Dynamic Memory Allocator for Sensor Operating System Design and Analysis *

Size: px
Start display at page:

Download "Dynamic Memory Allocator for Sensor Operating System Design and Analysis *"

Transcription

1 JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 26, 1-14 (2010) Dynamic Memory Allocator for Sensor Operating System Design and Analysis * HONG MIN, YOO-KUN CHO AND JI-MAN HONG + School of Computer Science and Engineering Seoul National University Gwanak-gu, Seoul, Korea {hmin; ykcho}@os.snu.ac.kr + School of Computing Soongsil University Dongjak-gu, Seoul, Korea jiman@ssu.ac.kr Dynamic memory allocation is an important mechanism used in operating systems. An efficient dynamic memory allocator can improve the performance of operating systems. In wireless sensor networks, sensor nodes have miniature computing device, small memory space and very limited battery power. Therefore, it is important that sensor operating systems operate efficiently in terms of energy consumption and resource management. And the role of dynamic memory allocator in sensor operating system is more important than one of general operating system. In this paper, we propose a new dynamic memory allocation scheme that resolves the existing problems in dynamic memory allocators. We implemented our scheme on Nano-Qplus which is a sensor operating system based on multi-threading. Our experimental results and static analysis result show our scheme performs efficiently in terms of the execution time and the memory space compared with existing memory allocation mechanisms. Keywords: dynamic memory allocator, sensor operating system, wireless sensor networks, memory management scheme, multi-threading 1. INTRODUCTION Wireless sensor networks is a new research topic that has drawn great attention recently. The rapid advancement in computing technology, wireless communication technology and Micro-Elector-Mechanical system technology have resulted in the development of smarter and smaller devices. These devices, has integrated micro-sensing and actuation with onboard processing and wireless communications capabilities. Wireless sensor networks have become popular over the past few years and have captured the attention and imagination of many researchers, encompassing a board spectrum of ideas [3, 7]. The main purpose of the wireless sensor networks is to monitor the natural environment. Potential application fields include scientific data gathering such as environment monitoring and control systems, military systems, automatic manufacturing systems, surveillance systems, and medical systems. Wireless sensor networks also can be used even in the harsh environments [4, 5, 8]. Received September 30, 2008; accepted January 7, Communicated by Sung Y. Shin, Jiman Hong and Tei-Wei Kuo. * This work was supported by the Soongsil University Research Fund and the Ministry of Knowledge Economy (MKE), Korea, under the Information Technology Research Center (ITRC) support program supervised by the Institute for Information Technology Advancement (IITA). + Corresponding author. 1

2 2 HONG MIN, YOO-KUN CHO AND JI-MAN HONG Wireless sensor networks are generally made up of hundreds or even thousands of deployed sensor nodes that were designed to be very cost efficient in terms of production cost. The sensor nodes have miniature computing devices, extremely small memory space, and very limited battery power. The important constraints of wireless sensor networks are low energy consumption and limited resources. Therefore, operating systems that run on the sensor nodes must also operate efficiently in terms of energy consumption and resources management. And the operating systems must minimize execution time and maximize resource utilization. For this reason, sensor operating systems need a time and space efficient memory allocation mechanism. Many kinds of researches have been conducted on wireless sensor networks, including TinyOS [6], SOS [9], MANTIS OS [7], and Nano-Qplus [3]. Fig. 1 presents the memory model of TinyOS. TinyOS uses the static memory allocation scheme that does not support the heap space and the dynamic memory allocation. Global variables are occupied in the conserved region. Local variables and function parameters are stored in the stack region. Only one process can run at one time and this memory layout is determined at compile time. Stack Free Global variable Fig. 1. Memory model of TinyOS. SOS, MANTIS OS, and Nano-Qplus use dynamic memory allocation mechanisms to support dynamic loadable module and multi-threading techniques. However, these dynamic memory allocation mechanisms can be used for general purpose computing environment as there isn t a need for a large memory space and power, and so are not suitable for sensor nodes. In this paper, we propose new dynamic memory allocation scheme to improve the time and space-efficiency of memory allocation mechanism that aims at minimizing fragmentation ratio and average response time. The remaining parts of this paper are composed as follows. In section 2, we explain some related works done on dynamic memory allocation mechanisms. Section 3 describes the characteristics of wireless sensor networks and sensor nodes. We also present some examples of the practical usage of dynamic memory allocation mechanisms of existing sensor operating systems. Then, we explain about the design and implementation of our scheme in more detail. In section 4, we present and evaluate the performance of our scheme compared with other existing memory allocation mechanisms for sensor nodes. In section 5, we apply static analysis for showing that our system can adapt the specific application properly. Finally, conclusions are presented in section RELATED WORKS In this section, we briefly introduce prior works relating to dynamic memory allocation mechanisms. Many programmers avoid considering a dynamic allocation in many situations, because of substantial space overhead and time cost. In [1], Paul et al. insisted

3 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS 3 that the costs of dynamic memory allocation are simply overestimated and many good allocation schemes overcome these costs. Considerable researches [10-16] have been done on dynamic memory allocation to improve the performance of the memory related tasks on existing operating systems. They can be classified as follows: sequential fits [12], segregated fits [10, 11], buddy systems [13-15], and hybrid mechanisms [16]. The sequential fits manage the memory space by the linear-list of all the free blocks in memory, and it supports allocation and release of various-size blocks on the linear-list. Typically, the boundary tags [12] technique is used to support efficient coalescing and merging blocks. The famous variants include first fit, best fit, next fit, and worst fit [17]. In those mechanisms, no internal fragmentation occurs. Instead, the worst case response time is O(N) because it must search for an appropriate block of the total memory space. The segregated fits use free lists of each segregated memory space to improve the response time of the memory allocation and release mechanism. In this mechanism, each list holds free blocks of particular size, and there are two major variants: simple powerof-n free lists and segregated sequential fit. The power-of-two lists stores buffers of a particular size and all the sizes are powers of two. If the size of a user s request is not powers of two, the system rounds up the size of the request and allocate it appropriately. Thus, its response time is O(1). In the worst case, the internal fragmentation may increase the fragmentation of the memory space up to 50% [17]. The segregated sequential fit uses the lists that are divided into particular sizes to reduce the time consumed to search the memory space. If the number of division is k, then the average response time is O(N/k) [11]. Peterson et al. proposed the buddy systems [14]. This approach creates appropriate buffers by coalescing adjacent free buffers and splitting the larger one. Thus, it provides flexibility, allowing memory to be reused for buffers of various different sizes. However, it has a problem of internal fragmentation, which may increase the fragmentation up to 25% [18]. In [16], Masmano et al. proposed a new dynamic memory allocator for real-time systems. It uses hybrid techniques of segregated fits with the boundary tags technique to minimize the worst case execution time. 3. ALGORITHM DESIGN AND IMPLEMENTATION In this section, we describe the requirements for wireless sensor networks including the platform of sensor nodes and explain about the existing constraints. We also present examples related to the practical usage of memory allocation mechanisms on existing sensor operating systems and then explain about the algorithm design and implementation of our scheme in detail. 3.1 Design Goals In general, wireless sensor networks consist of many sensor nodes and it is very important to minimize the production cost to enhance networks efficiency. Such restriction limits computing power, memory space, and the batteries. For example, Berkeley s MICA motes have only 8-bit processor, 4 KB memory space, and 2xAA batteries [19]. Therefore, the limited memory and energy have to be efficiently utilized. In other words, the memory space must be managed in accordance with space and energy-efficient mem-

4 4 HONG MIN, YOO-KUN CHO AND JI-MAN HONG ory allocation mechanism. These are design goals that should be considered in the design process of an efficient memory allocation mechanism for wireless sensor networks. Execution time: it is proportional to the energy consumption of the memory allocation mechanism, thus, the total execution time have to be minimized to reduce the amount of energy consumption. Low fragmentation ratio: the internal and external fragmentation may spoil the memory utilization, thus it must be minimized. Small management space: the size of data structures and the metadata that are used for managing the memory bock is also important. If dynamic allocator occupies a large space for sustaining the memory state, the rest free space may decrease. 3.2 Prior Dynamic Allocation Methods Figs. 2 and 3, show some practical uses of the dynamic memory allocation mechanisms on existing operating systems for wireless sensor networks [3, 7, 9]. The SOS requires a dynamic memory allocation and uses a similar mechanism as the power of two free lists [9]. It consists of 16 32, 32 16, bytes memory blocks. The total size of memory bock is 1536 bytes. Similar to the segregated free lists, it only needs O(1) to find an appropriate block. But, in the SOS, a serious internal fragmentation may be occurred, decreasing the efficacy in utilization of the memory space. If we request the free space of 128 byte for five times in a row, this memory allocator returns the failure in spite of it has enough free space. Fig. 2 shows the memory space of the SOS. Fig. 2. Memory management structure on SOS. MANTIS OS and Nano-Qplus support preemptive thread scheduler for multimodal sensing tasks. They need a dynamic memory management to allocate threads stacks and use sequential fits with best fit policy. Thus, they need O(N) for linear searching the total memory space, but there is a possibility that they may overuse the limited power of batteries. And boundary tags that is the metadata of free and allocated memory block decrease the memory utilization. Fig. 3 presents the example of the MANTIS OS and Nano-Qplus memory management system.

5 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS 5 Fig. 3. Memory management structure on MANTIS OS and Nano-Qplus. 3.3 System Overview Our dynamic memory allocation scheme efficiently utilizes the tiny memory space in sensor operating systems. It adaptively uses the techniques of sequential fits (bitmap fits), segregated free lists, and the buddy systems to fulfill the essential requirements for wireless sensor networks. Generally, the sequential fits are good at minimizing fragmentation ratio, and the segregated free lists perform well in terms of execution time. In addition, buddy systems can provide flexibility and scalability to the target operating systems. Fig. 4. System overview of our scheme. Fig. 4 illustrates the relationship between physical memory space and the data structures used in our scheme. In Fig. 4, the data structures consist of the bitmap, n global entries and the local table of segregated entries. Each global entry has a block type identifier and the address of a memory block. The local table entries are combined by the power-of-two (8; 16; 32; 64; 128 bytes) address entries, and each one has the m entries of address that points to the memory block. The bitmap is used for mapping and checking the used area of the physical memory space, and each bit is mapped to 8 bytes of the actual memory space. The global and local table entries manage the free memory blocks. For example, the local table entries can manage the free blocks with maximum m entries, and the remaining free blocks are saved on global entries. In sensor nodes, the memory space is very limited and thus cannot be used excessively. However, our scheme can give

6 6 HONG MIN, YOO-KUN CHO AND JI-MAN HONG better utilization of the total memory space using limited number of the global and the local table entries. There is possibility that, it may slightly increase the average execution time of a task. 3.4 Implementation We show the detailed description of the basic operation and algorithms on our scheme. Initialization: The data structures are statically located on the global variables of the data region. The counter field and the bitmap are set to 0. Block Allocation: If an allocation request arrives with R size our scheme searches suitable block that greater than or equal to the size of 2 log2rsize on the global and the local table entries. If a block is found, it returns to the user. Otherwise, our scheme searches on the bitmap with first fit policy and returns the found block. Finally, it marks the bitmap of the allocated. Block Free: If a release request arrives with R size our scheme re-registers the released block to appropriate entries and releases the bitmap of the released memory block. Coalescing and Splitting Blocks: Similarly to the buddy systems, our scheme manages memory space in power of two blocks. It coalesces and splits the memory blocks if needed. If an allocation request arrives with R size and our mechanism succeeds to find a free block of the 2 log2rsize bytes, then our scheme splits the remaining 2 log2rsize R size bytes block into multiple power of two blocks. The split blocks are reregistered to the global or the local table entries. On the other hand, when a release request arrives with R size, it searches the adjacent bytes memory space for coalescing. Data Structure Management: There are three-level data structures: local table entries, global table entries, and bitmap. It is similar to hierarchical cache in computer architecture. For example, our scheme searches to find an appropriate block in this order (local, global, bitmap). If the local table entries become empty, it has to be replenished by the global entries. In this way, if the global entries become empty, then it must be filled up by searching the bitmap. (a) Allocate 88 bytes. (b) Releasing 88 bytes. Fig. 5. An example of allocating and releasing 88 bytes in our scheme. Fig. 5 shows an example of way in which 88 bytes of memory space is allocated and released when using our scheme. If a user requests 88 bytes of memory space, it begins searching for an adequate memory block. As a result, a 128 bytes memory block is selected because the 2 log288 is 128. It then splits into 88 and 40 bytes. The 88 bytes are allocated for the requested user, and the remaining 40 bytes are split and re-register to the

7 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS 7 power of two the local table entries (32 and 8 bytes blocks). It should be noted that if the user request that allocated 88 bytes block be released, it starts searching adjacent 128 bytes memory space because the 2 log288 is 128. Then, the 8 and 32 free blocks are coalesced with the released 88 bytes. As a result, 128 bytes memory block is generated and registered to the local or global table entries. The following Algorithms 1 and 2 summarize our memory allocation and release mechanisms. Algorithm 1 Allocation mechanism. malloc(r size ) Scan a free memory block 2 log2rsize. If search in the local table = TRUE, Return the address of free block. Splitting the rest block and register the split blocks to entries. Else if search in the global table = TRUE, Return the address of free block. Splitting the rest block and register the split blocks to entries. Update the local table entries. Else if search in the bitmap = TRUE, Return the address of free block. Splitting the rest block and register the split blocks to entries. Update the local table entries. Else, Return FAIL. In Algorithm 2, the time consumed to search for the coalescing memory block is only O(1) because the region of the search space is very limited. In our scheme, the space is bitmap and the size is only 8 bytes (one byte of the bitmap corresponds to 64 bytes of the physical memory space). Therefore, it does not consume a long time to search for the coalescing memory space. Algorithm 2 Releasing mechanism. free(ptr, R size ) Release R size memory space. If search the adjacent free space = TRUE, Coalescing the memory blocks and register to entries. 4. EXPERIMENTAL ANALYSIS In this section, we will verify the performance of our scheme. We experimented on our dynamic memory allocation mechanism in actual sensor nodes to evaluate its performance and compared the results with other dynamic memory allocation mechanisms of existing sensor operating systems.

8 8 HONG MIN, YOO-KUN CHO AND JI-MAN HONG 4.1 Experimental Environment In our experiment, we used Octacomm s Nano-24 wireless sensor platform [20], which is similar to the Berkeley s MICAZ sensor board. Octacomm supports Nano- Qplus kernel source for Nano-24 sensor board. But in SOS, there is no adequate kernel source for Nano-24 sensor board. For our experiment, we ported the SOS kernel to the Nano-24 sensor board. The kernel version of SOS is 05-july and Nano-Qplus is 1.6.0e. 4.2 Experimental Results The memory allocation mechanisms are known to affect the time and space efficiency of the operating system. Therefore, in this study, we focused on the fragmentation ratio, the size of available free space, and the total execution time of the memory allocation schemes for demonstrating the efficiency of the dynamic memory allocation mechanisms. In our experiments, we compared the performance of the following memory allocation mechanisms. SOS: SOS memory allocator. (Kernel version: 05-july) NANO: Nano-Qplus (MANTIS OS) s memory allocator. (Kernel version: ) Our scheme: the proposed memory allocator. Table 1. Total execution time of the memory allocators. (1tick = 16ms) Test set Our scheme Nano SOS Test set Test set Test set Test set Test set Avg. execution time Table 1 shows the total execution time taken by the above memory allocation schemes for completing five types of test sets. In these experiments, 200 allocations and release requests were used and the domains of the request size were 8~128 bytes. We conducted five random test sets and measured the execution time respectively. In Table 1, the SOS execution time is smaller than those of others because SOS uses fixed allocation policy. In addition, execution time of our scheme is faster than NANO. Fig. 6 shows the fragmentation ratio of three memory allocation mechanisms, respectively and the x-axis shows the fragmentation ratio while the y-axis is time slice. In the result, the SOS is poorer than others. This is because the memory space of SOS divided by the fixed size blocks, which means the large amount of the internal fragmented blocks increase the fragmentation ratio. In case of Nano-Qplus and MANTIS OS, the variation of fragmentation ratio fluctuates varies widely. This is attributed to the fact that this dynamic allocator makes whole as time elapses. In other words, after repeating allocation and free operation, the external fragmentation increases the fragmentation ratio. In contrast, our scheme provides efficient coalescing and splitting operation, and as a result, fragmentation ratio is stable.

9 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS 9 Fig. 6. Fragmentation ratio of the memory allocators. Fig. 7. The size of rest free memory. Fig. 7 presents the size of rest free memory and the x-axis represent the memory size (bytes) while the y-axis shows time slice. As a mentioned before, SOS allocation mechanism generates huge internal fragmentation. Thus, SOS size of rest free memory is smaller than that of the others. Nano-Qplus and MANTIS OS used boundary tags for managing free and allocated memory blocks. It caused additional overhead, and so, Nano-Qplus and MANTIS OS can be said to be smaller than our scheme. Table 2. Execution time of Surge application. (1tick = 16ms) Surge application Our scheme Nano SOS Execution time Table 2 shows the execution time of dynamic memory allocators in Surge application. Surge application that is used to collecting data in wireless sensor networks computes sensing values, and this causes the packet and transmits the packet to sink node periodically.

10 10 HONG MIN, YOO-KUN CHO AND JI-MAN HONG Fig. 8 shows the fragmentation ratio and the size of rest free memory space for dynamic allocation mechanisms respectively. The results of the actual trace [2] are the same as that of random trace. (a) Fragmentation ratio. (b) The size of rest free memory. Fig. 8. Results of the actual trace. Based on these results, we can conclude that the proposed our scheme performs significantly better than the existing memory allocation mechanisms. 5. STATIC ANALYSIS FOR OUR SCHEME In this section, we apply static analysis to our scheme for each specific application. By using static analysis, we can determine the maximum memory size for dynamic allocation and use this information to design the application specific sensor node. 5.1 Static Analysis Model L. Unnikrishnan et al. [19] suggested heap static analysis scheme of heap space for high level language. They measured heap space using constructor count vectors, which are vectors of integers with one element corresponding to each data constructor. By using the heap allocation bound function, they traced the reference counter that is the number of pointer of each data object and find the maximum one. Static analysis for Wireless sensor networks application is simpler than general purpose application. In wireless sensor networks application, control flow is simple and requesting for dynamic allocation is uncommon. Also, there are no multiple pointers that are pointing the same data object. So, we apply static analysis to our scheme for advising to the application specific sensor node. For applying static analysis of L. Unnikrishnan et al., we adjusted some variables to implement in Wireless sensor networks application. We did not use any concept of constructor count vectors, and we defined the object block vector of which entries contain reference counter of each block size. We also managed the maximum reference counter of each block. Fig. 9 shows how object block vector and the maximum reference counter are updated.

11 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS 11 Fig. 9. Static analysis model. We define object block vector and maximum reference counter by each block size. When the memory request is detected, we increase the corresponding vector element. If the reference counter is larger than the previous one, maximum reference counter vector is updated. In this way, we can derive the maximum heap size for executing the specific sensor application. 5.2 Static Analysis Results We tested this static analysis to three sensor applications which are the most typical programs in wireless sensor networks. Blink (App1): blinking the led periodically CountToRm (App2): sending the counter to receiver by using the radio module Surge (App3): collecting information and using the routing protocol Fig. 10 compares the result between our static analysis model and actual trace. In a simple case (App1), our model predicted the maximum heap size accurately. In complex case (App2 and App3), this model can make the memory usage over-estimated, but the difference is not critical. By using this information, we can improve the design of a sensor node that can be support a specific sensor application.

12 12 HONG MIN, YOO-KUN CHO AND JI-MAN HONG Fig. 10. The maximum heap size prediction. 6. CONCLUSIONS Wireless sensor networks are composed of hundreds or even thousands of deployed sensor nodes that are designed under the constraints of cost efficiency. Therefore, an operating system that runs on tiny sensor nodes a time and space efficient memory allocation scheme, because each sensor node has only small memory space with limited batteries. In this paper, we proposed an efficient dynamic memory allocation scheme to improve the time and space efficiency of the memory management in tiny sensor nodes. It is designed to minimize internal and external fragmentation and to improve repose time of the memory management for sensor nodes. Our experimental results show that our mechanism outperforms all existing memory allocation mechanisms on sensor operating system. By using our static analysis model, we can predict the maximum heap memory size and design the application specific sensor nodes. REFERENCES 1. P. R. Willson, M. S. Johnstone, M. Neely, and D. Boles, Dynamic storage allocation: A survey and critical review, in Proceedings of International Workshop on Memory Management, 1995, pp E. Zorn and D. Grunwald, Evaluating models of memory allocation, ACM Transactions on Modeling and Computer Simulation, 1994, pp

13 DYNAMIC MEMORY ALLOCATOR FOR SOS DESIGN AND ANALYSIS K. Lee, Y. Shin, H. Choi, and S. Park, A design of sensor network system based on scalable and reconfigurable nano-os platform, in Proceedings of IT-Soc International Conference, 2004, pp J. D. Lundquist, D. R. Cayan, and M. D. Dettinger, Meteorology and hydrology in yosemite national park: A sensor network application, Lecture Note in Computer Science, Vol. 2634, 2003, pp I. Akyildiz, W. Su, Y. Sankarasubramaniam, and E. Cayirci, A survey on sensor networks, IEEE Communications Magazine, Vol. 2, 2002, pp P. Levis, S. Madden, D. Gay, J. Polastre, R. Szewczyk, A. Woo, E. Brewer, and D. Culler, The emergence of networking abstractions and techniques in Tinyos, in Proceedings of the 1st USENIX/ACM Symposium on Networked Systems Design and Implementation, 2004, pp S. Bhatti, J. Carlson, H. Dai, J. Deng, J. Rose, A. Sheth, B. Shucker, C. Gruenwald, A. Torgerson, and R. Han, Mantis OS: An embedded multithreaded operating system for wireless micro sensor platforms, ACM Kluwer Mobile Networks and Applications Journal, Special Issue on Wireless Sensor Networks, 2005, pp M. Hirafuji, T. Fukatsu, H. Hu, T. Kiura, M. Laurenson, D. He, A. Yamakawa, A. Imada, and S. Ninomiya, Advanced sensor-network with field monitoring servers and metbroker, in Proceedings of CIGR International Conference, 2004, pp C. C. Han, R. Kumar, R. Shea, E. Kohler, and M. B. Srivastava, A dynamic operating system for sensor nodes, in Proceedings of MobiSys, 2005, pp M. K. McKusick and M. J. Karels, Design of a general purpose memory allocator for the 4.3bsd Unix kernel, in Proceedings of the San Francisco USENIX Conference, 1988, pp D. Lea, A Memory Allocator, Unix/Mail, D. E. Knuth, The art of computer programming, Fundamental Algorithms, Vol. 1, Addison-Wesley, U.S.A., K. C. Knowlton, A fast storage allocator, Communications of the ACM, Vol. 8, 1965, pp J. L. Peterson and T. A. Norman, Buddy systems, Communications of the ACM, Vol. 20, 1977, pp I. P. Page and J. Hagins, Improving the performance of buddy systems, IEEE Transactions on Computers, Vol. C-35, 1986, pp M. Masmano, I. Ripoll, A. Crespo, and J. Real, Tlsf: A new dynamic memory allocator for real-time systems, in Proceedings of Euromicro Conference on Real-Time Systems, 2004, pp U. Vahalia, Unix Internals: The New Frontiers, Prentice Hall, U.S.A., M. S. Johnstone and P. R. Wilson, The memory fragmentation problem: solved? ACM SIGPLAN Notices, Vol. 34, 1999, pp U. Leena, D. S. Scoot, and A. L. Yanhong, Automatic accurate stack space and heap space analysis for high-level languages, Lecture Notes in Computer Science, Vol. 1474, 1998, pp Crossbow, Octacomm,

14 14 HONG MIN, YOO-KUN CHO AND JI-MAN HONG Hong Min received his B.E. degree in Computer Science from Handong University, Pohang, Korea, in He has been with School of Computer Science and Engineering, Seoul National University since 2005, where currently he is a Ph.D. candidate student. His research interests include embedded systems, storage management systems, and sensor networks. Yoo-Kun Cho received the B.E. degree from Seoul National University, Korea, in 1971 and the Ph.D. degree in Computer Science from the University of Minnesota at Minneapolis in He has been with the School of Computer Science and Engineering, Seoul National University since 1979, where he is currently a professor. He was a visiting assistant professor at the University of Minnesota during 1985 and a director of the Educational and Research Computing Center at Seoul National University from 1993 to He was president of the Korea Information Science Society during He was a member of the program committee of the IPPS/SPDP in 1997 and the International Conference on High Performance Computing from 1995 to His research interests include operating systems, algorithms, system security, and fault-tolerant computing systems. He is a member of the IEEE. Ji-Man Hong received the B.S. degree in Computer Science from Korea University, Seoul Korea in 1994 and the M.E. and Ph.D. degrees in Computer Engineering from Seoul National University, Seoul Korea, in 1997, and 2003, respectively. He was an assistant professor at Kwangwoon University from 2004 to He has been with School of Computing, Soongsil University, Seoul, Korea, since 2007, where currently he is an assistant professor. From 2000 to 2003, he served as a Chief of Technical Officer in the R&D center of GmanTech Incorporated Company, Seoul, Korea. His research interests include embedded operating systems, fault tolerance computing systems, distributed computing systems, and sensor network systems.

AN EVOLVABLE OPERATING SYSTEM FOR WIRELESS SENSOR NETWORKS

AN EVOLVABLE OPERATING SYSTEM FOR WIRELESS SENSOR NETWORKS AN EVOLVABLE OPERATING SYSTEM FOR WIRELESS SENSOR NETWORKS THU-THUY DO, DAEYOUNG KIM, TOMAS SANCHEZ LOPEZ, HYUNHAK KIM, SEONGKI HONG, MINH-LONG PHAM Information and Communications University, 119 Munjiro,

More information

System Development Process based on Embedded Linux and Sensor Node

System Development Process based on Embedded Linux and Sensor Node System Development Process based on Embedded Linux and Sensor Node Shin-Hyeong Choi 1* and Hyoung-Keun Park 2 1* Dept. of Control & Instrumentation Engineering, Kangwon National University, 1 Joongang-ro

More information

NanoMon: An Adaptable Sensor Network Monitoring Software

NanoMon: An Adaptable Sensor Network Monitoring Software NanoMon: An Adaptable Sensor Network Monitoring Software Misun Yu, Haeyong Kim, and Pyeongsoo Mah Embedded S/W Research Division Electronics and Telecommunications Research Institute (ETRI) Gajeong-dong

More information

Memory Allocation Technique for Segregated Free List Based on Genetic Algorithm

Memory Allocation Technique for Segregated Free List Based on Genetic Algorithm Journal of Al-Nahrain University Vol.15 (2), June, 2012, pp.161-168 Science Memory Allocation Technique for Segregated Free List Based on Genetic Algorithm Manal F. Younis Computer Department, College

More information

Multi-level Metadata Management Scheme for Cloud Storage System

Multi-level Metadata Management Scheme for Cloud Storage System , pp.231-240 http://dx.doi.org/10.14257/ijmue.2014.9.1.22 Multi-level Metadata Management Scheme for Cloud Storage System Jin San Kong 1, Min Ja Kim 2, Wan Yeon Lee 3, Chuck Yoo 2 and Young Woong Ko 1

More information

DAG based In-Network Aggregation for Sensor Network Monitoring

DAG based In-Network Aggregation for Sensor Network Monitoring DAG based In-Network Aggregation for Sensor Network Monitoring Shinji Motegi, Kiyohito Yoshihara and Hiroki Horiuchi KDDI R&D Laboratories Inc. {motegi, yosshy, hr-horiuchi}@kddilabs.jp Abstract Wireless

More information

Implementation of Buffer Cache Simulator for Hybrid Main Memory and Flash Memory Storages

Implementation of Buffer Cache Simulator for Hybrid Main Memory and Flash Memory Storages Implementation of Buffer Cache Simulator for Hybrid Main Memory and Flash Memory Storages Soohyun Yang and Yeonseung Ryu Department of Computer Engineering, Myongji University Yongin, Gyeonggi-do, Korea

More information

Multithreading Optimization Techniques for Sensor Network Operating Systems

Multithreading Optimization Techniques for Sensor Network Operating Systems Multithreading Optimization Techniques for Sensor Network Operating Systems Hyoseung Kim and Hojung Cha Department of Computer Science, Yonsei University Seodaemun-gu, Shinchon-dong 134, Seoul 120-749,

More information

An Empirical Approach - Distributed Mobility Management for Target Tracking in MANETs

An Empirical Approach - Distributed Mobility Management for Target Tracking in MANETs An Empirical Approach - Distributed Mobility Management for Target Tracking in MANETs G.Michael Assistant Professor, Department of CSE, Bharath University, Chennai, TN, India ABSTRACT: Mobility management

More information

A Security Architecture for. Wireless Sensor Networks Environmental

A Security Architecture for. Wireless Sensor Networks Environmental Contemporary Engineering Sciences, Vol. 7, 2014, no. 15, 737-742 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ces.2014.4683 A Security Architecture for Wireless Sensor Networks Environmental

More information

Two-Level Metadata Management for Data Deduplication System

Two-Level Metadata Management for Data Deduplication System Two-Level Metadata Management for Data Deduplication System Jin San Kong 1, Min Ja Kim 2, Wan Yeon Lee 3.,Young Woong Ko 1 1 Dept. of Computer Engineering, Hallym University Chuncheon, Korea { kongjs,

More information

Lalit Saraswat 1 and Pankaj Singh Yadav 2

Lalit Saraswat 1 and Pankaj Singh Yadav 2 Computing For Nation Development, March 10 11, 2011 Bharati Vidyapeeth s Institute of Computer Applications and Management, New Delhi A Comparative Analysis of Wireless Sensor Network Operating Systems

More information

DESIGN ISSUES AND CLASSIFICATION OF WSNS OPERATING SYSTEMS

DESIGN ISSUES AND CLASSIFICATION OF WSNS OPERATING SYSTEMS DESIGN ISSUES AND CLASSIFICATION OF WSNS OPERATING SYSTEMS ANIL KUMAR SHARMA 1, SURENDRA KUMAR PATEL 2, & GUPTESHWAR GUPTA 3 1&2 Department of I.T. and Computer Application, Dr. C.V.Raman University, Kota,

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

A Data De-duplication Access Framework for Solid State Drives

A Data De-duplication Access Framework for Solid State Drives JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 28, 941-954 (2012) A Data De-duplication Access Framework for Solid State Drives Department of Electronic Engineering National Taiwan University of Science

More information

Designing and Embodiment of Software that Creates Middle Ware for Resource Management in Embedded System

Designing and Embodiment of Software that Creates Middle Ware for Resource Management in Embedded System , pp.97-108 http://dx.doi.org/10.14257/ijseia.2014.8.6.08 Designing and Embodiment of Software that Creates Middle Ware for Resource Management in Embedded System Suk Hwan Moon and Cheol sick Lee Department

More information

Design of a NAND Flash Memory File System to Improve System Boot Time

Design of a NAND Flash Memory File System to Improve System Boot Time International Journal of Information Processing Systems, Vol.2, No.3, December 2006 147 Design of a NAND Flash Memory File System to Improve System Boot Time Song-Hwa Park*, Tae-Hoon Lee*, and Ki-Dong

More information

Reconfigurable Architecture Requirements for Co-Designed Virtual Machines

Reconfigurable Architecture Requirements for Co-Designed Virtual Machines Reconfigurable Architecture Requirements for Co-Designed Virtual Machines Kenneth B. Kent University of New Brunswick Faculty of Computer Science Fredericton, New Brunswick, Canada ken@unb.ca Micaela Serra

More information

Using Protothreads for Sensor Node Programming

Using Protothreads for Sensor Node Programming Using Protothreads for Sensor Node Programming Adam Dunkels Swedish Institute of Computer Science adam@sics.se Oliver Schmidt oliver@jantzerschmidt.de Thiemo Voigt Swedish Institute of Computer Science

More information

An Active Packet can be classified as

An Active Packet can be classified as Mobile Agents for Active Network Management By Rumeel Kazi and Patricia Morreale Stevens Institute of Technology Contact: rkazi,pat@ati.stevens-tech.edu Abstract-Traditionally, network management systems

More information

How To Write An Underwater Operating System For A Sensor Network (Uan)

How To Write An Underwater Operating System For A Sensor Network (Uan) Aqua-OS: An Operating System for Underwater Acoustic Networks Haining Mo, Son Le, Zheng Peng, Zhijie Shi, and Jun-Hong Cui Department of Computer Science and Engineering, University of Connecticut, Storrs,

More information

How To Test A Robot Platform And Its Components

How To Test A Robot Platform And Its Components An Automated Test Method for Robot Platform and Its Components Jae-Hee Lim 1, Suk-Hoon Song 1, Jung-Rye Son 1, Tae-Yong Kuc 2, Hong-Seong Park 3, Hong-Seok Kim 4 1,2 School of Information and Communication,

More information

Load Balancing in Distributed Data Base and Distributed Computing System

Load Balancing in Distributed Data Base and Distributed Computing System Load Balancing in Distributed Data Base and Distributed Computing System Lovely Arya Research Scholar Dravidian University KUPPAM, ANDHRA PRADESH Abstract With a distributed system, data can be located

More information

Dynamic Memory Management for Embedded Real-Time Systems

Dynamic Memory Management for Embedded Real-Time Systems Dynamic Memory Management for Embedded Real-Time Systems Alfons Crespo, Ismael Ripoll and Miguel Masmano Grupo de Informática Industrial Sistemas de Tiempo Real Universidad Politécnica de Valencia Instituto

More information

HHB+tree Index for Functional Enhancement of NAND Flash Memory-Based Database

HHB+tree Index for Functional Enhancement of NAND Flash Memory-Based Database , pp. 289-294 http://dx.doi.org/10.14257/ijseia.2015.9.9.25 HHB+tree Index for Functional Enhancement of NAND Flash Memory-Based Database Huijeong Ju 1 and Sungje Cho 2 1,2 Department of Education Dongbang

More information

AN EFFICIENT STRATEGY OF AGGREGATE SECURE DATA TRANSMISSION

AN EFFICIENT STRATEGY OF AGGREGATE SECURE DATA TRANSMISSION INTERNATIONAL JOURNAL OF REVIEWS ON RECENT ELECTRONICS AND COMPUTER SCIENCE AN EFFICIENT STRATEGY OF AGGREGATE SECURE DATA TRANSMISSION K.Anusha 1, K.Sudha 2 1 M.Tech Student, Dept of CSE, Aurora's Technological

More information

Data Storage Framework on Flash Memory using Object-based Storage Model

Data Storage Framework on Flash Memory using Object-based Storage Model 2011 International Conference on Computer Science and Information Technology (ICCSIT 2011) IPCSIT vol. 51 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V51. 118 Data Storage Framework

More information

Least Slack Time Rate First: an Efficient Scheduling Algorithm for Pervasive Computing Environment

Least Slack Time Rate First: an Efficient Scheduling Algorithm for Pervasive Computing Environment Journal of Universal Computer Science, vol. 17, no. 6 (2011), 912-925 submitted: 15/5/10, accepted: 30/11/10, appeared: 28/3/11 J.UCS Least Slack Time Rate First: an Efficient Scheduling Algorithm for

More information

IMAV: An Intelligent Multi-Agent Model Based on Cloud Computing for Resource Virtualization

IMAV: An Intelligent Multi-Agent Model Based on Cloud Computing for Resource Virtualization 2011 International Conference on Information and Electronics Engineering IPCSIT vol.6 (2011) (2011) IACSIT Press, Singapore IMAV: An Intelligent Multi-Agent Model Based on Cloud Computing for Resource

More information

Analysis of Compression Algorithms for Program Data

Analysis of Compression Algorithms for Program Data Analysis of Compression Algorithms for Program Data Matthew Simpson, Clemson University with Dr. Rajeev Barua and Surupa Biswas, University of Maryland 12 August 3 Abstract Insufficient available memory

More information

An Efficient Hybrid Data Gathering Scheme in Wireless Sensor Networks

An Efficient Hybrid Data Gathering Scheme in Wireless Sensor Networks An Efficient Hybrid Data Gathering Scheme in Wireless Sensor Networks Ayon Chakraborty 1, Swarup Kumar Mitra 2, and M.K. Naskar 3 1 Department of CSE, Jadavpur University, Kolkata, India 2 Department of

More information

An Intelligent Car Park Management System based on Wireless Sensor Networks

An Intelligent Car Park Management System based on Wireless Sensor Networks An Intelligent Car Park Management System based on Wireless Sensor Networks Vanessa W.S. Tang, Yuan Zheng, Jiannong Cao Internet and Mobile Computing Lab Department of Computing, The Hong Kong Polytechnic

More information

Lecture 10: Dynamic Memory Allocation 1: Into the jaws of malloc()

Lecture 10: Dynamic Memory Allocation 1: Into the jaws of malloc() CS61: Systems Programming and Machine Organization Harvard University, Fall 2009 Lecture 10: Dynamic Memory Allocation 1: Into the jaws of malloc() Prof. Matt Welsh October 6, 2009 Topics for today Dynamic

More information

Data Management in Sensor Networks

Data Management in Sensor Networks Data Management in Sensor Networks Ellen Munthe-Kaas Jarle Søberg Hans Vatne Hansen INF5100 Autumn 2011 1 Outline Sensor networks Characteristics TinyOS TinyDB Motes Application domains Data management

More information

IMPLEMENTATION OF FPGA CARD IN CONTENT FILTERING SOLUTIONS FOR SECURING COMPUTER NETWORKS. Received May 2010; accepted July 2010

IMPLEMENTATION OF FPGA CARD IN CONTENT FILTERING SOLUTIONS FOR SECURING COMPUTER NETWORKS. Received May 2010; accepted July 2010 ICIC Express Letters Part B: Applications ICIC International c 2010 ISSN 2185-2766 Volume 1, Number 1, September 2010 pp. 71 76 IMPLEMENTATION OF FPGA CARD IN CONTENT FILTERING SOLUTIONS FOR SECURING COMPUTER

More information

Towards Lightweight Logging and Replay of Embedded, Distributed Systems

Towards Lightweight Logging and Replay of Embedded, Distributed Systems Towards Lightweight Logging and Replay of Embedded, Distributed Systems (Invited Paper) Salvatore Tomaselli and Olaf Landsiedel Computer Science and Engineering Chalmers University of Technology, Sweden

More information

Consecutive Geographic Multicasting Protocol in Large-Scale Wireless Sensor Networks

Consecutive Geographic Multicasting Protocol in Large-Scale Wireless Sensor Networks 21st Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications Consecutive Geographic Multicasting Protocol in Large-Scale Wireless Sensor Networks Jeongcheol Lee, Euisin

More information

Design of Remote data acquisition system based on Internet of Things

Design of Remote data acquisition system based on Internet of Things , pp.32-36 http://dx.doi.org/10.14257/astl.214.79.07 Design of Remote data acquisition system based on Internet of Things NIU Ling Zhou Kou Normal University, Zhoukou 466001,China; Niuling@zknu.edu.cn

More information

Segmentation. 16.1 Segmentation: Generalized Base/Bounds

Segmentation. 16.1 Segmentation: Generalized Base/Bounds 16 Segmentation So far we have been putting the entire address space of each process in memory. With the base and bounds registers, the OS can easily relocate processes to different parts of physical memory.

More information

Resource Allocation Schemes for Gang Scheduling

Resource Allocation Schemes for Gang Scheduling Resource Allocation Schemes for Gang Scheduling B. B. Zhou School of Computing and Mathematics Deakin University Geelong, VIC 327, Australia D. Walsh R. P. Brent Department of Computer Science Australian

More information

Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing

Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing www.ijcsi.org 227 Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing Dhuha Basheer Abdullah 1, Zeena Abdulgafar Thanoon 2, 1 Computer Science Department, Mosul University,

More information

Wireless Sensor Networks Database: Data Management and Implementation

Wireless Sensor Networks Database: Data Management and Implementation Sensors & Transducers 2014 by IFSA Publishing, S. L. http://www.sensorsportal.com Wireless Sensor Networks Database: Data Management and Implementation Ping Liu Computer and Information Engineering Institute,

More information

Adaptive Transaction Management Protocols for Mobile Client Caching DBMSs *

Adaptive Transaction Management Protocols for Mobile Client Caching DBMSs * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 18, 445-457 (2002) Short Paper Adaptive Transaction Management Protocols for Mobile Client Caching DBMSs * ILYOUNG CHUNG, LE GRUENWALD *, CHONG-SUN HWANG

More information

Binary search tree with SIMD bandwidth optimization using SSE

Binary search tree with SIMD bandwidth optimization using SSE Binary search tree with SIMD bandwidth optimization using SSE Bowen Zhang, Xinwei Li 1.ABSTRACT In-memory tree structured index search is a fundamental database operation. Modern processors provide tremendous

More information

A Slow-sTart Exponential and Linear Algorithm for Energy Saving in Wireless Networks

A Slow-sTart Exponential and Linear Algorithm for Energy Saving in Wireless Networks 1 A Slow-sTart Exponential and Linear Algorithm for Energy Saving in Wireless Networks Yang Song, Bogdan Ciubotaru, Member, IEEE, and Gabriel-Miro Muntean, Member, IEEE Abstract Limited battery capacity

More information

Parallel Ray Tracing using MPI: A Dynamic Load-balancing Approach

Parallel Ray Tracing using MPI: A Dynamic Load-balancing Approach Parallel Ray Tracing using MPI: A Dynamic Load-balancing Approach S. M. Ashraful Kadir 1 and Tazrian Khan 2 1 Scientific Computing, Royal Institute of Technology (KTH), Stockholm, Sweden smakadir@csc.kth.se,

More information

EFFICIENT EXTERNAL SORTING ON FLASH MEMORY EMBEDDED DEVICES

EFFICIENT EXTERNAL SORTING ON FLASH MEMORY EMBEDDED DEVICES ABSTRACT EFFICIENT EXTERNAL SORTING ON FLASH MEMORY EMBEDDED DEVICES Tyler Cossentine and Ramon Lawrence Department of Computer Science, University of British Columbia Okanagan Kelowna, BC, Canada tcossentine@gmail.com

More information

Adaptive MAC Protocol for Emergency Data Transmission in Wireless Body Sensor Networks

Adaptive MAC Protocol for Emergency Data Transmission in Wireless Body Sensor Networks , pp. 205-216 http://dx.doi.org/10.14257/ijseia.2015.9.9.18 Adaptive MAC Protocol for Emergency Data Transmission in Wireless Body Sensor Networks Rae Hyun Kim and Jeong Gon Kim 1 Department of Electronic

More information

Data Backup and Archiving with Enterprise Storage Systems

Data Backup and Archiving with Enterprise Storage Systems Data Backup and Archiving with Enterprise Storage Systems Slavjan Ivanov 1, Igor Mishkovski 1 1 Faculty of Computer Science and Engineering Ss. Cyril and Methodius University Skopje, Macedonia slavjan_ivanov@yahoo.com,

More information

A Web-Based Sensor Data Management System for Distributed Environmental Observation

A Web-Based Sensor Data Management System for Distributed Environmental Observation A Web-Based Sensor Data Management System for Distributed Environmental Observation Takahiro Torii, Yusuke Yokota, and Eiji Okubo Index Terms Sensor Web, sensor network, distributed data management, query

More information

Keywords Distributed Computing, On Demand Resources, Cloud Computing, Virtualization, Server Consolidation, Load Balancing

Keywords Distributed Computing, On Demand Resources, Cloud Computing, Virtualization, Server Consolidation, Load Balancing Volume 5, Issue 1, January 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Survey on Load

More information

Efficient Data Replication Scheme based on Hadoop Distributed File System

Efficient Data Replication Scheme based on Hadoop Distributed File System , pp. 177-186 http://dx.doi.org/10.14257/ijseia.2015.9.12.16 Efficient Data Replication Scheme based on Hadoop Distributed File System Jungha Lee 1, Jaehwa Chung 2 and Daewon Lee 3* 1 Division of Supercomputing,

More information

Using Received Signal Strength Variation for Surveillance In Residential Areas

Using Received Signal Strength Variation for Surveillance In Residential Areas Using Received Signal Strength Variation for Surveillance In Residential Areas Sajid Hussain, Richard Peters, and Daniel L. Silver Jodrey School of Computer Science, Acadia University, Wolfville, Canada.

More information

Performance Oriented Management System for Reconfigurable Network Appliances

Performance Oriented Management System for Reconfigurable Network Appliances Performance Oriented Management System for Reconfigurable Network Appliances Hiroki Matsutani, Ryuji Wakikawa, Koshiro Mitsuya and Jun Murai Faculty of Environmental Information, Keio University Graduate

More information

Development of Integrated Management System based on Mobile and Cloud service for preventing various dangerous situations

Development of Integrated Management System based on Mobile and Cloud service for preventing various dangerous situations Development of Integrated Management System based on Mobile and Cloud service for preventing various dangerous situations Ryu HyunKi, Moon ChangSoo, Yeo ChangSub, and Lee HaengSuk Abstract In this paper,

More information

Cyber Forensic for Hadoop based Cloud System

Cyber Forensic for Hadoop based Cloud System Cyber Forensic for Hadoop based Cloud System ChaeHo Cho 1, SungHo Chin 2 and * Kwang Sik Chung 3 1 Korea National Open University graduate school Dept. of Computer Science 2 LG Electronics CTO Division

More information

Lorien: A pure dynamic component-based Operating System for Wireless Sensor Networks

Lorien: A pure dynamic component-based Operating System for Wireless Sensor Networks Lorien: A pure dynamic component-based Operating System for Wireless Sensor Networks ABSTRACT Barry Porter Computing Department Lancaster University Lancaster, England barry.porter@comp.lancs.ac.uk In

More information

An Efficient Checkpointing Scheme Using Price History of Spot Instances in Cloud Computing Environment

An Efficient Checkpointing Scheme Using Price History of Spot Instances in Cloud Computing Environment An Efficient Checkpointing Scheme Using Price History of Spot Instances in Cloud Computing Environment Daeyong Jung 1, SungHo Chin 1, KwangSik Chung 2, HeonChang Yu 1, JoonMin Gil 3 * 1 Dept. of Computer

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

A RFID Data-Cleaning Algorithm Based on Communication Information among RFID Readers

A RFID Data-Cleaning Algorithm Based on Communication Information among RFID Readers , pp.155-164 http://dx.doi.org/10.14257/ijunesst.2015.8.1.14 A RFID Data-Cleaning Algorithm Based on Communication Information among RFID Readers Yunhua Gu, Bao Gao, Jin Wang, Mingshu Yin and Junyong Zhang

More information

15 th TF-Mobility Meeting Sensor Networks. Torsten Braun Universität Bern braun@iam.unibe.ch www.iam.unibe.ch/~rvs

15 th TF-Mobility Meeting Sensor Networks. Torsten Braun Universität Bern braun@iam.unibe.ch www.iam.unibe.ch/~rvs 15 th TF-Mobility Meeting Sensor Networks Torsten Braun Universität Bern braun@iam.unibe.ch www.iam.unibe.ch/~rvs Overview 2 Ubiquitous Computing > Vision defined by Mark Weiser in 1991 Seamless integration

More information

Enery Efficient Dynamic Memory Bank and NV Swap Device Management

Enery Efficient Dynamic Memory Bank and NV Swap Device Management Enery Efficient Dynamic Memory Bank and NV Swap Device Management Kwangyoon Lee and Bumyong Choi Department of Computer Science and Engineering University of California, San Diego {kwl002,buchoi}@cs.ucsd.edu

More information

RMTool: Component-Based Network Management System for Wireless Sensor Networks

RMTool: Component-Based Network Management System for Wireless Sensor Networks RMTool: Component-Based Network Management System for Wireless Sensor Networks Inuk Jung and Hojung Cha Department of Computer Science, Yonsei University, Sinchondong, Seodaemungu, Seoul, Korea {inukj,hjcha}@mobed.yonsei.ac.kr

More information

EFFICIENT DETECTION IN DDOS ATTACK FOR TOPOLOGY GRAPH DEPENDENT PERFORMANCE IN PPM LARGE SCALE IPTRACEBACK

EFFICIENT DETECTION IN DDOS ATTACK FOR TOPOLOGY GRAPH DEPENDENT PERFORMANCE IN PPM LARGE SCALE IPTRACEBACK EFFICIENT DETECTION IN DDOS ATTACK FOR TOPOLOGY GRAPH DEPENDENT PERFORMANCE IN PPM LARGE SCALE IPTRACEBACK S.Abarna 1, R.Padmapriya 2 1 Mphil Scholar, 2 Assistant Professor, Department of Computer Science,

More information

Keywords: Dynamic Load Balancing, Process Migration, Load Indices, Threshold Level, Response Time, Process Age.

Keywords: Dynamic Load Balancing, Process Migration, Load Indices, Threshold Level, Response Time, Process Age. Volume 3, Issue 10, October 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Load Measurement

More information

An Efficient QoS Routing Protocol for Mobile Ad-Hoc Networks *

An Efficient QoS Routing Protocol for Mobile Ad-Hoc Networks * An Efficient QoS Routing Protocol for Mobile Ad-Hoc Networks * Inwhee Joe College of Information and Communications Hanyang University Seoul, Korea iwj oeshanyang.ac.kr Abstract. To satisfy the user requirements

More information

Wireless Sensor Networks: A Distributed Operating Systems approach

Wireless Sensor Networks: A Distributed Operating Systems approach Wireless Sensor Networks: A Distributed Operating Systems approach Paul Hunkin University of Waikato pwh4@cs.waikato.ac.nz Tony McGregor University of Waikato tonym@cs.waikato.ac.nz ABSTRACT Wireless sensor

More information

Chapter 7 Memory Management

Chapter 7 Memory Management Operating Systems: Internals and Design Principles Chapter 7 Memory Management Eighth Edition William Stallings Frame Page Segment A fixed-length block of main memory. A fixed-length block of data that

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

Last Class: OS and Computer Architecture. Last Class: OS and Computer Architecture

Last Class: OS and Computer Architecture. Last Class: OS and Computer Architecture Last Class: OS and Computer Architecture System bus Network card CPU, memory, I/O devices, network card, system bus Lecture 3, page 1 Last Class: OS and Computer Architecture OS Service Protection Interrupts

More information

Development of Integrated Management System based on Mobile and Cloud Service for Preventing Various Hazards

Development of Integrated Management System based on Mobile and Cloud Service for Preventing Various Hazards , pp. 143-150 http://dx.doi.org/10.14257/ijseia.2015.9.7.15 Development of Integrated Management System based on Mobile and Cloud Service for Preventing Various Hazards Ryu HyunKi 1, Yeo ChangSub 1, Jeonghyun

More information

Preserving Message Integrity in Dynamic Process Migration

Preserving Message Integrity in Dynamic Process Migration Preserving Message Integrity in Dynamic Process Migration E. Heymann, F. Tinetti, E. Luque Universidad Autónoma de Barcelona Departamento de Informática 8193 - Bellaterra, Barcelona, Spain e-mail: e.heymann@cc.uab.es

More information

A Non-beaconing ZigBee Network Implementation and Performance Study

A Non-beaconing ZigBee Network Implementation and Performance Study A Non-beaconing ZigBee Network Implementation and Performance Study Magnus Armholt Email: magnus.armholt@tut.fi Sakari Junnila Email: sakari.junnila@tut.fi Irek Defee Email: irek.defee@tut.fi Abstract

More information

Dynamic Thread Pool based Service Tracking Manager

Dynamic Thread Pool based Service Tracking Manager Dynamic Thread Pool based Service Tracking Manager D.V.Lavanya, V.K.Govindan Department of Computer Science & Engineering National Institute of Technology Calicut Calicut, India e-mail: lavanya.vijaysri@gmail.com,

More information

DeuceScan: Deuce-Based Fast Handoff Scheme in IEEE 802.11 Wireless Networks

DeuceScan: Deuce-Based Fast Handoff Scheme in IEEE 802.11 Wireless Networks : Deuce-Based Fast Handoff Scheme in IEEE 82.11 Wireless Networks Yuh-Shyan Chen, Chung-Kai Chen, and Ming-Chin Chuang Department of Computer Science and Information Engineering National Chung Cheng University,

More information

QuickDB Yet YetAnother Database Management System?

QuickDB Yet YetAnother Database Management System? QuickDB Yet YetAnother Database Management System? Radim Bača, Peter Chovanec, Michal Krátký, and Petr Lukáš Radim Bača, Peter Chovanec, Michal Krátký, and Petr Lukáš Department of Computer Science, FEECS,

More information

Semester Thesis Traffic Monitoring in Sensor Networks

Semester Thesis Traffic Monitoring in Sensor Networks Semester Thesis Traffic Monitoring in Sensor Networks Raphael Schmid Departments of Computer Science and Information Technology and Electrical Engineering, ETH Zurich Summer Term 2006 Supervisors: Nicolas

More information

OPTIMIZED SENSOR NODES BY FAULT NODE RECOVERY ALGORITHM

OPTIMIZED SENSOR NODES BY FAULT NODE RECOVERY ALGORITHM OPTIMIZED SENSOR NODES BY FAULT NODE RECOVERY ALGORITHM S. Sofia 1, M.Varghese 2 1 Student, Department of CSE, IJCET 2 Professor, Department of CSE, IJCET Abstract This paper proposes fault node recovery

More information

ACCELERATING SELECT WHERE AND SELECT JOIN QUERIES ON A GPU

ACCELERATING SELECT WHERE AND SELECT JOIN QUERIES ON A GPU Computer Science 14 (2) 2013 http://dx.doi.org/10.7494/csci.2013.14.2.243 Marcin Pietroń Pawe l Russek Kazimierz Wiatr ACCELERATING SELECT WHERE AND SELECT JOIN QUERIES ON A GPU Abstract This paper presents

More information

Implementation and Performance Evaluation of M-VIA on AceNIC Gigabit Ethernet Card

Implementation and Performance Evaluation of M-VIA on AceNIC Gigabit Ethernet Card Implementation and Performance Evaluation of M-VIA on AceNIC Gigabit Ethernet Card In-Su Yoon 1, Sang-Hwa Chung 1, Ben Lee 2, and Hyuk-Chul Kwon 1 1 Pusan National University School of Electrical and Computer

More information

FPGA area allocation for parallel C applications

FPGA area allocation for parallel C applications 1 FPGA area allocation for parallel C applications Vlad-Mihai Sima, Elena Moscu Panainte, Koen Bertels Computer Engineering Faculty of Electrical Engineering, Mathematics and Computer Science Delft University

More information

Operating System for the K computer

Operating System for the K computer Operating System for the K computer Jun Moroo Masahiko Yamada Takeharu Kato For the K computer to achieve the world s highest performance, Fujitsu has worked on the following three performance improvements

More information

ENERGY-EFFICIENT TASK SCHEDULING ALGORITHMS FOR CLOUD DATA CENTERS

ENERGY-EFFICIENT TASK SCHEDULING ALGORITHMS FOR CLOUD DATA CENTERS ENERGY-EFFICIENT TASK SCHEDULING ALGORITHMS FOR CLOUD DATA CENTERS T. Jenifer Nirubah 1, Rose Rani John 2 1 Post-Graduate Student, Department of Computer Science and Engineering, Karunya University, Tamil

More information

A Novel Way of Deduplication Approach for Cloud Backup Services Using Block Index Caching Technique

A Novel Way of Deduplication Approach for Cloud Backup Services Using Block Index Caching Technique A Novel Way of Deduplication Approach for Cloud Backup Services Using Block Index Caching Technique Jyoti Malhotra 1,Priya Ghyare 2 Associate Professor, Dept. of Information Technology, MIT College of

More information

High-Performance IP Service Node with Layer 4 to 7 Packet Processing Features

High-Performance IP Service Node with Layer 4 to 7 Packet Processing Features UDC 621.395.31:681.3 High-Performance IP Service Node with Layer 4 to 7 Packet Processing Features VTsuneo Katsuyama VAkira Hakata VMasafumi Katoh VAkira Takeyama (Manuscript received February 27, 2001)

More information

Content-Aware Load Balancing using Direct Routing for VOD Streaming Service

Content-Aware Load Balancing using Direct Routing for VOD Streaming Service Content-Aware Load Balancing using Direct Routing for VOD Streaming Service Young-Hwan Woo, Jin-Wook Chung, Seok-soo Kim Dept. of Computer & Information System, Geo-chang Provincial College, Korea School

More information

3-12 Autonomous Access Control among Nodes in Sensor Networks with Security Policies

3-12 Autonomous Access Control among Nodes in Sensor Networks with Security Policies 3-12 Autonomous Access Control among Nodes in Sensor Networks with Security Policies This paper describes a new framework of policy control sensor networks. Sensor networks are shared by various applications,

More information

packet retransmitting based on dynamic route table technology, as shown in fig. 2 and 3.

packet retransmitting based on dynamic route table technology, as shown in fig. 2 and 3. Implementation of an Emulation Environment for Large Scale Network Security Experiments Cui Yimin, Liu Li, Jin Qi, Kuang Xiaohui National Key Laboratory of Science and Technology on Information System

More information

Contiki - a Lightweight and Flexible Operating System for Tiny Networked Sensors

Contiki - a Lightweight and Flexible Operating System for Tiny Networked Sensors Contiki - a Lightweight and Flexible Operating System for Tiny Networked Sensors Adam Dunkels, Björn Grönvall, Thiemo Voigt Swedish Institute of Computer Science {adam,bg,thiemo}@sics.se Abstract Wireless

More information

Security Optimization and Data Classification in Wireless Sensor Networks

Security Optimization and Data Classification in Wireless Sensor Networks Security Optimization and Data Classification in Wireless Sensor Networks Dilek Karabudak Computer Engineering Department Bilkent University Ankara, TR 653 Email: dilekk@cs.bilkent.edu.tr Abstract Large

More information

Performance analysis of a Linux based FTP server

Performance analysis of a Linux based FTP server Performance analysis of a Linux based FTP server A Thesis Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Technology by Anand Srivastava to the Department of Computer Science

More information

Congestion Control in WSN using Cluster and Adaptive Load Balanced Routing Protocol

Congestion Control in WSN using Cluster and Adaptive Load Balanced Routing Protocol Congestion Control in WSN using Cluster and Adaptive Load Balanced Routing Protocol Monu Rani 1, Kiran Gupta 2, Arvind Sharma 3 1 M.Tech (Student), 2 Assistant Professor, 3 Assistant Professor Department

More information

Forced Low latency Handoff in Mobile Cellular Data Networks

Forced Low latency Handoff in Mobile Cellular Data Networks Forced Low latency Handoff in Mobile Cellular Data Networks N. Moayedian, Faramarz Hendessi Department of Electrical and Computer Engineering Isfahan University of Technology, Isfahan, IRAN Hendessi@cc.iut.ac.ir

More information

Comparative Analysis of Congestion Control Algorithms Using ns-2

Comparative Analysis of Congestion Control Algorithms Using ns-2 www.ijcsi.org 89 Comparative Analysis of Congestion Control Algorithms Using ns-2 Sanjeev Patel 1, P. K. Gupta 2, Arjun Garg 3, Prateek Mehrotra 4 and Manish Chhabra 5 1 Deptt. of Computer Sc. & Engg,

More information

Voice Transmission over Wireless Sensor Networks

Voice Transmission over Wireless Sensor Networks Voice Transmission over Wireless Sensor Networks Lin-Huang Chang, Chao-Chieh Chen, Tsung-Han Lee Department of Computer and Information Science, National Taichung University, Taichung, Taiwan lchang@mail.ntcu.edu.tw

More information

A Study of Low Cost Meteorological Monitoring System Based on Wireless Sensor Networks

A Study of Low Cost Meteorological Monitoring System Based on Wireless Sensor Networks , pp.100-104 http://dx.doi.org/10.14257/astl.2014.45.19 A Study of Low Cost Meteorological Monitoring System Based on Wireless Sensor Networks Li Ma 1,2,3, Jingzhou Yan 1,2,Kuo Liao 3,4, Shuangshuang Yan

More information

Design and Implementation of the Heterogeneous Multikernel Operating System

Design and Implementation of the Heterogeneous Multikernel Operating System 223 Design and Implementation of the Heterogeneous Multikernel Operating System Yauhen KLIMIANKOU Department of Computer Systems and Networks, Belarusian State University of Informatics and Radioelectronics,

More information

CROSS LAYER BASED MULTIPATH ROUTING FOR LOAD BALANCING

CROSS LAYER BASED MULTIPATH ROUTING FOR LOAD BALANCING CHAPTER 6 CROSS LAYER BASED MULTIPATH ROUTING FOR LOAD BALANCING 6.1 INTRODUCTION The technical challenges in WMNs are load balancing, optimal routing, fairness, network auto-configuration and mobility

More information

Delivering Quality in Software Performance and Scalability Testing

Delivering Quality in Software Performance and Scalability Testing Delivering Quality in Software Performance and Scalability Testing Abstract Khun Ban, Robert Scott, Kingsum Chow, and Huijun Yan Software and Services Group, Intel Corporation {khun.ban, robert.l.scott,

More information

Accelerate Cloud Computing with the Xilinx Zynq SoC

Accelerate Cloud Computing with the Xilinx Zynq SoC X C E L L E N C E I N N E W A P P L I C AT I O N S Accelerate Cloud Computing with the Xilinx Zynq SoC A novel reconfigurable hardware accelerator speeds the processing of applications based on the MapReduce

More information