Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Cluster load prediction method and device and storage medium

A technology of load forecasting and clustering, which is applied in the electric power field, can solve problems such as roughly ignoring details in forecasting and affecting the refinement of cluster loads, and achieve the effects of improving forecasting results, fast and accurate judgments, and fast updates

Pending Publication Date: 2020-05-22
ZTE CORP
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional research is to analyze and forecast from the overall load and external data, but there is a problem that the forecast roughly ignores the details, which affects the refinement of the cluster load forecast

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
  • Cluster load prediction method and device and storage medium
  • Cluster load prediction method and device and storage medium
  • Cluster load prediction method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0134] The distributed power consumption data is the load of 873 households in a certain area from June to August (collection interval every 5 minutes), the external data is meteorological data (collection interval of 1 hour) and holiday information, and the forecast target is based on June and July Based on the actual data, the training prediction model predicts the daily power consumption of the cluster load formed by 873 households every day in August.

[0135] 1. Data preprocessing

[0136] 1) Convert the electricity consumption data of a single user to find the daily electricity consumption of each user;

[0137] 2) Smoothing the abnormal value of electricity consumption, the formula is:

[0138]

[0139] In the above formula, the abnormal value is the nth day; L n is the power consumption on the nth day; m is the range of days for average smoothing, which can be set as a positive integer according to the usage requirements; L i is the electricity consumption on the...

example 2

[0153] The distributed power consumption data is the electricity consumption of some provinces, municipalities and autonomous regions (6) in the country from 2004 to 2015, and the external data is the regional GDP from 2004 to 2015. The data are shown in Table 1 below. The load forecasting problem is based on the distributed power consumption data from 2004 to 2012 and the external data from 2004 to 2015 to predict the national annual electricity consumption from 2013 to 2015.

[0154] Table 1 Electricity Consumption and Gross Production Value

[0155]

[0156]

[0157] 1. Data preprocessing

[0158] In this embodiment, the data source is normal, has been processed, the data is authentic and reliable, and has high availability, so no preprocessing is required in this embodiment.

[0159] 2. Individual load forecasting algorithm training

[0160] This embodiment belongs to long-term period load forecasting, and the data sample is small, so the data relationship between ...

example 3

[0168] The distributed power consumption data is the electricity load curve (5-minute precision) of each commercial district in a certain city, and the external data is the flow of public transportation (bus, subway, taxi) within the coverage of each commercial district (1-hour precision) and the data of each commercial district Location weather information (temperature, rainfall, 1 hour accuracy). The cluster load forecasting problem is to predict the electricity load curve of the city's commercial district based on the external data of the next day through the training of historical data.

[0169] 1. Data preprocessing

[0170] 1. According to the electricity consumption load curve required for the forecasting problem, the time scale of electricity consumption data and external data needs to be adjusted to the same level. Extend the external data, and average the data with 1-hour accuracy to one data every 5 minutes.

[0171] 2. In addition, normalize the external data to ...

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 cluster load prediction method and device, and a storage medium. The method comprises the steps of obtaining historical power consumption data of each individual in a samplecluster corresponding to a to-be-predicted cluster and external data of the same period; learning and fitting the historical power consumption data of the individual and the external data of the sameperiod through a machine learning algorithm to form a power consumption load prediction model of the individual; acquiring external data of a to-be-predicted cluster, predicting the overall load of the to-be-predicted cluster through an individual power consumption load prediction model based on the external data of the to-be-predicted cluster, and predicting the overall load of the to-be-predicted cluster in combination with the individual power consumption load prediction model and an error correction model. According to the invention, the refinement degree and the prediction effect of cluster load prediction are improved.

Description

technical field [0001] The present invention relates to the field of electric power technology, in particular to a cluster load forecasting method, device and storage medium based on distributed power consumption data and external information. Background technique [0002] Power system load forecasting is a very important content for power system operation scheduling and power generation planning. Necessary content for grid commercial operation. Traditional research is to analyze and forecast from the overall load and external data, but there is a problem that the forecast roughly ignores the details, which affects the refinement of the cluster load forecast. Contents of the invention [0003] The main purpose of the present invention is to provide a cluster load forecasting method, device and storage medium, aiming at improving the refinement and forecasting effect of cluster load forecasting. [0004] In order to achieve the above object, a cluster load forecasting met...

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): G06Q10/04G06Q50/06G06N3/08
CPCG06Q10/04G06Q50/06G06N3/08
Inventor 黎昱汪建汤奕崔晗
Owner ZTE CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com