Abstract: Although the wireless cooperative networks (WCN) significantly improve the communication quality and network throughput of wireless communications. However, it still faces the challenge of the network lifetime and the energy replenishment due to the energy limitation of relay nodes. In order to tackle this challenge, A multi-relay wireless cooperative network combined with the simultaneous wireless information and power transfer (SWIPT) is proposed and the theoretical performance under the Nakagami-m assumption is analyzed. The selection of the optimal relay node for wireless cooperative networks in the framework of the proposed system is studied. The outage probability of the system under different optimal relay selection strategies is obtained, and its correctness is verified by Monte Carlo simulations. The factors that affect the system outage probability are analyzed through a series of simulations. Furthermore, the feedforward neural network (FNN) machine learning algorithm is used to optimize the selection of relay nodes. The experimental results show that: the accuracy of selecting the optimal relay selection is around 93%.

Key words: wireless cooperative network, simultaneous wireless information and power transfer (SWIPT), feedforward neural network, maximum ratio combining