Service migration with edge collaboration: Multi-agent deep reinforcement learning approach combined with user preference adaptation

Shiyou Chen, Lanlan Rui, Zhipeng Gao, Yang Yang, Xuesong Qiu, Shaoyong Guo

Abstract: Highlights•Lightweight service migration benefits from content sharing of edge servers.•Users with different preferences are grouped into clusters based on the context.•Adaptive decision making based on multi-agent deep reinforcement learning.•The method improves efficiency and scalability of diversified services migration.•Performance improves the continuity of edge computing services for mobile users.