Quantile probabilistic short-term power load prediction integration method

Abstract

The invention relates to a quantile probabilistic short-term power load prediction integration method, and belongs to the technical field of power system analysis. The method comprises the steps of: dividing historical load data into two parts, wherein the first part is used for training a single quantile probabilistic prediction model; and the second part is used for determining the weights of multiple prediction methods, so that load prediction is integrated; performing bootstrap sampling on the first part of data, so that multiple new training data sets are obtained; for each training dataset, training three regression models including a neural network quantile regression model, a random forest quantile regression model and a gradual gradient regression tree quantile regression model;and, establishing an optimization model by taking the quantile loss minimization as a target function on the second part of data set, and determining the weights of all kinds of quantile regression models, so that a quantile probabilistic integration load prediction model is finally obtained. By means of the method in the invention, on the basis of all kinds of single prediction models, the probabilistic load prediction precision is further improved; and the running cost of the power system is easily reduced.

Description

technical field [0001] The invention relates to a quantile probabilistic short-term power load forecasting integration method, which belongs to the technical field of power system analysis. Background technique [0002] Load forecasting is the basis of power system planning and operation. High-precision load forecasting can assist the power system to make better decisions, thereby effectively reducing the corresponding planning and operating costs. Traditional point forecasting can only provide an estimate of future load, but cannot describe the uncertainty of future load. However, in recent years, with the continuous growth of distributed renewable energy and the access of energy storage and electric vehicles, the power load has shown stronger uncertainty. So more and more scholars carry out the research of probabilistic load forecasting. Probabilistic load forecasting can represent the uncertainty of the load to be forecasted in the form of confidence intervals, probabi...

AI Technical Summary

Problems solved by technology

In the context of increasing load uncertainty due to load diversification, probabilistic power load forecasting models have been proposed more and more. However, in the field of power load forecasting, there is no related research on the integration of quantile probability forecasting. Research

Images