Distribution network material demand multiple regression prediction technology based on correlation factor analysis

Abstract

The invention discloses a distribution network material demand multiple regression prediction technology based on correlation factor analysis. Under the background of rapid development of economy and continuous acceleration of urbanization pace, an electric power distribution network project serves as a core part of infrastructure construction, and the importance of demand prediction of the electric power distribution network project is increasingly prominent. The demand of power distribution network materials is influenced by various factors, such as economic growth, population change, industrial structure, technical progress and the like, and the related historical data accumulation sample size is small. If only the historical time sequence data of the material quantity is predicted, on one hand, the prediction effect is limited by the existing small data sample size, and on the other hand, the prediction result is not accurate enough due to neglecting the influence of other important influence factors. According to the method, four related factors of the distribution network are comprehensively considered based on correlation analysis, the four related factors comprise the number of projects, the issued plan amount, the power supply amount and the GDP, all the influence factors are combined, and the distribution network materials are predicted through multiple regression. According to the invention, auxiliary support can be carried out on material purchasing related work of a material department, the purchasing cost and the inventory cost are saved to a great extent, and the enterprise competitiveness is improved.

Description

Technical Field

[0001] The present invention relates to a power grid data processing technology, in particular to a distribution network material demand multivariate regression prediction technology based on correlation factor analysis. Background Art

[0002] Reliable power supply is related to the national economy and people's livelihood. With the development of my country's economy, the scale of my country's power generation and power consumption has always been huge, and will continue to grow in the future. These put forward higher requirements for the rapid and high-quality construction of power projects. Compared with the main grid project, the distribution network project is an important infrastructure for end users and people's livelihood. Most of the power distribution network projects are short-term and fast projects. Usually, the construction and renovation period is short, and the supply of equipment and materials is scattered, fragmented, low in certainty and high in timeliness. As a result, the distribution network materials of the provincial material company are often of various types, high supply response speed, high demand uncertainty, and large differences in demand characteristics.

[0003] In the existing technology, traditional material management mainly carries out material procurement business based on projects such as infrastructure, technical transformation, and business expansion. This model has achieved relatively good results for the supply of main grid materials, but for the distribution network material management business, facing the current situation of short project cycle, strong suddenness, and high supply requirements, it is difficult to meet the requirements of efficient management of distribution network materials by only collecting and analyzing data from the entire process of material supply. It is necessary to strengthen the preparation and forecast analysis of power distribution network material demand plans. At present, most scholars at home and abroad mainly use forecasting models and technologies to carry out forecasts such as material demand. The relevant models and technologies mainly include time series models, regression analysis models, intelligent models and algorithms, etc.

[0004] The shortcomings of the prior art are mainly reflected in the following aspects: First, the complexity and uncertainty of material demand. Due to the strong professionalism, variety, specifications, and large quantity differences of power materials, the regularity of material consumption is not significant, and there are typical seasonal fluctuations, which makes demand forecasting difficult. Second, there is a lack of combined forecasting of continuous and intermittent demand. Due to the weak correlation between demand characteristics, it is impossible to make clear classifications based on demand characteristics to select a forecasting model. Third, there is a deviation between the plan and actual demand. In the specific implementation process, there is a large deviation between the planned submission amount and the actual demand. In the long run, it will seriously affect the accuracy of the annual distribution network material plan. The multivariate regression prediction technology for distribution network material demand based on correlation factor analysis provided by the present invention is proposed precisely to address these shortcomings of the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a multivariate regression prediction technology for distribution network material demand based on correlation factor analysis to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a multivariate regression prediction technology for distribution network material demand based on correlation factor analysis, which predicts distribution network materials through a data import module, a data cleaning module, a correlation analysis module, a regression analysis module and a data prediction module;

[0007] The data import module converts the format of the data extracted from the source end and imports it;

[0008] Data cleaning module, which pre-processes data, including data cleaning, data integration, data transformation, data standardization, and abnormal data deletion;

[0009] Correlation analysis module, calculates the Pearson correlation coefficient of each influencing factor, and combines the influencing factors based on the results;

[0010] Regression analysis module, establishes various multivariate regression equations, tests the results and determines the optimal regression equation;

[0011] Data prediction module, imports prediction data for training.

[0012] In the above technical solution, the multivariate regression prediction technology for distribution network material demand based on correlation factor analysis provided by the present invention has the following beneficial effects:

[0013] 1. Improve comprehensiveness: Multiple regression forecasting technology can consider the impact of multiple independent variables on the dependent variable and explain the changes of the dependent variable more comprehensively. In the distribution network material demand forecast, multiple influencing factors can be considered at the same time, such as seasonal changes, market trends, historical data, etc., to provide more accurate forecast results.

[0014] 2. Improve forecast accuracy: The regression coefficient is used to quantify the influence of each independent variable, providing the ability to explain and predict the dependent variable. This helps material managers understand which factors have the greatest impact on material demand, so as to make more targeted material allocation and management decisions. In addition, this method makes a comprehensive judgment on the results obtained by different forecasting methods, integrates and balances the relative error rates between various models, reduces the errors that may be caused by a single model, and improves the accuracy of the forecast.

[0015] 3. Provide forecasting and decision support: Use multivariate linear regression models for forecasting and decision support, such as predicting sales, assessing market demand, etc. In distribution network material management, this means that future material demand can be predicted, preparations can be made in advance, and the risk of material shortages or surpluses can be reduced.

[0016] 4. Realize intelligent prediction: Realize intelligent prediction of distribution network material demand, optimize material prediction methods, select the optimal prediction algorithm, and improve the reliability of distribution network material demand prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 A schematic diagram of the system operation flow provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0020] Embodiment 1

[0021] See also Figure 1 , the embodiment of the present invention provides a multivariate regression prediction technical solution for distribution network material demand based on correlation factor analysis: through the correlation analysis and calculation of various influencing factors of distribution network material prediction and distribution network material prediction, at the same time, with the help of data import module, data cleaning module, correlation analysis module, regression analysis module, data prediction module, distribution network materials are predicted;

[0022] The data import module converts the format of the data extracted from the source end and imports it;

[0023] Data cleaning module, which pre-processes data, including data cleaning, data integration, data transformation, data standardization, and abnormal data deletion;

[0024] Correlation analysis module, calculates the Pearson correlation coefficient of each influencing factor, and combines the influencing factors based on the results;

[0025] Regression analysis module, establishes various multivariate regression equations, tests the results and determines the optimal regression equation;

[0026] Data prediction module, imports prediction data for training.

[0027] In another embodiment provided by the present invention, the association analysis module includes the following steps:

[0028] S1, calculate the correlation coefficient: In Pearson correlation analysis, for two variables x and y, several sets of data can be obtained through experiments, recorded as (x i ,y i )(i=1,2,...,n), the Pearson correlation coefficient is defined as the quotient of the covariance and standard deviation of the estimated sample, then the mathematical expression of the correlation coefficient is:

[0029]

[0030] Among them, x and y are the means of n test values, r is the Pearson correlation coefficient, x i and i are the data points of the two variables, and x and y are the means of the two variables.

[0031] S2, significance test: perform P value test;

[0032] S3, combination of influencing factors: Combine the influencing factors according to the degree of correlation.

[0033] In another embodiment provided by the present invention, the regression analysis module includes the following steps:

[0034] S1, establish linear regression equation: determine the multiple regression equation of material demand forecasting model;

[0035] The regression equation is in the form:

[0036] y=a0+a1x1+......+a k x k +ε

[0037] Among them, a0 is the intercept of the regression equation, a1...a k is the regression coefficient, ε is the random error term, x is the explanatory variable, and y is the explained variable.

[0038] S2, goodness of fit test: Goodness of fit test is an important step to test the fit effect of the constructed regression model on the sample data. The determination coefficient R is usually used. 2 As an evaluation indicator for goodness of fit test;

[0039] Coefficient R 2 The calculation formula is:

[0040]

[0041] Where: SSE is the error sum of squares, SST is the total deviation sum of squares, and SSR is the residual sum of squares.

[0042] S3, significance test: F test and t test;

[0043] S4, prediction accuracy test: calculate the relative error rate of each multivariate regression equation and compare them;

[0044] S5, determine the optimal regression equation.

[0045] In yet another embodiment provided by the present invention, the data prediction module;

[0046] Using the distribution network material collection data from the data import module and the optimal regression equation determined by the regression analysis module, select material categories to predict distribution network materials.

[0047] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. Based on the multivariate regression prediction technology of distribution network material demand based on correlation factor analysis, distribution network materials are predicted through data import module, data cleaning module, correlation analysis module, regression analysis module and data prediction module; The data import module converts the format of the data extracted from the source end and imports it; Data cleaning module, which pre-processes data, including data cleaning, data integration, data transformation, data standardization, and abnormal data deletion; Correlation analysis module, calculates the Pearson correlation coefficient of each influencing factor, and combines the influencing factors based on the results; Regression analysis module, establishes various multivariate regression equations, tests the results and determines the optimal regression equation; Data prediction module, imports prediction data for training. In the above technical solution, the multivariate regression prediction technology for distribution network material demand based on correlation factor analysis provided by the present invention has the following beneficial effects:

1. Improve comprehensiveness: Multiple regression forecasting technology can consider the impact of multiple independent variables on the dependent variable and explain the changes of the dependent variable more comprehensively. In the distribution network material demand forecast, multiple influencing factors can be considered at the same time, such as seasonal changes, market trends, historical data, etc., to provide more accurate forecast results.

2. Improve forecast accuracy: The regression coefficient is used to quantify the influence of each independent variable, providing the ability to explain and predict the dependent variable. This helps material managers understand which factors have the greatest impact on material demand, so as to make more targeted material allocation and management decisions. In addition, this method makes a comprehensive judgment on the results obtained by different forecasting methods, integrates and balances the relative error rates between various models, reduces the errors that may be caused by a single model, and improves the accuracy of the forecast.

3. Provide forecasting and decision support: Use multivariate linear regression models for forecasting and decision support, such as predicting sales, assessing market demand, etc. In distribution network material management, this means that future material demand can be predicted, preparations can be made in advance, and the risk of material shortages or surpluses can be reduced.

4. Realize intelligent prediction: Realize intelligent prediction of distribution network material demand, optimize material prediction methods, select the optimal prediction algorithm, and improve the reliability of distribution network material demand prediction.

Images