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

multi-grid load forecasting method based on BP neural network

A technology of BP neural network and power grid load, applied in the direction of biological neural network model, prediction, neural architecture, etc., can solve the problems of different degrees of accuracy and algorithm efficiency, achieve good generalization and convergence, and improve Effects of Accurate, Precise Load Forecasting

Inactive Publication Date: 2019-02-22
STATE GRID SHAANXI ELECTRIC POWER RES INST +3
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There are many methods of load forecasting, most of which focus on traditional forecasting methods, and there are varying degrees of problems in accuracy and algorithm efficiency

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
  • multi-grid load forecasting method based on BP neural network
  • multi-grid load forecasting method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] The short-term load forecasting method of the multivariate power grid disclosed by the invention uses a BP neural network algorithm to perform sample training.

[0072] In the multiple power grid, electricity consumption is mainly concentrated in industrial and agricultural production, post and telecommunications, municipal transportation, commerce, and electricity consumption for urban and rural residents. Factors affecting the electricity load include temperature changes, weather changes, date types, day time changes, season types, and holiday factors. In load forecasting, factors such as historical load data, temperature, holidays, and weather changes are mainly considered.

[0073] When calculating through the BP neural network, the factors that affect the load forecast are considered, and the input variables are determined as: temperature, historical load value, weather type, holidays and daily time changes.

[0074] In the short-term load forecasting method of th...

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 multi-grid load forecasting method based on BP neural network, which comprises the following steps: calling data from a multi-grid historical database to establish a BP neural network sample input variable data array; Determine the number of hidden layer neurons in BP neural network model; Calculate the output of output layer in BP neural network model; The output error of single sample and the total output error of all samples in BP neural network sample training are calculated. Judge the end condition of sample training; The predicted load value is output by the model after training. The method of the invention is based on a BP neural network model, has good generalization and convergence, and can more accurately meet the actual prediction requirements.

Description

technical field [0001] The invention belongs to the technical field of smart grid dispatching, and in particular relates to a multi-element grid load forecasting method based on BP neural network. Background technique [0002] With the increasing scale of power grid construction, especially the grid-connected operation of multiple power sources such as wind and photovoltaic power sources, the scale and complexity of the power system continue to increase. The optimal control of power systems in various regions plays a key role. With the continuous improvement of power grid informatization, the data collected and stored in the power grid is becoming more and more diverse. Load forecasting based on historical data has become an independent and indispensable part, which is a prerequisite for power system planning. Among them, power load forecasting mainly refers to the forecasting of the power load in the next few hours, one day to several days, which can not only provide guara...

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
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04
CPCG06Q10/04G06Q50/06G06N3/045Y04S10/50
Inventor 吴子豪王若谷程松张燕平王永庆师鹏尚渭萍朱超李明梁苗朱丹玥朱明辉田刚旗白欢王军娥唐露甜李高阳王岳彪李广王辰曦
Owner STATE GRID SHAANXI ELECTRIC POWER RES INST
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