Multi-Agent Deep Deterministic Policy Gradient-Based Computation Offloading and Resource Allocation for ISAC-Aided 6G V2X Networks

Vehicular communications in future sixth-generation (6G) networks are expected to leverage integrated sensing and communications (ISAC) and mobile edge computing (MEC) techniques. However, the rapid proliferation of vehicle user equipment (V-UE) and the diversity of ISAC-aided and MEC-empowered vehicular communication and computation services demand a more intelligent and efficient resource allocation framework for next-generation vehicular networks. To address this issue, we propose a comprehensive ISAC-aided vehicle-to-everything (V2X) MEC framework, where V-UEs can offload their tasks to the edge server collocated at the roadside unit (RSU). We aim to minimise the long-term average total service delay of all V-UEs by jointly optimising the offloading decisions of all V-UEs, the computation resource allocation at the ISAC-aided RSU, the transmission power and the allocation of resource blocks for all V-UEs, where the total service delay of a V-UE includes the task processing delay and the transmission delay if the V-UE offloads its task to the RSU. To solve the formulated mixed integer non-linear programming problem, we design a multi-agent deep deterministic policy gradient (MADDPG)-based offloading optimisation and resource allocation algorithm (MADDPG-O2RA2). Simulation results demonstrate that our proposed algorithm outperforms the benchmarks in terms of convergence and the long-term average delay among all V-UEs.