Self-Adaptive Dissemination of Data in Dynamic Sensor Networks

The distribution of data in large dynamic wireless sensor networks presents a difficult problem due to node mobility, link failures, and traffic congestion. In this paper, we propose a framework for adaptive flooding protocols suitable for disseminating data in large-scale dynamic networks without a central controlling entity. The framework consists of cooperating mobile agents and a reinforcement learning component with function approximation and state generalization. A component for agent coordination is provided, as well as rules for agent replication, mutation, and annihilation. We examine the adaptability of this framework to a data dissemination problem in a simulation experiment.