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

Power system short-term load prediction method under a Hadoop framework

A short-term load forecasting, power system technology, applied in forecasting, electrical digital data processing, instruments, etc., to achieve the effect of fast operation efficiency, improved forecasting accuracy, and improved accuracy

Pending Publication Date: 2019-04-12
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is aimed at the problem of improving the accuracy and efficiency of power system short-term load forecasting, and proposes a short-term load forecasting method for power systems under the framework of Hadoop to improve forecasting accuracy and efficiency

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 system short-term load prediction method under a Hadoop framework
  • Power system short-term load prediction method under a Hadoop framework
  • Power system short-term load prediction method under a Hadoop framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Such as figure 1 Shown is the concrete flowchart of the VMD-DBN power system short-term load forecasting method under a kind of Hadoop framework of the present invention, comprises the following steps: Step 1: Utilize the variational mode decomposition method VMD to decompose the original historical load data into different characteristics modal function component; Step 2: Using mutual information theory, select the variable with the highest correlation from the historical load, temperature and date type as the input variable; Step 3: Use the modal function component data samples with different characteristics obtained in Step 1 as The deep belief network DBN prediction model input under the Hadoop framework, at the same time input the randomly generated weights and thresholds of each layer of the deep belief network, and enter the deep belief network under the Hadoop framework to correct, iterate, and optimize the weights and thresholds of the current sample. The be...

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 power system short-term load prediction method under a Hadoop framework. The method comprises the following steps: decomposing original historical load data into modal function components with different characteristics by using a variational mode decomposition method VMD; selecting a variable with the highest correlation from the historical load, the temperature and thedate type as an input variable by utilizing a mutual information theory; Using the modal function component data samples with different characteristics as deep belief network prediction model input under a Hadoop framework; meanwhile, randomly generated weight values and threshold values of all layers of the deep belief network are input, a deep belief load prediction model under a Hadoop framework is entered to correct, iterate and optimize the weight values and the threshold values of the current sample, and an optimal weight threshold value is trained and stored; and inputting the input variable of the to-be-predicted day into the prediction model to obtain a prediction result. The method provided by the invention has higher prediction precision and timeliness.

Description

technical field [0001] The invention relates to a power system load forecasting technology, in particular to a power system short-term load forecasting method combined with variational mode decomposition VMD and deep belief network DBN under the Hadoop framework. Background technique [0002] Power system load forecasting refers to starting from the changes in the power system load itself and the influence laws of meteorological, economic and other factors, through the research and analysis of historical data, to explore the internal relationship between load and influencing factors and the law of development and change. Based on the development trend of meteorological, economic and other factors, the power demand is forecasted. Among them, short-term forecasting is a research focus in power system load forecasting, and its forecasting accuracy directly affects the safe, economical and stable operation of the power system and the realization of scientific management and sche...

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): G06F16/182G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 彭道刚邓步青赵慧荣于会群李一琨林栋
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER