stoica (UC Berkeley). Slides used with permission from author. All rights remain with author. Definition Network defines addressing, routing,

More information

RVS-Seminar Overlay Multicast Quality of Service and Content Addressable Network (CAN)

RVS-Seminar Overlay Multicast Quality of Service and Content Addressable Network (CAN) RVS-Seminar Overlay Multicast Quality of Service and Content Addressable Network (CAN) Luca Bettosini Universität Bern Outline > Goals / Motivation ( CAN ) > Content Addressable Network > CAN Multicast

More information

Energy Efficient Load Balancing among Heterogeneous Nodes of Wireless Sensor Network

Energy Efficient Load Balancing among Heterogeneous Nodes of Wireless Sensor Network Energy Efficient Load Balancing among Heterogeneous Nodes of Wireless Sensor Network Chandrakant N Bangalore, India nadhachandra@gmail.com Abstract Energy efficient load balancing in a Wireless Sensor

More information

Traceroute-Based Topology Inference without Network Coordinate Estimation

Traceroute-Based Topology Inference without Network Coordinate Estimation Traceroute-Based Topology Inference without Network Coordinate Estimation Xing Jin, Wanqing Tu Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water

More information

GRIDB: A SCALABLE DISTRIBUTED DATABASE SHARING SYSTEM FOR GRID ENVIRONMENTS *

GRIDB: A SCALABLE DISTRIBUTED DATABASE SHARING SYSTEM FOR GRID ENVIRONMENTS * GRIDB: A SCALABLE DISTRIBUTED DATABASE SHARING SYSTEM FOR GRID ENVIRONMENTS * Maha Abdallah Lynda Temal LIP6, Paris 6 University 8, rue du Capitaine Scott 75015 Paris, France [abdallah, temal]@poleia.lip6.fr

More information

PERFORMANCE STUDY AND SIMULATION OF AN ANYCAST PROTOCOL FOR WIRELESS MOBILE AD HOC NETWORKS

PERFORMANCE STUDY AND SIMULATION OF AN ANYCAST PROTOCOL FOR WIRELESS MOBILE AD HOC NETWORKS PERFORMANCE STUDY AND SIMULATION OF AN ANYCAST PROTOCOL FOR WIRELESS MOBILE AD HOC NETWORKS Reza Azizi Engineering Department, Bojnourd Branch, Islamic Azad University, Bojnourd, Iran reza.azizi@bojnourdiau.ac.ir

More information

DFSgc. Distributed File System for Multipurpose Grid Applications and Cloud Computing

DFSgc. Distributed File System for Multipurpose Grid Applications and Cloud Computing DFSgc Distributed File System for Multipurpose Grid Applications and Cloud Computing Introduction to DFSgc. Motivation: Grid Computing currently needs support for managing huge quantities of storage. Lacks

More information

Stability of QOS. Avinash Varadarajan, Subhransu Maji {avinash,smaji}@cs.berkeley.edu

Stability of QOS. Avinash Varadarajan, Subhransu Maji {avinash,smaji}@cs.berkeley.edu Stability of QOS Avinash Varadarajan, Subhransu Maji {avinash,smaji}@cs.berkeley.edu Abstract Given a choice between two services, rest of the things being equal, it is natural to prefer the one with more

More information

Calto: A Self Sufficient Presence System for Autonomous Networks

Calto: A Self Sufficient Presence System for Autonomous Networks Calto: A Self Sufficient Presence System for Autonomous Networks Abstract In recent years much attention has been paid to spontaneously formed Ad Hoc networks. These networks can be formed without central

More information

Enhancing Secure File Transfer by Analyzing Repeated Server Based Strategy using Gargantuan Peers (G-peers)

Enhancing Secure File Transfer by Analyzing Repeated Server Based Strategy using Gargantuan Peers (G-peers) Enhancing Secure File Transfer by Analyzing Repeated Server Based Strategy using Gargantuan Peers (G-peers) Kaushik Sekaran Assistant Professor School of Computing Science & Engineering VIT University,

More information

Mobile File-Sharing over P2P Networks

Mobile File-Sharing over P2P Networks Category: P2P obile File-Sharing over P2P Networks Lu Yan Åbo Akademi, Finland INTRODUCTION Peer-to-peer (P2P) computing is a networking and distributed computing paradigm which allows the sharing of computing

More information

Analysis of IP Network for different Quality of Service

Analysis of IP Network for different Quality of Service 2009 International Symposium on Computing, Communication, and Control (ISCCC 2009) Proc.of CSIT vol.1 (2011) (2011) IACSIT Press, Singapore Analysis of IP Network for different Quality of Service Ajith

More information

MASHUPS are an icon of Web 2.0 applications. A

MASHUPS are an icon of Web 2.0 applications. A , 23-25 October, 2013, San Francisco, USA MashChord: A Structured Peer-to-Peer Architecture for Mashups Based on Chord Osama Al-Haj Hassan, Ashraf Odeh, and Anas Abu Taleb Abstract Mashups are key category

More information

A P2PSIP event notification architecture

A P2PSIP event notification architecture A P2PSIP event notification architecture Georgios Panagiotou Appear Networks AB, Kista Science Tower, 164 51 Kista, Sweden Email: georgios.panagiotou@appearnetworks.com Alisa Devlic Appear Networks AB,

More information

T he Electronic Magazine of O riginal Peer-Reviewed Survey Articles ABSTRACT

T he Electronic Magazine of O riginal Peer-Reviewed Survey Articles ABSTRACT SECOND QUARTER 2005, VOLUME 7, NO. 2 IEEE C OMMUNICATIONS SURVEYS T he Electronic Magazine of O riginal -Reviewed Survey Articles www.comsoc.org/pubs/surveys A SURVEY AND COMPARISON OF PEER-TO-PEER OVERLAY

More information

LOAD BALANCING AND EFFICIENT CLUSTERING FOR IMPROVING NETWORK PERFORMANCE IN AD-HOC NETWORKS

LOAD BALANCING AND EFFICIENT CLUSTERING FOR IMPROVING NETWORK PERFORMANCE IN AD-HOC NETWORKS LOAD BALANCING AND EFFICIENT CLUSTERING FOR IMPROVING NETWORK PERFORMANCE IN AD-HOC NETWORKS Saranya.S 1, Menakambal.S 2 1 M.E., Embedded System Technologies, Nandha Engineering College (Autonomous), (India)

More information

INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY

INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY [Kavita, 2(4): April, 2013] ISSN: 2277-9655 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY Histogram Based Live Streaming in Peer to Peer Dynamic Balancing & Clustering System

More information

AN OVERVIEW OF QUALITY OF SERVICE COMPUTER NETWORK

AN OVERVIEW OF QUALITY OF SERVICE COMPUTER NETWORK Abstract AN OVERVIEW OF QUALITY OF SERVICE COMPUTER NETWORK Mrs. Amandeep Kaur, Assistant Professor, Department of Computer Application, Apeejay Institute of Management, Ramamandi, Jalandhar-144001, Punjab,

More information

Influence of Load Balancing on Quality of Real Time Data Transmission*

Influence of Load Balancing on Quality of Real Time Data Transmission* SERBIAN JOURNAL OF ELECTRICAL ENGINEERING Vol. 6, No. 3, December 2009, 515-524 UDK: 004.738.2 Influence of Load Balancing on Quality of Real Time Data Transmission* Nataša Maksić 1,a, Petar Knežević 2,

More information

Intelligent Content Delivery Network (CDN) The New Generation of High-Quality Network

Intelligent Content Delivery Network (CDN) The New Generation of High-Quality Network White paper Intelligent Content Delivery Network (CDN) The New Generation of High-Quality Network July 2001 Executive Summary Rich media content like audio and video streaming over the Internet is becoming

More information

Acknowledgements. Peer to Peer File Storage Systems. Target Uses. P2P File Systems CS 699. Serving data with inexpensive hosts:

Acknowledgements. Peer to Peer File Storage Systems. Target Uses. P2P File Systems CS 699. Serving data with inexpensive hosts: Acknowledgements Peer to Peer File Storage Systems CS 699 Some of the followings slides are borrowed from a talk by Robert Morris (MIT) 1 2 P2P File Systems Target Uses File Sharing is one of the most

More information

UK Interconnect White Paper

UK Interconnect White Paper UK Interconnect White Paper 460 Management Management Management Management 460 Management Management Management Management AI073 AI067 UK Interconnect White Paper Introduction The UK will probably have

More information

A NOVEL RESOURCE EFFICIENT DMMS APPROACH

A NOVEL RESOURCE EFFICIENT DMMS APPROACH A NOVEL RESOURCE EFFICIENT DMMS APPROACH FOR NETWORK MONITORING AND CONTROLLING FUNCTIONS Golam R. Khan 1, Sharmistha Khan 2, Dhadesugoor R. Vaman 3, and Suxia Cui 4 Department of Electrical and Computer

More information

Performance Monitoring on Networked Virtual Environments

Performance Monitoring on Networked Virtual Environments Performance Monitoring on Networked Virtual Environments C. Bouras 1, 2, E. Giannaka 1, 2 Abstract As networked virtual environments gain increasing interest and acceptance in the field of Internet applications,

More information

Peer-VM: A Peer-to-Peer Network of Virtual Machines for Grid Computing

Peer-VM: A Peer-to-Peer Network of Virtual Machines for Grid Computing Peer-VM: A Peer-to-Peer Network of Virtual Machines for Grid Computing (Research Proposal) Abhishek Agrawal (aagrawal@acis.ufl.edu) Abstract This proposal discusses details about Peer-VM which is a peer-to-peer

More information

5. Peer-to-peer (P2P) networks

5. Peer-to-peer (P2P) networks 5. Peer-to-peer (P2P) networks PA191: Advanced Computer Networking I. Eva Hladká Slides by: Tomáš Rebok Faculty of Informatics Masaryk University Autumn 2015 Eva Hladká (FI MU) 5. P2P networks Autumn 2015

More information

PEER TO PEER FILE SHARING USING NETWORK CODING

PEER TO PEER FILE SHARING USING NETWORK CODING PEER TO PEER FILE SHARING USING NETWORK CODING Ajay Choudhary 1, Nilesh Akhade 2, Aditya Narke 3, Ajit Deshmane 4 Department of Computer Engineering, University of Pune Imperial College of Engineering

More information

International Journal of Advanced Research in Computer Science and Software Engineering

International Journal of Advanced Research in Computer Science and Software Engineering Volume 2, Issue 9, September 2012 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com An Experimental

More information

A Reputation Management System in Structured Peer-to-Peer Networks

A Reputation Management System in Structured Peer-to-Peer Networks A Reputation Management System in Structured Peer-to-Peer Networks So Young Lee, O-Hoon Kwon, Jong Kim and Sung Je Hong Dept. of Computer Science & Engineering, Pohang University of Science and Technology

More information

Fault-Tolerant Framework for Load Balancing System

Fault-Tolerant Framework for Load Balancing System Fault-Tolerant Framework for Load Balancing System Y. K. LIU, L.M. CHENG, L.L.CHENG Department of Electronic Engineering City University of Hong Kong Tat Chee Avenue, Kowloon, Hong Kong SAR HONG KONG Abstract:

More information

The necessity of multicast for IPTV streaming

The necessity of multicast for IPTV streaming The necessity of multicast for IPTV streaming ARIANIT MARAJ, ADRIAN SHEHU Telecommunication Department Faculty of Information Technology, Polytechnic University of Tirana Tirana, Republic of Albania arianit.maraj@ptkonline.com,

More information

Extending the Internet of Things to IPv6 with Software Defined Networking

Extending the Internet of Things to IPv6 with Software Defined Networking Extending the Internet of Things to IPv6 with Software Defined Networking Abstract [WHITE PAPER] Pedro Martinez-Julia, Antonio F. Skarmeta {pedromj,skarmeta}@um.es The flexibility and general programmability

More information

Plaxton routing. Systems. (Pastry, Tapestry and Kademlia) Pastry: Routing Basics. Pastry: Topology. Pastry: Routing Basics /3

Plaxton routing. Systems. (Pastry, Tapestry and Kademlia) Pastry: Routing Basics. Pastry: Topology. Pastry: Routing Basics /3 Uni Innsbruck Informatik Uni Innsbruck Informatik Peerto topeer Systems DHT examples, part (Pastry, Tapestry and Kademlia) Michael Welzl michael.welzl@uibk.ac.at DPS NSG Team http://dps.uibk.ac.at dps.uibk.ac.at/nsg

More information

Hybrid Overlay Multicast Framework draft-irtf-sam-hybrid-overlay-framework-01.txt. John Buford, Avaya Labs Research

Hybrid Overlay Multicast Framework draft-irtf-sam-hybrid-overlay-framework-01.txt. John Buford, Avaya Labs Research Hybrid Overlay Multicast Framework draft-irtf-sam-hybrid-overlay-framework-01.txt John Buford, Avaya Labs Research Topics SAM Charter Recap and Problem Statement AMT(Automatic Multicast Tunneling) Overview

More information

Interconnection Networks. Interconnection Networks. Interconnection networks are used everywhere!

Interconnection Networks. Interconnection Networks. Interconnection networks are used everywhere! Interconnection Networks Interconnection Networks Interconnection networks are used everywhere! Supercomputers connecting the processors Routers connecting the ports can consider a router as a parallel

More information

An Introduction to Peer-to-Peer Networks

An Introduction to Peer-to-Peer Networks An Introduction to Peer-to-Peer Networks Presentation for MIE456 - Information Systems Infrastructure II Vinod Muthusamy October 30, 2003 Agenda Overview of P2P Characteristics Benefits Unstructured P2P

More information

Storage Systems Autumn 2009. Chapter 6: Distributed Hash Tables and their Applications André Brinkmann

Storage Systems Autumn 2009. Chapter 6: Distributed Hash Tables and their Applications André Brinkmann Storage Systems Autumn 2009 Chapter 6: Distributed Hash Tables and their Applications André Brinkmann Scaling RAID architectures Using traditional RAID architecture does not scale Adding news disk implies

More information

A Self-Organizing Crash-Resilient Topology Management System for Content-Based Publish/Subscribe

A Self-Organizing Crash-Resilient Topology Management System for Content-Based Publish/Subscribe A Self-Organizing Crash-Resilient Topology Management System for Content-Based Publish/Subscribe R. Baldoni, R. Beraldi, L. Querzoni and A. Virgillito Dipartimento di Informatica e Sistemistica Università

More information