Day-ahead electricity price prediction method based on EEMD-CNN + SAE-RFR hybrid algorithm

Abstract

The invention discloses a day-ahead electricity price prediction method based on an EEMD-CNN + SAE-RFR hybrid algorithm. The day-ahead electricity price prediction method comprises the steps of: A, combining historical electricity prices and original data of influence factors of the historical electricity prices to form an original feature time sequence matrix of a current prediction day d; B, performing data preprocessing on the original feature time sequence matrix; C, decomposing the preprocessed original feature sequence matrix into a plurality of multi-frequency modal components by using ensemble empirical mode decomposition, and combining the multi-frequency modal components into a plurality of multi-frequency two-dimensional feature matrixes according to high and low combined subsequences of frequencies; D, predicting the two-dimensional feature matrix of each frequency through a deep learning network model based on a convolutional neural network-stacked auto-encoder, and outputting a plurality of multi-frequency prediction time sequence subitems according to the frequency; and E, performing reconstruction fitting on all the prediction time sequence subitems by using a random forest regression algorithm to obtain a final electricity price prediction value. The method has the advantages of high accuracy, high model learning convergence speed and good result stability.

Description

technical field [0001] The invention relates to the technical field of electricity price prediction, in particular to a day-ahead electricity price prediction method based on EEMD-CNN+SAE-RFR hybrid algorithm. Background technique [0002] In recent years, since the introduction of deregulation policies, profit maximization among power market participants such as power generation, transmission and distribution companies has introduced and increased competition in the industry, and has also promoted the improvement of power generation efficiency and consumer benefits. Among them, day-ahead electricity price prediction has become an important research task in market competition. Because day-ahead power price forecasting can be applied to estimation, pricing of derivative power products, and risk management, based on accurate day-ahead power price forecasting, it not only enables power suppliers to formulate bidding policies to increase settlement amount and obtain maximum bene...

AI Technical Summary

Problems solved by technology

[0003] In the modern electricity market, due to seasonal changes, market bidding strategies and multiple external factors, the electricity price often shows a high degree of stochastic nonlinearity, spikes, periodicity, and cross-sectional and serial correlation, which makes high Accurate electricity price forecasting is challenging

The widely studied electricity price prediction models are mainly divided into two categories: linear statistical models and nonlinear machine learning models. The learning algorithm may have its own limitations, such as: low prediction accuracy, slow learning and training convergence, unstable prediction results, etc.

Images