Electricity price prediction method based on empirical mode decomposition and minimum gated memory network quantile regression

Abstract

The invention aims to solve the problems that an existing electricity market electricity price prediction method consumes too long time, more samples cannot be trained to improve the prediction precision and mainly has limitations that research on point prediction, electricity price interval prediction and probability density estimation is less, and more effective information cannot be provided for market participants to make an optimal market strategy. An electricity price prediction method based on empirical mode decomposition and minimum gated memory network quantile regression is established, the electricity price sequence is decomposed into a plurality of modal components by adopting empirical mode decomposition; QR and MGM are combined to form a hybrid model QR-MGM to predict each modal component under different quantiles, and KDE is adopted for a reconstructed prediction result to obtain a probability density function of the electricity price, so that the uncertainty of prediction can be quantified, and the probability density function of the electricity price can also be obtained.

Description

technical field [0001] The invention relates to the field of electricity price prediction methods, in particular to an electricity price prediction method based on empirical mode decomposition and quantile regression of minimum gated memory network. Background technique [0002] In an open electricity market, the price mechanism has an important impact on the fair trade among market participants and the interaction between supply and demand. The volatility and uncertainty of electricity prices inject vitality into the electricity market, but also increase the difficulty of electricity price forecasting. Accurate short-term electricity price forecasting can provide effective decision-making guidance for each participant in the electricity market when formulating the optimal market strategy, improve the matching degree between supply and demand in the electricity market, reduce the electricity cost of customers with electricity demand, and improve the power supply enterprises....

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the current electricity price prediction method in the current electricity market takes too long, more samples cannot be trained to improve the prediction accuracy, and it is mainly limited to point prediction. To solve the problem of providing more effective information for operators to formulate optimal market strategies, a power price forecasting method based on empirical mode decomposition and quantile regression of minimum gated memory network was established.

Images