Application of Adaptive Whale Optimization Algorithm Based BP Neural Network in RSSI Positioning

The paper proposes a wireless sensor network (WSN) localization algorithm based on adaptive whale neural network and extended Kalman filtering to address the problem of excessive reliance on environmental parameters A and signal constant n in traditional signal propagation path loss models. This algorithm utilizes the adaptive whale optimization algorithm to iteratively optimize the parameters of the backpropagation (BP) neural network, thereby enhancing its prediction performance. To address the issue of low accuracy and large errors in traditional received signal strength indication (RSSI), the algorithm first uses the extended Kalman filtering model to smooth the RSSI signal values to suppress the influence of noise and outliers on the estimation results. The processed RSSI values are used as inputs to the neural network, with distance values as outputs, resulting in more accurate ranging results. Finally, the position of the node to be measured is determined by combining the weighted centroid algorithm. Experimental simulation results show that compared to the standard centroid algorithm, weighted centroid algorithm, BP weighted centroid algorithm, and whale optimization algorithm (WOA)-BP weighted centroid algorithm, the proposed algorithm reduces the average localization error by 58.23%, 42.71%, 31.89%, and 17.57%, respectively, validating the effectiveness and superiority of the algorithm.