Optimization Method for Task Offloading Decision and Edge Resource Allocation in Distribution Networks

doi:10.3778/j.issn.1002-8331.2304-0293

Abstract

Abstract: Mobile edge computing can reduce the pressure of massive data transmission and processing in core distribution networks, compared to cloud computing, the computing limitations of edge nodes poses a challenge to the efficient utilization of edge resources. Based on this, a task offloading decision and edge resource allocation optimization method in distribution networks is proposed. First of all, in a distribution network scenario containing multiple edge nodes and multiple user devices, a cloud-edge-end three-layer edge computing offloading and resource allocation model is constructed. Secondly, the optimization process is divided into two stages：computing offloading and resource auction. In computing offloading stage, an online decision algorithm based on DRL is proposed, and in resource auction stage, a multi round iterative auction mechanism based on compensation strategy is designed. Finally, a task offloading and resource allocation optimization method based on improved DQN algorithm is proposed. The simulation results show that the proposes algorithm can effectively improve system computing energy efficiency and edge node efficiency in dynamically changing distribution network scenarios.

Key words: mobile edge computing, distribution network, task offloading, resource allocation

摘要： 移动边缘计算可以减轻配电网核心网络中海量数据的传输及处理压力，相对于云计算，边缘节点有限的计算能力使边缘资源的高效利用成为挑战。基于此，提出一种配电网中任务卸载决策与边缘资源分配优化方法。在包含多边缘节点多用户设备的配电网场景中，考虑任务随机、资源有限、计算能力不均衡及时延要求高等因素，构建云-边-端三层任务卸载及边缘资源分配优化模型；将优化过程分为计算卸载和资源拍卖两个阶段，在计算卸载阶段设计基于DRL的在线决策算法，在资源拍卖阶段设计基于补偿策略的多轮迭代拍卖算法；提出基于改进DQN算法的任务卸载与资源分配优化方法。仿真结果表明，在动态变化的配电网场景中，所提算法可有效提高系统计算能效和边缘节点效益。

关键词: 移动边缘计算, 配电网, 任务卸载, 资源分配

DUO Chunhong, KUANG Zhu, QI Guoliang, MEI Huawei, LI Baogang, LI Yongqian. Optimization Method for Task Offloading Decision and Edge Resource Allocation in Distribution Networks[J]. Computer Engineering and Applications, 2024, 60(5): 281-290.

朵春红, 匡竹, 齐国梁, 梅华威, 李保罡, 李永倩. 配电网中任务卸载决策与边缘资源分配优化方法[J]. 计算机工程与应用, 2024, 60(5): 281-290.

References

[1] 李知艺, 宋克轩. 基于云边协同计算的主动配电网调度研究评述[J]. 浙江电力, 2021, 40(6): 15-21.
LI Z Y, SONG K X. An overview of ADNs dispatching based on coordinated cloud-edge computing[J]. Zhejiang Electric Power, 2021, 40(6): 15-21.
[2] 孙浩洋, 张冀川, 王鹏, 等. 面向配电物联网的边缘计算技术[J]. 电网技术, 2019, 43(12): 4314-4321.
SUN H Y, ZHANG J C, WANG P, et al. Edge computation technology based on distribution internet of things[J]. Power System Technology, 2019, 43(12): 4314-4321.
[3] CHANG Z, LIU L, GUO X, et al. Dynamic resource allocation and computation offloading for IoT fog computing system[J]. IEEE Transactions on Industrial Informatics, 2020, 17(5): 3348-3357.
[4] HOU X, REN Z, WANG J, et al. Reliable computation offloading for edge-computing-enabled software-defined IoV[J]. IEEE Internet of Things Journal, 2020, 7(8): 7097-7111.
[5] CHEN Y, LIU Z, ZHANG Y, et al. Deep reinforcement learning-based dynamic resource management for mobile edge computing in industrial internet of things[J]. IEEE Transactions on Industrial Informatics, 2020, 17(7): 4925-4934.
[6] 曹绍华, 姜佳佳, 陈舒, 等. A-DDPG: 多用户边缘计算系统的卸载研究[J]. 计算机工程与应用, 2023, 59(1): 259-268.
CAO S H, JIANG J J, CHEN S, et al. A-DDPG: research on offloading of multi-user edge computing system[J]. Computer Engineering and Applications, 2023, 59(1): 259-268.
[7] XIONG X, ZHENG K, LEI L, et al. Resource allocation based on deep reinforcement learning in IoT edge computing[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(6): 1133-1146.
[8] KHORAMNEIAD F, EROL-KANTARCI M. On joint offloading and resource allocation: a double deep Q-network approach[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(4): 1126-1141.
[9] QIAN L, WU Y, JIANG F, et al. NOMA assisted multi-task multi-access mobile edge computing via deep reinforcement learning for industrial Internet of things[J]. IEEE Transactions on Industrial Informatics, 2020, 17(8): 5688-5698.
[10] LIANG F, YU W, LIU X, et al. Towards deep Q-network based resource allocation in industrial internet of things[J]. IEEE Internet of Things Journal, 2021, 9(12): 9138-9150.
[11] XI L, WANG Y, WANG Y, et al. Deep reinforcement learning-based service-oriented resource allocation in smart grids[J]. IEEE Access, 2021, 9: 77637-77648.
[12] XU S, LIAO B, YANG C, et al. Deep reinforcement learning assisted edge-terminal collaborative offloading algorithm of blockchain computing tasks for energy Internet[J]. International Journal of Electrical Power & Energy Systems, 2021, 131: 107022.
[13] DING Y, LIU C, ZHOU X, et al. A code-oriented partitioning computation offloading strategy for multiple users and multiple mobile edge computing servers[J]. IEEE Transactions on Industrial Informatics, 2019, 16(7): 4800-4810.
[14] HUANG M, LIU W, WANG T, et al. A cloud-MEC collabor-
ative task offloading scheme with service orchestration[J]. IEEE Internet of Things Journal, 2019, 7(7): 5792-5805.
[15] ZHOU F, HU R Q. Computation efficiency maximization in wireless-powered mobile edge computing networks[J]. IEEE Transactions on Wireless Communications, 2020, 19(5): 3170-3184.
[16] 施丽琴, 叶迎晖, 卢光跃. 无线供能边缘计算网络中系统计算能效最大化资源分配方案[J]. 通信学报, 2020, 41(10): 59-69.
SHI L Q, YE Y H, LU G Y. Computation energy efficiency maximization based resource allocation scheme in wireless powered mobile edge computing network[J]. Journal on Communications, 2020, 41(10): 59-69.
[17] LI Q, YAO H, MAI T, et al. Reinforcement-learning-and belief-learning-based double auction mechanism for edge computing resource allocation[J]. IEEE Internet of Things Journal, 2019, 7(7): 5976-5985.
[18] WANG Q, GUO S, WANG Y, et al. Incentive mechanism for edge cloud profit maximization in mobile edge computing[C]//Proceedings of the IEEE International Conference on Communications (ICC), 2019: 1-6.
[19] 陈思光, 陈佳民, 赵传信. 基于深度强化学习的云边协同计算迁移研究[J]. 电子学报, 2021, 49(1): 157-166.
CHEN S G, CHEN J M, ZHAO C X. Deep reinforcement learning based cloud-edge collaborative computation offloading mechanism[J]. Acta Electronica Sinica, 2021, 49(1): 157-166.
[20] YUE Y, WEN S, LIU J. A double auction-based approach for multi-user resource allocation in mobile edge computing[C]//Proceedings of the 14th International Wireless Communications & Mobile Computing Conference (IWCMC), 2018.
[21] CHEN M, HAO Y. Task offloading for mobile edge computing in software defined ultra-dense network[J]. IEEE Journal on Selected Areas in Communications, 2018, 36(3): 587-597.
[22] 林艳, 闫帅, 张一晋, 等. 基于交通流量预测的车联网双边拍卖边缘计算迁移方案[J]. 通信学报, 2020, 41(12): 205-214.
LIN Y, YAN S, ZHANG Y J, et al. Flow-of-traffic prediction program based mobile edge computing for Internet of vehicles using double auction[J]. Journal on Communications, 2020, 41(12): 205-214.
[23] LIN J, HUANG L, ZHANG H, et al. A novel latency-guaranteed based resource double auction for market-oriented edge computing[J]. Computer Networks, 2021, 189: 107873.
[24] LU W, ZHANG S, XU J, et al. Truthful multi-resource transaction mechanism for p2p task offloading based on edge computing[J]. IEEE Transactions on Vehicular Technology, 2021, 70(6): 6122-6135.