Decentralized optimization of wireless sensor network lifetime based on neural network dynamics

The wireless sensor networks, which collect various data from a physical environment, are usually defined as an ad hoc network consisted of a huge number of tiny wireless sensor nodes whose computing power and battery capacity are limited. Because it is difficult to replace all of batteries on such a huge number of sensor nodes, maximization of the lifetime of the network has been one of the important research issues. To optimize such a network with a huge number of the sensor nodes, autonomous and decentralized computing and reconfiguration schemes can be considered suitable. Therefore, in this paper, we propose a routing reconfiguration method based on an autonomous optimization dynamics of the mutually connected neural network which minimizes its own energy function with autonomous and distributed computing. We show that the proposed method can optimize the routes for maximizing the lifetime of the sensor network, without any centralized computing nodes.