A Multi-Task Learning Model for Super Resolution of Wireless Channel Characteristics

TL;DR

This paper introduces a multi-task learning convolutional neural network model that significantly improves super resolution of wireless channel characteristics, reducing reliance on costly measurements and simulations in 5G and 6G system design.

Contribution

It presents a novel multi-task learning CNN with residual connections for super resolution of wireless channel data, outperforming existing models and demonstrating practical benefits.

Findings

Achieves high accuracy in mean absolute error and error standard deviation

Outperforms state-of-the-art deep learning models in channel super resolution

Ablation studies confirm the importance of multi-task learning techniques

Abstract

Channel modeling has always been the core part in communication system design and development, especially in 5G and 6G era. Traditional approaches like stochastic channel modeling and ray-tracing (RT) based channel modeling depend heavily on measurement data or simulation, which are usually expensive and time consuming. In this paper, we propose a novel super resolution (SR) model for generating channel characteristics data. The model is based on multi-task learning (MTL) convolutional neural networks (CNN) with residual connection. Experiments demonstrate that the proposed SR model could achieve excellent performances in mean absolute error and standard deviation of error. Advantages of the proposed model are demonstrated in comparisons with other state-of-the-art deep learning models. Ablation study also proved the necessity of multi-task learning and techniques in model design. The contribution in this paper could be helpful in channel modeling, network optimization, positioning and other wireless channel characteristics related work by largely reducing workload of simulation or measurement.