Refined load prediction method combining historical data and real-time influencing factors

Abstract

Provided is a refined load prediction method combining historical data and real-time influencing factors. The core of the method is to improve load prediction accuracy. With the rapid development of asmart grid technology, higher and higher requirements are raised on the accuracy of load prediction. Combining multi-source data such as load and weather, the invention proposes to establish corresponding prediction models for different daily attributes and to establish a general-purpose prediction model applicable to all daily attributes in a specific region. Firstly a correlation coefficient isutilized to quantitatively analyze the correlation degree between load and temperature, humidity and other weather influencing factors; secondly a function is used to fit the trend of the nonlinear influence of main influencing factors on load; finally two prediction models are established to predict the load of a certain prefecture-level city in Zhejiang in 2013. Prediction results indicate thatthe prediction accuracy of the method is obviously higher than that of a traditional prediction method. Based on the existing research, the method significantly improves the prediction accuracy.

Description

technical field [0001] The invention belongs to the technical field of power distribution big data under the background of a smart grid, and its core lies in improving the accuracy of load forecasting. Background technique [0002] Load forecasting is an important basis for the safe and stable operation of the power system, and it is also a basic work of power system planning, planning and dispatching. With the rapid development of smart grid technology, power production and consumption are more market-oriented, and the real-time result data of load forecasting will become one of the most important data in power trading, which puts higher demands on the accuracy and real-time performance of load forecasting. requirements. Accurate load forecasting plays a fundamental role in ensuring the interests of various economic entities, and the operation planning of enterprises in all links of the power system depends on accurate load forecasting. Among them, power generation compan...

AI Technical Summary

Problems solved by technology

[0003] In load forecasting, since there are many factors that affect the load, and the influence of different factors on the load is nonlinear, this will cause the accuracy of load forecasting to not be significantly improved.

Images