Unlock instant, AI-driven research and patent intelligence for your innovation.

An Optimal Nonparametric Interval Forecasting Method for Electric Power Load

A technology for power load and forecasting methods, which is applied in forecasting, data processing applications, instruments, etc. to achieve the effect of improving computing efficiency

Active Publication Date: 2021-10-08
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the time-varying, non-stationary, asymmetric, and multi-modal characteristics of the probability distribution of electric loads, the parametric assumptions of traditional interval forecasting on the distribution and the symmetry restrictions on the end-point quantile levels lead to a relatively conservative interval width.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Optimal Nonparametric Interval Forecasting Method for Electric Power Load
  • An Optimal Nonparametric Interval Forecasting Method for Electric Power Load
  • An Optimal Nonparametric Interval Forecasting Method for Electric Power Load

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and implementation examples.

[0033] (1) First, the nominal coverage of the given prediction interval is 100(1-β)%; construct the training data set and the test dataset x t is the explanatory variable composed of historical data, y t is the predicted label value of the electric load;

[0034] (2) Randomly given the input weight vector and hidden layer bias of the extreme learning machine, the regression function f(x t , ω α )and The basic form of , where the output layer weight vector ω α and Variables to be optimized for network training;

[0035] (3) Use the quantile regression technique to obtain the quantile estimation of the training set prediction label at the β and (1-β) quantile levels, so as to construct the sub-prediction interval of the interval to be predicted

[0036] (4) Judging the prediction labels of the training set Whether it falls...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an optimal non-parameter interval prediction method of electric load, which belongs to the field of electric load prediction. This method builds a mixed integer programming model based on machine learning, ensures that the interval coverage meets the confidence level through mixed integer constraints, and takes the minimization of the interval width as the training goal, and gets rid of the parametric probability distribution and single analysis of traditional power load interval forecasting. Bit-level restrictions, with stronger adaptability and flexibility. Aiming at this mixed integer programming model, an integer variable reduction method based on quantile estimation is proposed, which effectively reduces the size of the original problem and significantly improves the solution efficiency.

Description

technical field [0001] The invention relates to an optimal non-parameter interval prediction method of electric load, which belongs to the field of electric load prediction. Background technique [0002] With the large-scale access of distributed power, electric vehicles, energy storage and other equipment on the demand side, the power load presents more significant randomness and uncertainty, which brings severe challenges to power system planning, operation control, and market transactions. Accurate and reliable power load probabilistic forecasting can provide important information support for power system decision-making, and has far-reaching significance for ensuring the safe, stable and economical operation of the power system. [0003] Compared with the deterministic forecast with mathematical expectation as the output, the prediction interval can cover the real value of the electric load with a given confidence level, so as to better quantify the uncertainty of the el...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06
CPCG06Q10/04G06Q10/067G06Q50/06
Inventor 万灿赵长飞宋永华曹照静
Owner ZHEJIANG UNIV