Enhancing beyond 5G connectivity and security: optimizing user-to-multiple AP associations with hybrid deep learning and innovative optimization techniques

Enhancing beyond 5G connectivity and security: optimizing user-to-multiple AP associations with hybrid deep learning and innovative optimization techniques

연구 분야: Networking

학회: The Journal of Supercomputing

The investigation of sophisticated methods to maximize user-to-multiple access point (AP) associations has been spurred by the unwavering need for fast, dependable connectivity in Beyond 5G (B5G) networks. This paper proposed a novel approach for selecting optimal AP by combining state-of-the-art deep learning (DL) architectures such as Alex Net, ResNet50, and Darknet53 with an innovative hybrid optimization algorithm. The adaptive feature of the FOX-inspired optimization algorithm is combined with the efficiency of the standard Gazelle optimization algorithm in this study. Combining these two optimization strategies guarantees a balanced trade-off between exploration and exploitation, leading to selecting APs that optimize network performance while adjusting to changing environmental conditions. This strategy not only improves connectivity but also advances wireless network evolution, establishing the way for effective and flexible B5G communication systems. The optimization of user-to-multiple AP associations in B5G networks presents a comprehensive challenge that this research attempts to handle through the smooth integration of cutting-edge optimization methods with DL approaches.