Non-Cooperative Computation Offloading in Mobile Cloud Computing



Similar documents
A game-theoretic approach to computation offloading in mobile cloud computing

Processing of Mix- Sensi0vity Video Surveillance Streams on Hybrid Clouds

Toward a Smart Platform for Data Stream Processing in Smart Cities: Distributed Qos-aware Scheduling in Storm

Optimal Pricing and Service Provisioning Strategies in Cloud Systems: A Stackelberg Game Approach

Experiments on cost/power and failure aware scheduling for clouds and grids

Cloud Compu?ng & Big Data in Higher Educa?on and Research: African Academic Experience

EDUCATION Laurea degree in Computer Science summa cum laude from the University of Pisa, Italy in 1984.

Chapter 3. Database Architectures and the Web Transparencies

Mobile Cloud Computing: Paradigms and Challenges 移 动 云 计 算 : 模 式 与 挑 战

Data Management in the Cloud: Limitations and Opportunities. Annies Ductan

A Game Theoretic Formulation of the Service Provisioning Problem in Cloud Systems

Communica)on and sensor network technologies for smart ci)es

Internet Storage Sync Problem Statement

Mobile Hybrid Cloud Computing Issues and Solutions

Scalable Mul*- Class Traffic Management in Data Center Backbone Networks

MTD Keystone s Multiple Service Platforms

Business Con*nuity with Docker

So#ware Product Lines for Automa5c Mul5- Cloud Configura5on

Contrail : Open Compu0ng Infrastructures For Elas0c Services Un approccio federa0vo alla creazione di pia=aforme Cloud affidabili

How To Make A Cloud Based Computer Power Available To A Computer (For Free)

Cloud Compu)ng: Overview & challenges. Aminata A. Garba

NCTA Cloud Architecture

Leveraging the Hybrid Cloud For Complete Data Protec:on. Private Public Managed

How To Understand Cloud Computing

IMCM: A Flexible Fine-Grained Adaptive Framework for Parallel Mobile Hybrid Cloud Applications

Data Center Evolu.on and the Cloud. Paul A. Strassmann George Mason University November 5, 2008, 7:20 to 10:00 PM

Gaming as a Service. Prof. Victor C.M. Leung. The University of British Columbia, Canada

Software-Defined Networking

Scalus A)ribute Workshop. Paris, April 14th 15th

Generalized Nash Equilibria for the Service Provisioning Problem in Cloud Systems

Can Cloud Hos+ng Providers Really Replace. Your Cri(cal IT Infrastructure?

Heuristic policies for SLA provisioning in Cloud-based service providers

Project Por)olio Management

Resource Pricing and Provisioning Strategies in Cloud Systems: A Stackelberg Game Approach

Big Data. The Big Picture. Our flexible and efficient Big Data solu9ons open the door to new opportuni9es and new business areas

ICN based Scalable Video Conferencing on Virtual Edge Service Routers (VSER) Platform

OFERTIE OpenFlow Experiments in Real- Time Interac7ve Edutainment

Cloud computing research activities at. Jordan University of Science and Technology. Yaser Jararweh. Irbid, Jordan

Cloud Compu)ng in Educa)on and Research

Mobile Cloud Computing. Chamitha de Alwis, PhD Senior Lecturer University of Sri Jayewardenepura

How To Create An Ad Hoc Cloud On A Cell Phone

Parametric Analysis of Mobile Cloud Computing using Simulation Modeling

SUMMIT. November 2010

The Development of Cloud Interoperability

AWS Security & Compliance

GÉANT Cloud Ac-vity Towards Pan- European Cloud Services Kris?n Selvaag

How To Manage A Mobile Device Management At Harvard

Mobile Computing: the Next Decade

Contact Center Rou,ng Strategies for Improving Customer Experience

The Library (Big) Data scien4st

Cisco. Daneyon Hansen 3/28/ Cisco and/or its affiliates. All rights reserved. Cisco Confiden+al 1

Interna'onal Standards Ac'vi'es on Cloud Security EVA KUIPER, CISA CISSP HP ENTERPRISE SECURITY SERVICES

GRNET Cloud Compu7ng Services An Overview

N. J. Pramod Dhinakar 1, G. Kishore Kumar 2, M. Raghavendra 3

Everything You Need to Know about Cloud BI. Freek Kamst

Cloud Compu)ng. Yeow Wei CHOONG Anne LAURENT

Return on Experience on Cloud Compu2ng Issues a stairway to clouds. Experts Workshop Nov. 21st, 2013

From reconfigurable transceivers to reconfigurable networks, part II: Cognitive radio networks. Loreto Pescosolido

1294 IEEE COMMUNICATIONS SURVEYS & TUTORIALS, VOL. 15, NO. 3, THIRD QUARTER 2013

Project Overview. Collabora'on Mee'ng with Op'mis, Sept. 2011, Rome

Mobile Cloud Computing Challenges

Components of Technology Suppor4ng Data Intensive Research

Mission. To provide higher technological educa5on with quality, preparing. competent professionals, with sound founda5ons in science, technology

FUTURE URBAN SYSTEMS: THE CONVERGENCE OF A SMART INTEGRATED INFRASTRUCTURE

Every time you use a voice command. A Brief History of. A Personal Journey from Odyssey Through Cyber Foraging to Cloudlets.

Big Data and Clouds: Challenges and Opportuni5es

Chapter 19 Cloud Computing for Multimedia Services

Data Warehousing. Yeow Wei Choong Anne Laurent

The Last Piece of the Puzzle From Legacy to SDN and NFV. Benjamin Then

emontage: An Architecture for Rapid Integration of Situational Awareness Data at the Edge

Getting Real with Policies for Software Defined Infrastructure. Manish Dave Principal Engineer, Intel IT

SDN- based Mobile Networking for Cellular Operators. Seil Jeon, Carlos Guimaraes, Rui L. Aguiar

1. Introduc+on and Background. 2. Service Overview. 3. Your Requirements. Cloud Services so far Feasibility Study Next Steps Procurement, POC

Ch. 13 Cloud Services. Magda El Zarki Dept. of CS UC, Irvine

Webinar: Having the Best of Both World- Class Customer Experience and Comprehensive Iden=ty Security

Low-Overhead Hard Real-time Aware Interconnect Network Router

Data Center DC planning for the next 5 10 years. Copyright Experture and Robert Frances Group, all rights reserved

Integrating Mobile Internet of Things and Cloud Computing towards Scalability: Lessons Learned from Existing Fog Computing Architectures

Generalized Architecture for Dynamic Infrastructure Services

Nokia Datacenter Services

Asynchronous Dynamic Load Balancing (ADLB)

CHAPTER 7 SUMMARY AND CONCLUSION

IoT Week 2015 Lisbon June, 16 th - 18 th 2015

Mobile Cloud Computing: Survey & Discussion. Jianting Yue Sep 27, 2013

Cloud Computing project Report

Map- reduce, Hadoop and The communica3on bo5leneck. Yoav Freund UCSD / Computer Science and Engineering

A Comparative Study of cloud and mcloud Computing

A Virtual Cloud Computing Provider for Mobile Devices

Cloudian The Storage Evolution to the Cloud.. Cloudian Inc. Pre Sales Engineering

Automated Provisioning of Cloud and Cloudlet Applications

Hybrid Cloud Customer Engagements

BUILDING BLOCKS AND CHALLENGES. of the Internet of Things

Denis Caromel, CEO Ac.veEon. Orchestrate and Accelerate Applica.ons. Open Source Cloud Solu.ons Hybrid Cloud: Private with Burst Capacity

Reducing Configuration Complexity with Next Gen IoT Networks

Telephone Related Queries (TeRQ) IETF 85 (Atlanta)

UAB Cyber Security Ini1a1ve

ANALYTICAL TECHNIQUES FOR DATA VISUALIZATION

Seamless Application Execution in Mobile Cloud Computing: Motivation, Taxonomy, and Open Challenges

Web Application Deployment in the Cloud Using Amazon Web Services From Infancy to Maturity

DDS-Enabled Cloud Management Support for Fast Task Offloading

Transcription:

Joint CLEEN and ACROSS Workshop on Cloud Technology and Energy Efficiency in Mobile Communications Non-Cooperative Computation Offloading in Mobile Cloud Computing Valeria Cardellini University of Roma Tor Vergata, Italy Joint work with: V. De Nitto Personè, V. Di Valerio, F. Facchinei, V. Grassi, F. Lo Presti, V. Piccialli

Computation offloading n Mobile devices have limited computing and processing capabilities Battery life! n Old idea: offload computation to some surrogate server (cyber foraging) n Mobile-cloud convergence n Increasing number of latency-sensitive, compute-intensive and memory-intensive applications on mobile devices Wearable cognitive assistance, edge analytics in IoT, automotive environments, Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 2

Cloud- based augmenta0on of mobile devices n Resource- limited mobile devices can overcome their limita0ons by offloading opera0ons to more powerful servers Either proximate, i.e. single hop (cloudlet) or mul0- hop (cloud data center) Wireless AP Mobile devices Cloudlet Distant cloud servers on Internet Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 3

Cloudlet n Self- managed data center with soc state and located at the network edge Consistent with Fog compu0ng ( Fog is the cloud close to the ground ) and micro cloud concepts n Example of cloudlet infrastructure and socware Cloudlet- specific extensions to OpenStack (by Satya at CMU) Nokia LTE base sta0on with cloudlet- like hos0ng infrastructure Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 4

Three- 0er architecture n Hybrid three- 0er architecture for mobile- cloud convergence Local 0er: mobile nodes Middle 0er: energy- unlimited but resource- limited nearby cloudlets within one wireless hop of mobile devices Remote 0er: resourceful distant cloud servers n Where to offload? How to get the benefits of external servers for offloading while limi0ng latency issues of distant servers and considering energy constraints of mobile devices Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 5

Our proposal n Non- coopera0ve game theore0c approach to analyze and manage the computa0on offloading strategy Unmanaged usage scenario: no central authority Mul0ple non- coopera0ve mobile devices share the cloudlet limited compu0ng resources Mobile devices can send their computa0ons to any of the three 0ers V. Cardellini, V. De NiTo Personè, V. Di Valerio, F. Facchinei, V. Grassi, F. Lo Pres0, V. Picciali, A game- theore0c approach to computa0on offloading in mobile cloud compu0ng, Mathema5cal Programming, available online, Apr. 2015. Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 6

Our goal n Determine whether and where to offload a task based on the impact this has on the user experience, expressed through QoS measures Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 7

System model n Standard queueing theory for system model To capture the effects of computa0on offloading (i.e., task conten0on on shared resources) on users perceived performance Focus on task response 0me 8

Problem formula0on n To determine the op0mal strategy, each user needs to solve: n Problem formula0on: generalized Nash equilibrium problem (GNEP) Both the players objec0ve func0ons and the strategy sets depend on the other players strategies Jointly convex game (common linear constraint) 9

GNEP proper0es and distributed algorithm n Game can be solved by finding a solu0on to a suitable Varia0onal Inequality We show equilibrium existence and monotonicity proper0es of the GNEP n Distributed algorithm for compu0ng an equilibrium strategy for each mobile user n Its design required us: To analyze in- depth the underlying equilibrium problem To apply some very recent algorithmic developments n Appealing for real- world implementa0on Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 10

Distributed algorithm n Synchronous and itera0ve Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 11

Numerical results cloudlet cloudlet cloud mobile mobile cloud Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 12

Numerical results cloudlet mobile cloud cloudlet n Price of anarchy Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 13

Prototype architecture n Working prototype based on offloading middleware Offloading at method granularity Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 14

Prototype addi0onal features n Adapta0on capabili0es based on MAPE cycle n Discovery and deployment of offloading service Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 15

Prototype results: face recogni0on Cloud server: AWS EC2 m3.xlarge Cloud server: AWS EC2 m3.2xlarge Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 16

Conclusions n Non- coopera0ve usage scenario for computa0on offloading in a three- 0er architecture Users try to take advantage selfishly of the available cloudlet resources Solu0on with solid theore0cal founda0on and appealing for real- world implementa0on Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 17

Future work n Possible extension of our proposal Remove limita0on on user generated load (cannot exceed the mobile device capacity) Consider mul0ple class model of tasks launched by users Include monetary cost n More general challenges Use cloudlets to improve reliability Consider mul0ple (possibly coopera0ve) cloudlets Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 18

That s All Folks! Thank you for the aten0on cardellini@ing.uniroma2.it htp://www.ce.uniroma2.it/~valeria Non-Cooperative Computation Offloading in Mobile Cloud Computing @EUCNC'15 Workshop 1, June 29 2015 19