Multi-Agent DRL for Multi-Objective Twin Migration Routing with Workload Prediction in 6G-enabled IoV

TL;DR

This paper presents a multi-agent deep reinforcement learning framework for optimizing vehicle twin migration in 6G-enabled Internet of Vehicles, improving latency and reducing packet loss through workload prediction and dynamic routing.

Contribution

It introduces a novel VT migration framework using LSTM-Transformer workload prediction and a DM-MAPPO algorithm for optimal migration routing in complex 6G IoV environments.

Findings

Migration latency reduced by 20.82%

Packet loss decreased by 75.07%

Effective workload prediction improves migration decisions

Abstract

Sixth Generation (6G)-enabled Internet of Vehicles (IoV) facilitates efficient data synchronization through ultra-fast bandwidth and high-density connectivity, enabling the emergence of Vehicle Twins (VTs). As highly accurate replicas of vehicles, VTs can support intelligent vehicular applications for occupants in 6G-enabled IoV. Thanks to the full coverage capability of 6G, resource-constrained vehicles can offload VTs to edge servers, such as roadside units, unmanned aerial vehicles, and satellites, utilizing their computing and storage resources for VT construction and updates. However, communication between vehicles and edge servers with limited coverage is prone to interruptions due to the dynamic mobility of vehicles. Consequently, VTs must be migrated among edge servers to maintain uninterrupted and high-quality services for users. In this paper, we introduce a VT migration framework in 6G-enabled IoV. Specifically, we first propose a Long Short-Term Memory (LSTM)-based Transformer model to accurately predict long-term workloads of edge servers for migration decision-making. Then, we propose a Dynamic Mask Multi-Agent Proximal Policy Optimization (DM-MAPPO) algorithm to identify optimal migration routes in the highly complex environment of 6G-enabled IoV. Finally, we develop a practical platform to validate the effectiveness of the proposed scheme using real datasets. Simulation results demonstrate that the proposed DM-MAPPO algorithm significantly reduces migration latency by 20.82% and packet loss by 75.07% compared with traditional deep reinforcement learning algorithms.