Hybrid Coevolutionary Bat-Cuckoo Algorithm and Real-Time Delay Estimation for Efficient Routing in Wireless Sensor Networks

The adaptive and efficient routing approach introduced in this work for real-time Wireless Sensor Network (WSN) is based on the Hybrid Coevolutionary Bat-Cuckoo Algorithm (HCBCA). The model leverages the local refinement capabilities of the Bat Algorithm (BA), combined with the exploratory power of Cuckoo Search (CS) through Levy flights, to co-evolve adaptive convergence within the learning framework. Routing decisions are optimized using a Real-Time Delay Estimator (RTDE) that incorporates fuzzy logic and an Adaptive Path Fitness Evaluator (APFE), which combines delay, energy, and reliability into a unified scoring metric. The proposed framework is designed with a view of development of significant decrease in time transmission, increases packet delivery ratio (PDR), and saves energy under different dynamic network scenarios, demonstrating its categorized scale as a robust solution for delay-sensitive WSN applications.