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

Load extreme value curve prediction method and system based on fusion model

A technology that combines models and extreme value curves. It is applied in prediction, biological neural network models, character and pattern recognition, etc. It can solve problems such as large predictions and difficulties, and achieve the effect of solving difficult prediction problems.

Inactive Publication Date: 2021-08-20
NARI TECH CO LTD +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For the load data with both stationary time series and non-stationary time series, the existing load extreme value curve prediction methods have great prediction difficulties

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
  • Load extreme value curve prediction method and system based on fusion model
  • Load extreme value curve prediction method and system based on fusion model
  • Load extreme value curve prediction method and system based on fusion model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0037] like figure 1 As shown, a load extreme curve prediction method based on the fusion model includes the following steps:

[0038] Step 1, collect electricity consumption data related to load extreme value prediction;

[0039] Step 2, obtaining the characteristics of the electricity consumption data from the electricity consumption data;

[0040] Step 3. Input the characteristics of electricity consumption data into the pre-trained fusion model to predict the load extreme curve; where the fusion model is formed by the fusion of several XGBoost models, several SLSTM models and several INDRNN models.

[0041] The above method uses a number of very different models to construct a fusion mode...

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 a load extreme value curve prediction method based on a fusion model. The method comprises the following steps: collecting power consumption data related to load extreme value prediction; acquiring power utilization data characteristics from the power utilization data; and inputting the power utilization data characteristics into a pre-trained fusion model, and predicting a load extreme value curve, wherein the fusion model is formed by fusing a plurality of XGBoost models, a plurality of SLSTM models and a plurality of INDRNN models. Meanwhile, the invention discloses a corresponding system. According to the invention, the XGBoost model, the SLSTM model and the INDRNN model are fused for prediction, and the problem that prediction is difficult due to the fact that load data have a stationary time sequence and a non-stationary time sequence is effectively solved.

Description

technical field [0001] The invention relates to a load extremum curve prediction method and system based on a fusion model, belonging to the field of electric power metering. Background technique [0002] The extreme load curve prediction of the station area is to use data mining technology to effectively predict the maximum load of the station area in the next 30 days under the full consideration of the operating characteristics of the power consumption information collection system, capacity increase decision-making, natural conditions and social influence conditions; Value curve prediction is conducive to strengthening the orderly power consumption management, rationally arranging the operation mode of the power grid, improving the status quo of heavy overload management, improving the efficiency and effect of heavy overload equipment management, and providing guarantee for the safe and economical operation of the peak summer power system. It has important practical signi...

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): G06Q10/04G06K9/62G06N3/04G06Q50/06
CPCG06Q10/04G06Q50/06G06N3/045G06F18/25
Inventor 张士成陆春艳陶晓峰吴少雄刘涅煊熊霞邓良柱何旭张罗平
Owner NARI TECH CO LTD