Toward the Intelligent OFDM Receiving Method With Hybrid Knowledge and Data Driven in IoT

Bin Wang, Hui Dai, Huaji Zhou, Zhuang Yuan

Abstract: Orthogonal frequency-division multiplexing (OFDM) is regarded as one of the key technologies in wireless communications, particularly in the integration of space and ground networks. Nevertheless, the performance of OFDM communication systems will degrade significantly in complex scenarios, which brings severe challenge to reliable information recovery at the receiver. To address this issue, we propose an intelligent receiving method for OFDM communication based on dual-channel convolutional neural network (DCNet) from the perspective of combining knowledge and data-driven, which introduces the domain knowledge of channel estimation to assist the stability of OFDM signal recovery. The experimental results under various simulation conditions demonstrate that the proposed method can effectively enhance the performance of information recovery in OFDM communication systems.