Wireless Body Area Network Optimization using Genetic Algorithm

This paper proposes an energy-aware optimization technique suitable for Wireless Body Area Networks (WBANs) towards addressing the challenging problem of high consumption in wearable health monitoring tools. As these devices manage the health of humans, it is vital that they last long and are fully functional hence energy saving comes into play. To resolve this issue, we propose a loss function that optimizes the energy consumption between sensor nodes and central processing unit (CPUs), as distance is directly proportional to power use. The Euclidean distance formula leads to a structure which lessens these distances and in turn lowering costs of energy during data transfer improving the network performance. In addition, we embed a Genetic Algorithm (GA) into our method. This approach refines the placement of sensor nodes (for 15 generations) iteratively to minimize distance and energy efficiently. Our experimental results show that an impressive reduction in energy consumption can be achieved by our method, demonstrating the potential of our approach to enable eco-friendly WBAN applications not only for healthcare solutions but also for a wider range of other applications. The research could help improve the efficiency and sustainability of wearable technology so that it remains an effective tool in monitoring health.