ANN-BASED FUTURE PREDICTION MODEL FOR ENERGY EFFICIENT SLEEP/WAKE SCHEDULING IN WSN

Abstract

Wireless Sensor Networks (WSNs) play a significant role in various applications such as environmental monitoring, smart agriculture, and industrial automation. However, the major limitation of WSNs is the restricted energy availability of sensor nodes, which directly affects network lifetime and performance. Continuous operation of nodes leads to rapid energy depletion, making efficient energy management a critical requirement. This paper proposes an AI-based future prediction model for energy-efficient sleep/wake scheduling in Wireless Sensor Networks. The proposed approach employs an Artificial Neural Network (ANN) to perform intelligent node state classification based on multiple parameters, including residual energy, distance to the cluster head, and traffic load. In addition, a predictive mechanism is incorporated to estimate future energy conditions, enabling proactive and adaptive scheduling decisions. The model is implemented in MATLAB and evaluated over multiple simulation rounds. Performance metrics such as energy consumption and network lifetime are analyzed. The results demonstrate that the proposed method significantly reduces energy usage, maintains balanced node activity, and enhances overall network lifetime compared to conventional approaches.