Abstract:
In order to solve the common problems of local optimization, low accuracy and slow convergence speed in intelligent algorithms for coverage optimization in Wireless Sensor Networks (WSN), an improved swarm intelligence algorithm, the Emperor Penguin Difference Algorithm (EPDEA), is proposed. EPDEA initializes the population and calculates the current individual fitness value, and continuously updates the location through the grouping behavior, searches for and replaces the penguin individual that is better than the current individual, when the optimal value falls into the local optimal state difference algorithm is introduced to mutate, crossover, and select individuals until the maximum number of iterations is met. The algorithm effectively prevents the original algorithm from falling into a local optimum and increases the diversity of the original cluster. EPDEA and the improved gray wolf algorithm are simulated under different number of nodes. The results show that EPDEA can reach a coverage rate of close to 97% under the condition of faster convergence, and the sensor nodes in this paper have better accommodation under the spatial distribution. Research shows EPDEA can effectively optimize the node distribution of Wireless Sensor Network, increase network coverage, and improve network quality.