A Self-Adaptive Sleep/Active Approach for Wireless Sensors Network
Keywords:
Reinforcement learning, sleep, active, listen, transmission.Abstract
Continues active state approach is one of the basic problem in wireless sensors network, the energy of sensors nodes is limited and they are not chargeable. The purpose of sleep/active approach is to save the energy power of each node by keeping nodes in enactive mode until they must have message to be transfer and there by maximizing their lifetime. In this presented papers, a self-adaptive sleep/active organize approach is proposed. Unlike most existing studies that use the duty cycling technique, which experience a imbalance between packet delivery delay and energy saving, the proposed approach, which does not use duty cycling, avoids such imbalance. The proposed approach, based on the reinforcement learning technique, permit each node to automatically decide its own operation mode in any one of these (sleep, listen, or transmission) in each different timeslot in a decentralized manne