Short-term building load probability density prediction method

Abstract

The invention relates to a short-term building load probability density prediction method, which comprises the following steps of: 1) screening an original exogenous variable by adopting an orthogonalmaximum correlation coefficient by taking a maximum correlation coefficient and minimum redundancy as principles to obtain a selected exogenous variable; 2) for the selected exogenous variable, introducing a binary risk indication variable to improve the accuracy of peak load prediction; 3) constructing a convolution gating quantile regression model, taking the screened exogenous variables and binary risk indication variables as input together, and taking building load prediction values under different quantiles as output for training; and 4) predicting by adopting the trained constructed convolution gating quantile regression model to obtain predicted values under different quantiles, and obtaining a probability density distribution function from the predicted values under the differentquantiles through a fitted kernel function. Compared with the prior art, the method has the advantages of improving the peak time prediction accuracy, improving the prediction precision, fully extracting features and the like.

Description

technical field [0001] The invention relates to the field of big data prediction of building loads, in particular to a short-term building load probability density prediction method based on orthogonal maximum correlation coefficient feature selection and convolution gating neural network. Background technique [0002] Short-term load forecasting (STLF) is crucial for the stability and economic development of modern power systems for regional loads (such as smart homes, microgrids and active distribution networks), the diversity of user characteristics and demands Uncertainty in response makes forecasting more difficult. Inaccurate load forecasting will have an adverse effect on production planning. Power load is affected by factors such as weather, economy, and holidays. If all factors are considered, it will increase computational complexity and affect forecasting. precision. [0003] Short-term building load is the foundation and key of power system economic dispatch, un...

AI Technical Summary

Problems solved by technology

Existing forecasts use all factors as input variables of the forecasting model, which greatly increases the computational complexity, leads to the disaster of dimensionality, and affects the results of building load forecasting. Moreover, most of the current short-term building load forecasting is point load forecasting, and point load forecasting The forecasting elasticity of is not enough, the accuracy is not enough, and it cannot describe the uncertainty of load forecasting with higher permeability

Images