Fractional-Order Distributed Kalman Filter in Virtualized Sensor Networks by Diffusion Strategies

Abstract

Wireless sensor networks are applied in a broad range of applications such as medical, industrial and military fields.Therefore, a precise Kalman filter mechanism is needed for dynamic configuration of topologies in sensor networks in order to ensure accuracy and precision of sensor measurements.On the other hand, fractional calculus as a generalization of integer order operators enables modeling of physical systems with high accuracy.Hence, a new fractional-order distributed Kalman filter algorithm is presented in this study to estimate the states in sensor networks.Therefore, as a generalization of filtering algorithm a fractional order Kalman filter algorithm is proposed.For this purpose, fractional-order distributed Kalman filter algorithms and fractional diffusion Kalman filters are formulated and their performance is evaluated based on mean squares for algorithm feasibility analysis. Simulations show that performance of the proposed algorithm is improved in terms of accuracy and efficiency compared to previous methods such as conventional fractional Kalman filter