A Survey on Deep Learning-based Resource Allocation Schemes

Abstract

The growing number of complex and heterogeneous nodes and base station applications has required a high computational complexity to handle wireless resources. To tackle this problem, deep learning-based resource allocation schemes have emerged to alleviate the excessive overhead issue of conventional iterative algorithms. Specifically, the deep learning technique is primarily divided into three types: supervised learning, unsupervised, and reinforcement learning. In this paper, we review the deep learning-based resource allocation schemes based on the aforementioned training methods, and the limitations and technical challenges in the future are addressed.