Multi-source data correction method and system based on interpolation method and time sequence intelligent method

By combining interpolation and time-series intelligent methods, a multi-source data correction method was developed to address the issue of neglecting periodicity, trends, and monotonicity in power grid data acquisition. This method enables accurate and real-time correction of power grid data, thereby improving the operation, maintenance, and monitoring capabilities of the power grid system.

CN116662841BActive Publication Date: 2026-03-24OPERATION & MAINTENANCE BRANCH OF NINGBO POWER TRANSMISSION & TRANSFORMATION CONSTR CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-04-12
Publication Date
2026-03-24

AI Technical Summary

Technical Problem

Existing technologies fail to effectively consider the periodicity, trend, or monotonicity of data during power grid data acquisition, making it difficult to obtain accurate and real-time corrected data after data interpolation, which affects the normal operation of the power grid system and the accuracy of decision-making.

Method used

A multi-source data correction method based on interpolation and time-series intelligent methods is adopted. The k-Means algorithm is used to detect abnormal data, and the abnormal data prediction model is trained by combining time-series prediction method. Abnormal data is predicted and removed according to the data change pattern. Interpolation is performed using fitted curves or neighboring point data to ensure the accuracy and real-time performance of the data.

Benefits of technology

It improves the accuracy and real-time performance of power grid anomaly data correction, ensures the data quality of power grid system operation and maintenance and monitoring, and reduces the threat of anomaly data to power grid security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116662841B_ABST
    Figure CN116662841B_ABST
Patent Text Reader

Abstract

The application discloses a multi-source data correction method and system based on an interpolation method and a time sequence intelligent method, and the method comprises the following steps: acquiring multi-source heterogeneous data in a historical period; detecting abnormal data in the multi-source heterogeneous data in the historical period; predicting the abnormal data frequency according to the abnormal data occurrence period in the multi-source heterogeneous data in the historical period; eliminating the abnormal data in the multi-source heterogeneous data in the next period according to the abnormal data frequency to form an effective multi-source heterogeneous data set, and interpolating the vacancy after eliminating the abnormal data in the effective multi-source heterogeneous data set. According to the time sequence prediction method combined with the interpolation method, the application predicts the data value of the time period with abnormal data in the next period according to the objective law of power grid data collection, corrects the abnormal data of the power grid, improves the accuracy of abnormal data correction, and ensures that the related data obtained better supports the operation and monitoring of the power grid system.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Time series data anomaly detection method and device, electronic equipment and storage medium

    CN113342610A

  • Data management method and device of power system, equipment and medium

    CN115794578A