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

A load forecasting method and memory and system including the method

A load forecasting and historical load technology, applied in the fields of memory and system, can solve the problems of subjectivity of intelligent forecasting algorithm, system complexity and efficiency, and achieve the effect of simple and intuitive clustering and accurate results.

Active Publication Date: 2021-11-09
广州水沐青华科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the blindness of empirical methods in the prior art, the subjectivity, system complexity and efficiency of intelligent forecasting algorithms, the present invention provides a load forecasting method to solve the above problems

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
  • A load forecasting method and memory and system including the method
  • A load forecasting method and memory and system including the method
  • A load forecasting method and memory and system including the method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The invention provides a load forecasting method. Several major factors that affect the power load are extracted and used as the basis for clustering, and then polynomial fitting is performed on each clustering result to obtain multiple functions, and finally the final prediction function is integrated according to the contribution rate of the clustering. The invention effectively improves the polynomial fitting algorithm, and improves the accuracy of the algorithm while ensuring the simplicity and operability of the prediction algorithm. Below, in conjunction with accompanying drawing and specific embodiment, the present invention is described further:

[0043] The present invention analyzes the data through the principal component analysis method, and obtains that temperature, humidity, and wind speed are important factors affecting power loads, and that in the same climate, the power loads on working days and non-working days are significantly different. Therefore, ...

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 power load forecasting method. The method preliminarily divides the data according to whether it is a holiday or not, and performs secondary division on the results of the preliminary division according to the temperature, humidity and wind speed to obtain a plurality of small classifications; then, for each Multinomial fitting is performed on small categories to obtain multiple fitting functions; finally, the final prediction function is integrated according to each category. The invention effectively improves the polynomial fitting algorithm, and can improve the accuracy of the algorithm while ensuring the simplicity and operability of the prediction algorithm.

Description

technical field [0001] The invention relates to the field of power load forecasting in smart grids, in particular to a load forecasting method and a memory and a system including the method. Background technique [0002] As the basis of power system operation, power load forecasting can guide the configuration of power equipment and the supply of power. The accuracy of the forecast is directly related to the effect of the entire power system. If the forecast result is lower than the actual value, the power demand cannot be met, and there will be a large-scale power outage, which may even cause the system to be paralyzed. If the forecast result is higher than the actual value, configure of electrical equipment will be idle, resulting in a waste of resources. [0003] The traditional method of forecasting medium and long-term power loads adopts empirical methods, such as "dividing pork from top to bottom" or "combining dishes from bottom to top", which is relatively weak in t...

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): G06Q10/04G06K9/62G06Q50/06
CPCG06Q10/04G06Q50/06G06F18/23211G06F18/2415
Inventor 孙立明
Owner 广州水沐青华科技有限公司