Channel prediction method based on the data-driving for distribution automation main station

Abstract

A data-driven channel prediction method for distribution automation master is proposed to address the poor quality of communication network and communication system transmission problems in distribution network communication. In this paper, an adaptive broad learning network (ABLN) consisting of a standard broad learning network and a hybrid learning network is introduced to predict the channel state information of the communication system. Among them, the hybrid learning network is used to solve the ill-conditioned solution problem when estimating the output weight matrix of the standard broad learning network. Therefore, the ABLN produces sparse output weight matrices and provides excellent prediction performance. In the simulation analysis, the outdoor and indoor scenes are considered based on OFDM system. The prediction performance of ABLN is subsequently evaluated in one step prediction and multistep prediction. The results show that for the prediction performance is concerned, the maximum improvement of ABLN is about 96.49% as compared to other evaluation models, indicating that the CSI is effectively predicted by the ABLN to support the adaptive transmission of the main station of the distribution automation and to satisfy the quality of the communication network of the distribution network.