Differential Evolutionary Optimization Algorithm for Energy-Efficient Routing Strategy in Wireless Sensor Networks

Abstract

Modern communication systems depend mostly on wireless sensor networks (WSNs), yet resource constraints and dynamic topologies cause major difficulties in energy efficiency and safe data transmission. Dealing with these problems, this work presents Exponentially-Enhanced Whale- Differential Evolution Optimisation (E-WDEO), a new routing system meant to improve network longevity and performance. The proposed model runs in two phases: first, cluster heads are chosen by a hybrid metaheuristic combining Differential Evolution (DE) and Whale Optimisation Algorithm (WOA), therefore guaranteeing best resource distribution. Then effective routing paths are found via a fitness-driven path selection technique including parameters including distance, energy, and latency. The E-WDEO model reduces the problems of high packet loss, energy depletion, and latency rather successfully. Over 1000 rounds, simulations on a 500-node network show notable performance gains including 85.2 J energy savings, 750 kbps throughput, 0.07 seconds latency, and a 9% packet loss. Compared to present techniques, the proposed approach considerably reduces computing cost and preserves 480 active nodes. These results demonstrate E-WDEO's capacity to deliver robust and efficient data transfer, hence extending the lifetime of the network. Future studies aimed at additional advancements in energy economy and Quality of Service (QoS) combine metaheuristics with deep learning approaches.