A Joint Allocation Algorithm of Computing and Communication Resources Based on Reinforcement Learning in MEC System
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
For the mobile edge computing (MEC) system supporting dense network, a joint allocation algorithm ofcomputing and communication resources based on reinforcement learning is proposed. The energyconsumption of task execution is defined as the maximum energy consumption of each user's task execution inthe system. Considering the constraints of task unloading, power allocation, transmission rate and calculationresource allocation, the problem of joint task unloading and resource allocation is modeled as a problem ofmaximum task execution energy consumption minimization. As a mixed integer nonlinear programmingproblem, it is difficult to be directly solve by traditional optimization methods. This paper uses reinforcementlearning algorithm to solve this problem. Then, the Markov decision-making process and the theoretical basisof reinforcement learning are introduced to provide a theoretical basis for the algorithm simulation experiment. Based on the algorithm of reinforcement learning and joint allocation of communication resources, the jointoptimization of data task unloading and power control strategy is carried out for each terminal device, and thelocal computing model and task unloading model are built. The simulation results show that the total taskcomputation cost of the proposed algorithm is 5%–10% less than that of the two comparison algorithms underthe same task input. At the same time, the total task computation cost of the proposed algorithm is more than5% less than that of the two new comparison algorithms.
Abstract
For the mobile edge computing (MEC) system supporting dense network, a joint allocation algorithm ofcomputing and communication resources based on reinforcement learning is proposed. The energyconsumption of task execution is defined as the maximum energy consumption of each user's task execution inthe system. Considering the constraints of task unloading, power allocation, transmission rate and calculationresource allocation, the problem of joint task unloading and resource allocation is modeled as a problem ofmaximum task execution energy consumption minimization. As a mixed integer nonlinear programmingproblem, it is difficult to be directly solve by traditional optimization methods. This paper uses reinforcementlearning algorithm to solve this problem. Then, the Markov decision-making process and the theoretical basisof reinforcement learning are introduced to provide a theoretical basis for the algorithm simulation experiment. Based on the algorithm of reinforcement learning and joint allocation of communication resources, the jointoptimization of data task unloading and power control strategy is carried out for each terminal device, and thelocal computing model and task unloading model are built. The simulation results show that the total taskcomputation cost of the proposed algorithm is 5%–10% less than that of the two comparison algorithms underthe same task input. At the same time, the total task computation cost of the proposed algorithm is more than5% less than that of the two new comparison algorithms.
참고문헌 (16)
- P. Mach, "Mobile edge computing : a survey on architecture and computation offloading", IEEE Communications Surveys & Tutorials, 19(3), pp.1628~1656 (2017)
- C. Li, "Dynamic multi-user computation offloading for wireless powered mobile edge computing", Journal of Network and Computer Applications, 131, pp.1~15 (2019)
- Y. Mao, "A survey on mobile edge computing : the communication perspective", IEEE Communications Surveys & Tutorials, 19(4), pp.2322~2358 (2017)
- J. Liu, "Delay-optimal computation task scheduling for mobile-edge computing systems", Proceedings of 2016 IEEE International Symposium on Information Theory (ISIT), pp.1451~1455 (2016)
- M. H. Chen, "Joint offloading decision and resource allocation for multi-user multitask mobile cloud", Proceedings of 2016 IEEE International Conference on Communications (ICC),, pp.1~6 (2016)
- M. H. Chen, "Joint offloading and resource allocation for computation and communication in mobile cloud with computing access point", Proceedings of the IEEE Conference on Computer Communications (INFOCOM),, pp.1~9 (2017)
- J. Li, "Deep reinforcement learning based computation offloading and resource allocation for MEC", Proceedings of 2018 IEEE Wireless Communications and Networking Conference (WCNC),, pp.1~6 (2018)
- Z. Wei, "Dynamic edge computation offloading for internet of things with energy harvesting : a learning method", IEEE Internet of Things Journal, 6(3), pp.4436~4447 (2018)
- W. Chen, "Cost minimization for cooperative mobile edge computing systems", Proceedings of 2019 28th Wireless and Optical Communications Conference (WOCC),, pp.1~5 (2019)
- T. Q. Dinh, "Offloading in mobile edge computing : task allocation and computational frequency scaling", IEEE Transactions on Communications, 65(8), pp.3571~3584 (2017)
- Z. Zhang, "Collaborative task offloading with computation result reusing for mobile edge computing", The Computer Journal, 62(10), pp.1450~1462 (2019)
- T. Alfakih, "Task offloading and resource allocation for mobile edge computing by deep reinforcement learning based on SARSA", IEEE Access, 8, pp.54074~54084 (2020)
- T. D. Parker, "Cortical microstructure in young onset Alzheimer's disease using neurite orientation dispersion and density imaging", Human Brain Mapping, 39(7), pp.3005~3017 (2018)
- D. Ramachandran, "Smoothed sarsa : reinforcement learning for robot delivery tasks", Proceedings of 2009 IEEE International Conference on Robotics and Automation, pp.2125~2132 (2009)
- A. Larmo, "RAN overload control for machine type communications in LTE", Proceedings of 2012 IEEE Globecom Workshops, pp.1626~1631 (2012)
- X. Chen, "Efficient multi-user computation offloading for mobile-edge cloud computing", IEEE, 2015, pp.24(5), 2795~2808