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

Deep regression forest short-term load prediction method based on expandable information

A short-term load forecasting and regression forest technology, which is applied in forecasting, instrumentation, character and pattern recognition, etc., can solve the problems of dependent training effect and slow DNN training speed, achieve high load forecasting accuracy, improve short-term load forecasting effect, The effect of low prediction error

Active Publication Date: 2020-01-24
GUANGXI UNIV
View PDF3 Cites 2 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
  • Deep regression forest short-term load prediction method based on expandable information
  • Deep regression forest short-term load prediction method based on expandable information
  • Deep regression forest short-term load prediction method based on expandable information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0027] figure 1 It is a multi-granularity scanning process diagram of the method of the present invention. figure 1 In , it is assumed that there is a sample with 200-dimensional feature vectors that has not been scanned at multiple granularities. The Deep Regression Forest algorithm hopes to solve binary classification problems. The specific steps of multi-granularity scanning are as follows: First, set a 50-dimensional vector window to slide the value on the original feature vector, and the default step size is 1, then 151 50-dimensional vectors can be obtained. Then, the obtained vectors were classified by two different types of forest models, and 151 2-dimensional classification vectors were obtained respectively. Finally, all the classification vectors are co...

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 prediction method based on expandable information. By taking expandable data such as climate, weather, historical power load, date, large-scale activity, emergency data, disaster data and the like as input, and taking short-term power load of a power system as output, the deep regression forest short-term load prediction method trainsa proposed deep regression forest model. The trained deep regression forest model can obtain a high-precision prediction value without manually debugging hyper-parameters, and the deep regression forest short-term load prediction method is good in generalization ability, does not need to be deeply understood by multiple specific objects, and only needs to serialize the 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 the fusion of various information of climate, weather, power load, date and large-scale activities, which is suitable for short-term load forecasting of power systems. Background technique [0002] As one of the important daily tasks of the power dispatching department, load forecasting can guide the power production department to formulate power generation plan and power system operation mode economically. Accurate load forecasting is conducive to improving the safety and stability of the power system, reducing the cost of power generation, and improving the overall efficiency of power companies. For a long time, domestic and foreign scholars have done a lot of research on the theory and method of load forecasting. Among them, the traditional time series method, as a representative of the classical load forecasti...

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