An energy-saving and emission-reducing method and system considering carbon asset management of enterprises

Abstract

The present application relates to the technical field of data processing, in particular to a kind of energy-saving emission reduction method and system considering enterprise carbon asset management, collect historical and current month's energy consumption data, carbon emission data and production output data;Correlation coefficient of energy consumption data sequence, carbon emission data sequence and production output data sequence is calculated;The simple prediction value of current month's energy consumption data is obtained by fitting the element value in energy consumption data sequence;Energy carbon emission correlation degree is obtained by combining autocorrelation coefficient and carbon emission data;Yield carbon emission correlation degree is obtained;Carbon emission risk coefficient is obtained according to energy carbon emission correlation degree and yield carbon emission correlation degree;Carbon asset management is realized according to carbon emission risk coefficient combined with early warning threshold value, thereby realizing the energy-saving emission reduction of enterprise carbon asset management, the problem that carbon emission exceeds standard due to carbon emission data monitoring not in time is solved, which is helpful to the energy-saving emission reduction and reasonable operation of enterprise.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to an energy-saving and emission-reduction method and system that takes into account corporate carbon asset management. Background Technology

[0002] Currently, corporate carbon asset management technologies mostly utilize linear regression, ridge regression, and other regression models to fit the impact of various influencing factors on carbon emissions, quantifying the degree of impact of different factors on carbon emissions and carbon assets. Existing carbon asset management energy conservation and emission reduction technologies largely focus on optimizing regression algorithm models, but carbon asset management requires a large amount of accurate data for calculations, such as energy consumption and carbon emissions. However, the collection and recording of carbon asset-related data by most enterprises is incomplete, neglecting the quality of carbon asset data, which affects the reliability and accuracy of carbon asset management results.

[0003] It is necessary to analyze the accurate relationship between a company's energy consumption data, production output data, and carbon asset data in order to achieve energy conservation and emission reduction in corporate carbon asset management and mitigate the management problems caused by inaccurate carbon emission data monitoring. Summary of the Invention

[0004] To address the aforementioned technical problems, the present invention aims to provide an energy-saving and emission-reduction method and system that considers corporate carbon asset management. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of the present invention provide an energy conservation and emission reduction method considering corporate carbon asset management, the method comprising the following steps:

[0006] Collect historical and current month's energy consumption, carbon emission, and production data for enterprises; obtain energy consumption, carbon emission, and production data sequences; obtain the autocorrelation coefficients of the energy consumption, carbon emission, and production data sequences.

[0007] The volatility coefficient of the energy consumption data series is obtained from the autocorrelation coefficient of the energy consumption data series; the volatility coefficients of the carbon emission data series and the production output data series are obtained; a simple forecast value of the energy consumption data for the current month is obtained; the real-time energy consumption correlation degree for the current month is obtained from the volatility coefficient and the simple forecast value; the energy carbon emission correlation degree is obtained from the real-time energy consumption correlation degree for the current month; the production carbon emission correlation degree is obtained; and the carbon emission impact factor is obtained from the energy carbon emission correlation degree and the production carbon emission correlation degree.

[0008] Carbon emission risk coefficients are obtained based on carbon emission impact factors; carbon asset management is achieved based on carbon emission risk coefficients.

[0009] Preferably, the energy consumption data sequence is a sequence composed of historical monthly energy consumption data.

[0010] Preferably, obtaining the fluctuation coefficient of the energy consumption data sequence based on the autocorrelation coefficient of the energy consumption data sequence specifically includes:

[0011] Obtain the calculation result of an exponential function with the natural constant as the base and the autocorrelation coefficient of the energy consumption data series as the exponent; calculate the mean of the absolute values ​​of the differences between all adjacent elements in the energy consumption data series; calculate the product of the calculation result and the mean; and use the product as the fluctuation coefficient of the energy consumption data series.

[0012] Preferably, obtaining a simple predicted value of the energy consumption data for the current month specifically involves:

[0013] The energy consumption data sequence is used as the ordinate and the month is used as the horizontal axis to fit the data, resulting in a fitted curve, which is denoted as the energy consumption fitted curve. The ordinate value of the current month on the energy consumption fitted curve is then used as a simple prediction of the energy consumption data for the current month.

[0014] Preferably, the step of obtaining the real-time energy consumption correlation for the current month based on the fluctuation coefficient and simple prediction value specifically includes:

[0015] The energy consumption data generated up to the current moment in the current month is taken as the actual value of the energy consumption data for the current month; the absolute value of the difference between the simple predicted value and the actual value of the energy consumption data for the current month is calculated; the fluctuation coefficient of the energy consumption data sequence is calculated as the product of the absolute value of the difference; the sum of the product and a preset minimum positive number is used as the denominator, and the ratio of the autocorrelation coefficient of the energy consumption data sequence to the denominator is calculated, and the ratio is used as the real-time energy consumption correlation degree for the current month.

[0016] Preferably, the energy carbon emission correlation degree obtained based on the real-time energy consumption correlation degree of the current month is expressed as follows:

[0017]

[0018] In the formula, For the correlation between energy and carbon emissions, The correlation between real-time energy consumption for the current month. The lengths of the energy consumption data sequence and the carbon emission data sequence, The first in the energy consumption data sequence One value, Let be the mean of all elements in the energy consumption data series. The first in the carbon emission data sequence One value, This represents the mean of all elements in the carbon emission data series. The volatility coefficient represents the energy consumption data series. The fluctuation coefficient represents the carbon emission data series. The DTW distance between the energy consumption data series and the carbon emission data series. It is a preset minimum positive number.

[0019] Preferably, the step of obtaining the carbon emission impact factor based on the correlation between energy carbon emissions and production carbon emissions specifically includes:

[0020] Calculate the ratio of monthly carbon emissions to the number of days in the month; calculate the mean of all the ratios, and record it as the daily average carbon emissions; use the product of energy carbon emissions correlation, production carbon emissions correlation, and daily average carbon emissions as the carbon emissions impact factor.

[0021] Preferably, obtaining the carbon emission risk coefficient based on the carbon emission impact factor specifically includes:

[0022] Calculate the sum of energy consumption data and production output data generated in the current month up to the current moment; calculate the carbon emission impact factor, the total number of days in the current month, and the product of the sum; calculate the ratio of the product to the number of days in the current month up to the current moment; use the ratio as the carbon emission risk coefficient.

[0023] Preferably, the carbon asset management based on the carbon emission risk factor specifically includes:

[0024] A preset warning threshold is set; if the carbon emission risk coefficient is greater than or equal to the warning threshold, the carbon emissions for the month will exceed the standard and production needs to be stopped and adjusted in time; if the carbon emission risk coefficient is less than the warning threshold, the carbon emissions for the month will be normal.

[0025] Secondly, embodiments of the present invention also provide an energy-saving and emission-reduction system that takes into account corporate carbon asset management, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0026] The embodiments of the present invention have at least the following beneficial effects:

[0027] This invention comprehensively analyzes energy consumption data and production output data closely related to corporate carbon emission data to obtain a carbon emission risk coefficient. The carbon emission risk coefficient is then used to achieve carbon asset management, thereby achieving the goal of energy conservation and emission reduction. This not only saves energy but also improves the cost-effectiveness of enterprises, making them more conducive to sustainable development.

[0028] To avoid carbon emission exceedances due to untimely monitoring of carbon emission data, this invention collects historical and current month energy consumption data, carbon emission data, and production output data; calculates the autocorrelation coefficients of the energy consumption data series, carbon emission data series, and production output data series; obtains a simple prediction value of the current month's energy consumption data by fitting the element values ​​in the energy consumption data series; obtains the real-time energy consumption correlation degree for the current month by combining the autocorrelation coefficients; obtains the energy-carbon emission correlation degree by combining the carbon emission data; obtains the production carbon emission correlation degree; obtains the carbon emission risk coefficient based on the energy-carbon emission correlation degree and the production carbon emission correlation degree; and realizes carbon asset management by combining the carbon emission risk coefficient with the early warning threshold, which helps enterprises save energy, reduce emissions, and operate rationally. Attached Figure Description

[0029] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart illustrating the steps of an energy conservation and emission reduction method considering corporate carbon asset management, as provided in one embodiment of the present invention;

[0031] Figure 2 This is a diagram illustrating the specific steps involved in carbon asset management. Detailed Implementation

[0032] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an energy-saving and emission-reduction method and system considering corporate carbon asset management proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0034] The following description, in conjunction with the accompanying drawings, details a specific scheme for an energy-saving and emission-reduction method and system that considers corporate carbon asset management, provided by this invention.

[0035] Please see Figure 1The diagram illustrates a flowchart of an energy conservation and emission reduction method considering corporate carbon asset management, according to an embodiment of the present invention. The method includes the following steps:

[0036] Step S001: Collect historical and current month's energy consumption data, carbon emission data, and production output data for the enterprise.

[0037] Energy consumption, such as electricity and gas, is inevitable in the production and operation of enterprises, which in turn generates carbon emissions. Changes in production output also affect energy consumption and carbon emissions. Therefore, this application collects monthly energy consumption, carbon emission, and production output data for the past two years. The monthly energy consumption data is arranged in ascending order by time as the energy consumption data sequence, denoted as Sequence A; the monthly carbon emission data is arranged in ascending order by time as the carbon emission data sequence, denoted as Sequence B; and the monthly production output data is arranged in ascending order by time as the production output data sequence, denoted as Sequence C. The data in Sequences A, B, and C are normalized using a maximum-minimum normalization algorithm to eliminate the influence of units and dimensions. Implementers may also use other normalization algorithms to normalize the above three sequences; this application does not impose specific restrictions.

[0038] Meanwhile, energy consumption data generated up to the present moment in the current month. and production output data Collect the data.

[0039] Considering that the collected energy consumption, carbon emission, and production data may contain outliers that could affect the accuracy of data analysis, this paper takes the energy consumption data series as an example and uses the Z-score method to obtain outlier values ​​in series A. The Z-score method is a well-known technique, and its specific process will not be elaborated here. If the Z-score of an outlier is greater than twice the mean, it is considered to be larger than other values. The carbon emission and production data for the same month are then compared with historical data. If the carbon emission and production data are also larger than those of other months, the outlier is treated as a normal value. If the carbon emission and production data are smaller than those of other months, and the differences are not significant, the abnormal value is marked as an outlier and removed. The outlier is then filled using the mean-filling method. Similarly, outliers are removed and filled for other data series.

[0040] Step S002: Obtain the carbon emission impact factor by analyzing the correlation between the enterprise's energy consumption data, production output data and carbon emission data.

[0041] Since each data sequence has the same length, its length is denoted as N; that is, the lengths of the energy consumption data sequence, carbon emission data sequence, and production output data sequence are all N. Because historical data generally exhibits certain patterns of change during normal production processes, these patterns may be linear or non-linear. These patterns can be used to predict future data, and the difference between predicted and actual values ​​can help companies make relevant adjustments. To obtain these patterns, taking the energy consumption data sequence as an example, the lag step size of the energy consumption data sequence is calculated as follows: autocorrelation coefficient It should be noted that the value of h can be set by the implementer, and this embodiment does not impose specific restrictions. The autocorrelation coefficient is a well-known technique, and the specific process will not be elaborated further. Autocorrelation coefficient of energy consumption data series. This indicates the energy consumption data series at a lag step size. The degree of autocorrelation is given by a factor of -1 to 1. The larger the absolute value, the stronger the autocorrelation of the energy consumption data series.

[0042] when A value close to 1 indicates a positive correlation between the energy consumption data series and the lag step. In this embodiment... This means that there is a high degree of synchronicity between the increase or decrease of the current observation value and the change of the next observation value, that is, the change of the current observation value can predict the change of the next observation value very well.

[0043] when A value close to -1 indicates a negative correlation in the energy consumption data series over the lag step. This means there is a highly inverse relationship between the increase or decrease of the current observation and the change in the next observation; that is, the trend of the current observation is exactly opposite to the trend of the next observation.

[0044] when When the value is close to 0, it indicates that the energy consumption data series has no obvious correlation in terms of lag step, and the changes between the values ​​are uncorrelated.

[0045] The autocorrelation coefficient of the carbon emission data series is obtained through the above steps. And the autocorrelation coefficient of production output data series Because businesses may experience seasonal fluctuations such as peak and off-peak seasons, energy consumption data also exhibits cyclical fluctuations. When the autocorrelation coefficient is high, the likelihood of cyclical fluctuations in the data is also higher.

[0046] Since the autocorrelation coefficient primarily reflects the linear correlation of a series and is difficult to use to determine nonlinear correlations, energy consumption data is closely related to carbon emission data, production output data, etc. When one type of data fluctuates, the corresponding other characteristic data will also change. To better determine the data changes within the series, the data fluctuation of each characteristic data series is analyzed. Based on the changes in the energy consumption data series, the fluctuation coefficient of the energy consumption data series is calculated, expressed as:

[0047]

[0048] In the formula, The volatility coefficient represents the energy consumption data series. The autocorrelation coefficient of the energy consumption data series. It is an exponential function with base e. This indicates the number of data points contained in the energy consumption data sequence. This represents the first data point in the energy consumption data sequence. A number, This represents the first data point in the energy consumption data sequence. A numerical value. Volatility coefficient. This indicates the numerical fluctuations in energy consumption data within a sequence. Significant changes or instability in energy consumption values ​​are noted. The value will increase, and carbon emissions may exceed the limit, requiring increased vigilance. The higher the autocorrelation coefficient of the energy consumption data series, the higher the possibility of periodic fluctuations in the data, and therefore the higher the volatility coefficient.

[0049] The fluctuation coefficient of the carbon emission data series is obtained through the above method and denoted as . And the volatility coefficient of the production output data series, denoted as .

[0050] To make a simple prediction of the energy consumption data for the current month, the month is used as the horizontal axis and the energy consumption value of each data point in the energy consumption data sequence is used as the vertical axis to obtain each coordinate point. The least squares method is used to fit each coordinate point, and the fitted curve is used as the energy consumption fitted curve. The specific month number of the current month is substituted into the energy consumption fitted curve. That is, if the current month is month k, then k is substituted into the energy consumption fitted curve, and the resulting energy consumption value is used as the simple prediction value of the energy consumption data for the current month.

[0051] Based on the autocorrelation coefficient and volatility coefficient of the energy consumption data series, combined with a simple forecast of the current month's energy consumption data, the energy consumption data for the current month is analyzed to calculate the real-time energy consumption correlation degree for the current month. The expression is as follows:

[0052]

[0053] In the formula, The correlation between real-time energy consumption for the current month, The autocorrelation coefficient of the energy consumption data series. The volatility coefficient of the energy consumption data series. This is a simple forecast of energy consumption for the current month. This represents the energy consumption data generated up to the current moment in the current month, and is recorded as the actual value of the energy consumption data for the current month. The value is a preset, extremely small positive number, used to avoid a denominator of 0. In this embodiment, the value is... The value is set to 0.001. In other embodiments of this application, the implementer may set the value according to the actual situation. The higher the autocorrelation coefficient of the energy consumption data series, the greater the correlation between the energy consumption data of historical months and the energy consumption data of the current month, and the greater the correlation of real-time energy consumption. The lower the fluctuation coefficient of the energy consumption data series, the more stable and regular the distribution of the energy consumption data series, and the easier it is to predict the energy consumption data of the current month through the energy consumption data of historical months, and the greater the correlation of real-time energy consumption of the current month. This represents the difference between the predicted energy consumption value obtained from the fitted energy consumption curve and the actual value. The smaller the difference, the more the energy consumption data conforms to the distribution pattern of the fitted energy consumption curve, and the greater the correlation of real-time energy consumption.

[0054] The correlation between real-time production output and output for the current month is obtained through the above methods. .

[0055] Since a company's energy consumption data, production output data, and carbon emission data are closely related, and the amount of energy consumption and production output indirectly affects the level of carbon emissions, the relationship between energy consumption data, production output data, and carbon emission data is analyzed separately, and the correlation between energy consumption and carbon emissions and the correlation between production output and carbon emissions are calculated. The expressions are as follows:

[0056]

[0057]

[0058] In the formula, For the correlation between energy and carbon emissions, The correlation between real-time energy consumption for the current month, The lengths of the energy consumption data sequence and the carbon emission data sequence, The first in the energy consumption data sequence One value, Let be the mean of all elements in the energy consumption data series. The first in the carbon emission data sequence One value, This represents the mean of all elements in the carbon emission data series. The DTW distance between the energy consumption data series and the carbon emission data series; For the correlation between production and carbon emissions, To determine the correlation between real-time production output and output, For the production output data sequence of the first One value, This represents the mean of all elements in the production output data series. The DTW distance is the distance between the production output data series and the carbon emission data series. This represents the difference in the fluctuation coefficient between carbon emission data series and energy consumption data series; the smaller the difference, the greater the correlation between energy and carbon emissions. This represents the difference between sequences A and B; the smaller the difference, the greater the correlation between energy and carbon emissions. This indicates the cross-correlation between sequences A and B; the stronger the cross-correlation, the greater the degree of association. This indicates the correlation between energy consumption data for the current month and historical months. The larger the value, the greater the correlation between energy and carbon emissions. The correlation between production and carbon emissions follows the same logic, and will not be elaborated further. , All are preset, extremely small positive numbers, and their purpose is to avoid a denominator of 0. In the embodiments of this application, , The values ​​are all set to 0.001. In other embodiments of this application, the implementer may set the values ​​according to the actual situation. , The value of .

[0059] Since carbon emission data is influenced by both energy consumption and production output data, the carbon emission impact factor is calculated by combining the correlation between energy carbon emissions and production carbon emissions. The expression is as follows:

[0060]

[0061] In the formula, As a factor affecting carbon emissions, For the correlation between energy and carbon emissions, For the correlation between production and carbon emissions, The first in the carbon emission data sequence One value, The length of the carbon emission data sequence, The first in the carbon emission data sequence The number of days in the month corresponding to each value. The normalization function used in this application embodiment is the tanh function. Many existing normalization functions exist, and implementers may also use other normalization functions. Normalization is performed, but this application does not impose specific limitations. The greater the correlation between energy and carbon emissions, the greater the impact of energy consumption on carbon emissions, and thus the larger the carbon emission impact factor; the greater the correlation between production and carbon emissions, the greater the impact of production on carbon emissions, and thus the larger the carbon emission impact factor. It represents the average daily carbon emissions, and is a priori knowledge of carbon emissions. The larger the value, the greater the impact on carbon emissions.

[0062] Step S003: Obtain the carbon emission risk coefficient through the carbon emission impact factor, and implement carbon asset management based on the carbon emission risk coefficient.

[0063] Because carbon emission data typically has a certain delay, real-time monitoring of carbon emission data is quite difficult. Accurately measuring and estimating carbon emissions requires collecting and processing large amounts of data, as well as performing complex calculations and analyses. Waiting until problems are detected in the carbon emission data before taking relevant measures would cause significant losses to enterprises. Monitoring real-time energy consumption and production output data is much easier. Therefore, this embodiment comprehensively considers carbon emission influencing factors, real-time energy consumption data, and real-time production output data to calculate the carbon emission risk coefficient, expressed as:

[0064]

[0065] In the formula, For carbon emission risk factor, As a factor affecting carbon emissions, This refers to energy consumption data generated up to the current moment in the current month. This refers to the production output data generated up to the current moment in the current month. This represents the number of days in the current month up to the current moment. This represents the total number of days in the current month. The carbon emission impact factor indicates the degree of influence of current energy consumption and production data on carbon emission data. The higher the current energy consumption and production data, as well as the higher the carbon emission impact factor, the greater the impact on carbon emissions, and the greater the carbon emission risk factor. The purpose is to estimate the data for the entire month in which the current moment occurs based on the data already generated at the current moment.

[0066] Set an early warning threshold K. It should be noted that K is a dimensionless value, which implementers can set themselves based on historical data backtesting or actual carbon emission management targets.

[0067] In this embodiment, the calculation model of this scheme is run over a historical year to obtain a series of "carbon emission risk coefficients" for each historical month. Simultaneously, the actual carbon emissions for these months are compared to determine whether they exceed the limit, thereby identifying an optimal warning threshold K. In this embodiment, the value of K is 50. If... If this occurs, an alarm will be issued, indicating that the carbon emissions for the month may exceed the limit, requiring immediate production shutdowns and adjustments; if If the carbon emissions for the month are normal, production and operation can continue. This achieves carbon asset management and realizes the goal of energy conservation and emission reduction. A schematic diagram of the carbon asset management process is shown below. Figure 2 As shown.

[0068] Based on the same inventive concept as the above methods, embodiments of the present invention also provide an energy-saving and emission-reduction system that considers corporate carbon asset management, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described energy-saving and emission-reduction methods that consider corporate carbon asset management.

[0069] In summary, the embodiments of the present invention provide an energy-saving and emission-reduction method that considers corporate carbon asset management. By comprehensively analyzing energy consumption data and production output data that are closely related to corporate carbon emission data, a carbon emission risk coefficient is finally obtained. The carbon emission risk coefficient is used to realize carbon asset management, thereby achieving the goal of energy saving and emission reduction. While saving energy, it improves the cost-effectiveness of enterprises and is more conducive to the sustainable development of enterprises.

[0070] To avoid carbon emission exceedances due to untimely monitoring of carbon emission data, this embodiment collects historical and current month energy consumption data, carbon emission data, and production output data; calculates the autocorrelation coefficients of the energy consumption data series, carbon emission data series, and production output data series; obtains a simple prediction value of the current month's energy consumption data by fitting the element values ​​in the energy consumption data series; obtains the real-time energy consumption correlation degree for the current month by combining the autocorrelation coefficients; obtains the energy carbon emission correlation degree by combining the carbon emission data; obtains the production carbon emission correlation degree; obtains the carbon emission risk coefficient based on the energy carbon emission correlation degree and the production carbon emission correlation degree; and realizes carbon asset management based on the carbon emission risk coefficient and the early warning threshold, which helps enterprises save energy, reduce emissions, and operate rationally.

[0071] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0072] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An energy conservation and emission reduction method considering corporate carbon asset management, characterized in that, The method includes the following steps: Collect historical and current month's energy consumption data, carbon emission data, and production output data for enterprises; obtain energy consumption data sequences, carbon emission data sequences, and production output data sequences. Obtain the autocorrelation coefficient of the energy consumption data series; obtain the volatility coefficient of the energy consumption data series based on the autocorrelation coefficient; obtain the volatility coefficients of the carbon emission data series and the production output data series; obtain a simple forecast value of the energy consumption data for the current month; obtain the real-time energy consumption correlation degree for the current month based on the volatility coefficient and the simple forecast value; obtain the energy carbon emission correlation degree based on the real-time energy consumption correlation degree for the current month; obtain the production carbon emission correlation degree; obtain the carbon emission impact factor based on the energy carbon emission correlation degree and the production carbon emission correlation degree. Carbon emission risk coefficients are obtained based on carbon emission impact factors; carbon asset management is achieved based on carbon emission risk coefficients.

2. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The energy consumption data sequence is a sequence composed of historical monthly energy consumption data.

3. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The step of obtaining the fluctuation coefficient of the energy consumption data series based on the autocorrelation coefficient of the energy consumption data series specifically includes: Obtain the calculation result of an exponential function with the natural constant as the base and the autocorrelation coefficient of the energy consumption data series as the exponent; calculate the mean of the absolute values ​​of the differences between all adjacent elements in the energy consumption data series; calculate the product of the calculation result and the mean; and use the product as the fluctuation coefficient of the energy consumption data series.

4. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The process of obtaining a simple prediction of the current month's energy consumption data is as follows: The energy consumption data sequence is used as the ordinate and the month is used as the horizontal axis to fit the data, resulting in a fitted curve, which is denoted as the energy consumption fitted curve. The ordinate value of the current month on the energy consumption fitted curve is then used as a simple prediction of the energy consumption data for the current month.

5. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The correlation between the real-time energy consumption for the current month, obtained based on the fluctuation coefficient and simple prediction value, specifically includes: The energy consumption data generated up to the current moment in the current month is taken as the actual value of the energy consumption data for the current month; the absolute value of the difference between the simple predicted value and the actual value of the energy consumption data for the current month is calculated; the fluctuation coefficient of the energy consumption data sequence is calculated as the product of the absolute value of the difference; the sum of the product and a preset minimum positive number is used as the denominator, and the ratio of the autocorrelation coefficient of the energy consumption data sequence to the denominator is calculated, and the ratio is used as the real-time energy consumption correlation degree for the current month.

6. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The energy carbon emission correlation degree is obtained based on the real-time energy consumption correlation degree of the current month, and the expression is: In the formula, For the correlation between energy and carbon emissions, The correlation between real-time energy consumption for the current month. The lengths of the energy consumption data sequence and the carbon emission data sequence, The first in the energy consumption data sequence One value, Let be the mean of all elements in the energy consumption data series. The first in the carbon emission data sequence One value, This represents the mean of all elements in the carbon emission data series. The volatility coefficient represents the energy consumption data series. The fluctuation coefficient represents the carbon emission data series. The DTW distance between the energy consumption data series and the carbon emission data series. It is a preset minimum positive number.

7. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The carbon emission impact factor obtained based on the correlation between energy carbon emissions and production carbon emissions specifically includes: Calculate the ratio of monthly carbon emissions to the number of days in the month; calculate the mean of all the ratios, and record it as the daily average carbon emissions; use the product of energy carbon emissions correlation, production carbon emissions correlation, and daily average carbon emissions as the carbon emissions impact factor.

8. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The process of obtaining the carbon emission risk coefficient based on carbon emission impact factors specifically includes: Calculate the sum of energy consumption data and production output data generated in the current month up to the current moment; calculate the carbon emission impact factor, the total number of days in the current month, and the product of the sum; calculate the ratio of the product to the number of days in the current month up to the current moment; use the ratio as the carbon emission risk coefficient.

9. The energy conservation and emission reduction method considering enterprise carbon asset management as described in claim 1, characterized in that, The carbon asset management based on carbon emission risk factors specifically includes: A preset warning threshold is set; if the carbon emission risk coefficient is greater than or equal to the warning threshold, the carbon emissions for the month will exceed the standard and production needs to be stopped and adjusted in time; if the carbon emission risk coefficient is less than the warning threshold, the carbon emissions for the month will be normal.

10. An energy-saving and emission-reduction system considering corporate carbon asset management, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as claimed in any one of claims 1-9.

Images