A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL
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) communicatio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3449 |
| _version_ | 1797607071887130624 |
|---|---|
| author | Dunxing Long Qiong Wu Qiang Fan Pingyi Fan Zhengquan Li Jing Fan |
| author_facet | Dunxing Long Qiong Wu Qiang Fan Pingyi Fan Zhengquan Li Jing Fan |
| author_sort | Dunxing Long |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T05:26:08Z |
| format | Article |
| id | doaj.art-bcdcf0ac85344f059f44776913683c71 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:26:08Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bcdcf0ac85344f059f44776913683c712023-11-17T17:32:42ZengMDPI AGSensors1424-82202023-03-01237344910.3390/s23073449A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRLDunxing Long0Qiong Wu1Qiang Fan2Pingyi Fan3Zhengquan Li4Jing Fan5School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, ChinaSchool of Internet of Things Engineering, Jiangnan University, Wuxi 214122, ChinaQualcomm, San Jose, CA 95110, USADepartment of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaSchool of Internet of Things Engineering, Jiangnan University, Wuxi 214122, ChinaUniversity Key Laboratory of Information and Communication on Security Backup and Recovery in Yunnan Province, Yunnan Minzu University, Kunming 650500, ChinaIn 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.https://www.mdpi.com/1424-8220/23/7/3449vehicular edge computing (VEC)power allocationMIMO-NOMAD2Ddeep deterministic policy gradient (DDPG)decentralized |
| spellingShingle | Dunxing Long Qiong Wu Qiang Fan Pingyi Fan Zhengquan Li Jing Fan A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL Sensors vehicular edge computing (VEC) power allocation MIMO-NOMA D2D deep deterministic policy gradient (DDPG) decentralized |
| title | A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL |
| title_full | A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL |
| title_fullStr | A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL |
| title_full_unstemmed | A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL |
| title_short | A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL |
| title_sort | power allocation scheme for mimo noma and d2d vehicular edge computing based on decentralized drl |
| topic | vehicular edge computing (VEC) power allocation MIMO-NOMA D2D deep deterministic policy gradient (DDPG) decentralized |
| url | https://www.mdpi.com/1424-8220/23/7/3449 |
| work_keys_str_mv | AT dunxinglong apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT qiongwu apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT qiangfan apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT pingyifan apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT zhengquanli apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT jingfan apowerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT dunxinglong powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT qiongwu powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT qiangfan powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT pingyifan powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT zhengquanli powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl AT jingfan powerallocationschemeformimonomaandd2dvehicularedgecomputingbasedondecentralizeddrl |