Abstract

Wireless Sensor Networks (WSNs) are critical in various applications but face challenges in multi-cluster environments due to data aggregation and routing inefficiencies. This study addresses these issues by proposing an advanced approach leveraging the Deep K Nearest Neighbors (Deep KNN) algorithm for clustering. The method optimizes data routing by dynamically adjusting cluster heads based on deep learning insights, thereby enhancing energy efficiency and prolonging network lifespan. The experimental results, conducted on a simulated WSN platform, demonstrate significant improvements: a 30% reduction in energy consumption, a 20% increase in data transmission efficiency, and a 15% enhancement in network coverage compared to traditional methods. This approach not only improves network performance metrics but also ensures robustness and scalability in dynamic WSN environments.