Carbon asset management system and method suitable for park

Abstract

The invention discloses a carbon asset management system and method suitable for a park. The method comprises the following steps: obtaining production data of each enterprise factory in a park, and extracting carbon activity operation data of each enterprise factory; carrying out full-course characterization on the carbon activity of each enterprise factory, and estimating carbon emission information corresponding to the carbon activity of each enterprise factory; calculating and obtaining predicted carbon emission quota assets of each enterprise factory based on a pre-configured carbon emission calculation formula; in combination with the carbon emission quota asset information of each enterprise factory, judging whether the current carbon emission quota assets of each enterprise factory are sufficient or not; analyzing the relationship between the carbon asset price and the transaction volume, and constructing a carbon asset transaction risk assessment model; according to the invention, the carbon asset management activity of each enterprise factory in the park is improved in a targeted manner, the carbon activity state of each enterprise factory is adaptively adjusted in real time, overall optimization configuration of carbon emission quota assets of each enterprise factory in the park is realized, and predictability and reliability of park carbon asset management are improved.

Description

Technical Field

[0001] The present invention relates to the field of carbon asset technology, and in particular to a carbon asset management system and method suitable for a park. Background Art

[0002] In recent years, the impact of global warming has become increasingly serious, and the extreme consequences of climate change have become increasingly worrying and important to countries around the world. Carbon emissions are one of the main factors causing global temperature rise. Excessive burning of coal and oil will cause greenhouse effects and global sea level rise. The extreme weather disasters caused by climate change will cause significant losses to human survival, health and property safety. How to ensure the sustainable supply of energy for human society while reasonably controlling carbon emissions, increasing efforts to govern the environment, reducing pollutants, making enterprises have a low-carbon awareness, and developing a green and low-carbon economy has become a hot topic in recent years.

[0003] With the proposal of "carbon peak and carbon neutrality", and in view of the fact that current energy consumption and CO2 emissions are still increasing, the existing plan is to establish a carbon trading market mechanism and use market means to guide social entities to reasonably control carbon emissions. Carbon asset management takes corporate carbon data statistical management as its capability cornerstone, carbon quota assets as its core, and domestic and foreign emission reductions as its focus, and successively carries out quota management, carbon asset development, etc. to increase economic benefits and social value. Summary of the invention

[0004] Purpose of the invention: In view of the defects of the prior art, the present invention provides a carbon asset management system and method suitable for the park, which obtains the production data of each enterprise factory in the park, and obtains the carbon activity management data of each enterprise factory through screening and feature extraction; the carbon activities of each enterprise factory are fully characterized, so as to accurately estimate the carbon emission information corresponding to the carbon activities of each enterprise factory; based on the pre-configured carbon emission calculation formula, combined with the historical carbon activity data of each enterprise factory, the estimated carbon emission quota assets of each enterprise factory are calculated; combined with the carbon emission quota asset information of each enterprise factory, the current carbon emission quota assets of each enterprise factory are judged. Whether the production is sufficient; analyze the relationship between carbon asset prices and trading volume, find the fluctuation rules of market trading prices, and build a carbon asset trading risk assessment model to provide a reliable basis for carbon asset trading of enterprises in the park; consider carbon asset trading based on carbon market research and forecasts, and maximize the economic management of the park's carbon assets by purchasing or delaying the sale of carbon quota assets in advance; combined with the results of carbon trading, improve the carbon asset management activities of each enterprise and factory in the park in a targeted manner, and adaptively adjust the carbon activity status of each enterprise and factory in real time to achieve the coordinated and optimized allocation of carbon emission quota assets of each enterprise and factory in the park, and improve the predictability and reliability of the park's carbon asset management.

[0005] Technical solution: On the one hand, the present invention provides a carbon asset management system suitable for a park, including: an operating data collection module, a carbon activity data screening module, a carbon activity trajectory analysis module, a carbon emission estimation module, an estimated carbon emission quota asset estimation module, a carbon asset coordination module, a carbon asset trading management module, and a carbon activity adjustment module;

[0006] The business data collection module is used to obtain the production data of each enterprise factory in the park within a preset time period;

[0007] The carbon activity data screening module is used to identify and extract features from the production data of each enterprise and factory in the park, and screen out the operating data related to carbon activities;

[0008] The carbon activity trajectory analysis module is used to analyze and process the carbon activity management data involved in each enterprise and factory in the park to obtain the carbon activity trajectory data of each enterprise and factory in the park;

[0009] The carbon emission estimation module is used to perform big data prediction processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period;

[0010] The estimated carbon emission quota asset estimation module is used to perform big data forecasting and processing on the historical carbon activity management data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park;

[0011] The carbon asset coordination module is used to compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets;

[0012] The carbon activity adjustment module is used to adjust the carbon activity realization status of the target object according to the judgment result of the carbon emission quota asset sufficiency status of each enterprise factory in the park.

[0013] The carbon asset trading management module is used to analyze the relationship between carbon asset prices and trading volumes, find the fluctuation patterns of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading with the goal of achieving economic maximization through early acquisition or delayed sale of carbon quota assets with the overall management of the park's carbon assets.

[0014] Furthermore, the business data collection module is provided with a business data specific behavior frequency collection module and a business data preset time period length collection module;

[0015] The business data specific behavior frequency collection module is used to obtain the historical business data of the target object, and extract the average occurrence frequency of the specific type of business activity behavior of the target object from the historical business data;

[0016] The business data preset time period length confirmation module is used to determine the length of the preset time period corresponding to the business data of the target object after obtaining the average occurrence frequency of the specific type of historical business activity behavior, so that the business data of the target object obtained includes at least a predetermined number of record data corresponding to the characteristic type of business activity behavior.

[0017] Further, the carbon activity data screening module is provided with an operating data classification module and a carbon activity data marking module;

[0018] The business data classification module is used to obtain the data content characteristics of all business sub-data contained in the business data, and classify all business sub-data according to the data content characteristics to obtain business sub-data sets corresponding to different types of business activities;

[0019] The carbon activity data labeling module uses an extreme learning machine to perform keyword recognition and data screening on all business sub-data contained in the business sub-data set, and determines that the corresponding business sub-data set belongs to the business sub-data set involving carbon activities by pre-setting business sub-data keywords, and labels the business sub-data containing the predetermined keywords.

[0020] Furthermore, the carbon activity trajectory analysis module analyzes and processes the operating data related to carbon activities to determine the carbon activity characteristic information of all operating sub-data contained in the operating data related to carbon activities; based on the carbon activity characteristic information, all operating sub-data belonging to the same carbon activity are integrated and arranged in chronological order of the carbon activity occurrence time to form carbon activity trajectory data.

[0021] Furthermore, the carbon emission estimation module is provided with carbon emission estimation models for multiple industries and multiple regions, integrating the carbon accounting structures, standards and calculation formulas of different industries and different regions, and matching the carbon emission estimation model based on the industry and region to which the enterprise belongs.

[0022] Furthermore, the estimated carbon emission quota asset estimation module is provided with a carbon activity data training module, a carbon activity data feature extraction module and a carbon asset assessment model training module;

[0023] The carbon activity data training module is used to obtain a carbon activity data training set, and classify the carbon activity data training set based on the carbon activity type to obtain carbon activity data training subsets for different types of carbon activities;

[0024] The carbon activity data feature extraction module is used to extract the data features of each carbon activity data contained in each carbon activity data training subset, and construct a feature vector of each carbon activity data training subset; wherein the data feature refers to the estimated carbon emission quota assets corresponding to each carbon activity data;

[0025] The carbon asset assessment model training module trains the deep learning model based on the feature vectors of all carbon activity data training subsets to obtain an estimated carbon emission quota asset estimation model;

[0026] Through the estimated carbon emission quota asset estimation model A(p, qd), the carbon emission data (carbon emission quota assets) in a certain period of time in the future can be predicted based on historical operating data. This prediction model represents the non-stationary random sequence Y t After d times of difference processing, we get the stationary sequence X t , and then fit the stationary sequence to A(p,q); where the stationary sequence X t The expression is:

[0027]

[0028] in, is an autoregressive process, p is the autoregressive order, is the autoregression coefficient; ε t -φ1ε t-1 -…-φ q ε t-q is a smoothing process, q is the sliding average order, φ1…φ q is the sliding average coefficient; ε t is a white noise sequence in the form of W(0,σ 2 ); when q = 0, the sequence X t becomes an autoregressive model; when p = 0, the sequence X t It becomes a moving average model.

[0029] The estimated carbon emission quota asset estimation model is used to perform big data prediction processing on the carbon activity trajectory data, estimate the carbon asset information that is expected to be allocated to the target object within a preset time period, and identify the carbon activity name on the carbon asset information.

[0030] Furthermore, the carbon asset coordination module is used to compare the carbon emission information corresponding to all carbon activities with the carbon emission quota assets of the target object, and determine whether the carbon emissions corresponding to each carbon activity are less than or equal to the carbon emission quota asset value of the carbon activity; if so, it is determined that the target object is in a state of sufficient carbon emission quota assets under the corresponding carbon activity; if not, it is determined that the target object is not in a state of sufficient carbon emission quota assets under the corresponding carbon activity.

[0031] Set the carbon emission quota obtained by the enterprise as PE; record the comprehensive carbon emission data of the enterprise obtained during the time monitoring period as TZ; set the warning ratio data and record it as ZB;

[0032] When TZ≥PE*ZB, carbon emission warning information is generated to the enterprise management module, and the enterprise management module plans its carbon emission usage data;

[0033] When TZ≤PE*ZB, there is no need to generate corresponding carbon emission warning information to the enterprise management module.

[0034] Furthermore, the carbon activity adjustment module performs a secondary distribution of carbon emission quota assets for all carbon activities that are not in a state of sufficient carbon emission quota assets based on the remaining carbon emission quota asset values ​​of all carbon activities that are in a state of sufficient carbon emission quota assets; and determines whether the target object as a whole is currently in a state of sufficient carbon emission quota assets based on the result of the secondary distribution.

[0035] Further, the carbon asset trading management module is provided with a carbon asset trading market analysis module, a trading risk assessment module and a trading risk avoidance module;

[0036] The carbon asset trading market analysis module is used to analyze the relationship between carbon quota prices and trading volumes, find price changes and patterns, and predict the basic trend of carbon quota asset prices in combination with the economic operation and development stage, so as to maximize the economic benefits of the park's carbon assets by purchasing or delaying the sale of carbon quota assets in advance;

[0037] The transaction risk assessment module uses the mean, standard deviation, skewness, kurtosis and JB statistic of the carbon emission transaction price rate of return as indicators for descriptive analysis, and establishes a carbon trading risk assessment model based on GARCH-VaR;

[0038] The VaR model is as follows:

[0039] prob(ΔP≤VaR)=a

[0040] Among them, P is the probability that the asset value loss is less than the upper limit of possible loss, ΔP represents the loss value caused by a financial asset within a certain holding period Δt, and VaR is the value at risk under a given confidence level a, which indicates the upper limit of possible loss value. a is a given confidence level, which can generally be 90%, 95% or 99%.

[0041] Assuming the initial price of a financial asset is P0 and the rate of return is R, the end-of-period value is expressed as follows:

[0042] P=P0(1+R)

[0043] The conditional variance of carbon trading price returns calculated by the GARCH model is as follows:

[0044] Assuming the expected value and volatility of the rate of return R are μ and e, the minimum value of the financial asset under a given confidence level is as follows:

[0045] P * =P0(1+R * )

[0046] The minimum value P can be obtained from the relationship between the end-of-period value and the minimum value of the financial asset under a given confidence level. * Or the minimum rate of return R * as follows:

[0047]

[0048] Applying the conditional variance of carbon trading price returns calculated by the GARCH model to the estimation of VaR can yield the GARCH-VaR risk assessment model, as shown below:

[0049]

[0050] The transaction risk avoidance module conducts decentralized transactions of the park's carbon assets among multiple parties to avoid the risks brought about by large fluctuations in carbon asset prices before the deadline for fulfillment, thereby achieving optimal cost fulfillment and carbon asset value preservation and appreciation.

[0051] On the other hand, the present invention also provides a carbon asset management method applicable to a park, the method comprising:

[0052] Obtain production data of each enterprise factory in the park within a preset time period;

[0053] Identify and extract features from the production data of each enterprise and factory in the park, and filter out the operating data related to carbon activities;

[0054] Analyze and process the carbon activity management data of each enterprise and factory in the park to obtain the carbon activity trajectory data of each enterprise and factory in the park;

[0055] Carry out big data prediction and processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period;

[0056] Conduct big data forecasting and processing of the historical carbon activity management data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park;

[0057] Compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets;

[0058] Adjust the carbon activity realization status of the target object based on the judgment results of the sufficient status of carbon emission quota assets of each enterprise and factory in the park;

[0059] Analyze the relationship between carbon asset prices and trading volume, find the fluctuation patterns of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading with the goal of achieving economic maximization through early acquisition or delayed sale of carbon quota assets in the park through coordinated management of carbon assets.

[0060] Beneficial effects: Compared with the prior art, the beneficial effects of the present invention are: a carbon asset trading market analysis module is provided, which can analyze the relationship between the price and trading volume of carbon quota assets, find price changes and rules, and predict the basic trend of carbon quota asset prices in combination with the economic operation and development stage, and maximize the economic benefits of the park's carbon assets by purchasing carbon quota assets in advance or delaying the sale of carbon quota assets; a trading risk assessment module is provided, which can assess the volatility risk of quantitative carbon trading prices, which has certain practical significance for realizing the construction of a unified carbon trading market; a trading risk avoidance module is provided, which can avoid the risks brought by large fluctuations in carbon asset prices before the compliance deadline by conducting decentralized transactions of the park's carbon assets with multiple parties, so as to achieve optimal cost compliance and carbon asset preservation and appreciation.

[0061] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 This is a schematic diagram of the structure of a carbon asset management system applicable to a park disclosed in an embodiment of the present invention.

[0064] Figure numerals: operating data collection module 1, carbon activity data screening module 2, carbon activity trajectory analysis module 3, carbon emission estimation module 4, expected carbon emission quota asset estimation module 5, carbon asset coordination module 6, carbon asset trading management module 7, carbon activity adjustment module 8. DETAILED DESCRIPTION

[0065] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0066] like Figure 1 As shown, the embodiment of the present invention provides a carbon asset management system suitable for a park, including: an operating data collection module 1, a carbon activity data screening module 2, a carbon activity trajectory analysis module 3, a carbon emission estimation module 4, an estimated carbon emission quota asset estimation module 5, a carbon asset coordination module 6, a carbon asset trading management module 7, and a carbon activity adjustment module 8;

[0067] The business data collection module 1 is used to obtain the production data of each enterprise factory in the park within a preset time period, including: a business data specific behavior frequency collection module and a business data preset time period length collection module;

[0068] The business data specific behavior frequency collection module is used to obtain the historical business data of the target object, and extract the average occurrence frequency of the specific type of business activity behavior of the target object from the historical business data;

[0069] The business data preset time period length confirmation module is used to determine the length of the preset time period corresponding to the business data of the target object after obtaining the average occurrence frequency of the specific type of historical business activity behavior, so that the business data of the target object obtained includes at least a predetermined number of record data corresponding to the characteristic type of business activity behavior.

[0070] Specifically, the data collected by the operating data collection module 1 include electricity meters, water meters, gas meters, heat meters, flue gas parameter monitoring instruments, greenhouse gas monitoring instruments and production system metering instruments, but are not limited to the above instruments.

[0071] The carbon activity data screening module 2 is used to identify and extract features of production data of various enterprises and factories in the park, and screen out business data related to carbon activities, including: business data classification module and carbon activity data marking module;

[0072] The business data classification module is used to obtain the data content characteristics of all business sub-data contained in the business data, and classify all business sub-data according to the data content characteristics to obtain business sub-data sets corresponding to different types of business activities;

[0073] The carbon activity data labeling module uses an extreme learning machine to perform keyword recognition and data screening on all business sub-data contained in the business sub-data set, and determines that the corresponding business sub-data set belongs to the business sub-data set involving carbon activities by pre-setting business sub-data keywords, and labels the business sub-data containing the predetermined keywords.

[0074] Specifically, the business sub-data sets are respectively provided with an abnormal threshold of the corresponding data, and the abnormal threshold is the maximum cumulative number of abnormal information. For the corresponding data abnormal information, it is archived and the number is marked;

[0075] Whether to generate corresponding abnormal warning information and send it to the park enterprise processing unit is determined based on the relationship between the number of marking times and the abnormal threshold; when the data processing unit receives the corresponding serious data abnormality information, it immediately generates the corresponding serious data abnormality warning information to the park enterprise processing unit; when normal data information is received, no corresponding measures are taken.

[0076] The carbon activity trajectory analysis module 3 is used to analyze and process the carbon activity management data involved in each enterprise and factory in the park to obtain the carbon activity trajectory data of each enterprise and factory in the park; based on the carbon activity characteristic information, all the management sub-data belonging to the same carbon activity are integrated and arranged in the order of the carbon activity occurrence time to form the carbon activity trajectory data;

[0077] Specifically, the carbon activity characteristic information includes carbon activity type information and carbon activity occurrence time information.

[0078] The carbon emission estimation module 4 is used to perform big data prediction and processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period. The carbon emission estimation module 4 is provided with carbon emission estimation models for multiple industries and multiple regions, integrating the carbon accounting structure, standards and calculation formulas of different industries and different regions, and matching the carbon emission estimation model based on the industry and region to which the enterprise belongs;

[0079] Specifically, the carbon emission estimation module 4 summarizes the formula or parameter values ​​for calculating carbon emissions. For park enterprises in different regions, carbon emissions need to be calculated through flexibly configured carbon emission calculation formulas. In order to reduce the work of manually sorting report data, artificial intelligence technology can be used to realize the intelligent calculation of carbon emissions of each power plant, that is, the carbon trajectory data of each enterprise in the park and the carbon emission calculation formula corresponding to the enterprise are input into an intelligent matching model, and the system can automatically extract the data required by the carbon emission calculation formula to calculate carbon emissions, and automatically calculate the carbon emissions of each enterprise in the park.

[0080] The estimated carbon emission quota asset estimation module 5 is used to perform big data prediction processing on the historical carbon activity operation data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park, including: a carbon activity data training module, a carbon activity data feature extraction module and a carbon asset assessment model training module;

[0081] The carbon activity data training module is used to obtain a carbon activity data training set, and classify the carbon activity data training set based on the carbon activity type to obtain carbon activity data training subsets for different types of carbon activities;

[0082] The carbon activity data feature extraction module is used to extract the data features of each carbon activity data contained in each carbon activity data training subset, and construct a feature vector of each carbon activity data training subset; wherein the data feature refers to the estimated carbon emission quota assets corresponding to each carbon activity data;

[0083] The carbon asset assessment model training module trains the deep learning model based on the feature vectors of all carbon activity data training subsets to obtain an estimated carbon emission quota asset estimation model;

[0084] Using the estimated carbon emission quota asset estimation model, the carbon activity trajectory data is processed for big data prediction, the carbon asset information that is expected to be allocated to the target object within a preset time period is estimated, and the carbon asset information is processed for identification of the carbon activity name;

[0085] Specifically, as an optional implementation, the prediction model A(p, qd) can be used to predict carbon emission data (carbon emission quota assets) within a certain period of time in the future based on historical operating data. The prediction model represents the non-stationary random sequence Y t After d times of difference processing, we get the stationary sequence X t , and then fit the stationary sequence to A(p,q); where the stationary sequence X t The expression is:

[0086]

[0087] in, is an autoregressive process, p is the autoregressive order, is the autoregression coefficient; ε t -φ1ε t-1 -…-φ q ε t-q is a smoothing process, q is the sliding average order, φ1…φ q is the sliding average coefficient; ε t is a white noise sequence in the form of W(0,σ 2 ); when q = 0, the sequence Xt becomes an autoregressive model; when p = 0, the sequence X t It becomes a moving average model.

[0088] Through the above prediction model, the carbon emission data of the park enterprises in a certain period of time in the future can be predicted, so as to estimate the expected carbon emissions and expected quotas of the enterprise in that period of time, and then estimate the assets based on the expected carbon emissions and expected carbon quotas.

[0089] The carbon asset coordination module 6 is used to compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets;

[0090] Specifically, it is determined whether the carbon emission amount corresponding to each carbon activity is less than or equal to the carbon emission quota asset value of the carbon activity; if so, it is determined that the target object is in a sufficient state of carbon emission quota assets under the corresponding carbon activity; if not, it is determined that the target object is not in a sufficient state of carbon emission quota assets under the corresponding carbon activity;

[0091] It should be noted that the carbon asset coordination module 6 will set corresponding proportion reminders, and its specific implementation process includes:

[0092] Set the carbon emission quota obtained by the enterprise as PE; record the comprehensive carbon emission data of the enterprise obtained during the time monitoring period as TZ; set the warning ratio data and record it as ZB;

[0093] When TZ≥PE*ZB, carbon emission warning information is generated to the enterprise management module, and the enterprise management module plans its carbon emission usage data;

[0094] When TZ≤PE*ZB, there is no need to generate corresponding carbon emission warning information to the enterprise management module.

[0095] The carbon activity adjustment module 7 adjusts the carbon activity realization status of the target object according to the judgment result of the carbon emission quota asset sufficiency status of each enterprise factory in the park, including: based on the remaining carbon emission quota asset value of all carbon activities in the carbon emission quota asset sufficiency status, the carbon emission quota assets of all carbon activities that are not in the carbon emission quota asset sufficiency status are secondary distributed, and according to the result of the secondary distribution, it is judged whether the target object is currently in the carbon emission quota asset sufficiency status as a whole;

[0096] Specifically, the carbon emission estimation module 4 calculates the total amount of carbon emissions generated by the enterprise in the current calculation cycle based on the carbon emission data. The carbon activity adjustment module 7 calculates the remaining carbon emissions that can be generated based on the total amount of carbon emissions generated and the current remaining carbon quota of the enterprise. At the same time, the production orders and historical production orders of the enterprise are obtained in combination with the carbon emission data obtained by the carbon activity data screening module 2 to calculate the necessary carbon emissions and unnecessary carbon emissions in the remaining time of the current calculation cycle, and adjust the unnecessary carbon emissions. It should be noted that the necessary carbon emission data is calculated based on the order, and the carbon emissions generated by completing the order are the necessary carbon emissions. If the time occupied by the order exceeds the current calculation cycle, it will not be predicted in combination with the historical order data. If the time occupied by the order does not exceed the current calculation cycle, It is necessary to combine historical order data to predict the carbon emissions for the remaining time of the current calculation cycle. Necessary carbon emissions cannot be adjusted. The adjustment principle for non-essential carbon emissions is that within the current calculation cycle, if the necessary carbon emissions plus the non-essential carbon emissions are less than or equal to the company's remaining carbon quota, no adjustment will be made. If the necessary carbon emissions plus the non-essential carbon emissions are greater than the company's remaining carbon quota, adjustments will be made. Before adjustments, it is necessary to perform a priority evaluation based on the identification of the carbon emission data obtained by the carbon activity data screening module 2, and sort them from high to low priority. The generation of low-priority carbon emission data will be stopped first, until within the current calculation cycle, the necessary carbon emissions plus the non-essential carbon emissions are less than or equal to the company's remaining carbon quota, and the carbon emission adjustment data is output.

[0097] The carbon asset trading management module 8 is used to analyze the relationship between carbon asset prices and trading volumes, find the fluctuation pattern of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading with the goal of achieving economic maximization through early acquisition or delayed sale of carbon quota assets in the park through coordinated management of carbon assets;

[0098] Specifically, the carbon asset trading management module 8 is provided with a carbon asset trading market analysis module, a trading risk assessment module and a trading risk avoidance module;

[0099] The carbon asset trading market analysis module adopts the GARCH model to fit the volatility of the carbon emission rights yield time series characteristics, analyzes its heteroscedasticity phenomenon and volatility characteristics, and explores the price fluctuations in the carbon emission rights trading market. The definition of the GARCH model is derived as follows:

[0100] Formula (1) and Formula (2) show the basic equation form of the model, where R is the sequence to be analyzed (here refers to the price of carbon asset transactions), μ is the expected mean of the sequence R, ε is the residual, σ is the volatility variance of the sequence R, α, β, γ are the coefficients to be estimated, p and q represent the maximum lag order of the previous variance and the previous residual, and Formula (3) is called the GARCH (p, q) model, which contains p GARCH terms and q ARCH terms respectively. The meaning of Formula (3) is that the variance of the sequence R in the tth period is subject to the constant variance α and the previous variance estimate and the previous new information residual This means that if the variance of the series R in period (t-1) is When it is larger, traders will pay more attention to the variance σ of the next period. 2 The estimated value is larger, that is, financial time series data often show volatility cluster characteristics. If p and q in equation (2) are both equal to 1, then equation (2) becomes equation (3), and equation (3) is called the GARCH (1,1) model, that is, the model contains one ARCH term and one GARCH term.

[0101] R t =μ t -ε t (1)

[0102]

[0103]

[0104] It should be noted that the most commonly used model in financial time series analysis is the GARCH (1, 1) model. The necessary and sufficient condition for the stability of this model is that β+γ<1 in formula (3).

[0105] The transaction risk assessment module uses the GARCH-VaR model to measure the mainstream risks of the carbon asset trading market. The VaR model is as follows:

[0106] prob(ΔP≤VaR)=a (4)

[0107] Among them, P is the probability that the asset value loss is less than the upper limit of possible loss, ΔP represents the loss value caused by a certain financial asset within a certain holding period Δt, and VaR is the value at risk under a given confidence level a, which represents the upper limit of possible loss value. a is a given confidence level, which can generally be 90%, 95% or 99%. Assuming the initial price of a financial asset is P0 and the rate of return is R, the end-of-period value can be obtained by formula (5).

[0108] Assuming that the expected value and volatility of the rate of return R are μ and e, the minimum value of the financial asset under a given confidence level is given by equation (6). The relationship between equations (5) and (6) can lead to equation (7). On this basis, finding VaR is equivalent to determining the minimum value P * Or the minimum rate of return R * .

[0109] P=P0(1+R) (5)

[0111] P * =P0(1+R * ) (6)

[0112]

[0113] Applying the conditional variance of carbon trading price returns calculated by the GARCH model to the estimation of VaR can obtain the GARCH-VaR risk assessment model, as shown in formula (8):

[0114]

[0115] For different risk management, confidence and holding period, specific issues need to be analyzed. The historical backtesting method is used to examine whether the GARCH-VaR method can effectively measure the risk of the carbon trading market. The actual rate of return and the estimated VaR for the entire period are compared. If the actual rate of return is greater than VaR, it is recorded as a breakthrough. If the confidence level is set to 99%, the probability of a breakthrough should be 1%.

[0116] The decentralized trading module will conduct decentralized trading of the park's carbon assets among multiple parties based on the risk assessment feedback results, so as to avoid the risks brought about by large fluctuations in carbon asset prices before the compliance deadline, and achieve optimal cost compliance and carbon asset preservation and appreciation.

[0117] On the other hand, the present invention also provides a carbon asset management method applicable to a park, the method comprising:

[0118] Obtain production data of each enterprise factory in the park within a preset time period;

[0119] Identify and extract features from the production data of each enterprise and factory in the park, and filter out the operating data related to carbon activities;

[0120] Analyze and process the carbon activity management data of each enterprise and factory in the park to obtain the carbon activity trajectory data of each enterprise and factory in the park;

[0121] Carry out big data prediction and processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period;

[0122] Conduct big data forecasting and processing of the historical carbon activity management data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park;

[0123] Compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets;

[0124] Adjust the carbon activity realization status of the target object based on the judgment results of the sufficient status of carbon emission quota assets of each enterprise and factory in the park;

[0125] Analyze the relationship between carbon asset prices and trading volume, find the fluctuation patterns of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading with the goal of achieving economic maximization through early acquisition or delayed sale of carbon quota assets in the park through coordinated management of carbon assets.

[0126] Other technical features of the carbon asset management method applicable to a park described in the present invention are similar to the corresponding carbon asset management system applicable to a park, and will not be repeated here.

[0127] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

[0128] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0130] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A carbon asset management system suitable for a park, characterized in that: include: Operation data collection module (1), carbon activity data screening module (2), carbon activity trajectory analysis module (3), carbon emission estimation module (4), estimated carbon emission quota asset estimation module (5), carbon asset coordination module (6), carbon activity adjustment module (7), carbon asset trading management module (8); The business data collection module (1) is used to obtain the production data of each enterprise factory in the park within a preset time period; The carbon activity data screening module (2) is used to identify and extract features from the production data of each enterprise and factory in the park, and screen out the operating data related to carbon activities; The carbon activity trajectory analysis module (3) is used to analyze and process the carbon activity management data involved in each enterprise and factory in the park, and obtain the carbon activity trajectory data of each enterprise and factory in the park; The carbon emission estimation module (4) is used to perform big data prediction processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period; The estimated carbon emission quota asset estimation module (5) is used to perform big data forecasting processing on the historical carbon activity management data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park; The carbon asset coordination module (6) is used to compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets; The carbon activity adjustment module (7) adjusts the carbon activity realization status of the target object based on the judgment result of the sufficient status of the carbon emission quota assets of each enterprise and factory in the park; The carbon asset trading management module (8) is used to analyze the relationship between carbon asset prices and trading volumes, find the fluctuation patterns of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading by purchasing carbon quota assets in advance or selling them later with the goal of achieving economic maximization through the overall management of the park's carbon assets.

2. A carbon asset management system suitable for a park according to claim 1, characterized in that: The business data collection module (1) is provided with a business data specific behavior frequency collection module and a business data preset time period length collection module; The business data specific behavior frequency collection module is used to obtain the historical business data of the target object, and extract the average occurrence frequency of the specific type of business activity behavior of the target object from the historical business data; The business data preset time period length collection module is used to determine the length of the preset time period corresponding to the business data of the target object after obtaining the average occurrence frequency of the specific type of historical business activity behavior, and the business data of the target object at least includes a predetermined number of record data corresponding to the specific type of business activity behavior.

3. According to claim 1, a carbon asset management system suitable for a park is characterized in that: The carbon activity data screening module (2) is provided with an operating data classification module and a carbon activity data marking module; The business data classification module is used to obtain the data content characteristics of all business sub-data contained in the business data, and classify all business sub-data according to the data content characteristics to obtain business sub-data sets corresponding to different types of business activities; The carbon activity data labeling module uses an extreme learning machine to perform keyword recognition and data screening on all business sub-data contained in the business sub-data set, and determines that the corresponding business sub-data set belongs to the business sub-data set involving carbon activities by pre-setting business sub-data keywords, and labels the business sub-data containing the predetermined keywords.

4. According to claim 1, a carbon asset management system suitable for a park is characterized in that: The carbon activity trajectory analysis module (3) analyzes and processes the business data related to carbon activities to determine the carbon activity characteristic information of all business sub-data contained in the business data related to carbon activities; Based on the carbon activity characteristic information, all operating sub-data belonging to the same carbon activity are integrated and arranged in the order of the occurrence time of the carbon activity to form carbon activity trajectory data.

5. A carbon asset management system suitable for a park according to claim 4, characterized in that: The carbon activity characteristic information includes carbon activity type information and carbon activity occurrence time information.

6. The carbon asset management system applicable to a park according to claim 1 is characterized in that: The carbon emission estimation module (4) is provided with carbon emission estimation models for multiple industries and multiple regions, integrating carbon accounting structures, standards and calculation formulas for different industries and different regions, and matching the carbon emission estimation model based on the industry and region to which the enterprise belongs.

7. The carbon asset management system applicable to a park according to claim 1 is characterized in that: The estimated carbon emission quota asset estimation module (5) is provided with a carbon activity data training module, a carbon activity data feature extraction module and a carbon asset assessment model training module; The carbon activity data training module is used to obtain a carbon activity data training set, and classify the carbon activity data training set based on the carbon activity type to obtain carbon activity data training subsets for different types of carbon activities; The carbon activity data feature extraction module is used to extract the data features of each carbon activity data contained in each carbon activity data training subset, and construct a feature vector of each carbon activity data training subset; wherein the data feature refers to the estimated carbon emission quota assets corresponding to each carbon activity data; The carbon asset assessment model training module trains the deep learning model based on the feature vectors of all carbon activity data training subsets to obtain an estimated carbon emission quota asset estimation model; Through the estimated carbon emission quota asset estimation model A(p, qd), the carbon emission data in a certain period of time in the future is predicted based on historical operating data. This prediction model represents the non-stationary random sequence Y t After d times of difference processing, we get the stationary sequence X t , and then fit the stationary sequence to A(p,q); where the stationary sequence X t The expression is: in, is an autoregressive process, p is the autoregressive order, is the autoregression coefficient; ε t -φ1ε t-1 --φ q ε t-q is a smoothing process, q is the sliding average order, φ1φ q is the sliding average coefficient; ε t is a white noise sequence in the form of W(0,σ 2 ); when q = 0, the sequence X t becomes an autoregressive model; when p = 0, the sequence X t Become a moving average model; The estimated carbon emission quota asset estimation model is used to perform big data prediction processing on the carbon activity trajectory data, estimate the carbon asset information that is expected to be allocated to the target object within a preset time period, and identify the carbon activity name on the carbon asset information.

8. The carbon asset management system applicable to a park according to claim 1 is characterized by: The carbon asset coordination module (6) is used to compare the carbon emission information corresponding to all carbon activities with the carbon emission quota assets of the target object, and determine whether the carbon emission corresponding to each carbon activity is less than or equal to the carbon emission quota asset value of the carbon activity; If so, it is determined that the target object is in a state of sufficient carbon emission quota assets under the corresponding carbon activity; If not, it is determined that the target object is not in a state of sufficient carbon emission quota assets under the corresponding carbon activity; The carbon emission quota obtained by the enterprise is set as PE; the comprehensive carbon emission data of the enterprise obtained during the time monitoring period is recorded as TZ; Set the warning ratio data and record it as ZB; When TZ≥PE*ZB, carbon emission warning information is generated to the enterprise management module, and the enterprise management module plans its carbon emission usage data; When TZ≤PE*ZB, there is no need to generate corresponding carbon emission warning information to the enterprise management module.

9. The carbon asset management system applicable to a park according to claim 1, characterized in that: The carbon activity adjustment module (7) performs secondary distribution of carbon emission quota assets for all carbon activities that are not in a state of sufficient carbon emission quota assets based on the remaining carbon emission quota asset values ​​of all carbon activities that are in a state of sufficient carbon emission quota assets; and determines whether the target object as a whole is currently in a state of sufficient carbon emission quota assets based on the result of the secondary distribution.

10. The carbon asset management system applicable to a park according to claim 1, characterized in that: The carbon asset trading management module (8) is provided with a carbon asset trading market analysis module, a trading risk assessment module and a trading risk avoidance module; The carbon asset trading market analysis module is used to analyze the relationship between carbon quota prices and trading volumes, find price changes and patterns, and predict the basic trend of carbon quota asset prices in combination with the economic operation and development stage, so as to maximize the economic benefits of the park's carbon assets by purchasing or delaying the sale of carbon quota assets in advance; The transaction risk assessment module uses the mean, standard deviation, skewness, kurtosis and JB statistic of the carbon emission transaction price rate of return as indicators for descriptive analysis, and establishes a carbon trading transaction risk assessment model based on GARCH-VaR; The transaction risk avoidance module conducts decentralized transactions of the park's carbon assets among multiple parties to avoid the risks brought about by large fluctuations in carbon asset prices before the deadline for fulfillment, thereby achieving optimal cost fulfillment and carbon asset value preservation and appreciation.

11. A carbon asset management system suitable for a park according to claim 10, characterized in that: include: The GARCH-VaR carbon trading transaction risk assessment model includes a VaR model and a GARCH model; The VaR model is as follows: prob(ΔP≤VaR)=a; Among them, P is the probability that the asset value loss is less than the upper limit of possible loss, ΔP represents the loss value caused by a certain financial asset within a certain holding period Δt, VaR is the value at risk under a given confidence level a, indicating the upper limit of the loss value, a is a given confidence level, and the value is 90%, 95% or 99%; Assuming the initial price of a financial asset is P0 and the rate of return is R, the end-of-period value is expressed as follows: P = P0(1+R); The conditional variance of carbon trading price returns calculated by the GARCH model is as follows: Assuming the expected value and volatility of the rate of return R are μ and e, the minimum value of the financial asset under a given confidence level is as follows: P * =P0(1+R * ); The minimum value P can be obtained from the relationship between the end-of-period value and the minimum value of the financial asset under a given confidence level. * Or the minimum rate of return R * as follows: Applying the conditional variance of carbon trading price returns calculated by the GARCH model to the estimation of VaR can yield the GARCH-VaR risk assessment model, as shown below:

12. A carbon asset management method applicable to a park, characterized in that: The method includes: Obtain production data of each enterprise factory in the park within a preset time period; Identify and extract features from the production data of each enterprise and factory in the park, and filter out the operating data related to carbon activities; Analyze and process the carbon activity management data of each enterprise and factory in the park to obtain the carbon activity trajectory data of each enterprise and factory in the park; Carry out big data prediction and processing on the carbon activity trajectory data of each enterprise and factory in the park, and estimate the carbon emission information corresponding to the carbon activities of each enterprise and factory in the park within a preset time period; Conduct big data forecasting and processing of the historical carbon activity management data of each enterprise and factory in the park, and calculate the estimated carbon emission quota assets of each enterprise and factory in the park; Compare the carbon emission information of each enterprise and factory in the park with the carbon emission quota asset information to determine whether each enterprise and factory in the park is currently in a state of sufficient carbon emission quota assets; Adjust the carbon activity realization status of the target object based on the judgment results of the sufficient status of carbon emission quota assets of each enterprise and factory in the park; Analyze the relationship between carbon asset prices and trading volume, find the fluctuation patterns of market trading prices, build a carbon asset trading risk assessment model, consider carbon asset trading based on carbon market research and forecasts, and conduct carbon asset trading with the goal of achieving economic maximization through early acquisition or delayed sale of carbon quota assets in the park through coordinated management of carbon assets.

Images