Adaptive learning FOA algorithm with energy consumption balancing for coverage optimization in WSNs

Abstract

Wireless sensor networks (WSNs) are widely used in environmental monitoring, industrial manufacturing, disaster relief, healthcare, and energy management. However, the development of WSNs still faces many challenges related to coverage and energy balancing among the distributed nodes. To address the above issues, we propose an adaptive learning Fruit Fly Optimization Algorithm (FOA) to optimize the nodes’ coverage and energy balancing in 2D and more complex 3D environments. Adaptive learning FOA incorporates a fusion of adaptive virtual force modeling and adaptive small habitat techniques to enhance initial search capabilities and maintain search balance in later stages. Moreover, we employ dynamic oppositional learning (DOL) and adaptive dimensional learning (ADL) to avoid falling into local optima and to improve search accuracy. Additionally, we introduce a real-time node energy consumption model, which calculates energy consumption during movement, coverage, and iteration of nodes. The proposed model enables continuous monitoring of node energy, helping to prevent energy loss and node failure, thereby enhancing the overall performance and stability of WSNs. The simulation results demonstrate the effectiveness of our approach: in the 2D scenario, the adaptive learning FOA achieves a maximum coverage rate of 94.86% and an average coverage rate of 94.18%, while in the 3D scenario, it reaches a maximum coverage rate of 97.68% and an average coverage rate of 96.32%. These results highlight the significant improvements in coverage and energy balancing, confirming the potential of our method to optimize WSN performance in diverse environments.