An Immune Chaotic Niche Genetic Algorithm for Monitoring Distribution Problem in Self-Organizing Wireless Sensor Network

Abstract

Abstract Due to the sensors are restricted in sensing capabilities, monitoring distribution has become a challenging problem in self-organizing wireless sensor network (SOWSN). Micro nodes are self-organized tiny devices with limited sensing capabilities. Careful monitoring distribution scheme can be a suitable optimizing means for achieving the required high target detection rate goals, comprising sensing capacity restrictions. However, the monitoring distribution problem is a typical NP-hard combinatorial stochastic optimization problem. In this study, an immune chaotic niche genetic algorithm (ICNGA) to enhance the target detection rate is explored. Advanced operators such as immune operator and chaotic operator are also incorporated into the ICNGA to increase the explore capacity. The represented immune selection and chaotic generation depending on ICNGA with global search capability can simultaneously optimize multiple variables. Simulation results identify that the proposed algorithm can get a higher target detection rate over SFLA and SA. Besides that, the convergence speed of the presented ICNGA is much higher than that of SFLA and SA. So the proposed method significantly enhanced the efficiency.