A3C-based load-balancing solution for computation offloading in SDN-enabled vehicular edge computing networks

被引：0
作者：
Lingyu Lu
Jing Yu
Haifeng Du
Xiang Li
机构：
[1] Beijing Jiaotong University,School of Software Engineering
[2] Beijing Jiaotong University,School of Computer and Information Technology
[3] Beijing Sankuai Online Technology Co.,undefined
[4] Ltd,undefined
来源：
Peer-to-Peer Networking and Applications | 2023年 / 16卷
关键词：
MEC; IoV; SDN; Computation offloading; Load balancing; Deep Reinforcement Learning;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In the Internet of vehicles (IoV), various applications emerging to provide users with safe, reliable, and comfortable driving services have caused explosive demand for computing capability. It is very challenging for vehicles with limited resources to meet the real-time demand. Mobile Edge Computing (MEC) is a convenient solution that utilizes computing resources at the network edge to enhance the capability of vehicles. With the help of MEC, vehicles can offload parts of tasks to nearby MEC servers to reduce the response cost. However, with the increase of vehicles, the unbalanced load among servers may lead to the unbalanced resource allocation and the degradation of task completion ratio. To address this problem, we first propose an SDN-enabled vehicular edge computing network architecture to facilitate the management of IoV with a global view. Then, the joint optimization problem of computation offloading and load balancing is formulated as a sequential decision problem to minimize the system cost in terms of time and energy. An A3C-based solution is proposed to solve the offloading decisions. Further, we develop the simple computation resource allocation scheme and calculation method of offloading ratio, respectively. Finally, the simulation results demonstrate the superior performance of our proposed algorithm compared to the benchmark solutions.
引用
收藏
页码：1242 / 1256
页数：14
相关论文
共 82 条
[1]  
Zhou H(2020)Evolutionary v2x technologies toward the internet of vehicles: Challenges and opportunities Proc IEEE 108 308-323
[2]  
Xu W(2020)Priority-aware task offloading in vehicular fog computing based on deep reinforcement learning IEEE Trans Veh Technol 69 16067-16081
[3]  
Chen J(2020)Intelligent task offloading in vehicular edge computing networks IEEE Wirel Commun 27 126-132
[4]  
Wang W(2020)Advanced deep learning-based computational offloading for multilevel vehicular edge-cloud computing networks IEEE Access 8 137052-137062
[5]  
Shi J(2019)Computation offloading for mobile edge computing enabled vehicular networks IEEE Access 7 62624-62632
[6]  
Du J(2020)Joint optimization of computation offloading and task scheduling in vehicular edge computing networks IEEE Access 8 10466-10477
[7]  
Wang J(2019)Computation offloading and resource allocation for cloud assisted mobile edge computing in vehicular networks IEEE Trans Veh Technol 68 7944-7956
[8]  
Wang J(2020)Deep reinforcement learning-based adaptive computation offloading for mec in heterogeneous vehicular networks IEEE Trans Veh Technol 69 7916-7929
[9]  
Yuan J(2020)Deep reinforcement learning based resource management for multi-access edge computing in vehicular networks IEEE Transactions on Network Science and Engineering 7 2416-2428
[10]  
Guo H(2020)Deep-reinforcement-learning-based offloading scheduling for vehicular edge computing IEEE Internet Things J 7 5449-5465
123456789