Computer Science ›› 2020, Vol. 47 ›› Issue (10): 247-255.doi: 10.11896/jsjkx.190900106

• Computer Network • Previous Articles     Next Articles

Computation Offloading Scheduling Technology for DNN Applications in Edge Environment

HU Jun-qin1,2, ZHANG Jia-jun1,2, HUANG Yin-hao1,2, CHEN Xing1,2, LIN Bing2,3   

  1. 1 College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350116,China
    2 Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou 350116,China
    3 College of Physics and Energy,Fujian Normal University,Fuzhou 350117,China
  • Received:2019-09-16 Revised:2019-10-22 Online:2020-10-15 Published:2020-10-16
  • About author:HU Jun-qin,born in 1997,postgraduate.His main research interests include computation offloading and Intelligent Computing.
    CHEN Xing,born in 1985,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include system software,software self-adaptation and cloud computing.
  • Supported by:
    National Key R&D Program of China (2018YFB1004800),Talent Program of Fujian Province for Distinguished Young Scholars in Higher Education and Guiding Project of Fujian Province (2018H0017).

Abstract: Deep neural network (DNN) applications require high performance of running equipment,and can not run directly on mobile devices with limited computing resources.It is an effective method to offload some computationally complex neural network layers to resource-rich edges or remote clouds for execution by computation offloading technology.Computation offloading will incur additional time overhead.If the offloading process lasts too long,the user experience will be seriously affected.To this end,in order to obtain the minimum average response time of multi-task parallel scheduling in edge environment,this paper first proposes the computation offloading scheduling problem for DNN applications in edge environment,and designs an evaluation algorithm for the solution to the problem.Then two scheduling algorithms,greedy algorithm and genetic algorithm,are designed to solve the problem.Finally,an evaluation experiment is set up to compare and analyze the performance of the two algorithms in five different edge environments.The experimental data shows that the solution obtained by the proposed algorithms in this paper is very close to the optimal solution.Compared with traditional offloading schemes,greedy algorithm can obtain a scheduling scheme with shorter average response time.The average response time of genetic algorithm is shorter than that of greedy algorithm,but its running time is significantly longer.The experimental results show that the proposed two scheduling algorithms can effectively reduce the average response time of computation offloading scheduling for DNN applications in edge environment and improve user experience.

Key words: Computation offloading, DNN applications, Edge computing, Genetic algorithm, Greedy algorithm, Task scheduling

CLC Number: 

  • TP301
[1]CHEN X,JIAO L,LI W,et al.Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing [J].IEEE/ACM Transactions on Networking,2015,24(5):2795-2808.
[2]KUMAR K,LIU J,LU Y H,et al.A Survey of Computation Offloading for Mobile Systems [J].Mobile Networks & Applications,2013,18(1):129-140.
[3]WANG C,LI Z.A Computation Offloading Scheme on Handheld Devices [J].Journal of Parallel & Distributed Computing,2004,64(6):740-746.
[4]KANG Y P,HAUSWALD J,GAO C,et al.Neurosurgeon:Collaborative Intelligence Bet-ween the Cloud and Mobile Edge [J].Acm Sigplan Notices,2017,52(4):615-629.
[5]JIA M,LIANG W F,XU Z C,et al.QoS-Aware Cloudlet Load Balancing in Wireless Metropolitan Area Networks [J].IEEE Transactions on Cloud Computing,2018,PP(99):1-1.
[6]LIU J Y,WANG X W,HUANG M.Research on an Intelligent Local Mobile Cloud Resource Allocation Mechanism[J].Netinfo Security,2016(10):60-68.
[7]WANG D L,YI J Y,LI S H,et al.Task Scheduling of Cloud Computing Based on Fusion of Load Balancing and Bat Algorithm[J].Netinfo Security,2017(1):23-28.
[8]BHARATI R D,SURADKAR J A.Computation Offloading:Overview,Frameworks and Challenges [J].International Journal of Computer Applications,2016,134(6):28-31.
[9]FENG X,DING F,JIE L,et al.Phone2Cloud:Exploiting Computation Offloading for Energy Saving on Smartphones in Mobile Cloud Com-puting [J].Information Systems Frontiers,2014,16(1):95-111.
[10]ALAM G R,HASSAN M M,UDDIN M Z,et al.AutonomicComputation Offloading in Mobile Edge for IoT Applications [J].Future Generation Computer Systems,2019,90(1):149-157.
[11]MACH P,BECVAR Z.Mobile Edge Computing:A Survey onArchitecture and Com-putation Offloading [J].IEEE Communications Surveys & Tutorials,2017,19(3):1-1.
[12]JEONG H J,JEONG I C,LEE H J,et al.Computation Offloading for Machine Learning Web Apps in the Edge Server Environment[C]//2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).New York:IEEE,2018:1492-1499.
[13]JIA M,CAO J,LEI Y.Heuristic Offloading of Concurrent Tasks for Computation-intensive Applications in Mobile Cloud Computing[C]//Computer Communications Workshops.New York:IEEE Press,2014:352-357.
[14]MAO Y,ZHANG J,LETAIEF K B,et al.Dynamic Computation Offloading for Mobile-Edge Computing With Energy Harvesting Devices [J].IEEE Journal on Selected Areas in Communications,2016,34(12):3590-3605.
[15]LIU J,MAO Y,ZHANG J,et al.Delay Optimal Computation Task Scheduling for Mobile-Edge Computing Systems[C]// IEEE International Symposium on Information Theory.New York:IEEE Press,2016:1451-1455.
[16]GUO S,LIU J,YANG Y,et al.Energy-Efficient Dynamic Computation Offloading and Cooperative Task Scheduling in Mobile Cloud Com-puting [J].IEEE Transactions on Mobile Computing,2019,18(2):319-333.
[17]ZHANG Y,CHEN X,CHEN Y,et al.Cost Efficient Scheduling for Delay-Sensitive Tasks in Edge Computing System[C]//2018 IEEE International Conference on Services Computing (SCC).New York:IEEE Press,2018:73-80.
[18]QI B,WU M,ZHANG L.A DNN-based Object Detection System on Mobile Cloud Computing[C]//2017 17th International Symposium on Communications and Information Technologies (ISCIT).New York:IEEE Press,2017:1-6.
[19]OMARA F A,ARAFA M M.Genetic Algorithms for TaskScheduling Problem [J].Journal of Parallel and Distributed Computing,2010,70(1):13-22.
[20]WU A S,YU H,JIN S,et al.An Incremental Genetic Algorithm Approach to Multiprocessor Scheduling [J].IEEE Transactions on Parallel and Distributed Systems,2004,15(9):824-834.
[21]KWOK Y,AHMAD I.Static Scheduling Algorithms for Allocating Directed Task Graphs to Multiprocessors [J].Acm Computing Surveys,1999,31(4):406-471.
[22]ZHONG J,HU X,GU M,et al.Comparison of Performance between Different Selection Strategies on SimpleGenetic Algorithms[C]//Computational Intelligence for Modelling,Control and Automation.New York:IEEE Press,2005:1115-1121.
[23]UMBARKAR A J,SHETH P D.Crossover Operators in Genetic Algorithms:A Review [J].ICTACT Journal on Soft Computing,2015,6(1):1083-1092.
[24]LIM S M,SULTAN A B,SULAIMAN M N,et al.Crossover and Mutation Operators of Genetic Algorithms [J].International Journal of Machine Learning and Computing,2017,7(1):9-12.
[1] SUN Hui-ting, FAN Yan-fang, MA Meng-xiao, CHEN Ruo-yu, CAI Ying. Dynamic Pricing-based Vehicle Collaborative Computation Offloading Scheme in VEC [J]. Computer Science, 2022, 49(9): 242-248.
[2] YU Bin, LI Xue-hua, PAN Chun-yu, LI Na. Edge-Cloud Collaborative Resource Allocation Algorithm Based on Deep Reinforcement Learning [J]. Computer Science, 2022, 49(7): 248-253.
[3] ZHANG Chong-yu, CHEN Yan-ming, LI Wei. Task Offloading Online Algorithm for Data Stream Edge Computing [J]. Computer Science, 2022, 49(7): 263-270.
[4] LI Meng-fei, MAO Ying-chi, TU Zi-jian, WANG Xuan, XU Shu-fang. Server-reliability Task Offloading Strategy Based on Deep Deterministic Policy Gradient [J]. Computer Science, 2022, 49(7): 271-279.
[5] YUAN Hao-nan, WANG Rui-jin, ZHENG Bo-wen, WU Bang-yan. Design and Implementation of Cross-chain Trusted EMR Sharing System Based on Fabric [J]. Computer Science, 2022, 49(6A): 490-495.
[6] YANG Hao-xiong, GAO Jing, SHAO En-lu. Vehicle Routing Problem with Time Window of Takeaway Food ConsideringOne-order-multi-product Order Delivery [J]. Computer Science, 2022, 49(6A): 191-198.
[7] FANG Tao, YANG Yang, CHEN Jia-xin. Optimization of Offloading Decisions in D2D-assisted MEC Networks [J]. Computer Science, 2022, 49(6A): 601-605.
[8] LIU Zhang-hui, ZHENG Hong-qiang, ZHANG Jian-shan, CHEN Zhe-yi. Computation Offloading and Deployment Optimization in Multi-UAV-Enabled Mobile Edge Computing Systems [J]. Computer Science, 2022, 49(6A): 619-627.
[9] XIE Wan-cheng, LI Bin, DAI Yue-yue. PPO Based Task Offloading Scheme in Aerial Reconfigurable Intelligent Surface-assisted Edge Computing [J]. Computer Science, 2022, 49(6): 3-11.
[10] SHEN Biao, SHEN Li-wei, LI Yi. Dynamic Task Scheduling Method for Space Crowdsourcing [J]. Computer Science, 2022, 49(2): 231-240.
[11] ZHANG Hai-bo, ZHANG Yi-feng, LIU Kai-jian. Task Offloading,Migration and Caching Strategy in Internet of Vehicles Based on NOMA-MEC [J]. Computer Science, 2022, 49(2): 304-311.
[12] LIN Chao-wei, LIN Bing, CHEN Xing. Study on Scientific Workflow Scheduling Based on Fuzzy Theory Under Edge Environment [J]. Computer Science, 2022, 49(2): 312-320.
[13] TAN Shuang-jie, LIN Bao-jun, LIU Ying-chun, ZHAO Shuai. Load Scheduling Algorithm for Distributed On-board RTs System Based on Machine Learning [J]. Computer Science, 2022, 49(2): 336-341.
[14] WU Shan-jie, WANG Xin. Prediction of Tectonic Coal Thickness Based on AGA-DBSCAN Optimized RBF Neural Networks [J]. Computer Science, 2021, 48(7): 308-315.
[15] LIANG Jun-bin, ZHANG Hai-han, JIANG Chan, WANG Tian-shu. Research Progress of Task Offloading Based on Deep Reinforcement Learning in Mobile Edge Computing [J]. Computer Science, 2021, 48(7): 316-323.
Full text



No Suggested Reading articles found!