Joint RAN Slicing and Computation Offloading for Autonomous Vehicular Networks: A Learning-Assisted Hierarchical Approach

Abstract

In this paper, a two-timescale radio access network (RAN) slicing and computing task offloading problem is investigated for a cloud-enabled autonomous vehicular network (C-AVN). We aim at jointly maximizing the communication and computing resource utilization with diverse quality-of-service (QoS) guarantee for autonomous driving tasks. Specifically, to capture the small-timescale network dynamics, a computing task scheduling problem is formulated as a stochastic optimization program, for maximizing the long-term network-wide computation load balancing with minimum task offloading variations. Due to the large problem size and unavailable network state transition probabilities, we employ cooperative multi-agent deep Q-learning (MA-DQL) with fingerprint to solve the problem by learning the set of stationary task offloading policies with stabilized convergence. Given the task offloading decisions, we further study a RAN slicing problem in a large timescale, which is formulated as a convex optimization program. We focus on optimizing the radio resource slicing ratios among base stations, to maximize the aggregate network utility with statistical QoS provisioning for autonomous driving tasks. Based on the impact of radio resource slicing on computation load balancing, we propose a two-timescale hierarchical optimization framework to maximize both communication and computing resource utilization. Extensive simulation results are provided to demonstrate the effectiveness of the proposed framework in comparison with state-of-the-art schemes.Index Terms-Autonomous vehicular networks, computing task offloading, RAN slicing, resource sharing, task scheduling, cooperative multi-agent deep Q-learning, learning-assisted hierarchical approach, diverse QoS provisioning.

DRL-assisted delay optimized task offloading in automotive-industry 5.0 based VECNs

“…We consider that the time domain is divided into τ n sections of equi-length m t-time slots pm, n, t P N q. The task generation probability follows a Bernoulli distribution with probability P, hence the mean rate of task arrivals λ ϑ " P{t [32]. Each offloading vehicle generates ϑ k task at the beginning of t-time slot, and each ϑ k task consists of a 6-tuple ϑ k " tc k , s k , t k , φ k , x k , d k u.…”

Semantic Communications for 6G Future Internet: Fundamentals, Applications, and Challenges

“…In recent years, with the development of hardware in vehicles and vehicular infrastructures, vehicles can be considered as intelligent agents with greater computing, caching and data storage capacities [110], [111]. Meanwhile, the traditional vehicular ad hoc network is expected to be transformed into the Internet of autonomous vehicles (IoAV) [112], [113], wherein the autonomous driving and cooperative vehicle networks can be achieved without the need of human involvement.…”

Joint Communication and Computation Offloading for Ultra-Reliable and Low-Latency With Multi-Tier Computing

“…The limited radio spectrum may also create an unstable and intermittent network connectivity to offload data from a massive number of UEs to ESs, resulting high end-to-end (e2e) latency communication and potentially high energy consumption. To overcome these challenges, an intelligent joint design of task offloading and resource allocation decisions is required to reap full advantage of edge and cloud computing to ultimately attain the optimal e2e latency while meeting URLLC requirements and other system constraints such as low energy consumption at edge devices [4]- [6].…”