Research on Communication Signal Coverage Methods Based on Recursive Genetic Algorithms

The availability of communication signals for dense wireless local area networks (WLANs) is being increasingly hindered by spectrum contention, interference, and traffic dynamics. Side effects of coverage can also be captured by higher layers, such as the transport or application layer; however, their sensing capabilities are limited, and their information may be strongly biased by the network conditions or the user traffic. In this paper, we explore a coverage-quality-aware optimization framework based on Recursive Genetic Algorithm (RGA) for multi–basic service set (BSS) WLAN environments. Signal coverage is considered as coverage quality and is then evaluated in an indirect manner using network layer performance metrics, namely throughput, packet delay, and control-frame reliability, which is measured using RTS frame loss. A private four-BSS spectrum management dataset produced by the Komondor WLAN simulator is utilized to test potential spectrum configurations. The suggested RGA refines the elite solutions to the maximum spectrum allocation iteratively under interference-aware scenarios. Experimental results demonstrate that the RGA outperforms static allocation, random selection, and the standard GA, with a best average throughput of 0.529, a lowest packet delay of 0.004, and a minimum RTS frame loss of 0.0065. Convergence and Pareto-based analyses further establish the stability as well as the multi-objective nature of the proposed approach. The results confirm that the dataset-driven design of the multi-BSS WLAN optimization by using network-level performance metrics plays a key role in providing a generalizable and reproducible tool for enhancing coverage quality of WLAN networks.