Key points are not available for this paper at this time.
Wireless Sensor Networks (WSNs) are an essential part of 5 G infrastructure, providing real-time monitoring and data transfer in different domains like smart cities, healthcare, and industrial automation. Despite this, data routing in such networks is still an area of concern due to limited node energy and dynamic network topology. The main problem handled is the high rate of node energy depletion due to ineffective clustering and routing, which shortens network lifetime. This instigates the creation of smart algorithms to trade off energy use and provides reliable communication. This paper presents a new routing protocol that integrates the Improved Snow Leopard Optimization Algorithm (ISLOA) to select cluster head (CH) and the Progressive Recurrent Generative Adversarial Network (PRGAN) to perform optimal data routing. The process starts with a single-hop cluster-based network simulation, where nodes are grouped into clusters using an Evolutionary Gravitational Neocognitron Neural Network (EGNNN). ISLOA chooses energy-efficient CHs by optimizing multi-constraint parameters like energy, distance, delay, and traffic density. PRGAN subsequently determines the optimal route to transfer aggregated information from CHs to the sink node with the smallest energy consumption, and delays the process. The proposed ISLOA-PRGAN scheme is executed in Python and records 0.3 %, 0.45 %, and 0.6 % reduced energy consumption, 7.56 %, 12.26 %, and 14.38 % improved packet delivery ratio, and 29.36 %, 20.98 %, and 27.7 % increased network lifetime compared to similar studies. In conclusion, the ISLOA-PRGAN framework tremendously enhances energy economy, network longevity, and data delivery reliability in 5 G WSNs, which is a big leap towards future wireless communications.
Pandi et al. (Mon,) studied this question.