Energy efficient and reliable data transmission in WBAN using multivariate gradient divergence African buffalo optimization

Abstract

SummaryWireless body area network (WBAN), a popular radio communication technique, tracks patients' health conditions remotely using small, low‐power, portable sensors positioned on the body to sense vital signs and send data to a control node. To sustain long‐term health monitoring, WBANs require significant energy from the nodes. This research proposes an energy efficient and reliable data transmission using multivariate gradient divergence African buffalo optimization (EEMGDABO) to minimize the delay of critical node data transmission by identifying the optimal path to the control node. The protocol comprises two key processes: winsorized correlative segmented symbolic regression with reinforcement learning (WCS‐SRRL) and the walrus optimization algorithm (WaOA) for accurate priority‐based classification of health data (normal, abnormal, and critical). The second process involves transferring these priority‐based data with reduced energy consumption and delay while increasing throughput by determining the best path from the critical node to the destination (hospital/doctor) using EEMGDABO, which calculates node distance and energy fitness value. Implemented in MATLAB with a health monitoring WBAN dataset, the proposed protocol demonstrates 23% less energy consumption, 12.33% less delay, and 23.44% higher network lifetime compared to existing optimization approaches.