Monthly power demand prediction method based on VMD-ANFIS-ARIMA

A technology for power demand and forecasting methods, applied in forecasting, neural learning methods, data processing applications, etc., can solve problems such as destroying the integrity of power demand data time series, to overcome uncertainty and volatility, reduce noise, improve The effect of prediction accuracy

CN112991088APending Publication Date: 2021-06-18STATE GRID ZHEJIANG ELECTRIC POWER +1
0 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-06-18

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a monthly power demand prediction method based on VMD-ANFIS-ARIMA, which solves the defects in the prior art, and comprises the following steps: 1, obtaining monthly power consumption sequence data, and determining the number of VMFs of VMD components; 2, taking the screened influence factors as independent variables, taking trend terms in the VMF as dependent variables, and using an ANFIS model to perform prediction; 3, carrying out sequence stability test on the VMF except the trend term, and determining the order of AR and MA according to the correlation coefficient and the partial autocorrelation coefficient of the VMF; 4, using an ARIMA model to carry out time sequence prediction on the VMFs except the trend term; and 5, performing linear reconstruction on each VMD component prediction result to obtain a final power consumption demand prediction result.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of power data analysis, in particular to a monthly power demand forecasting method based on VMD-ANFIS-AR IMA. Background technique

[0002] The power industry is an important energy pillar for social and economic take-off, advanced technology, and stable and convenient life. With the development of society and the continuous improvement of people's living standards, the demand for electric energy continues to increase. Good planning of future power grid construction and power production is an important guarantee for the continuous and rapid development of social and economic activities and the quality of life of residents. Power demand forecasting has always been an important topic in power systems, and it has important application values ​​in economic power generation, system security, management and planning. Therefore, it is extremely important for the planning and development of the power grid to use s...

Examples

Embodiment

[0058] A monthly electricity demand forecasting method based on VMD-ANFIS-ARIMA, such as figure 1 shown, including the following steps:

[0059] Step 1. Obtain monthly electricity consumption sequence data and determine the number of VMF components of VMD;

[0060] Step 2, using the screened influencing factors as independent variables and the trend items in VMF as dependent variables, use the ANFIS model to predict;

[0061] Step 3: Carry out sequence stationarity test on VMF other than the trend item, and determine the order of AR and MA according to its correlation coefficient and its partial autocorrelation coefficient;

[0062] Step 4, use the ARIMA model to perform time series forecasting of VMFs other than trend items;

[0063] Step 5, performing linear reconstruction on each VMD component prediction result to obtain the final power consumption demand prediction result.

[0064] Variational Mode Decomposition (Variational Mode Decomposition, VMD) is an adaptive, comp...