Intelligent approach for data collection in wireless sensor networks

In wireless sensor networks, one of most important issues is data collection from sensors to sink. Many researchers employ a mathematical formula to select the next forwarding node in the network-wide manner. We are motivated that surrounding environments for nodes are different in time and space. Because different situations of nodes are not considered for selecting the next forwarding node, the performance of data collection is degraded. In this paper, we present an intelligent approach for data collection in sensor networks. We model a nonlinear cost function for determining the next forwarder according to the input types whether inputs are correlated or uncorrelated for generating the output of the function. In our method, the correlated inputs are presented in a weighted sum with the dependent fashion but the uncoupled inputs with an independent fashion in the nonlinear function. The weights in the functions are determined to the direction in which the reliability of data collection maximizes. In the experimental section, we show that our method outperforms other conventional methods with respect to the efficiency in data collection from sensors to sink.