IRS辅助的海上立体通算融合网络计算卸载研究

张超越, 林彬, 那振宇, 肖仲明

doi:10.16411/j.cnki.issn1006-7736.2025.01.010

大连海事大学学报 >

2025 , Vol. 51 >Issue 1: 92 - 101

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2025.01.010

IRS辅助的海上立体通算融合网络计算卸载研究

展开

(1. 大连海事大学信息科学技术学院，辽宁大连 116026；2. 广东省空天通信与网络技术重点实验室，广东深圳，518055；3. 大连海事大学航海学院，辽宁大连 116026)

张超越（1995—），女，博士生，研究方向：海上通信网络和智能反射面。林彬*（1977—），女，博士，教授，博士生导师，研究方向：海上无线宽带通信与网络技术。E-mail：binlin@dlmu.edu.cn。那振宇（1981—），男，博士，教授，博士生导师，研究方向：空天地海一体化通信。肖仲明（1982—），男，副教授，研究方向：船舶自适应控制。

网络出版日期: 2024-09-07

基金资助

国家自然科学基金面上项目（62371085；51939001）；中央高校基本科研业务费专项资金资助项目（3132023514）；辽宁省自然科学基金面上项目（2023-MS-124）；广东省空天通信与网络技术重点实验室开放基金项目“面向6G空基网络的多维资源融合与分配”。

收起

Computation offloading in IRS-Assisted maritime three-dimensional communication-computing converged networks

Expand

(1. Information Science and Technology College, Dalian Maritime University, Dalian 116026, China; 2. Guangdong Key Laboratory of Aerospace Communication and Networking Technology, Shenzhen 518055, China;3. Navigation College, Dalian Maritime University, Dalian 116026, China)

Online published: 2024-09-07

Fold

摘要

针对海上立体通算融合网络面临的通信与计算资源瓶颈以及复杂无线环境问题，研究一种基于无人机携带智能反射面（Intelligent Reflecting Surface，IRS）辅助海上通算融合网络计算卸载方案。首先，构建以最小化总能耗为目标的无人艇计算卸载率、边缘服务器计算资源分配、IRS相位和部署的联合优化问题。其次，为解决高维耦合优化问题，基于交替优化方法将原始问题解耦为两层子问题进行迭代求解，分别基于松弛法和双延迟深度确定性策略梯度算法优化计算卸载率和通算资源。仿真结果表明，与基准方案相比，所提的计算卸载方案可以在满足时延要求下有效地降低总能能耗，并在各种任务场景中展现出优越的性能。相比于无IRS方案，所提的计算卸载方案在总能耗方面平均降低42.0%。

关键词： 海上立体通算融合网络; 智能反射面(IRS); 计算卸载; 无人艇(USV); 深度强化学习

本文引用格式

张超越, 林彬, 那振宇, 肖仲明 . IRS辅助的海上立体通算融合网络计算卸载研究[J]. 大连海事大学学报, 2025 , 51(1) : 92 -101 . DOI: 10.16411/j.cnki.issn1006-7736.2025.01.010

Abstract

In order to solve the limitation on communication and computation resources, and complex wireless environments in maritime three-dimensional communication-computing converged networks, the computation offloading scheme for Intelligent Reflecting Surface (IRS) mounted on Unmanned Aerial Vehicle (UIRS)-assisted maritime communication-computing converged networks was studied. The offloading ratios of Unmanned Surface Vehicles (USVs), computation resource allocation of edge server, UIRS phase shifts and deployment were jointly optimized, aiming at minimizing the total energy consumption. Due to the high-dimensional coupled variables, based on the iterative optimization method, the original problem is decomposed into two subproblems, where the relaxation method and Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm were used to solve the offloading ratios and communication-computing resources, respectively. Simulation results show that the proposed scheme can minimize the total energy consumption while satisfying the latency requirements, and perform superior performance under various scenarios. Moreover, in comparison with the scheme of without IRS, the total energy consumption in the proposed scheme is reduced by 42.0% on average.

Key words： maritime three-dimensional communication-computing converged network; Intelligent Reflecting Surface (IRS); computation offloading; unmanned surface vehicle (USV); deep reinforcement learning

参考文献

[1]关巍,崔哲闻,罗文哲.基于改进PPO算法的船舶自主避碰决策[J].大连海事大学学报, 2023, 49(4): 28-36.
GUAN W, CUI Z W, LUO W Z. Ship autonomous collision avoidance decision based on improved PPO algorithm[J]. Journal of Dalian Maritime University, 2023, 49(4): 28-36. (in Chinese)
[2]张文君,张英俊,刘子豪.智能船舶航行风险评估研究现状与发展趋势[J].大连海事大学学报, 2023, 49(4): 13-19.
ZHANG W J, ZHANG Y J, LIU Z H. Research status and development trends of intelligent ships navigation risk assessment[J]. Journal of Dalian Maritime University, 2023, 49(4): 13-19. (in Chinese)
[3]QIAN L P, ZHANG H S, WANG Q, et al. Joint multi-domain resource allocation and trajectory optimization in UAV-assisted maritime IoT networks[J]. IEEE Internet of Things Journal, 2022, 10(1): 539-552.
[4]WEI T, FENG W, CHEN Y F, et al. Hybrid satellite-terrestrial communication networks for the maritime internet of things: key technologies, opportunities, and challenges[J]. IEEE Internet of Things Journal, 2021, 8(11): 8910-8934.
[5]HUANG J, WANG C X, SUN Y Z, et al. Reconfigurable intelligent surfaces: Channel characterization and modeling[J]. Proceedings of the IEEE, 2022, 110(9): 1290-1311.
[6]YANG Y Z, GONG Y, WU Y C. Intelligent-reflecting-surface-aided mobile edge computing with binary offloading: energy minimization for IoT devices[J]. IEEE Internet of Things Journal, 2022, 9(15): 12973-12983.
[7]MAO S, ZHANG N, LIU L, et al. Computation rate maximization for intelligent reflecting surface enhanced wireless powered mobile edge computing networks[J]. IEEE Transactions on Vehicular Technology, 2021, 70(10): 10820-10831.
[8]HUANG X W, HUANG G F. Joint optimization of energy and task scheduling in wireless-powered IRS-assisted mobile edge computing systems[J]. IEEE Internet of Things Journal, 2023, 10(12): 10997-11013.
[9]ABDULLAH Z, CHEN G J, LAMBOTHARAN S, et al. Optimization of intelligent reflecting surface assisted full-duplex relay networks[J]. IEEE Wireless Communications Letters, 2020, 10(2): 363-367.
[10]WANG Z Y, WEI Y F, FENG Z Y, et al. Resource management and reflection optimization for intelligent reflecting surface assisted multi-access edge computing using deep reinforcement learning[J]. IEEE Transactions on Wireless Communications, 2022, 22(2): 1175-1186.
[11]PARK Y M, TUN Y K, HAN Z, et al. Trajectory optimization and phase-shift design in IRS-assisted UAV network for high speed trains[J]. IEEE Transactions on Vehicular Technology, 2022, 71(10): 11317-11321.
[12]ZHAI Z Y, DAI X H, DUO B, et al. Energy-efficient UAV-mounted RIS assisted mobile edge computing[J]. IEEE Wireless Communications Letters, 2022, 11(12): 2507-2511.
[13]CHEN G J, WU Q Q, LIU R Q, et al. IRS Aided MEC systems with binary offloading: a unified framework for dynamic IRS Beamforming[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(2): 349-365.
[14]ASIM M, ELAFFENDI M, EL-LATIF A A A. Multi-IRS and Multi-UAV-Assisted MEC system for 5G/6G networks: efficient joint trajectory optimization and passive beamforming framework[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(4): 4553-4564.
[15]DUAN R Y, WANG J J, JIANG C X, et al. Resource allocation for multi-UAV aided IoT NOMA uplink transmission systems[J]. IEEE Internet of Things Journal, 2019, 6(4): 7025-7037.
[16]ZHOU F H, WU Y P, HU R Q Y, et al. Computation rate maximization in UAV-Enabled Wireless-Powered Mobile-Edge computing systems[J] IEEE Journal on Selected Areas in Communications, 2018, 36(9): 1927-1941.
[17]DIAMOND S, BOYD S. Cvxpy: A python-embedded modeling language for convex optimization[J]. Journal of Machine Learning Research, 2017, 17:1-5.
[18]AI Q S, QIAO X H, LIAO Y Z, et al. Joint optimization of USVs communication and computation resource in IRS-aided wireless inland ship MEC networks[J]. IEEE Transactions on Green Communications and Networking, 2021, 6(2): 1023-1036.
[19]QI S, LIN B, DENG Y Q, et al. Minimizing maximum latency of task offloading for multi-UAV-assisted maritime search and rescue[J]. IEEE Transactions on Vehicular Technology, 2024,73(9):13625-13638.
[20]LYU L, CHU Z H, LIN B, et al. Fast trajectory planning for UAV-Enabled maritime IoT systems: A Fermat-point based approach[J]. IEEE Wireless Communications Letters, 2022, 11(2): 328-332.
[21]ZHANG J, GUO H Z, LIU J J, et al. Task offloading in vehicular edge computing networks: A load-balancing solution[J]. IEEE Transactions on Vehicular Technology, 2019, 69(2): 2092-2104.
[22]DAI M H, WU Y, QIAN L P, et al. UAV-Assisted multi-access computation offloading via hybrid NOMA and FDMA in marine networks[J]. IEEE Transactions on Network Science and Engineering, 2023, 10(1), 113-127.
[23]DABIRI M T, SADOUGH S M S. Optimal placement of UAV-assisted free-space optical communication systems with DF relaying[J]. IEEE Communications Letters, 2020, 24(1): 155-158.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献