Optimising power management in wireless sensor networks using machine learning: an experimental study on energy efficiency

Wireless sensor networks (WSNs) are critical in various applications, utilising small, energy-constrained nodes for data collection. A major challenge is extending the operational lifetime of these nodes without compromising data collection speed, as regular data aggregation consumes significant energy. This study introduces an energy-efficient approach using artificial intelligence (AI) to optimise data transmission by triggering updates only when significant changes occur. An impressive optimisation of up to 73% can be achieved, significantly improving energy efficiency by extending the battery life of a 3,400 mAh node from 191 to 330 hours. Additionally, four machine learning algorithms (LSTM, GRU, GB, and ANN) were evaluated for their predictive capabilities. Gradient boosting (GB) was selected for hardware implementation due to its optimal balance between accuracy and computational efficiency. This strategy reduces energy consumption while maintaining performance, making it ideal for resource-constrained WSN environments.