Big data-based mid-and-long term power load prediction method and system

A technology of load and data selection, applied in forecasting, data processing applications, complex mathematical operations, etc., can solve problems such as complexity, difficulty in forecasting, and insufficient research

Pending Publication Date: 2018-04-10
上海积成能源科技有限公司
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among the many factors affecting the grid load, some factors are certain, while others are uncertain, so it can be regarded as a gray system. This method is simple and practical, has high prediction accuracy, and ensures that the sample size and calculation workload do not change It increases with the change of time, but the determination of the model needs to go through a variety of tests to determine whether it is reasonable, which is relatively complicated
[0009] At present, a large number of theoretical studies have been carried out at home and abroad on the load forecasting of the power system. However, for the research on medium and long-term load forecasting, due to its large time span, wide area involved, and the influence of many factors such as the development of the national economy, its forecasting The difficulty is correspondingly greater, and the research on it is relatively insufficient

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
  • Big data-based mid-and-long term power load prediction method and system
  • Big data-based mid-and-long term power load prediction method and system
  • Big data-based mid-and-long term power load prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Step 1. Data selection and arrangement: According to load periodicity analysis theory, similarity analysis theory and correlation analysis of factors affecting load, select historical load data and historical meteorological data, establish month attribute binary parameters, month hour attribute binary parameters, week Attribute binary parameter, week hour attribute binary parameter. Among them, the forecast time unit, hours, 30 minutes or 15 minutes, etc. can be adjusted according to the forecast requirements. It is also possible to increase or decrease the corresponding data attribute parameters according to the load characteristics of the forecasted object.

[0016] Step 2. Perform data sample preprocessing according to the eigenvalue attributes that affect the load selected in step 1, as well as the data training set. The construction form is as follows:

[0017]

[0018] in , representing different data variables, and Indicates the unit of time, usually in h...

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 big data-based mid-and-long term power load prediction method and a system thereof. According to the invention, the mid-and-long term load prediction is divided into the three steps of big data acquisition, model training and execution prediction. The power load mid-and-long term prediction is very important content during the operation of a power market. The power load mid-and-long term prediction has great influence on both the long-term planning of the power system for market regulators, and the formulation of electricity purchasing or electricity selling contractsfor market participants.

Description

technical field [0001] The present invention relates to the technical field of power load forecasting, in particular to a medium and long-term power load forecasting method and system based on big data. Background technique [0002] The medium and long-term forecasting of power load is a very important content in the operation of power market. Whether it is used by market regulators for long-term planning of the power system, it also has a major impact on market participants in the formulation of power purchase or sale contracts. The invention discloses a medium and long-term prediction method for electric load. Forecasting load is roughly divided into three steps, data analysis, model building, and forecast calculation. With the development of the national economy and the improvement of people's living standards, electricity, as a very important energy source, has penetrated into every corner of society, and people have higher and higher requirements for the stability of ...

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): G06Q10/04G06F17/18G06Q50/06
CPCG06F17/18G06Q10/04G06Q50/06
Inventor 胡炳谦顾一峰周浩韩俊
Owner 上海积成能源科技有限公司
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