Deep Sequential Feature Learning for Phase Noise Compensation in Sub-THz Systems

For data rates exceeding several gigabits per second, which are achievable in fifth-generation wireless networks, the integration of subterahertz (sub-THz) communications has become increasingly important. However, hardware limitations, such as phase noise arising from local oscillator imperfections, can hinder the performance of sub-THz systems. This paper addresses the challenge of phase noise compensation for data decoding in orthogonal frequency division multiplexing systems. To address this issue, we propose a new sequential feature learning mechanism designed to capture both the subcarrier-shift invariance feature of phase noise and the subcarrier-dependent feature of intercarrier interference. The proposed approach involves empirical performance evaluations under various conditions and a theoretical analysis that considers computational complexity and the signal-to-interference-plus-noise power ratio. By performing comprehensive comparisons with existing analytical and deep learning-based methods, we demonstrate the effectiveness of our proposed method, even with an extremely low pilot overhead.