Service Migration Strategies Based on Partially Observable and Multi-Objective Optimization

Multi-access Edge Computing (MEC) extends cloud computing to the network edge, supporting resource-intensive mobile applications. Service migration ensures seamless continuity and high-quality service (QoS) when users move between MEC servers. In the Internet of Vehicles (IoV), the high mobility of vehicles causes network instability, complicating the collection of system information. In addition, vehicles impose strict latency and green energy requirements, and the search for the Pareto front among conflicting objectives increases the complexity of migration. Existing service migration methods rely on centralized decision making using complete system information, which is not suitable for the user-centric IoV environment. Current multi-objective reinforcement learning approaches lack sufficient exploration randomness, leading to suboptimal performance. We propose the Adversarial Variational State Inference with Maximum Entropy Multi-Objective Policy Optimization (AVSIMEMPO) algorithm to address the partially observable and multi-objective optimization problem, optimizing migration node selection. The service migration problem is modeled as a partially observable Markov decision process (POMDP). To solve this, we design an encoding network, AVSI, integrating Long ShortTerm Memory (LSTM), Variational Autoencoders (VAE), and adversarial learning to extract hidden state. We also introduce the Maximum Entropy Multi-Objective Policy Optimization (MEMPO) algorithm, which enhances exploration randomness through maximum entropy and dynamic weight design. Extensive experiments based on real mobility trajectories show that our method outperforms baseline algorithms and achieves nearoptimal results in various MEC scenarios.