A learning approach for multi-agent travelling problem with dynamic service requirement in mobile IoT

Abstract

Introducing mobile agents into modern IoT systems for service provision such wireless charging, real-time monitoring etc. can improve the economic efficiency, reduce energy consumption and human effort. The path planning of mobile agent(s) visiting specific locations to provide the required service is thus a critical problem. Different from the existing studies, this work considers the dynamic service requirements in practical systems, such as dynamic demand/emergency in each location which changes along time, and explores the large-scale Travelling Salesman Problem (TSP) with the dynamic service requirements. A Graph Attention based Pointer Network (GAPN) is proposed to address the problem, the objective of which is to maximize the number of successfully served nodes under dynamic temporal constraints while minimizing the tour length. The experimental results show that GAPN outperforms the existing heuristic-based and learning-based schemes in terms of TSP with dynamic temporal constraints and the large-scale TSP.