A game theory approach for cooperative control to improve data quality and false data detection in WSN

Abstract

[EN] New solutions are required for the management of heterogeneous distributed sensor networks in order to address the problem of data quality and false data detection in wireless sensor networks (WSNs). In this paper, we present a nonlinear cooperative control algorithm based on game theory. Here, a new model is proposed for the automatic processing and management of information in heterogeneous distributed WSNs. We apply our algorithm to a case study with the aim of improving the quality of temperature data collected from indoor surfaces by a WSN. Unlike the classic unsupervised methods, in the proposed algorithm, it is not necessary to define the number of clusters beforehand. Once the game reaches the game equilibrium, the resulting number of clusters can be used as input for the unsupervised classification analysis. Anomalous temperature values are corrected according to their neighborhood, without modifying the temperature clusters.