Resource Allocation for Delay-Sensitive Vehicle-to-Multi-Edges (V2Es) Communications in Vehicular Networks: A Multi-Agent Deep Reinforcement Learning Approach

Joint Service Caching and Computation Offloading Scheme Based on Deep Reinforcement Learning in Vehicular Edge Computing Systems

“…There have been emerging efforts on content caching and computation offloading in VEC [20], [21], [28]- [31]. Tian et al [30] propose a collaborative computation offloading and content caching method, by leveraging DRL for a selfdriving system.…”

“…Tian et al [30] propose a collaborative computation offloading and content caching method, by leveraging DRL for a selfdriving system. Wu et al [31] propose a multi-agent based reinforcement learning (RL) algorithm to make decisions on task offloading and edge caching to optimize both service latency and energy consumption of vehicles. The important difference between content caching and service caching is that the latter not only concerns storage capacity but also the computing capacity.…”

“…This smart driving assistance thus can significantly improve driving safety, reduce energy consumption, and enhance traffic management efficiency [32], [33]. Specifically, RL and DRL have been demonstrated to significantly improve the performances of vehicular task offloading [14], [20], [21], [29]- [31], [34]- [39]. Zhu et al [35] propose a multiagent DRL-based computation offloading scheme to minimize the total task execution delay of the considered system during a certain period.…”

“…Since the output data is typically much smaller than the input task size, we ignore the time delay of the output return process [31]. As the computing and storage resources are abundant in the cloud, we ignore the queuing and computing latency incurred by the cloud.…”

Vehicle to everything in the power grid (V2eG): A review on the participation of electric vehicles in power grid economic dispatch

“…It is difficult to cope with the communication demands of EV mobility. A vehicle to multi‐edges (V2Es) communication framework was built in [160], which makes full use of the interactive collaboration of edge nodes to process emergency information and complete services from vehicles promptly. A multi‐intelligent reinforcement learning (RL) approach is proposed to learn the dynamic communication states between vehicles and edge nodes and improve the efficiency of V2V services.…”