Privacy-preserving asynchronous information fusion method for AC and DC screen branch circuit sensors

Abstract

Due to the nonlinear property of asynchronous information between sensors, it is difficult to effectively control the data loss problem when fusing them, therefore, we propose a privacy-oriented fusion method for the asynchronous information of AC and DC screen tributary sensors. The asynchronous information characteristics of the AC/DC screen branch sensors are analyzed in terms of timestamp deviation, data consistency, data noise and interference, data discontinuity and data uncertainty, etc. With the help of nonlinear equations describing the asynchronous information of the AC/DC screen branch sensors, the original asynchronous information is fused and filtered in a recursive form, and the state vector estimates and covariance values of the asynchronous information collected by the AC/DC screen branch sensors are fused with the help of the RBF neural network. Then, the estimated values of state vector and covariance matrix are calculated in the RBF neural network to perform interactive multi-model fusion on the asynchronous information queue. In the test results, the data loss rate is stabilized within 3.0%.