Power load medium and long term prediction method based on improved grey prediction model

Abstract

The invention discloses a power load medium and long term prediction method based on an improved grey prediction model. In order to solve the problem that large errors are easily generated in a fixed model prediction time varying system, a model updating algorithm is provided, in other words, a method combining a sliding window algorithm with a traditional grey prediction model is adopted. The prediction model is recursively updated in a mode that a part of old data are deleted and a part of new data are introduced in a modeling sequence, key quantity a&b related to the mathematic model is decomposed, a recursive mathematical formula is simplified, and the influence of the length of a sliding window on modeling accuracy is discussed.

Description

technical field [0001] The invention belongs to the technical field of medium and long-term power system load forecasting, and relates to a gray forecasting model update algorithm and an electric load forecasting method of an optimal modeling sequence algorithm. Background technique [0002] After more than 20 years of development since Professor Deng Julong proposed the gray prediction model, the theory has been widely used in the fields of industry, agriculture, energy and transportation, especially Model. Although the gray forecasting model has received widespread attention, there are still many problems, especially in the field of medium and long-term forecasting of electric load. At present, many scholars have successively proposed improved methods, such as the prediction results of the Markov chain symbol correction gray model, the background value and initial value correction value of the gray model optimized by particle swarm optimization, the combined gray model ...

AI Technical Summary

Problems solved by technology

However, since the power system is changing all the time, its forecasting model should also be changing. Some improved gray forecasting algorithms have achieved better forecasting accuracy, but there are still the following problems: (1) Not suitable for medium and long-term forecasting

Due to the relatively large time span, multi-step forecasting is necessary, and using a fixed model to predict changing objects will obviously lead to large errors

(2) Repeated construction model calculation is cumbersome

Therefore, using a fixed forecasting model will lead to poor forecasting accuracy.

Images