Power consumer load interval prediction method based on deep learning

Abstract

The invention discloses a power consumer load interval prediction method based on deep learning. The method comprises the following steps of (1) establishing a large consumer historical load data preprocessing model; (2) establishing a load point prediction model based on an LSTM time recurrent neural network; and (3) adopting a load interval prediction algorithm of a point prediction value scaling coefficient. In this way, according to the method, a user load preprocessing model based on a state vector machine method is established to carry out preprocessing analysis on the single user historical data; and according to the processed historical data, an LSTM machine learning method is adopted to find a prediction model for reducing a user load prediction error to the maximum extent, and the load interval prediction of a single user is carried out by using a point prediction value scaling coefficient load interval prediction algorithm, so that the accurate load interval prediction can be carried out on the load of the single power user with strong random fluctuation, and the prediction accuracy of the user load is obviously superior to that of a traditional method.

Description

technical field [0001] The present invention relates to the field of electric power system automation, in particular to a method for predicting power user load intervals based on deep learning. Background technique [0002] The power system is a complex system composed of power plants, transmission lines, power distribution systems and loads. The economic operation of the power system is to provide power to users at the least cost under the condition of safety and reliability. Load forecasting is used as an energy management system (EMS ) and an important part of the operation and management of the power market, and its prediction results are closely related to the safe and economical operation of the power system. [0003] Load forecasting can generally be divided into ultra-short-term, short-term, medium-term and long-term forecasting according to different objectives. Ultra-short-term load forecasting refers to load forecasting within one hour in the future, and is mainly...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the existing load forecasting technologies and methods are aimed at the overall regional load, and the forecast for a single load user is rare. With the reform of the power demand side and the advancement of the power market, the fine forecasting of the individual load of large users is particularly important. Important; however, user-level load forecasting is quite different from traditional regional and system-level load forecasting, mainly reflected in the fact that regional system-level load is the combined effect of a large number of individual loads. Offset, the fluctuation of the regional system-level load is not obvious; and observing a large number of large-scale user daily load curves, it can be found that due to the unique production process or business activity rules of the industry, the user-level load curve is in its individuality. On the basis of the characteristics of large random fluctuations, the existing regional load prediction methods are not suitable for user load prediction in terms of describing random fluctuations. Therefore, it is necessary to study fine intervals suitable for user-level load Predictive methods are imperative

Images