BWK-FA: A Biologically Inspired Hybrid Algorithm for Benchmark and RNP Optimization
BWK-FA: A Biologically Inspired Hybrid Algorithm for Benchmark and RNP Optimization

Summary/Abstract: The Firefly Algorithm (FA) offers excellent search capability for optimization problems but often gets trapped in local optima due to the lack of mutation mechanisms. To address this issue, this study proposes a novel hybrid algorithm, which introduces Black-Winged Kite (BWK) population into the firefly algorithm, named BWK-FA. Inspired by the predatory behavior of BWK and the evasive response of fireflies, the proposed BWK-FA integrates four biologically-inspired strategies into the classical light-seeking movement. If the predation probability is satisfied, BWKs prey on the brightest firefly within the predation radius, while surrounding fireflies execute evasive movements; otherwise, BWKs are guided by the globally brightest firefly to sustain exploration. In addition, a population information exchange mechanism and an elite-guided strategy are introduced to further enhance search capability. The proposed algorithm is evaluated using benchmark test functions with different dimensional settings through multiple independent runs. Experimental results demonstrate that BWK-FA achieves superior solution quality, stable convergence behavior, and strong robustness compared with representative algorithms. BWK-FA is further validated on standard RFID network planning instances, significantly improving network performance in terms of coverage, interference suppression, power efficiency, and load balance. These findings highlight the proposed BWK-FA for addressing complex industrial optimization problems.

• Details
• Contents