Power data regression analysis method and system

Abstract

The invention discloses a multi-source power data regression analysis method and system, and the method comprises the following steps: inputting to-be-analyzed independent variables and dependent variables into a pre-trained power data regression analysis model, and obtaining an analysis result; wherein the step of acquiring the pre-trained power data regression analysis model comprises the following steps of: acquiring preset power encrypted data; constructing a linear equation set based on a power data regression analysis problem; solving to obtain regression analysis model parameters; and obtaining the pre-trained power data regression analysis model based on the obtained regression analysis model parameters. According to the method, the security multi-party computing technology is applied, the regression analysis model can be effectively constructed while the privacy information of the power data is not leaked, the potential safety hazard of the data is eliminated, and the utilization capability of the data of each power mechanism is improved.

Description

technical field [0001] The invention belongs to the technical field of power data security protection, and in particular relates to a multi-source power data regression analysis method and system. Background technique [0002] With the sharing and application of power data on a larger scale and on a larger scale, the value of open sharing of power data is not only reflected in the power industry, but also in many aspects such as national economic operation, social progress, and innovation and development of various industries. Under the background of in-depth docking and coupling of academic research, many universities and research institutions also hope to use massive real power data for research and analysis. Specifically, regression analysis is a predictive modeling technique. By constructing a regression model, predictive analysis, time series analysis, and the discovery of causal relationships between variables; in power systems, regression analysis can be used for load...

AI Technical Summary

Problems solved by technology

[0003] However, since data in the power industry is closely related to national security and personal privacy, there are a series of data security threats and hidden dangers in sharing data with research institutions, making it difficult for people outside the power industry to access real power data; if data encryption methods are used, It can only guarantee the security of the data transmission process. When it is used for analysis, it still needs to be decrypted before use, and there is still a security risk of data leakage.

On the other hand, the power industry involves a wide range, and the data of each power institution is usually limited to a single region or a single business scenario. Although research institutions can obtain part of the power data through cooperation with power institutions, only the data of one power institution It is difficult to meet the requirements of both data depth and breadth at the same time, and it is impossible to build an effective regression analysis model

Images