Energy-Efficient Coverage Enhancement Strategy for WSNs Based on a Competitive Learning Optimizer

Energy-efficient coverage enhancement (EEC) is a highly nonconvex and challenging optimization problem in wireless sensor networks (WSNs) deployment. Traditional intelligent optimization algorithms often suffer from premature convergence and low efficiency when solving the EEC problem. In this article, a competitive learning optimizer (CLO) is proposed and upgraded to a multiobjective competitive learning optimizer (MOCLO), which is inspired by the behavior of human competitive learning in workplace. In order to verify the single-objective optimization capability of CLO, it is applied to the coverage problem in 2-D and 3-D WSNs, and the simulation results indicate that CLO achieves the overall best results in terms of solution accuracy, stability and convergence by comparing with five well-regarded optimization algorithms. For solving the EEC problem in 2-D and 3-D WSNs, MOCLO is applied. By comparing three popular multiobjective optimization algorithms, it is found that MOCLO can consume less energy to achieve higher coverage, which proves the effectiveness and superiority of MOCLO in addressing the EEC problem.