Collaborative Optimization of Heterogeneous Resources in Air-Ground Computing Power Networks

doi:10.19678/j.issn.1000-3428.0069423

Abstract

Abstract:

To address the challenges of insufficient computing capacity of end users and the unbalanced distribution of computing power among edge nodes in computing power networks, this study proposes an Unmanned Aerial Vehicle (UAV)-assisted Device-to-Device (D2D) edge computing solution based on incentive mechanisms. First, under constraints involving computing resources, transmission power, and the unit pricing of computing resources, a unified optimization problem is formulated to maximize system revenue. This problem aims to optimize the task offloading ratio, computing resource constraints, UAV trajectory, as well as the transmission power and unit pricing of computing resources for both UAVs and users. The Proximal Policy Optimization (PPO) algorithm is employed to establish user offloading and purchasing strategies. In addition, an iterative strategy is implemented at each time step to solve the optimization problem and obtain the optimal solution. The simulation results demonstrate that the PPO-based system revenue maximization algorithm exhibits superior convergence and improves overall system revenue compared to the baseline algorithm.

Key words: air-ground computing power network, incentive mechanism, Device-to-Device (D2D) communication, computation offloading, Proximal Policy Optimization (PPO)

摘要：

针对算力网络中终端用户计算能力不足及边缘节点算力分配不均的问题, 提出一种以激励机制为基础的无人机(UAV)协同终端直连(D2D)边缘计算方案。首先, 在满足计算资源、发射功率、计算资源单价等限制条件下, 通过联合优化任务卸载比例、计算资源限制量、UAV飞行轨迹、UAV和用户的发射功率以及计算资源出售单价, 提出一个系统收益最大化问题。其次, 利用近端策略优化(PPO)确定用户卸载和购买策略, 通过在多个时间步骤上迭代优化策略最大化累积奖励, 并引入剪切项以限制策略更新的幅度, 以确保求解算法的稳定性。仿真结果显示, 基于PPO的系统收益最大化算法相比基线算法具有更好的收敛性, 并能够有效提升系统总收益。

关键词: 空地算力网络, 激励机制, 终端直连通信, 计算卸载, 近端策略优化

LI Bin, SHAN Huimin. Collaborative Optimization of Heterogeneous Resources in Air-Ground Computing Power Networks[J]. Computer Engineering, 2025, 51(5): 1-8.

李斌, 山慧敏. 空地算力网络中的异构资源协同优化[J]. 计算机工程, 2025, 51(5): 1-8.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069423

https://www.ecice06.com/EN/Y2025/V51/I5/1

Figures/Tables 7

Fig.1 System model

Fig.2 PPO-based DRL training framework

Fig.3 Comparison of convergence of rewards for different algorithms

Fig.4 Relationship between revenue of busy users and number of users

Fig.5 Relationship between total revenue and number of users

Fig.6 3D flight trajectory chart of UAV with multiple users

References 20

1	GAO M J , SHEN R J , SHI L , et al. Task partitioning and offloading in DNN-task enabled mobile edge computing networks. IEEE Transactions on Mobile Computing, 2023, 22 (4): 2435- 2445. doi: 10.1109/TMC.2021.3114193
2	陈阳, 皮德常, 代成龙, 等. 多无人机协同陆地设施辅助移动边缘计算的系统能耗最小化方法. 电子学报, 2023, 51 (4): 984- 992.
	CHEN Y , PI D C , DAI C L , et al. Energy minimization for multi-UAVs cooperative ground access points assisted mobile edge computing. Acta Electronica Sinica, 2023, 51 (4): 984- 992.
3	LI Y Q, YANG C X, DENG M X, et al. A dynamic resource optimization scheme for MEC task offloading based on policy gradient[C]//Proceedings of the IEEE 6th Information Technology and Mechatronics Engineering Conference. Washington D.C., USA: IEEE Press, 2022: 342-345.
4	FANG T , YUAN F , AO L , et al. Joint task offloading, D2D pairing, and resource allocation in device-enhanced MEC: a potential game approach. IEEE Internet of Things Journal, 2022, 9 (5): 3226- 3237. doi: 10.1109/JIOT.2021.3097754
5	LU W D , DING Y , GAO Y , et al. Secure NOMA-based UAV-MEC network towards a flying eavesdropper. IEEE Transactions on Communications, 2022, 70 (5): 3364- 3376. doi: 10.1109/TCOMM.2022.3159703
6	LIU Z Y, FAN J Y, GENG S Y, et al. Joint optimization of task offloading and computing resource allocation in MEC-D2D network[C]//Proceedings of the IEEE 5th International Conference on Computer and Communication Engineering Technology. Washington D.C., USA: IEEE Press, 2022: 256-260.
7	MOGHADDASI K, RAJABI S. Double deep Q-learning networks for energy-efficient IoT task offloading in D2D MEC environments[C]//Proceedings of the 7th International Conference on Internet of Things and Applications. Washington D.C., USA: IEEE Press, 2023: 1-6.
8	DAI X X , XIAO Z , JIANG H B , et al. Task co-offloading for D2D-assisted mobile edge computing in industrial Internet of Things. IEEE Transactions on Industrial Informatics, 2023, 19 (1): 480- 490. doi: 10.1109/TII.2022.3158974
9	GUO H Z , LIU J J . UAV-enhanced intelligent offloading for Internet of Things at the edge. IEEE Transactions on Industrial Informatics, 2020, 16 (4): 2737- 2746. doi: 10.1109/TII.2019.2954944
10	CHEN X F, CHEN T, ZHAO Z F, et al. Resource awareness in unmanned aerial vehicle-assisted mobile-edge computing systems[C]//Proceedings of the IEEE 91st Vehicular Technology Conference. Washington D.C., USA: IEEE Press, 2020: 1-6.
11	LI Y Y, FANG Y, QIU L. Joint computation offloading and communication design for secure UAV-enabled MEC systems[C]// Proceedings of the IEEE Wireless Communications and Networking Conference. Washington D.C., USA: IEEE Press, 2021: 1-6.
12	HU X Y , WONG K K , YANG K , et al. UAV-assisted relaying and edge computing: scheduling and trajectory optimization. IEEE Transactions on Wireless Communications, 2019, 18 (10): 4738- 4752. doi: 10.1109/TWC.2019.2928539
13	ZHANG L , ANSARI N . Latency-aware IoT service provisioning in UAV-aided mobile-edge computing networks. IEEE Internet of Things Journal, 2020, 7 (10): 10573- 10580. doi: 10.1109/JIOT.2020.3005117
14	CHEN J F , ZHAO Y S , XU Z M , et al. Resource allocation strategy for D2D-assisted edge computing system with hybrid energy harvesting. IEEE Access, 2020, 8, 192643- 192658. doi: 10.1109/ACCESS.2020.3032033
15	SONG Q L , QU L . UAV-D2D assisted latency minimization and load balancing in mobile edge computing with deep reinforcement learning. Berlin, Germany: Springer, 2024.
16	XU Y J , LIU Z J , HUANG C W , et al. Robust resource allocation algorithm for energy-harvesting-based D2D communication underlaying UAV-assisted networks. IEEE Internet of Things Journal, 2021, 8 (23): 17161- 17171. doi: 10.1109/JIOT.2021.3078264
17	NGUYEN M N , NGUYEN L D , DUONG T Q , et al. Real-time optimal resource allocation for embedded UAV communication systems. IEEE Wireless Communications Letters, 2019, 8 (1): 225- 228. doi: 10.1109/LWC.2018.2867775
18	韩跃林, 朱琦. 多用户D2D计算卸载与资源分配算法. 信号处理, 2024, 40 (2): 373- 384.
	HAN Y L , ZHU Q . Multi-user D2D computation offloading and resource allocation algorithm. Journal of Signal Processing, 2024, 40 (2): 373- 384.
19	PU X M , LEI T T , WEN W L , et al. Incentive mechanism and resource allocation for collaborative task offloading in energy-efficient mobile edge computing. IEEE Transactions on Vehicular Technology, 2023, 72 (10): 13775- 13780. doi: 10.1109/TVT.2023.3274513
20	SUN W J, ZHANG H X, WANG L Y, et al. Profit maximization task offloading mechanism with D2D collaboration in MEC networks[C]//Proceedings of the 11th International Conference on Wireless Communications and Signal Processing. Washington D.C., USA: IEEE Press, 2019: 1-6.

[1]	LI Shuyi, YANG Bo, CHEN Ling, SHEN Ling, TANG Wensheng. Surface Coverage Method Based on PPO with Adaptive Reward Function [J]. Computer Engineering, 2025, 51(3): 86-94.
[2]	GU Yonggen, LI Guoxiao, WU Xiaohong, TAO Jie, ZHANG Yanqiong. Incentive Mechanism for Multi-Task Federated Learning Under Budget Constraints [J]. Computer Engineering, 2024, 50(5): 149-157.
[3]	Yaoping ZENG, Yuting XIA, Weiwei JIANG, Yueqiang LIU. Research on UAV-Assisted Mobile Edge Computing Strategy with Weighted Energy Minimization [J]. Computer Engineering, 2024, 50(2): 288-297.
[4]	YANG Jianjun, TANG Dongming, LI Juguang, XIAO Yufeng. Task Offloading Strategy of MEC Based on Improved Artificial Hummingbird Algorithm [J]. Computer Engineering, 2024, 50(10): 291-301.
[5]	Yuqi BAN, Liguo DUAN, Haoyu WEN, Aiping LI, Jumin ZHAO. Research on Mobility-Aware Computation Offloading and Resource Allocation Strategy [J]. Computer Engineering, 2023, 49(8): 163-173.
[6]	LUO Huafeng, SHEN Yifei, RUAN Lixiang, DU Qiwei, ZHENG Xiang, CHEN Zhiqi, ZHANG Sheng. Frame Offloading Scheduling Algorithm for Real-time Object Detection in Edge Environment [J]. Computer Engineering, 2023, 49(5): 295-301,309.
[7]	YANG Junming, YIN Chao, YANG Zheng. Lightweight Privacy Preserving Proof of Location Protocol Based on Incentive Driven [J]. Computer Engineering, 2023, 49(3): 151-160.
[8]	ZHANG Bojun, GUO Yichen, WANG Zikai, HU Kai. Research on Data Sharing Incentive Mechanism Based on Smart Contract [J]. Computer Engineering, 2022, 48(8): 37-44.
[9]	ZHOU Qiang, LI Peng, NIE Lei. User Incentive Mechanism Based on Spatial-Temporal Correlation for Crowd Sensing [J]. Computer Engineering, 2021, 47(3): 227-236.
[10]	WANG Yan, GE Haibo, FENG Anqi. Computation Offloading Strategy in Cloud-Assisted Mobile Edge Computing [J]. Computer Engineering, 2020, 46(8): 27-34.
[11]	ZHU Lanting, SUN Lijun, YAN Yang. Parking Assistance Scheme Based on Reverse Auction in Vehicle Fog Computing [J]. Computer Engineering, 2020, 46(7): 14-20,29.
[12]	YANG Wenchao,WANG Jike,CUI Guanghai. Cooperation Promotion Mechanism of Social Networks Based on Nodes Strategy Learning Behaviors [J]. Computer Engineering, 2017, 43(11): 140-145.
[13]	LIU Fei, LUO Yong-long, GUO Liang-min, MA Yuan. Dynamic Trust Model for Personalized Cloud Services [J]. Computer Engineering, 2014, 40(4): 32-36.
[14]	WANG Shu-yin, YIN Gui-sheng, ZHAN Hao-min, LIU Jie. Bayesian Game Analysis for Entity Collaboration in Internetware System [J]. Computer Engineering, 2014, 40(2): 52-57.
[15]	ZHANG Hua-Feng, ZHANG Hong-Bin, GE Juan, ZHANG Shu-Kui. Selfish Node Detection System Based on Credit in Ad Hoc Network [J]. Computer Engineering, 2013, 39(6): 119-123.

Please choose a citation manager

Content to export