Check patentability & draft patents in minutes with Patsnap Eureka AI!

System model for predicting short-term power load based on gradient boost algorithm

A technology of power load and forecast value, which is applied in the field of forecasting short-term power load based on the gradient boosting algorithm, and can solve problems such as waste, difficulty in maintaining and changing the power system power supply and power balance

Inactive Publication Date: 2020-05-22
上海积成能源科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] As we all know, at present, electric energy cannot be stored in a large amount. In the power system, power generation and power consumption must be balanced, otherwise it will cause a lot of waste; at the same time, due to the time lag of the power system, the power load cannot follow its own The operation mode, the user's power consumption and other variables change, and it is difficult to maintain the power supply and power consumption balance of the power system

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
  • System model for predicting short-term power load based on gradient boost algorithm
  • System model for predicting short-term power load based on gradient boost algorithm
  • System model for predicting short-term power load based on gradient boost algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0007] Step 1. Obtain the historical data of the area by measuring or obtaining historical data, including wind and climate data for more than one year: temperature, humidity, wind speed, and sunshine hours, legal festivals, and historical power loads, among which The time resolution point of historical data is 1 hour, figure 2 is a sample electric load curve.

[0008] Step 2. Data preparation: , Represents the input data used to predict short-term power load, including historical hourly temperature, humidity, wind speed, sunshine, current hour, whether it is a holiday or weekend, the average load of the previous 24 hours, and the average load of the previous week . Indicates the power load, that is, the actual value, Indicates the amount of data. Indicates the actual power load, that is, the actual value, Indicates the amount of data. Represents the loss function, which is used to analyze the effect of the predicted value, where for the predicted value. The ...

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

At present, a large amount of electric energy cannot be stored, so that power generation and power utilization must be balanced in a power system, and otherwise, great waste will be caused. Meanwhile,due to the time lag of the power system, the power load cannot change along with changes of variables such as the operation mode of the power system and electricity consumption of users, the balancebetween power supply and electricity consumption of the power system is difficult to maintain, and therefore accurate prediction of the power load is particularly important. The invention puts forwarda system model for predicting a short-term power load based on a gradient boost algorithm, relates to the technical field of power system operation management, and mainly solves the problem of powerload prediction. According to the method, the future short-term power load is predicted through historical weather data and historical load data by using a gradient boost model, so that the safety andstability of the power system are improved, the power generation cost is reduced, and power supply and power utilization of the power system are balanced.

Description

technical field [0001] The present invention relates to a power system operation management technology, in particular to a method for predicting short-term power load based on a gradient boosting algorithm (Gradient Boosting). Background technique [0002] As we all know, at present, electric energy cannot be stored in a large amount. In the power system, power generation and power consumption must be balanced, otherwise it will cause a lot of waste; at the same time, due to the time lag of the power system, the power load cannot follow its own The operation mode, the user's power consumption and other variables change, and it is difficult to maintain the power supply and power consumption balance of the power system. Therefore, predicting the future load changes of the power system and taking necessary adjustment measures in advance are of great significance for maintaining the balance of the power system, improving the quality of power supply, and promoting social developm...

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): G06Q10/04G06Q10/06G06Q50/06
CPCG06Q10/04G06Q10/067G06Q50/06Y04S10/50Y02A30/00
Inventor 胡炳谦顾一峰周浩韩俊
Owner 上海积成能源科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More