An Improved Binary Wolf Pack Algorithm for Solving Optimal Sensor Selection Problems

The problem of selecting optimal sensors is a typical discrete combinatorial optimization problem, which is proved to be NP-hard. In this paper, an improved binary wolf pack algorithm (IBWPA) by adaptive step length, information interaction and difference evolution update strategy is proposed to choose the optimal sensors with high computational accuracy and robustness. Firstly, the wolves' position, motion operator, intelligent behaviors and rules of basic binary wolf algorithm for optimum in discrete state space are introduced. Then, tentative direction of scouting behavior based on information interaction, adaptive steps length of scouting and summoning behavior, as well as the differential evolution updates strategy are used to improve the traditional BWPA and the schemes and procedures of IBWPA are also presented. Finally, experiments show that compared with BPSO, BWPA and other sensor selection methods, the proposed IBWPA method has a better accuracy, robustness and global searching ability and the problem can be solved in reasonable computational time. Moreover, the effects of algorithm parameters on the performance of selecting optimum are also analyzed through simulation and theoretical analysis, which indicate that IBWPA can achieve a better tradeoff between the global searching ability and computational time by choosing reasonable parameters.