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

Power grid load prediction method

A forecasting method and grid load technology, applied in the field of electrical engineering, can solve problems such as error forecasting results and difficulty in providing

Pending Publication Date: 2020-09-22
STATE GRID HEBEI ELECTRIC POWER CO LTD +1
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, load forecasting in a geographically fixed subregion extracts the historical weather data and current weather data or forecast weather data to predict the load of the subregion. The location is uniquely bound, and when the partition area changes dynamically, it is difficult to provide an error-stable prediction result

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
  • Power grid load prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as figure 1 As shown, the present embodiment is a grid load forecasting method, comprising steps:

[0026] S100, establishing a relationship model between grid load and electricity price in a region.

[0027] S200. Obtain an electricity price sequence in the area.

[0028] S300. Substituting the power price sequence according to the relational model, and solving to obtain a grid load sequence in the region.

[0029] The relationship model of the present embodiment includes a PSO-based tracking system for multiple power price sequences and grid load sequences, which includes a PSO-based tracking module, a PSO-based discovery module and a PSO-based profile module; the PSO-based tracking module On the basis of using the prior state of an existing power price sequence, the initial state of the relationship matrix in the current sequence is obtained; the PSO-based discovery module discovers new power price sequences in multiple power price sequences through the partic...

Embodiment 2

[0043] This embodiment This embodiment is a grid load forecasting method, comprising steps:

[0044] S100, establishing a relationship model between grid load and electricity price in a region.

[0045] S200. Obtain an electricity price sequence in the area.

[0046] S300. Substituting the power price sequence according to the relational model, and solving to obtain a grid load sequence in the region.

[0047] The relationship model in this embodiment includes a prediction method F, which can be BP neural network method (BPNN), support vector machine method (SVM), wavelet transform and deep belief network method (WT+DBN), wavelet transform and long short-term memory One of network method (WT+LSTM), wavelet decomposition and support vector machine method (WD+SVM) or point prediction algorithm based on wavelet decomposition and convolutional neural network (WD+CNN), or an improved method including related steps.

[0048] The algorithm parameters in the prediction method F of t...

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 power grid load prediction method, and the method is used for predicting the conformance of a designated area of a dynamic power grid, and comprises the following steps: S100,establishing a relation model between the power grid load and the power price of one area; S200, obtaining an electric power price sequence in the region; S300, substituting the relation model into the power price sequence, and performing solving to obtain a power grid load sequence of the region. According to the invention, the electric power price of a subarea is sorted and collected, and a dynamic relation model about the electric power price and the power grid load based on machine learning is established, so the power grid load sequence of the subarea is obtained based on the relation model after the electric power price sequence is obtained.

Description

technical field [0001] The invention relates to the technical field of electrical engineering, and in particular designs a load forecasting method for a power grid under dynamic partitioning. Background technique [0002] Load forecasting is the key to affecting power grid dispatching and power balance. Accurate load forecasting is of great significance for optimizing the arrangement of power units, reducing the reserve capacity of units and trading in the power market. In the prior art, load forecasting in a geographically fixed subregion extracts the historical weather data and current weather data or forecast weather data to predict the load of the subregion. The location is uniquely bound. When the partition area changes dynamically, it is difficult to provide an error-stable prediction result. [0003] Reinforcement Learning (Reinforcement Learning, RL), also known as Reinforcement Learning, Evaluation Learning or Enhanced Learning, is one of the paradigms and methodol...

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): H02J3/00G06Q10/04G06N3/04G06N3/00
CPCH02J3/003G06N3/006G06Q10/04H02J2203/20G06N3/045Y04S10/50
Inventor 郭磊张伟周芳熠曹洋
Owner STATE GRID HEBEI ELECTRIC POWER CO LTD