Resource Allocation Strategy of Internet of Vehicles Using Reinforcement Learning
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
An efficient and reasonable resource allocation strategy can greatly improve the service quality of Internet ofVehicles (IoV). However, most of the current allocation methods have overestimation problem, and it isdifficult to provide high-performance IoV network services. To solve this problem, this paper proposes anetwork resource allocation strategy based on deep learning network model DDQN. Firstly, the methodimplements the refined modeling of IoV model, including communication model, user layer computing model,edge layer offloading model, mobile model, etc., similar to the actual complex IoV application scenario. Then,the DDQN network model is used to calculate and solve the mathematical model of resource allocation. Bydecoupling the selection of target Q value action and the calculation of target Q value, the phenomenon ofoverestimation is avoided. It can provide higher-quality network services and ensure superior computing andprocessing performance in actual complex scenarios. Finally, simulation results show that the proposed methodcan maintain the network delay within 65 ms and show excellent network performance in high concurrencyand complex scenes with task data volume of 500 kbits.
Abstract
An efficient and reasonable resource allocation strategy can greatly improve the service quality of Internet ofVehicles (IoV). However, most of the current allocation methods have overestimation problem, and it isdifficult to provide high-performance IoV network services. To solve this problem, this paper proposes anetwork resource allocation strategy based on deep learning network model DDQN. Firstly, the methodimplements the refined modeling of IoV model, including communication model, user layer computing model,edge layer offloading model, mobile model, etc., similar to the actual complex IoV application scenario. Then,the DDQN network model is used to calculate and solve the mathematical model of resource allocation. Bydecoupling the selection of target Q value action and the calculation of target Q value, the phenomenon ofoverestimation is avoided. It can provide higher-quality network services and ensure superior computing andprocessing performance in actual complex scenarios. Finally, simulation results show that the proposed methodcan maintain the network delay within 65 ms and show excellent network performance in high concurrencyand complex scenes with task data volume of 500 kbits.
참고문헌 (30)
- Sushil Kumar Singh, "BIIoVT: Blockchain-Based Secure Storage Architecture for Intelligent Internet of Vehicular Things", IEEE Consumer Electronics Magazine, 11(6), pp.75~82 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- P. K. Sharma, "Blockchain-based secure mist computing network architecture for intelligent transportation systems", IEEE Transactions on Intelligent Transportation Systems, 22(8), pp.5168~5177 (2021)
- Y. Xiao, "Key technologies of Internet of vehicles and their development trends and challenges", Communications Technology, 54(1), pp.1~8 (2021)
- L. Pu, "Chimera : an energy-efficient and deadline-aware hybrid edge computing framework for vehicular crowdsensing applications", IEEE Internet of Things Journal, 6(1), pp.84~99 (2019)
- Sushil Kumar Singh, "A deep learning-based IoT-oriented infrastructure for secure smart City", Sustainable Cities and Society, 60, pp.102252~ (2020), Elsevier BV[DOI]
- B. Fan, "Traffic-aware relay vehicle selection in millimeter-wave vehicle-to-vehicle communication", IEEE Wireless Communications Letters, 8(2), pp.400~403 (2019)
- H. Zhang, "The mobility management strategies by integrating mobile edge computing and CDN in vehicular networks", Journal of Electronics & Information Technology, 42(6), pp.1444~1451 (2020)
- M. Sohail, "Efficient data handover and intelligent information assessment in software-defined vehicular social networks", IET Intelligent Transport Systems, 13(12), pp.1814~1821 (2019)
- H. Yang, "Intelligent resource management based on reinforcement learning for ultra-reliable and low-latency IoV communication networks", IEEE Transactions on Vehicular Technology, 68(5), pp.4157~4169 (2019)
- X. Huang, "Delay-aware caching in Internet-of-Vehicles networks", IEEE Internet of Things Journal, 8(13), pp.10911~10921 (2021)
- J. Cheng, "Routing in internet of vehicles : a review", IEEE Transactions on Intelligent Transportation Systems, 16(5), pp.2339~2352 (2015)
- X. Wang, "Optimizing content dissemination for real-time traffic management in large-scale Internet of Vehicle systems", IEEE Transactions on Vehicular Technology, 68(2), pp.1093~1105 (2019)
- C. Chen, "Delay-optimized V2V-based computation offloading in urban vehicular edge computing and networks", IEEE Access, 8, pp.18863~18873 (2020)
- W. Zhuang, "SDN", NFV-empowered future IoV with enhanced communication, computing, and caching, 2020, pp.108(2), 274~291
- L. Zhang, "Energy-aware dynamic resource allocation in UAV assisted mobile edge computing over social Internet of Vehicles", IEEE Access, 6, pp.56700~56715 (2018)
- J. Kim, "A position-based resource allocation scheme for V2V communication", Wireless Personal Communications, 98(1), pp.1569~1586 (2018)
- F. Abbas, "A novel low-latency V2V resource allocation scheme based on cellular V2X communications", IEEE Transactions on Intelligent Transportation Systems, 20(6), pp.2185~2197 (2019)
- J. Wang, "Elastic vehicular resource providing based on service function-group resource mapping of smart identify network", IEEE Systems Journal, 12(2), pp.1897~1908 (2018)
- S. Wang, "Adaptive proportional fairness resource allocation for OFDM-based cognitive radio networks", Wireless Networks, 19(3), pp.273~284 (2013)
- Q. Zhang, "Dynamic task offloading and resource allocation for mobile-edge computing in dense cloud RAN", IEEE Internet of Things Journal, 7(4), pp.3282~3299 (2020)
- J. Zhang, "Joint resource allocation for latency-sensitive services over mobile edge computing networks with caching", IEEE Internet of Things Journal, 6(3), pp.4283~4294 (2019)
- S. S. Lee, "Resource allocation for vehicular fog computing using reinforcement learning combined with heuristic information", IEEE Internet of Things Journal, 7(10), pp.10450~10464 (2020)
- Chaoxiong Cui, "An LSTM-Method-Based Availability Prediction for Optimized Offloading in Mobile Edges", Sensors, 19(20), pp.4467~ (2019), MDPI AG[DOI]
- M. Chen, "Intelligent resource allocation management for vehicles network : an A3C learning approach", Computer Communications, 151, pp.485~494 (2020)
- J. Zhao, "Contract-based computing resource management via deep reinforcement learning in vehicular fog computing", IEEE Access, 8, pp.3319~3329 (2019)
- X. Xu, "A computation offloading method for edge computing with vehicleto-everything", IEEE Access, 7, pp.131068~131077 (2019)
- J. Kim, "Efficient groupcast schemes for vehicle platooning in V2V network", IEEE Access, 7, pp.171333~171345 (2019)
- H. Peng, "Vehicular communications : a network layer perspective", IEEE Transactions on Vehicular Technology, 68(2), pp.1064~1078 (2019)
- Y. Liu, "Deep reinforcement learning for offloading and resource allocation in vehicle edge computing and networks", IEEE Transactions on Vehicular Technology, 68(11), pp.11158~11168 (2019)
- M. S. Demir, "Comp-based dynamic handover for vehicular VLC networks", IEEE Communications Letters, 24(9), pp.2024~2028 (2020)