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

A short-term load forecasting method for deep regression forest based on scalable information

A regression forest and deep technology, applied in the field of short-term load forecasting of power systems, can solve the problems of slow DNN training speed and dependent training effect, achieve high load forecasting accuracy, low forecasting error, and improve the effect of short-term load forecasting

Active Publication Date: 2022-07-05
GUANGXI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, DNN still has a slow training speed, and the training effect depends on the artificial setting and adjustment of hyperparameters.

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 short-term load forecasting method for deep regression forest based on scalable information
  • A short-term load forecasting method for deep regression forest based on scalable information
  • A short-term load forecasting method for deep regression forest based on scalable information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] A kind of deep regression forest short-term load prediction method based on scalable information proposed by the present invention is described in detail as follows with reference to the accompanying drawings:

[0027] figure 1 It is the multi-granularity scanning process diagram of the method of the present invention. figure 1 Assume that there is a sample with 200-dimensional feature vector without multi-granularity scanning. The deep regression forest algorithm hopes to solve the binary classification problem. The specific steps of multi-granularity scanning are as follows: First, a 50-dimensional vector window is set to slide on the original feature vector, and the default step size is 1, then 151 50-dimensional vectors can be obtained. Then, the obtained vectors are classified by two different types of forest models, respectively, and 151 2-dimensional classification vectors are obtained. Finally, all the classification vectors are spliced ​​in order to form a 6...

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 provides a deep regression forest short-term load forecasting method based on scalable information. The method uses scalability data such as climate, weather, historical power load, date, large-scale activity, emergency event data and disaster data as input, The proposed deep regression forest model is trained with the short-term power load of the power system as the output. The trained deep regression forest model can obtain high-precision prediction values ​​without manual adjustment of hyperparameters, and the method has good generalization ability. It does not require in-depth understanding of specific objects, but only needs to serialize its data.

Description

technical field [0001] The invention belongs to the field of short-term load forecasting of power systems, and relates to a power load forecasting method based on climate, weather, power load, date and large-scale event information fusion, which is suitable for short-term load forecasting of power systems. Background technique [0002] As one of the important daily work of the power dispatching department, load forecasting can guide the power production department to economically formulate the power generation plan and the operation mode of the power system. Accurate load forecasting is conducive to improving the safety and stability of the power system, reducing power generation costs, and improving the overall efficiency of power companies. For a long time, scholars at home and abroad have carried out a lot of research on the theory and method of load forecasting. Among them, the traditional time series method, as the representative of the classical load forecasting metho...

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): G06Q10/04G06Q50/06G06K9/62
CPCG06Q10/04G06Q50/06G06F18/24323
Inventor 殷林飞
Owner GUANGXI UNIV