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

Typical-industry-oriented electric quantity pre-judging method based on economic indexes

An industrial and economical technology, applied in the field of forecasting the power demand of the power system, can solve the problems of lack of external data, lack of change trend forecast, low forecasting accuracy, etc., to simplify the work process, reduce personnel requirements, and simplify and standardize power forecasting mode effect

Pending Publication Date: 2019-10-08
STATE GRID TIANJIN ELECTRIC POWER +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional power demand forecasting is based on pure power information, and the lack of external data correlation analysis leads to the lack of forecasting of trends other than fitting laws, and the forecasting accuracy is not high

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
  • Typical-industry-oriented electric quantity pre-judging method based on economic indexes
  • Typical-industry-oriented electric quantity pre-judging method based on economic indexes
  • Typical-industry-oriented electric quantity pre-judging method based on economic indexes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0034] A method for predicting power consumption based on economic indicators for typical industries, such as figure 1 and figure 2 shown, including the following steps:

[0035] Step 1. Based on the electricity data, installed volume data and economic index data, preprocess the input layer electricity sales influencing factors;

[0036] The concrete steps of described step 1 include:

[0037] (1) Acquisition of electricity data, reported loading data and initialization data of economic indicators;

[0038] (2) if figure 2 As shown, the number of neural nodes in the hidden layer is given according to the empirical formula, and the calculation formula is:

[0039]

[0040] (3) Normalize the initialization data and optimize outlier data:

[0041] The initialization data becomes dimensionless data after normalization, and its calculation fo...

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 relates to a typical-industry-oriented electric quantity pre-judging method based on economic indexes. The typical-industry-oriented electric quantity pre-judging method is technically characterized by comprising the following steps: 1, preprocessing input layer electricity sale influence factors; 2, initializing a network node, and randomly assigning a connection weight value; 3, calculating outputs of the hidden layer and the output layer according to the input data and the connection weight; 4, calculating an error and a local gradient of each unit of the output layer; 5, correcting weights of the output layer and the hidden layer, and reducing errors; 6, judging whether all the samples are learned or not, and if not, continuing to calculate until all the samples are learned; 7, checking errors; and 8, outputting a result if the training error is smaller than a set error. According to the invention, personnel requirements can be reduced, and a working process is simplified and an electric quantity pre-judgment mode is standardized.

Description

technical field [0001] The invention belongs to the technical field of power system demand side management, and relates to a method for predicting demanded electricity in a power system, in particular to a method for predicting electricity based on an economic index for typical industries. Background technique [0002] At present, the maturity of electric power information technology makes the application of electric power big data have broad prospects. There are many types of electric power data and a wide range of data, which runs through the entire power production and consumption process. Power demand forecasting is of great significance to power construction planning, power grid dispatching control, and power market evaluation. Traditional power demand forecasting is based on pure power information. The lack of external data correlation analysis leads to the lack of forecasting of trends other than fitting laws, and the forecasting accuracy is not high. [0003] Moreov...

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): G06Q10/04G06Q10/06G06Q50/06G06N3/04G06N3/08
CPCG06Q10/04G06Q10/06315G06Q50/06G06N3/084G06N3/045
Inventor 贾晓亮张革彭宏王宏伟刘畅班全伦小翔杨钦臣
Owner STATE GRID TIANJIN ELECTRIC POWER