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

Short-term power load prediction method, computer equipment and storage medium

A short-term power load and power load technology, applied in the field of power engineering, can solve the problems of inaccurate feature extraction of meteorological factors and low prediction accuracy, and achieve the effect of improving globality and integrity and improving accuracy.

Pending Publication Date: 2022-03-11
STATE GRID ZHEJIANG ELECTRIC POWER CO LTD SHAOXING POWER SUPPLY CO +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the inaccurate feature extraction of meteorological factors and low forecasting accuracy in traditional short-term power load forecasting, the technical problem to be solved by the present invention is to provide a short-term power load forecasting method using KNN and BiLSTM to achieve higher precision forecasting

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
  • Short-term power load prediction method, computer equipment and storage medium
  • Short-term power load prediction method, computer equipment and storage medium
  • Short-term power load prediction method, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as Figure 1 to Figure 10 As shown, a short-term power load forecasting method using KNN and BiLSTM includes the following steps:

[0057] S1: Obtain weather data and power load data as sample data;

[0058] S2: Divide the sample data into training set and test set after cleaning and normalizing;

[0059] S3: Use the KNN algorithm to sort the sample data from large to small and obtain the eigenvalue K;

[0060] S4: Select all the weather factors contained in the first K eigenvalues ​​as input terminals for prediction;

[0061] S5: Input all weather factor data and historical power load data contained in the first K eigenvalues ​​as the training data for this prediction;

[0062] S6: Use BiLSTM to establish a power load forecasting model and adjust BiLSTM hyperparameters;

[0063] S7: Use mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE) and coefficient of determination R^2 to carry out detailed comparative analysis ...

Embodiment 2

[0189] This embodiment provides a computer device, including at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes The short-term power load forecasting method using KNN and BiLSTM described in Embodiment 1.

Embodiment 3

[0191]This embodiment provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the implementation of KNN and BiLSTM described in Embodiment 1 is realized. Short-term electric load forecasting method.

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 short-term power load prediction method, computer equipment and a storage medium. The prediction method comprises the following steps: S1, acquiring weather forecast data and power load data as sample data; s2, cleaning and normalizing the sample data, and dividing the sample data into a training set and a test set; s3, sorting the sample data from large to small by using a KNN algorithm to obtain a feature value K; s4, selecting all weather factors contained in the first K feature values as prediction input ends; s5, inputting all weather factor data and historical power load data contained in the first K feature values as training data of the prediction; s6, establishing a power load prediction model by adopting the BiLSTM and adjusting the hyper-parameters of the BiLSTM; s7, comparing and analyzing the prediction error; and S8, performing comparative analysis to obtain a characteristic value K of an optimal prediction result. According to the invention, the precision of short-term power load prediction is greatly improved.

Description

technical field [0001] The invention relates to electric power engineering technology, in particular to electric load forecasting technology. Background technique [0002] Accurate load forecasting can enable the staff to more reasonably arrange the start and stop of the generators inside the grid, which plays an important role in the safety of the power system, the stability of the grid, and the planning and scheduling of the grid, and has great practical significance. [0003] At present, the commonly used short-term power load methods at home and abroad can be divided into two categories, one is the traditional time series analysis methods, such as time series forecasting, exponential smoothing analysis method, multiple linear regression method, etc. This type of method has high requirements on the timing of data, but the nonlinear fitting ability is not strong. With the development of smart grid and the explosive growth of power data, the accuracy of the results predicte...

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): G06F30/27G06N3/04G06N3/08G06Q10/04G06Q50/06H02J3/00
CPCG06F30/27H02J3/003G06N3/084G06Q10/04G06Q50/06G06N3/044Y02E40/70Y02A30/00Y04S10/50
Inventor 张锋明俞键朱峰钱钢张心心孙滢涛何智频谢栋徐恩冉进文叶淑英陈水标周进李熙娟许永远吴洋陈坊梅青赵天剑
Owner STATE GRID ZHEJIANG ELECTRIC POWER CO LTD SHAOXING POWER SUPPLY CO
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