Software Demodulation of Weak Radio Signals using Convolutional Neural Network

2020-05-01

2020 IEEE 7th International Conference on Energy Smart Systems (ESS)

AI Summary

To address the poor robustness of JT65A protocol demodulation for weak MFSK signals under extremely low SNR (−30 dB to 0 dB) in additive white Gaussian noise (AWGN) channels—critical for wide-area power system monitoring—this paper proposes an end-to-end software demodulation method based on a deep convolutional neural network (DCNN). The approach jointly incorporates JT65A protocol specifications and MFSK signal modeling to enable channel-adaptive interference suppression. Experimental results demonstrate reliable communication at −28 dB SNR, with symbol error rate (SER) significantly outperforming conventional noncoherent demodulation. Across the full SNR range (−30 dB to 0 dB), the proposed method achieves performance within only 1.5 dB of the theoretical MFSK bound—the first systematic validation of JT65A’s interference resilience in this ultra-low-SNR regime. This work establishes a novel paradigm for reliable reception of ultra-weak wireless signals in wide-area synchronized monitoring applications.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In this paper we proposed the use of JT65A radio communication protocol for data exchange in wide-area monitoring systems in electric power systems. We investigated the software demodulation of the multiple frequency shift keying weak signals transmitted with JT65A communication protocol using deep convolutional neural network. We presented the demodulation performance in form of symbol and bit error rates. We focused on the interference immunity of the protocol over an additive white Gaussian noise with average signal-to-noise ratios in the range from −30 dB to 0 dB, which was obtained for the first time. We proved that the interference immunity is about 1.5 dB less than the theoretical limit of non-coherent demodulation of orthogonal MFSK signals.

Problem

• demodulate weak JT65A radio signals
• enhance interference immunity in noisy environments
• compare with theoretical demodulation limits

Innovation

• Convolutional neural network demodulation
• JT65A protocol for power systems
• Interference immunity over Gaussian noise