Machine learning for intelligent beam divergence compensation in orbital angular momentum-based wireless communication systems

Orbital Angular Momentum (OAM) multiplexing enables high spectral efficiency but suffers from severe signal degradation due to beam divergence. Traditional compensation methods are computationally intensive and slow, making them unsuitable for real-time use. This paper proposes a machine learning-based solution using a Deep Neural Network (DNN) that learns to predict optimal beamforming weights directly from environmental factors like distance and turbulence. A key innovation of this work is the use of a low-complexity learning framework that directly predicts hybrid beamforming weights for OAM beam divergence compensation, thereby avoiding repeated iterative optimization and enabling substantial latency reduction. Trained on diverse channel data, the model achieves over 96.2% of the optimal received power while reducing latency from 100 ms to just 0.5 ms—a 200× improvement. It generalizes well to unseen scenarios, including mobile users and hardware impairments, outperforming conventional and adaptive baselines. This work demonstrates a viable path toward adaptive, low-latency OAM systems for future 6G networks.