A Method for Measuring the Conduction Relationship of the Upstream and Downstream Industrial Chains Based on Power Data

Abstract

The present invention discloses a method for measuring the conduction relationship of the upstream and downstream industrial chains based on power data. The conduction relationship measurement method is as follows: model design; selecting indicators; performing frequency correlation analysis; performing cross-lag analysis. The model design adopts a cross-spectrum model based on the fluctuation relationship between two sequences. The frequency correlation analysis also includes normalizing the cross-amplitude spectrum to obtain a coherence spectrum. The in the cross-spectrum density function is the phase spectrum. The advantages of the present invention are as follows: The present invention uses the cross-spectrum method to analyze the full-cycle fluctuation process of the sequence, which can better present the structural relationship of the sequence periodic fluctuation as a whole. By performing threshold processing on the indicators, the influence of the indicator dimension, indicator extreme value, and indicator fluctuation can be eliminated. By normalizing the cross-amplitude, the influence of the magnitude of the sequence itself under investigation on the cross-amplitude spectrum can be eliminated, ensuring the accuracy and effectiveness of data analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial chain conduction relationships, and specifically refers to a method for measuring the upstream and downstream industrial chain conduction relationships based on power data. Background Art

[0002] The development status of industries directly determines the development speed and quality of the national economy. At the same time, there are direct or indirect connections among industries. The growth or decline of a certain industry has a direct impact on related industries and is transmitted to other industries through related industries, thereby affecting the entire national economy. This kind of industrial transmission is completed through the industrial chain.

[0003] As an important part of the national economy, industries play a decisive role in economic growth. The industries in the national economy influence and interact with each other, forming intricate industrial chain links and networks that cover the entire national economy and form a unique national economic structure. Starting from analyzing the form, composition, and transmission mechanism of the industrial chain, analyzing the impact of each industry in the national economy on economic growth, and thus studying industrial policies and macroeconomic policies to maintain stable economic growth. Summary of the Invention

[0004] The technical problem to be solved by the present invention is the above-mentioned technical problem, and a method for measuring the upstream and downstream industrial chain conduction relationships based on power data with accurate analysis is provided.

[0005] To solve the above technical problem, the technical solution provided by the present invention is: a method for measuring the upstream and downstream industrial chain conduction relationships based on power data, and the conduction relationship measurement method is as follows:

[0006] ①. Model design;

[0007] ②. Select indicators;

[0008] ③. Conduct frequency correlation analysis;

[0009] ④. Conduct cross-lag analysis. The model design adopts a cross-spectrum model based on the fluctuation relationship between two sequences. The cross-spectrum model includes three spectral terms: coherence spectrum, phase spectrum, and period. The indicator selection includes indicator processing, and the indicator processing is thresholding processing. Its calculation formula is as follows:

[0010]

[0011] Where represents the evaluation value of industry electricity consumption; y i represents the monthly electricity consumption of the industry; y 0 represents the threshold of industry electricity consumption;

[0012] The frequency correlation analysis described above uses the cross-spectral density function C xy (ω), and its formula is:

[0013]

[0014] where S xy (ω) is the cross-amplitude spectrum;

[0015] The frequency correlation analysis described above also includes normalizing the cross-amplitude spectrum to obtain the coherence spectrum, and in the cross-spectral density function is the phase spectrum.

[0016] As an improvement, the threshold is set using the spread breakpoint method, and its calculation formula is as follows:

[0017] d = FU + k * DF

[0018] where DF = FU - FL, FU represents the upper quartile of the data, FL represents the lower quartile of the data, and the value range of k is 1.5 to 3.

[0019] As an improvement, the calculation formula of the cross-amplitude spectrum is as follows:

[0020]

[0021] where a xy is the real part and is called the co-spectrum, and b xy is the imaginary part and is called the quadrature spectrum.

[0022] As an improvement, the calculation formula for normalizing the cross-amplitude spectrum is:

[0023]

[0024] where P x (ω) and P y (ω) are the spectral density functions of the time series X t and Y t respectively.

[0025] As an improvement, the calculation formula of the phase spectrum is:

[0026]

[0027] The advantages of the present invention compared with the prior art are as follows: The present invention uses the cross-spectrum method to analyze the full-period fluctuation process of the sequence, which can better present the structural relationship of the sequence periodic fluctuation as a whole. By thresholding the indicators, the influence of the indicator dimension, indicator extreme value, and indicator fluctuation can be eliminated. By standardizing the cross-amplitude, the influence of the magnitude of the sequence itself under investigation on the cross-amplitude spectrum can be eliminated, ensuring the accuracy and effectiveness of data analysis. Detailed implementation mode

[0028] The following further elaborates on the present invention.

[0029] Embodiment

[0030] Taking the ice and snow industry as an example, generally speaking, the ice and snow industry includes upstream and downstream industries such as ice and snow venues, ice and snow site facilities, sports equipment, transportation and tourism, leisure and entertainment, accommodation and catering, residential supporting, commercial complex, ice and snow competitions, training and education, extreme experiences, supporting energy including electricity, water, gas, heat, etc., and sports injury insurance including ice and snow site liability insurance, skiing personal accident insurance, ice and snow site facility property insurance, etc.; narrowly speaking, the ice and snow industry is the upstream and downstream industries directly related to ice and snow sports resources, facilities, and operation organizations. The upstream end includes equipment, equipment, site facility maintenance, etc.; the midstream end includes ice and snow sports clubs, ice and snow sports event organizations, etc.; the downstream end includes ice and snow sports experiences, ice and snow sports training, ice and snow sports-related auxiliary services, sports tourism, event support and service industries, etc.

[0031] Select the electricity consumption evaluation values of the three-level industries in the upstream, midstream, and downstream of the ice and snow industry in the marketing business as the basic indicators. Among them, the decision attribute is the electricity consumption of the downstream industry, and the conditional attribute is the monthly electricity consumption of the upstream industry corresponding to the downstream industry.

[0032] To eliminate the influence of the indicator dimension, indicator extreme value, and indicator fluctuation, combined with the distribution characteristics of specific indicator data, thresholding is performed on the indicators. The specific indicator calculation formula is as follows:

[0033]

[0034] Where represents the electricity consumption evaluation value of the industry; y i represents the monthly electricity consumption of the industry; y 0 represents the electricity consumption threshold of the industry.

[0035] Among them, the threshold setting adopts the spread breakpoint method, and the specific calculation is as follows:

[0036] d = FU + k * DF

[0037] where DF = FU - FL, FU represents the upper quartile of the data, FL represents the lower quartile of the data, and the value range of k is 1.5 to 3.

[0038] For the bivariate stationary time series X t and Y t of the upstream and downstream industries of the ice and snow industry, the cross-spectral density function C xy (ω) is a complex function, which consists of the real part a xy and the imaginary part b xy . a xy is called the co-spectrum, which reflects the correlation between two time series on the in-phase frequency components; b xy is called the quadrature spectrum, which reflects the correlation between two time series on the out-of-phase frequency components. The cross-spectral density function C xy (ω) can be expressed according to the polar coordinates of the complex number as:

[0039]

[0040] where S xy (ω) is the cross-amplitude spectrum, which is equal to the square root of the sum of the squares of the co-spectrum and the quadrature spectrum, that is It reflects the mutual relationship between the frequency components of the two sequences in terms of amplitude.

[0041] To eliminate the influence of the magnitude of the sequence itself under investigation on the cross-amplitude spectrum, the cross-amplitude spectrum can be standardized to obtain:

[0042]

[0043] where P x (ω) and P y (ω) are the spectral density functions of the time series X t and Y t respectively. The cross-amplitude spectrum after standardization is called the coherence spectrum, which reflects the correlation between the periods of the two sequences in the frequency domain. Its value range is [0, 1]. The closer the value is to 1, the more correlated the two sequences are at the frequency ω.

[0044] In the cross-spectral density function, is called the phase spectrum, and its calculation formula is The phase spectrum reflects the phase difference between the periods of the two sequences at each frequency, that is, the leading and lagging relationships between the two sequences in time.

[0045] The above description of the present invention and its embodiments is not restrictive. What is shown is only one of the embodiments of the present invention, and the actual structure is not limited thereto. In general, if those of ordinary skill in the art are inspired by it and design, without creative efforts, structural modes and embodiments similar to the technical solution without departing from the gist of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. A method for measuring the conduction relationship of the upstream and downstream industrial chains based on power data, characterized in that: the method for measuring the conduction relationship is as follows: ①. Model design; ②. Select indicators; ③. Conduct frequency correlation analysis; ④. Conduct cross-lag analysis, the model design adopts a cross-spectrum model based on the fluctuation relationship between two sequences. The cross-spectrum model includes three spectral terms: coherence spectrum, phase spectrum, and period. The indicator selection includes indicator processing, and the indicator processing is thresholding processing. Its calculation formula is as follows: wherein represents the evaluation value of the industrial electricity consumption; y i represents the monthly electricity consumption of the industry; y 0 represents the threshold value of the industrial electricity consumption; The frequency correlation analysis described above uses the cross-spectral density function C xy (ω), and its formula is as follows: Among them, S xy (ω) is the cross amplitude spectrum; The frequency correlation analysis further includes obtaining a coherence spectrum by normalizing the cross amplitude spectrum, where is the phase spectrum; The calculation formula of the cross-amplitude spectrum is as follows: where a xy is the real part called the cospectrum, and b xy is the imaginary part called the quadrature spectrum; The calculation formula for normalizing the cross-amplitude spectrum is: Among them, P x (ω) and P y (ω) are the spectral density functions of the time series X t and Y t respectively.

2. A method for measuring the conduction relationship of the upstream and downstream industrial chains based on power data according to claim 1, characterized in that: the threshold is set by the spread breakpoint method, and its calculation formula is as follows: d = FU + k * DF where DF = FU - FL, FU represents the upper quartile of the data, FL represents the lower quartile of the data, and the value range of k is 1.5 to 3.

3. A method for measuring the conduction relationship of the upstream and downstream industrial chains based on power data according to claim 1, characterized in that: the calculation formula of the phase spectrum is:

Images