Short-term load prediction method based on correlation analysis and Kalman filtering method

Abstract

The invention discloses a short-term load prediction method based on correlation analysis and a Kalman filtering method. The short-term load prediction method comprises the following steps: 1, constructing a weather similar day judgment model; 2, calculating a load correlation coefficient; 3, determining an inherent prediction error cd, an initial optimal prediction deviation vd and an initial overall deviation td; 4, determining a load observation sequence OEi and load prediction sequences FEi1 and FEi2; and 5, predicting the load PEi of the target date. By load historical data, a weather similar day discrimination model is created and weather influencing factors are introduced., meanwhile, the similarity of the short-term power load in a short time is considered; load parameters of adjacent days and previous weeks on the same day are introduced, meanwhile, the operability and prediction precision of the method are improved, a reliable basis is provided for power system planning, andthe invention has important significance in arrangement of work plans of power supply enterprises, formulation of emergency plans and guarantee of safety and reliability of power supply and can assist the power supply enterprises in work more accurately.

Description

technical field [0001] The invention relates to a short-term load forecasting method based on correlation analysis and Kalman filtering method, and belongs to the field of information technology. Background technique [0002] Power load forecasting is one of the important tasks of the main business departments of the power system. Load data is an important basis for power resource planning and development, optimal allocation, and power resource scheduling. Improving the technical level of load forecasting is conducive to improving the economic and social benefits of the power system. . [0003] In recent years, with the increase of residential electricity load, the fluctuation of grid load has become more and more obvious. Short-term load forecasting plays an important role in the arrangement of work plans of power supply enterprises, the formulation of emergency plans, and the safety and reliability of power supply. Significance, the traditional short-term load forecasting...

AI Technical Summary

Problems solved by technology

A large number of studies have proved the objective impact of weather factors on power loads, but the construction of quantitative impact models is difficult and the effect is not ideal, and it is difficult to support accurate load forecasting

Images