The rapid growth of the Internet of Things (IoT) has led to dense wireless sensor networks (WSNs) deployed in critical applications such as smart cities, industrial monitoring, and healthcare. However, energy constraints, unpredictable communication delays, and inefficient data aggregation remain significant challenges that limit network reliability and operational lifespan. Traditional approaches often fail to balance delay minimization with energy efficiency, especially in large-scale or dynamic networks. To address these issues, this study proposes CTSO-DRNN, a novel framework that integrates Chronological Tangent Search Optimization (CTSO) with a Deep Recurrent Neural Network (DRNN) for accurate delay prediction and optimized data aggregation. The framework constructs Link Delay-Distance (LDD) trees to guide hierarchical communication and leverages CTSO to optimize the DRNN for predicting network delays, enabling adaptive scheduling and energy-aware operation. Experimental findings from simulated WSNs comprising 100 to 250 nodes indicate that the CTSO-DRNN approach decreases the average communication delay by roughly 28% to 60%, increases link lifetime by 8% to 30%, and reduces routing distance by 14% to 25% when compared to various leading-edge techniques across diverse network densities. These improvements highlight the framework’s ability to maintain low latency, prolong network operation, and enhance overall energy efficiency.
Siyal et al. (Thu,) studied this question.