Industrial structure based electricity consumption demand prediction method

A technology of electricity demand and industrial structure, which is applied in the field of electric power, can solve the problems that the prediction results cannot reflect the actual change trend of electricity well, and the prediction error is large, so as to achieve the effect of small prediction error and accurate prediction result

Inactive Publication Date: 2016-03-02
STATE GRID SICHUAN ECONOMIC RES INST +1
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing electricity demand forecasting methods do not consider the impact of industrial structure adjustment on electricity demand, which makes the forecast error large, and the forecast results cannot reflect the actual change trend of electricity well.

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
  • Industrial structure based electricity consumption demand prediction method
  • Industrial structure based electricity consumption demand prediction method
  • Industrial structure based electricity consumption demand prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 It is a flowchart of a method for forecasting electricity demand based on industrial structure of the present invention, including:

[0024] Calculation of structural variables in electricity consumption intensity;

[0025] The structural variables are added to the input layer of the neural network, and electricity demand prediction is performed.

[0026] Further, the structural variable is calculated by the following formula:

[0027] e s n = Σ i e i 0 ( y i n - y i 0 ) ,

[0028] Among them, i represents the i-th industry, Indicates the power consumption intensity of the i industry in the nth period, Indicates the ratio of the output va...

Embodiment 2

[0066] In a specific embodiment, a BP neural network is used to predict the electricity demand from 2015 to 2020 by taking a certain provincial power grid as an example.

[0067] Specifically, Table 1 shows the training samples input by the BP neural network, where GDP is the conversion result of comparable prices in 2005. After the learning process, the training and inference results are shown in Table 2. From the prediction results, the maximum relative error of prediction is 3.10%, the minimum relative error is 0.21%, and the average relative error is 1.07%. After the network learning is over, for the training samples, except for the first two training sample points and 2009, the relative errors are relatively large, and the relative errors of the nearest five sample points are all within 1%.

[0068]

structure variable

efficiency variable

GDP (100 million yuan)

2006

40.60

-62.22

8367

2007

49.31

-145.32

9581

...

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 an industrial structure based electricity consumption demand prediction method, comprising the steps: calculating a structure variable in electricity consumption intensity; adding the structure variable to an input layer of a neural network and predicting an electricity consumption demand. According to the industrial structure based electricity consumption demand prediction method, the influence of the structure variable in the industrial structure on the electricity consumption demand is considered during prediction, the structure variable is used as an input of the neural network to predict the electricity consumption demand so that the prediction error is slight and a prediction result is accurate.

Description

technical field [0001] The invention relates to the field of electric power, in particular to a method for forecasting electricity demand based on industrial structure. Background technique [0002] The power industry is the driving force behind national economic and social development, and power consumption indicators are closely related to industrial production, energy consumption, and economic operation. Among the many factors affecting changes in electricity demand, industrial adjustment is a factor that cannot be ignored. Industrial adjustment is an important means to promote economic development, and it is also an important reason for fluctuations in power demand in planned areas. [0003] At present, the overall industrial development of some provinces is in the middle stage of industrialization. At the same time, the overall industrial development of the country has entered the late stage of industrialization. The output value structure of the three industrial struc...

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): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 冯瀚肖先勇张全明任志超陈礼频曹开江陈谦杜新伟王海燕汪伟马瑞光徐浩李锴科许双婷
Owner STATE GRID SICHUAN ECONOMIC RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap