Design of Multi-Source Heterogeneous Data Fusion Algorithm for Distribution Networks Based on Improved Kalman Filter

The complexity of multi-source heterogeneous data in distribution network is high and Significant deviations in multi-source heterogeneous data increase the complexity of fusion multi-source heterogeneous data in distribution network. Therefore, a multi-source heterogeneous data fusion algorithm based on Improved Kalman filter is designed. The correction process adjusts deviations in the initial multi-source heterogeneous data. Subsequently, the least squares method aligns the time series, while the Lagrange interpolation fills missing values. The distribution map method and Kalman filter algorithm are fused to improve the Kalman filter algorithm. The processed multi-source heterogeneous data are input into the improved algorithm. After removing the disturbed data from the distribution map, the data fusion is completed by Kalman filter. The experimental results show that the algorithm can achieve accurate missing data filling processing, and the average error between the current data, voltage data and actual data is 0.0082 and 0.0149 respectively, which are within the ideal error range. For all kinds of distribution network data with disturbance data, it can achieve high-quality data fusion processing, and the covariance difference of the fusion result is close to the demand covariance difference of 0.06, which meets the actual application requirements.