Zeng, Lingqiu (Chongqing University), Yang, Hao (Chongqing University), Han, Qingwen (Chongqing University), Song, Xinyue (Chongqing University), Ye, Lei (Chongqing University)

Lightweight Multi-Agent-Based Service Migration Strategy for Cross-Network Scenarios

Scheduled for presentation during the Regular Session "S07b-Smart Infrastructure and Data-Driven Sensing for Intelligent Mobility" (WE-EA-T7), Wednesday, November 19, 2025, 14:10−14:30, Coolangata 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Abstract

In the cross-network collaboration scenario, vehicles can request services through different communication methods. However, the fast movement of vehicles and the complexity of the network environment pose significant challenges. During the cross-network service migration process, effective migration strategies must be developed to ensure service quality and avoid service interruptions. This paper formulates cross-network service migration as an optimization problem and proposes a candidate node selection method that integrates graph search and k-nearest neighbors (k-NN) within the Markov Decision Process (MDP) framework. Building upon this, a lightweight model based on multi-agent, called LMA-D3QN (Lightweight Multi-Agent Double Deep Q-Network), is constructed. Simulation results show that the proposed method effectively improves the overall efficiency of service migration while reducing computational overhead.