A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL
Open Access
Abstract
In vehicular edge computing (VEC), some tasks can be processed either locally or on the mobile edge computing (MEC) server at a base station (BS) or a nearby vehicle. In fact, tasks are offloaded or not, based on the status of vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication. In this paper, device-to-device (D2D)-based V2V communication and multiple-input multiple-output and nonorthogonal multiple access (MIMO-NOMA)-based V2I communication are considered. In actual communication scenarios, the channel conditions for MIMO-NOMA-based V2I communication are uncertain, and the task arrival is random, leading to a highly complex environment for VEC systems. To solve this problem, we propose a power allocation scheme based on decentralized deep reinforcement learning (DRL). Since the action space is continuous, we employ the deep deterministic policy gradient (DDPG) algorithm to obtain the optimal policy. Extensive experiments demonstrate that our proposed approach with DRL and DDPG outperforms existing greedy strategies in terms of power consumption and reward.Keywords
Funding Information
- National Natural Science Foundation of China (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- State Key Laboratory of Integrated Services Networks (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- National Key Research and Development Program of China (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- National Social State Foundation of China (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- Yunnan Natural Science Foundation of China (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- the 111 Project (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
- Changzhou Key Laboratory of 5G+ Industrial Internet Fusion Application (61701197, 62161052, ISN23-11, 2021YFA1000500(4), 21XSH007, 202201AT070021, B23008, CM20223015)
This publication has 44 references indexed in Scilit:
- Mobile-Edge Computing for Vehicular Networks: A Promising Network Paradigm with Predictive Off-LoadingIEEE Vehicular Technology Magazine, 2017
- Vehicular Fog Computing: A Viewpoint of Vehicles as the InfrastructuresIEEE Transactions on Vehicular Technology, 2016
- Cluster-Based Radio Resource Management for D2D-Supported Safety-Critical V2X CommunicationsIEEE Transactions on Wireless Communications, 2015
- Power Control in D2D-Based Vehicular Communication NetworksIEEE Transactions on Vehicular Technology, 2015
- Radio Resource Management for D2D-Based V2V CommunicationIEEE Transactions on Vehicular Technology, 2015
- DREAM: Dynamic Resource and Task Allocation for Energy Minimization in Mobile Cloud SystemsIEEE Journal on Selected Areas in Communications, 2015
- Performance modeling and analysis of IEEE 802.11 DCF based fair channel access for vehicle-to-roadside communication in a non-saturated stateWireless Networks, 2014
- A Survey on Device-to-Device Communication in Cellular NetworksIEEE Communications Surveys & Tutorials, 2014
- Fundamentals of wireless communications2014
- Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical TablesAmerican Journal of Physics, 1988