Coalition game based relay decision distributed learning in high dynamic heterogeneous intelligent UAV networks

Issue title: Special Section: Recent Advances in Machine Learning and Soft Computing

Guest editors: Srikanta Patnaik

Article type: Research Article

Authors: Yao, Changhua | Chen, Xueqiang^{; *} | Wang, Lei | Tong, Wei | Wu, Xinrong | Zhang, Yuli | Yao, Kailing

Affiliations: Army Engineering University of PLA, Nanjing, China

Correspondence: [*] Corresponding author. Xueqiang Chen, Army Engineering University of PLA, Nanjing 210007, China. E-mail: [email protected].

Abstract: This paper investigates the energy optimization for high dynamic heterogeneous UAV swarm network. Due to the high dynamism of the UAV swarm’s topology, the approaches with high complexity, long computing time, or low converging speed would be inappropriate to efficiently form stable communication network. We propose an UAV relay selection coalition game model and the distributed fast UAV relay coalition formation algorithm to optimize the energy efficiency of the UAV swarm. First, we formulate the UAV relay selection problem as a coalition game model. Then we design a distributed fast UAV relay coalition formation algorithm which could converge to the stable state rapidly and optimize the swarm’s energy efficiency. The proposed approach could help UAV swarm form high energy efficient network in the high dynamism situation.

Keywords: Distributed learning, coalition game, intelligent decision, heterogeneous, high dynamism

DOI: 10.3233/JIFS-169574

Journal: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 1, pp. 133-140, 2018