Intelligent Monitoring Scheduling in Wireless Sensor Networks

This paper describes a dynamic distributed monitoring scheduling algorithm (SOMSA) for sensor networks based on artificial neural-networks self-organizing maps algorithm. During the training, the stable sensor nodes compete and cooperate with their neighbors to study the input patterns of the environment and update their internal prototype vectors using only local sensing and interactions. The adjustment stops gradually if the environment is changeless or gradually changed. In the end, the networks monitoring patterns will reflect the feature of the environment. Simulation indicates that this is a valid methodology, being especially promising for energy saving with limited resources.