Short-term load and photovoltaic power prediction method and system, equipment and medium

Abstract

The invention relates to a short-term load and photovoltaic power prediction method and system, equipment and a medium. The method comprises the steps that historical load information and historical photovoltaic power information are acquired; predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep belief network to obtain a first short-term load and photovoltaic power prediction result; predicting the historical load information and the historical photovoltaic power information by using a pre-trained long-short memory network toobtain a second short-term load and photovoltaic power prediction result; and performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result. The system, apparatus, medium include a carrier for performing the method. According to the invention, short-term load and photovoltaic power prediction can be carried out based on the dynamic combination deep learning model, so thatthe prediction precision is improved.

Description

technical field [0001] The invention relates to the technical field of short-term load and photovoltaic power forecasting, in particular to a short-term load and photovoltaic power forecasting method and its system, equipment, and medium. Background technique [0002] Short-term load forecasting is mainly used to forecast the power load in the next few minutes, hours or weeks, and to schedule the start-up and shutdown plans. It is of great significance for the optimal combination of units, economic dispatch, and optimal power flow. basis for the efficient functioning of markets. The generalized short-term load forecasting involves the forecasting of electricity load and the forecasting of photovoltaic power generation output. Conventional short-term load and photovoltaic forecasting models mainly include time series models, and machine learning models such as neural networks or support vector machines. [0003] At present, there are the following problems in short-term load...

AI Technical Summary

Problems solved by technology

[0004] On the one hand, more shallow learning methods are used. The learning ability of shallow learning algorithms is limited, and deep-level features cannot be effectively used in the training process, and the prediction accuracy can easily reach the bottleneck.

On the other hand, existing models often use one algorithm for prediction, and the robustness of a single algorithm is low. If a single algorithm falls into a local minimum during the training process, the corresponding prediction performance of the model is poor.

Images