Regulable load prediction method and system for users participating in orderly power utilization

A load forecasting and electricity user technology, which is applied in the field of adjustable load forecasting of users participating in orderly electricity consumption and load forecasting of electricity user regulation and control, can solve the difficulty of differentiated dispatching, the different sensitivity of grid dispatching response, and the difficulty in dispatching effect. Guarantee and other issues to achieve the effect of ensuring reliable power supply and ensuring safe and stable operation

Pending Publication Date: 2022-07-05
STATE GRID HUNAN ELECTRIC POWER +2
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the different power consumption methods of power users, the response sensitivity to grid dispatching is also different. Therefore, it is difficult to use the existing orderly power consumption plan to carry out differentiated dispatching for different users during peak power consumption, and the dispatching effect is also difficult to guarantee.

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
  • Regulable load prediction method and system for users participating in orderly power utilization
  • Regulable load prediction method and system for users participating in orderly power utilization
  • Regulable load prediction method and system for users participating in orderly power utilization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] like figure 1 As shown, the controllable load prediction method for participating in orderly electricity users in this embodiment includes:

[0065] 1) Construct the power characteristic index vector based on user power data and grid load data;

[0066] 2) Input the power characteristic index vector into the pre-trained machine learning model to obtain the corresponding user participation control load.

[0067] The power characteristic index vector constructed in step 1) of this embodiment includes: power consumption fluctuation rate, power consumption peak-to-valley difference, peak-to-average power consumption ratio, staggered peak load difference, weekly rest load difference, weekly load drop rate, maintenance load There are 8 characteristic indicators of difference and maximum utilization hour rate. User power data and grid load data refer to the hourly power data of the user in one month and the hourly load data of the power grid in the province within a month. Th...

Embodiment 2

[0096] This embodiment is basically the same as the first embodiment, and the main difference is: in order to improve the accuracy of the machine learning model in this embodiment, the function expression of the machine learning model in step 2) of this embodiment is:

[0097]

[0098] In the above formula, f(φ(X)) represents the output of the machine learning model, n is the total number of training samples, α i , is a pair of Lagrange multipliers, K(φ(X), φ(X i )) is the kernel function, φ(X) represents the input test group power characteristic index vector, φ(X) i ) represents the input training group i-th power characteristic index vector, and b is the displacement.

[0099] Kernel function K(φ(X), φ(X i )) can select a kernel function that satisfies the MERCER condition as required, for example, as an optional implementation, in this embodiment, the kernel function K(φ(X), φ(X) i )) adopts the radial basis function RBF, and its function expression is:

[0100] ...

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 adjustable load prediction method and system for users participating in orderly power utilization, and the method comprises the steps: constructing an electric quantity characteristic index vector based on the electric quantity data of users and the load data of a power grid, comprising the following eight characteristic indexes: power utilization fluctuation ratio, power utilization peak-valley difference, peak-to-average power utilization ratio, off-peak load difference, weekly rest load difference, weekly load drop rate, maintenance load difference and maximum utilization hour rate; and inputting the electric quantity characteristic index vector into a pre-trained machine learning model to obtain a corresponding user participation regulation and control load. According to the method, deep mining can be carried out on user electric quantity characteristics through machine learning, user adjustable load prediction based on historical electric quantity data is further realized, related business personnel can rapidly compile an orderly power utilization plan, and safe and stable operation of a power grid and reliable power supply are guaranteed.

Description

technical field [0001] The invention belongs to the power user regulation load prediction technology in the field of electric power dispatch, and in particular relates to a controllable load prediction method and system for participating in orderly electricity users. Background technique [0002] With the continuous development of the economy, the growth of power demand has become increasingly significant, and there is still a risk of unbalanced power supply and demand during the peak period of power consumption. Due to the different electricity consumption modes of power users, the response sensitivity to grid dispatching is also different. Therefore, it is difficult to use the existing orderly power consumption plan to perform differentiated dispatching for different users during peak power consumption, and the dispatching effect is difficult to guarantee. In order to improve the scientificity and rationality of the orderly electricity consumption plan, how to dynamically ...

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 Applications(China)
IPC IPC(8): G06Q10/06G06Q50/06G06N20/00
CPCG06Q10/06315G06Q50/06G06N20/00
Inventor 宁志毫王灿王小源周舟
Owner STATE GRID HUNAN ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap