Multivariable model and blind number theory-based spatial load prediction method

Abstract

The invention discloses a multivariable model and blind number theory-based spatial load prediction method. The method is characterized by comprising the steps of performing correlation analysis on total power loads based on numerous factors influencing changes of the total power loads, and determining main factors influencing the changes of the total power loads in the factors; by applying a multivariable analysis method, building a multivariable prediction model for predicting the total power loads by taking the main factors influencing the changes of the total power loads as input variables; establishing an index system for assessing development states of the main factors influencing the changes of the total power loads, calculating target annual values of the main factors influencing the changes of the total power loads, and predicting the total power loads by adopting the multivariable prediction model; and calculating target annual classified power load values by utilizing totalpower load prediction results, establishing a power geographic information system comprising land use information of to-be-predicted areas, and calculating out classified power load density, thereby obtaining power load values of power supply communities.

Description

[0001] The invention relates to the field of space load forecasting in urban distribution network planning, and is a space load forecasting method based on multivariate models and blind number theory. Background technique [0002] Spatial load forecasting (SLF) not only predicts the size of future load, but also predicts the location of future load growth. It refers to starting from the known power system, economy, society, weather, etc., through the analysis and research of historical data, to explore the internal relationship between things and the law of development and change, and to make pre-estimates and speculations on the load development. Therefore, space load forecasting is an extremely important research topic in the field of urban network planning. [0003] Spatial load forecasting methods are mainly divided into four categories: multivariate method, trend method, land use simulation method, and load density index method (classification and zoning method). It is di...

AI Technical Summary

Problems solved by technology

[0003] Spatial load forecasting methods are mainly divided into four categories: multivariate method, trend method, land use simulation method, and load density index method (classification and zoning method). It is difficult to fully grasp the law of load development; the land use simulation method is mainly suitable for situations where the land use planning is relatively uncertain. Due to the gradual standardization of urban planning in my country, the nature of future urban land use has basically been clarified, so the land use simulation method in domestic urban network planning fewer applications

[0004] In the prior art, when using multivariate forecasting models for space load forecasting, traditional methods such as linear regression, exponential smoothing, and gray theory are generally used to determine the target annual value of each variable, which is difficult to meet the accuracy requirements in practical applications.

Space load prediction based on blind number theory generally has the problem of insufficient consideration of load influencing factors, and the determination of the reliability of the value interval is highly subjective, and the data of evaluation indicators related to historical load influencing factors are not fully excavated. , its prediction accuracy is low

Images