Dynamic Link Scheduling in Wireless Networks Through Fuzzy-Enhanced Deep Learning

Abstract

In this paper, we present the Learning Greedy Link Scheduling (LGLS) algorithm, a novel approach for optimizing link scheduling in wireless networks. By integrating deep learning and fuzzy logic, LGLS predicts link quality probabilities, which provide critical topological information to dynamically manage wireless network interference. This approach enhances resource allocation efficiency, leading to better bandwidth and spectrum usage. Our comprehensive evaluation shows that LGLS outperforms traditional algorithms such as Local Greedy Scheduling (LGS), achieving link scheduling performance improvements ranging from 9.60% to 24.79% and activating up to 24.10% more links. These results demonstrate LGLS's robustness and efficiency in diverse network conditions, making it a promising solution for future wireless network optimization.