On-Demand Environment Perception and Resource Allocation for Task Offloading in Vehicular Networks

In vehicular edge computing networks, the real-time, on-demand scheduling of scarce network resources for environmental perception, task offloading, computation, and feedback is vital. However, these coupled processes make resource allocation challenging. Moreover, existing real-time channel measurement techniques in complex vehicular topologies present load, accuracy, and customization difficulties. To address these issues, this paper proposes an on-demand environmental perception and resource allocation strategy. Specifically, with the introduction of a channel knowledge base, we first analyze the coupling relationship between environmental perception, communication, and computation. A model is then proposed for task offloading to schedule the granularity of environment perception, communication resources, and computational resources dynamically. Subsequently, the resource allocation problem is formulated as an optimization problem, aiming to minimize system processing delay and maximize resource utilization while ensuring perception accuracy. To address this, a two-phase optimization-assisted deep reinforcement learning (DRL) algorithm is proposed. The initial phase uses convex optimization to approximate a solution. The second phase proposes a DRL-based algorithm to intelligently schedule dynamic network resources, with the first phase’s solution guiding the initial exploration space to enhance DRL training efficiency. Extensive simulation experiments verify the effectiveness of our proposal.

I. Introduction

Vehicular edge computing (VEC) technology deploys edge servers in vehicular networks (VNets) to provide additional computing power for mobile vehicles (MVs) with limited computational capabilities [1]. To achieve efficient task offloading of MVs, reduce task processing latency, and enhance MVs’ satisfaction, scholars have conducted extensive research from various perspectives. Some authors focus on task offloading strategies (Qin et al. [2], Liu et al. [3], Wang et al. [4]), while others concentrate on the joint task offloading and resource allocation (Fan et al. [5], Wang et al. [6], Malik and Vu [7]). In addition, the communication environment during task offloading significantly impacts the Quality of Service (QoS) of MVs [8]. Fig. 1 illustrates the structure of task offloading in VNets with environment perception. Here, gNBs are deployed at the roadside to process intensive tasks of MVs through vehicle-to-infrastructure (V2I) communications. When MVs are in different communication environments, such as , , and , or constantly moving within the same environment, their communication status changes, consequently impacting the overall network performance. As a result, some authors not only focus on the offloading and resource allocation but also on the communication environment perception for VEC networks (Wu et al. [9], Zheng et al. [10], Zhang et al. [8]). The aforementioned research works contribute efficient solutions for managing and controlling VEC networks. Fig. 1.

Structure of task offloading in VNets with environment-perception.