Adaptive transmission for Power Line Communication using neural networks

Abstract

Adaptive transmission methods can potentially aid to achieve high data rates in Power Line Communication (PLC) system. To realize this potential, the transmitter needs accurate Channel State Information (CSI) for the upcoming transmission frame. In this paper a channel prediction scheme for Exponential Effective SINR Mapping (EESM) algorithm using Neural Network for OFDM system is proposed to select a suitable Modulation and Coding Scheme (MCS) for the current PLC channel realization which renders high throughput, while maintaining a certain target Packet Error Rate (PER). The Neural Network is trained to predict the future channel condition so as to perform adaptive transmission. The performances of three different neural network models are evaluated and it is observed that the proposed channel prediction method has performed more accurately than the conventional prediction systems. The processing time of EESM algorithm improved from 2.31 seconds to 0.26 seconds and thus proving fast adaptation.