A Deployment and Coverage Optimization Algorithm for Self-Powered Wireless Sensor Networks Based on Hybrid Swarm Intelligence

Network deployment optimization is a very complex problem with many non-deterministic polynomial (NP)-hard solutions due to the limited communication distance and initial energy of self-powered wireless sensor network (SPWSN) nodes, as well as the many compromise optimization objectives that must be considered in node deployment, such as maximum network coverage, best network connectivity, longest network life, and maximum network reliability. The artificial bee colony (ABC) algorithm is a new metaheuristic algorithm based on swarm intelligence. Concerning the advantages of strong global optimization performance and ease of implementation, it is applied for solving complex nonlinear optimization problems. However, the ABC algorithm has the shortcomings of slow convergence and insufficient problem compatibility; therefore, it needs to be further improved. In this study, the ABC algorithm is improved, and some deployment optimization problems of wireless sensor networks are studied based on these algorithms. Aiming at the deployment coverage problem in wireless sensor networks, the corresponding intelligent fault-tolerant model of intracluster routing was established, and an improved ABC algorithm based on the Tabu search (TS-ABC) was constructed to enhance the deployment of wireless sensor networks and quickly find an alternative transmission path with a short delay and high reliability. Through the coding of multipath data transmission, ABC optimization, Tabu search collaborative update evolution, optimal selection, and other operations to solve the problem, it exhibits faster global convergence and high accuracy. Simulation results show that the proposed fault-tolerant routing method reduces data transmission delay significantly and improves network robustness and reliability.