Ultra-short-term power load prediction method

Abstract

The invention provides an ultra-short-term power load prediction method, which is characterized by comprising the following steps of: firstly, randomly generating a sufficient number of low-dimensional delay variable combinations according to multi-dimensional observation variables; then, mapping the data to a load at a specific future time point through a neural network prediction algorithm, obtaining a plurality of networks according to the mapping, and calculating a plurality of prediction values by each network; and finally, calculating a final prediction value through an aggregation estimation method. According to the method, the random distributed embedded framework and the BP neural network are combined, and the distribution information is created by utilizing the interaction between the high-dimensional variables to replace a time sequence lacking due to less training data, so that the amount of training data required by prediction is effectively reduced, the prediction precision is remarkably improved, and the stability is enhanced.

Description

technical field [0001] The invention relates to the technical field of electric load forecasting, and relates to an ultra-short-term electric load forecasting method. Background technique [0002] The ultra-short-term load forecasting of the power system is of great significance to the safe and economical operation of the distribution network and the planning of the distribution network. In the prior art, various forecasting methods have been proposed for ultra-short-term load forecasting, among which BP neural network has been widely used in load forecasting. However, the BP neural network also has its limitations: the prediction based on the BP neural network requires a large amount of historical data for training. When the training data is small, the prediction accuracy will drop significantly; when the network input dimension is large, the complexity of the network becomes exponential increases, the prediction accuracy will also decrease. Therefore, how to reduce the a...

AI Technical Summary

Problems solved by technology

However, the BP neural network also has its limitations: the prediction based on the BP neural network requires a large amount of historical data for training. When the training data is small, the prediction accuracy will drop significantly; when the network input dimension is large, the complexity of the network becomes exponential increases, the prediction accuracy will also decrease

So far, there have been no literature reports and practical applications on ultra-short-term power load forecasting methods that integrate random distributed embedding frameworks and BP neural networks.

Images