A carbon emission accounting system based on measurement

Abstract

The present invention discloses a carbon emission accounting system based on metering, which relates to the technical field of carbon emission accounting, including obtaining energy consumption data, modeling the collected energy consumption data, predicting energy consumption trends, analyzing energy consumption data, and generating preliminary carbon emission factors according to different energy types and consumption, iteratively optimizing the preliminary carbon emission factors through a carbon emission factor generation and optimization module, calculating carbon emissions using the optimized carbon emission factors, setting thresholds for comparison, real-time warning of abnormal carbon emissions, and matching emission reduction suggestions through an emission reduction optimization suggestion module. The present invention improves the automation and intelligence level of carbon emission management through energy consumption data acquisition, energy consumption trend prediction, carbon emission factor generation and optimization, and early warning and emission reduction optimization suggestions, and provides strong technical support for green and low-carbon transformation.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission accounting, and in particular to a carbon emission accounting system based on measurement. Background Art

[0002] In recent years, carbon emission accounting technology has made significant progress, and related technologies have continued to evolve towards integration, automation and intelligence. Traditional carbon emission accounting methods rely on manual data collection and calculation, which often have problems such as time delays and low data processing efficiency. However, with the advancement of information technology, especially the introduction of the Internet of Things, big data analysis and machine learning technology, intelligent carbon emission monitoring systems have gradually become a research hotspot. Some current research and application examples focus on dynamic monitoring of assets, estimation of carbon footprints, and optimization of carbon reduction strategies through real-time data analysis, which improves the timeliness and accuracy of carbon emission monitoring.

[0003] Although the rapid development of existing technologies has brought many conveniences, there are still some shortcomings. For example, many systems fail to provide comprehensive coverage in the acquisition and processing of energy consumption data, and usually focus on a single or a few types of energy, resulting in an inability to fully evaluate the carbon emissions of the entire energy system; in addition, the existing carbon emission factor calculation methods often lack a dynamic adjustment mechanism, and the response to environmental changes and socio-economic factors is not timely enough, and cannot effectively support the accurate generation and optimization of carbon emission factors; many systems do not use models that comprehensively consider multiple factors such as seasonality and external variables when preprocessing and predicting data, resulting in limited prediction accuracy; in terms of the abnormal carbon emission warning mechanism, although the warning threshold is set, there is a lack of intelligent processing capabilities to match emission reduction recommendations in real time, making it difficult to achieve rapid response in actual operations. Summary of the invention

[0004] In view of the above existing problems, the present invention provides a carbon emission accounting system based on metering to solve the problem that the prior art cannot comprehensively evaluate the carbon emission situation of the entire energy system.

[0005] In order to solve the above technical problems, a carbon emission accounting system based on metering is proposed, which includes energy consumption data acquisition module, data preprocessing module, energy consumption trend prediction module, carbon emission factor generation and optimization module, real-time monitoring and early warning module and emission reduction optimization suggestion module;

[0006] The energy consumption data acquisition module acquires energy consumption data; the data preprocessing module processes outliers, fills in missing data, and standardizes units for the collected energy consumption data; the energy consumption trend prediction module models the processed energy consumption data and predicts energy consumption trends; the carbon emission factor generation and optimization module analyzes the energy consumption data, generates preliminary carbon emission factors based on different energy types and consumption, introduces a reinforcement learning algorithm, and iteratively optimizes the preliminary carbon emission factors;

[0007] The iterative optimization includes, after generating the preliminary carbon emission factor, constructing a reinforcement learning model, learning the optimal strategy through interaction with the environment, iteratively optimizing the generated preliminary carbon emission factor, and outputting the optimized carbon emission factor;

[0008] The construction of the reinforcement learning model includes defining a state space consisting of energy consumption, preliminary carbon emission factors of energy and external environmental factors, defining a workspace including three adjustment measures of the carbon emission factors, and setting a reward function to reflect the influence of external environmental data;

[0009] Set the reward function formula to:

[0010] ;

[0011] ;

[0012] Among them, R is the reward obtained, is the current carbon emissions, is the original carbon emissions, is the weight factor, is the external environment influence function, is the regulating factor, External environmental factors;

[0013] The interactive learning with the environment includes obtaining current energy consumption data and initial carbon emission factor data, forming an initial state, and selecting an execution action according to the current state and the strategy obtained by the reinforcement learning algorithm. After executing the selected action, the carbon emission factor is updated, the new state after the execution of the action is observed, the current carbon emissions are recalculated, and a new state is obtained. The reward is calculated for feedback, and the current action is scored, the strategy is updated, and the steps of selecting an action, executing an action, observing a new state, feeding back a reward, and updating model parameters are repeated until the optimization goal is achieved;

[0014] The selection of an execution action includes increasing the carbon emission factor of energy, reducing the carbon emission factor of energy, and not changing the carbon emission factor of energy; the scoring formula for the current action is:

[0015] ;

[0016] Among them, Z is the action score, R is the reward obtained, is the discount factor, is the current estimated value, is the current state, For the selected action, The maximum evaluation value of the action selected in the new state; when the score is less than 50 points, the model parameters are updated and the strategy is adjusted immediately; when the score is greater than or equal to 50 points, the current strategy and model parameters are maintained;

[0017] The strategy adjustment formula is:

[0018] ;

[0019] in, is the updated estimated value, is the learning rate, Z is the action score, is the current estimated value;

[0020] The real-time monitoring and early warning module calculates carbon emissions using the optimized carbon emission factors, transmits the carbon emissions to the monitoring center in real time, sets thresholds for comparison, and issues real-time early warnings for abnormal carbon emissions. When abnormal carbon emissions occur, the emission reduction optimization suggestion module matches emission reduction suggestions according to the early warning results and automatically generates emission reduction suggestions.

[0021] As a preferred solution of the carbon emission accounting system based on metering described in the present invention, wherein: the acquisition of energy consumption data includes acquiring electricity consumption data, natural gas consumption data, water resource consumption data, thermal energy consumption data and renewable energy consumption data;

[0022] The electricity consumption data includes meter readings, electricity consumption time periods and peak and valley electricity price information; the natural gas consumption data includes meter readings, gas usage time and gas source type; the water resource consumption data includes meter readings, water usage and usage time; the thermal energy consumption data includes the usage of central heating, steam and hot water; the renewable energy consumption data includes the consumption of solar energy, wind energy and nuclear energy.

[0023] As a preferred solution of the carbon emission accounting system based on metering described in the present invention, wherein: the prediction of energy consumption trend includes preprocessing the acquired energy consumption data, using an autoregressive integral moving average model in combination with seasonal factors and external variables to build a model, and predicting the energy consumption trend according to the established model;

[0024] The preprocessing includes using statistical analysis methods to process outliers, filling missing data with interpolation methods, and standardizing energy consumption data of different units;

[0025] The autoregressive integrated moving average model formula is expressed as:

[0026] ;

[0027] in, is the energy consumption data at time point t, t is time, is a constant term, , , , is the coefficient of the autoregressive part, is the error term, , , is the coefficient of the moving average part, p is the number of autoregressive terms, q is the number of moving average terms, s is the seasonal period, , For time point , 2. , Energy consumption data, , , For time point , , Energy consumption data of q;

[0028] The energy consumption trend prediction formula is:

[0029] ;

[0030] in, is the prediction for the future k moments, is the predicted value at the time point before the predicted time point, is the prediction formula, is the external variable adopted at time point t.

[0031] As a preferred solution of the metering-based carbon emission accounting system described in the present invention, the generation of the preliminary carbon emission factor includes using the preprocessed energy consumption data to generate the preliminary carbon emission factor according to different energy types and consumption, and using the energy consumption data and the preliminary carbon emission factor to calculate the current carbon emissions.

[0032] The formula for generating the preliminary carbon emission factor is expressed as:

[0033] ;

[0034] ;

[0035] in, is the preliminary carbon emission factor, is the baseline emission value of energy, is the carbon emission factor adjustment function, is the energy output, is the climate influencing factor, is the impact factor of socioeconomic data, j is the variable index;

[0036] The formula for calculating the current carbon emissions is:

[0037] ;

[0038] in, is the current carbon emissions, is the energy consumption, is the preliminary carbon emission factor.

[0039] As a preferred solution of the carbon emission accounting system based on metering described in the present invention, wherein: the real-time transmission of carbon emissions to the monitoring center includes, according to the optimized carbon emission factor output by the model, calculating the carbon emissions by the emission factor, and transmitting the carbon emissions to the monitoring center in real time;

[0040] Real-time carbon emissions transmission includes encapsulating the calculated carbon emissions into a data packet for transmission, encrypting the data packet using the AES encryption algorithm, generating an encryption key, establishing an encrypted transmission channel between the data sender and the monitoring center using a secure transmission protocol, and confirming whether the server certificate of the monitoring center is valid. The encrypted data packet is sent to the monitoring center through the established encrypted transmission channel. After receiving the encrypted data, the monitoring center uses the corresponding decryption algorithm and key to decrypt the data packet. After decryption, the carbon emissions are verified for integrity using a hash function, and the decrypted and verified carbon emissions are stored in the monitoring center's data warehouse.

[0041] As a preferred solution of the carbon emission accounting system based on metering described in the present invention, the matching of emission reduction suggestions includes setting a carbon emission threshold, comparing the transmitted carbon emission with the carbon emission threshold in real time, giving a graded warning of abnormal carbon emission situations through comparison, and matching emission reduction suggestions according to the warning results;

[0042] The setting of the carbon emission threshold includes setting the daily carbon emission threshold at 500 kg, the weekly carbon emission threshold at 3,000 kg, and the monthly carbon emission threshold at 12,000 kg. When the real-time monitored carbon emissions exceed the set threshold, the alarm mechanism is triggered. When the carbon emissions are between 105% and 110% of the threshold, the carbon emissions are determined to be in the warning range, and the responsible person is notified via SMS to remind him to pay attention to the emissions; when the carbon emissions are between 110% and 150% of the threshold, the carbon emissions are determined to be in the severe warning range, and an emergency notice is immediately issued for review and response; when the carbon emissions exceed 150%, the carbon emissions are determined to be in the critical warning range, and an emergency notice is sent to require immediate action and on-site inspection.

[0043] As a preferred solution of the carbon emission accounting system based on metering described in the present invention, the emission reduction suggestions include reducing the burning of fossil fuels and switching to renewable solar and wind energy, improving production processes, and capturing and storing emitted carbon dioxide when a carbon emission warning is triggered;

[0044] The improved production processes include conducting a comprehensive energy audit, evaluating the energy consumption and carbon emissions in the current production process, identifying energy waste links, optimizing equipment operating parameters, redesigning the production process, reducing energy-intensive steps, and replacing old and inefficient equipment.

[0045] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a system for carbon emission accounting based on measurement when executing the computer program.

[0046] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of a system for carbon emission accounting based on metering are implemented.

[0047] Beneficial effects of the present invention: The present invention achieves comprehensive monitoring of various energy consumption situations by acquiring consumption data of electricity, natural gas, water resources, thermal energy and renewable energy, provides an accurate and comprehensive data basis for subsequent carbon emission accounting, and ensures the accuracy and reliability of the accounting; pre-processes the collected energy consumption data and establishes an autoregressive integral sliding average model to predict energy consumption trends, which helps enterprises or institutions to carry out effective energy management and planning; and uses the pre-processed data to preliminarily generate carbon emission factors and calculate the current carbon emissions, which lays the foundation for the accurate calculation of carbon emissions and helps to timely discover and deal with related problems; by constructing a reinforcement learning model and interactively learning with the environment The optimal strategy iteratively optimizes the initially generated carbon emission factors, improves the accuracy and adaptability of the factors, makes carbon emission accounting more accurate, and can dynamically adjust the strategy to adapt to changes in the external environment; uses the optimized carbon emission factors to calculate carbon emissions and transmits them to the monitoring center through encryption, ensuring the real-time and security of the data, so that the monitoring center can carry out effective monitoring and management in a timely manner; and by setting carbon emission thresholds, comparing the monitoring data with the thresholds in real time, it realizes graded early warning of abnormal carbon emissions, can promptly detect abnormal fluctuations and take corresponding measures; matches emission reduction recommendations based on early warning results, provides solutions for abnormal carbon emissions, reduces carbon emissions, and promotes sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 work, among which:

[0049] Figure 1 An overall flow chart of a carbon emission accounting system based on metering is provided for one embodiment of the present invention.

[0050] Figure 2 A system solution flow chart of a carbon emission accounting system based on metering is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a carbon emission accounting system based on metering, including: an energy consumption data acquisition module M100, a data preprocessing module M200, an energy consumption trend prediction module M300, a carbon emission factor generation and optimization module M400, a real-time monitoring and early warning module M500, and an emission reduction optimization suggestion module M600;

[0058] S1: Energy consumption data is acquired through the energy consumption data acquisition module, and outlier processing, missing data filling and unit standardization are performed on the collected energy consumption data through the data preprocessing module; the processed energy consumption data is modeled through the energy consumption trend prediction module to predict the energy consumption trend.

[0059] The obtaining of energy consumption data includes obtaining electricity consumption data, natural gas consumption data, water resource consumption data, thermal energy consumption data and renewable energy consumption data.

[0060] The electricity consumption data includes meter readings, electricity consumption time periods and peak and valley electricity price information; the natural gas consumption data includes meter readings, gas usage time and gas source type; the water resource consumption data includes meter readings, water usage and usage time; the thermal energy consumption data includes the usage of central heating, steam and hot water; the renewable energy consumption data includes the consumption of solar energy, wind energy and nuclear energy.

[0061] The energy consumption data acquisition module M100 is used to obtain energy consumption data of electricity, natural gas, water resources, thermal energy and renewable energy. Through energy acquisition, comprehensive monitoring of various energy consumption situations is achieved, providing an accurate and comprehensive data basis for subsequent carbon emission accounting, ensuring the accuracy and reliability of the accounting.

[0062] It should be noted that the prediction of energy consumption trend includes preprocessing the acquired energy consumption data, modeling using an autoregressive integrated moving average model in combination with seasonal factors and external variables, and predicting the energy consumption trend based on the established model.

[0063] The preprocessing includes using statistical analysis methods to process outliers, filling missing data using interpolation methods, and standardizing energy consumption data of different units; the data preprocessing module M200 is used to process outliers, fill missing data and standardize units of the collected energy consumption data.

[0064] The autoregressive integrated moving average model formula is expressed as:

[0065] ;

[0066] in, is the energy consumption data at time point t, t is time, is a constant term, , , , is the coefficient of the autoregressive part, is the error term, , , is the coefficient of the moving average part, p is the number of autoregressive terms, q is the number of moving average terms, s is the seasonal period, , For time point , 2. , Energy consumption data, , , For time point , , Energy consumption data of q.

[0067] The energy consumption trend prediction formula is:

[0068] ;

[0069] in, is the prediction for the future k moments, is the predicted value at the time point before the predicted time point, is the prediction formula, is the external variable adopted at time point t.

[0070] The energy consumption trend prediction module M300 is used to predict energy consumption trends using the autoregressive integrated moving average model, generate prediction results through historical energy consumption data analysis, and predict future energy demand in combination with seasonal factors and external variables.

[0071] The collected energy consumption data is preprocessed and an autoregressive integrated moving average model is established to predict energy consumption trends, which helps to carry out effective energy management and planning. On this basis, the preprocessed data is used to generate a preliminary carbon emission factor and calculate the current carbon emissions, which lays the foundation for the accurate calculation of carbon emissions and helps to promptly discover and deal with related problems.

[0072] S2: Analyze energy consumption data through the carbon emission factor generation and optimization module, generate preliminary carbon emission factors according to different energy types and consumption, introduce reinforcement learning algorithm, and iteratively optimize the preliminary carbon emission factors.

[0073] Furthermore, the generating of the preliminary carbon emission factor includes generating the preliminary carbon emission factor according to different energy types and consumption amounts using the preprocessed energy consumption data, and calculating the current carbon emissions using the energy consumption data and the preliminary carbon emission factor.

[0074] The formula for generating the preliminary carbon emission factor is expressed as:

[0075] ;

[0076] ;

[0077] in, is the preliminary carbon emission factor, is the baseline emission value of energy, is the carbon emission factor adjustment function, is the energy output, is the climate influencing factor, is the impact factor of socioeconomic data, and j is the variable index.

[0078] The formula for calculating the current carbon emissions is:

[0079] ;

[0080] in, is the current carbon emissions, is the energy consumption, is the preliminary carbon emission factor.

[0081] Furthermore, the iterative optimization includes, after generating the preliminary carbon emission factor, constructing a reinforcement learning model, learning the optimal strategy by interacting with the environment, iteratively optimizing the generated preliminary carbon emission factor, and outputting the optimized carbon emission factor; by constructing a reinforcement learning model and learning the optimal strategy by interacting with the environment, the preliminary generated carbon emission factor is iteratively optimized, thereby improving the accuracy and adaptability of the factor, making carbon emission accounting more accurate, and being able to dynamically adjust the strategy to adapt to changes in the external environment.

[0082] The construction of the reinforcement learning model includes defining a state space consisting of energy consumption, preliminary carbon emission factors of energy and external environmental factors, defining a workspace including three adjustment measures of the carbon emission factors, and setting a reward function to reflect the impact of external environmental data.

[0083] The reward function formula is:

[0084] ;

[0085] ;

[0086] Among them, R is the reward obtained, is the current carbon emissions, is the original carbon emissions, is the weight factor, is the external environment influence function, is the regulating factor, For external environmental factors.

[0087] The interactive learning with the environment includes obtaining current energy consumption data and initial carbon emission factor data, forming an initial state, and selecting an execution action based on the current state and the strategy obtained by the reinforcement learning algorithm. After executing the selected action, the carbon emission factor is updated, and the new state after the execution of the action is observed. The current carbon emissions are recalculated, and a new state is obtained. The reward is calculated for feedback, and the current action is scored, the strategy is updated, and the action selection, execution, observation of the new state, feedback of rewards and model parameter update steps are repeated until the optimization goal is reached.

[0088] The carbon emission factor generation and optimization module M400 is used to generate preliminary carbon emission factors according to different energy types and consumption, and perform iterative optimization using an optimization algorithm.

[0089] The selection of an execution action includes increasing the carbon emission factor of energy, reducing the carbon emission factor of energy, and not changing the carbon emission factor of energy; the scoring formula for the current action is:

[0090] ;

[0091] Among them, Z is the action score, R is the reward obtained, is the discount factor, is the current estimated value, is the current state, For the selected action, It is the maximum evaluation value for selecting an action in a new state; when the score is lower than 50 points, the model parameters are updated and the strategy is adjusted immediately; when the score is greater than or equal to 50 points, the current strategy and model parameters are maintained.

[0092] The strategy adjustment formula is:

[0093] ;

[0094] in, is the updated estimated value, is the learning rate, Z is the action score, The current estimated value.

[0095] S3: The real-time monitoring and early warning module uses the optimized carbon emission factors to calculate carbon emissions, transmits the carbon emissions to the monitoring center in real time, sets thresholds for comparison, and issues real-time early warnings for abnormal carbon emissions. When abnormal carbon emissions occur, the emission reduction optimization suggestion module matches the early warning results and automatically generates emission reduction suggestions.

[0096] Furthermore, the real-time transmission of carbon emissions to the monitoring center includes: outputting an optimized carbon emission factor according to the model, calculating the carbon emissions through the emission factor, and transmitting the carbon emissions to the monitoring center in real time; the real-time monitoring and early warning module M500 is used to transmit the optimized carbon emissions to the monitoring center in real time, set a carbon emission threshold, compare the monitored carbon emissions with the set threshold in real time, and perform graded early warning.

[0097] Real-time carbon emissions transmission includes encapsulating the calculated carbon emissions into a data packet for transmission, encrypting the data packet using the AES encryption algorithm, generating an encryption key, establishing an encrypted transmission channel between the data sender and the monitoring center using a secure transmission protocol, and confirming whether the server certificate of the monitoring center is valid. The encrypted data packet is sent to the monitoring center through the established encrypted transmission channel. After receiving the encrypted data, the monitoring center uses the corresponding decryption algorithm and key to decrypt the data packet. After decryption, the carbon emissions are verified for integrity using a hash function, and the decrypted and verified carbon emissions are stored in the monitoring center's data warehouse.

[0098] The carbon emissions are calculated using the optimized carbon emission factors and transmitted to the monitoring center through encryption, ensuring the real-time and security of the data, allowing the monitoring center to conduct effective monitoring and management in a timely manner.

[0099] Furthermore, the matching of emission reduction suggestions includes setting a carbon emission threshold, comparing the transmitted carbon emissions with the carbon emission threshold in real time, making graded warnings for abnormal carbon emissions through comparison, and matching emission reduction suggestions according to the warning results.

[0100] The setting of the carbon emission threshold includes setting the daily carbon emission threshold at 500 kg, the weekly carbon emission threshold at 3,000 kg, and the monthly carbon emission threshold at 12,000 kg. When the real-time monitored carbon emissions exceed the set threshold, the alarm mechanism is triggered. When the carbon emissions are between 105% and 110% of the threshold, the carbon emissions are determined to be in the warning range, and the responsible person is notified via SMS to remind him to pay attention to the emissions; when the carbon emissions are between 110% and 150% of the threshold, the carbon emissions are determined to be in the severe warning range, and an emergency notice is immediately issued for review and response; when the carbon emissions exceed 150%, the carbon emissions are determined to be in the critical warning range, and an emergency notice is sent to require immediate action and on-site inspection.

[0101] The emission reduction proposals include reducing fossil fuel combustion when carbon emission warnings are triggered, switching to renewable solar and wind energy, improving production processes, and capturing and storing emitted carbon dioxide.

[0102] The improved production process includes conducting a comprehensive energy audit, evaluating the energy consumption and carbon emissions in the current production process, identifying energy waste links, optimizing equipment operating parameters, redesigning the production process, reducing energy-intensive steps, and replacing old and inefficient equipment; by setting carbon emission thresholds and comparing monitoring data with the thresholds in real time, a graded early warning for abnormal carbon emissions is achieved, abnormal fluctuations can be detected in time and corresponding measures can be taken; and emission reduction recommendations are matched according to the early warning results to provide solutions for abnormal carbon emissions.

[0103] The emission reduction optimization suggestion module M600 is used to automatically generate emission reduction suggestions by matching corresponding emission reduction strategies according to early warning results when abnormal carbon emissions occur.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0105] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the system described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A carbon emission accounting system based on measurement, characterized by: It includes energy consumption data acquisition module, data preprocessing module, energy consumption trend prediction module, carbon emission factor generation and optimization module, real-time monitoring and early warning module and emission reduction optimization suggestion module; The energy consumption data acquisition module acquires energy consumption data; the data preprocessing module performs outlier processing, missing data filling and unit standardization on the collected energy consumption data; The energy consumption trend prediction module models the processed energy consumption data and predicts the energy consumption trend; The carbon emission factor generation and optimization module analyzes the energy consumption data, generates preliminary carbon emission factors according to different energy types and consumption, introduces a reinforcement learning algorithm, and iteratively optimizes the preliminary carbon emission factors; The iterative optimization includes, after generating the preliminary carbon emission factor, constructing a reinforcement learning model, learning the optimal strategy through interaction with the environment, iteratively optimizing the generated preliminary carbon emission factor, and outputting the optimized carbon emission factor; The construction of the reinforcement learning model includes defining a state space consisting of energy consumption, preliminary carbon emission factors of energy and external environmental factors, defining a workspace including three adjustment measures of the carbon emission factors, and setting a reward function to reflect the influence of external environmental data; Set the reward function formula to: ； ； Among them, R is the reward obtained, is the current carbon emissions, is the original carbon emissions, is the weight factor, is the external environment influence function, is the regulating factor, External environmental factors; The interactive learning with the environment includes obtaining current energy consumption data and initial carbon emission factor data, forming an initial state, and selecting an execution action according to the current state and the strategy obtained by the reinforcement learning algorithm. After executing the selected action, the carbon emission factor is updated, the new state after the execution of the action is observed, the current carbon emissions are recalculated, and a new state is obtained. The reward is calculated for feedback, and the current action is scored, the strategy is updated, and the steps of selecting an action, executing an action, observing a new state, feeding back a reward, and updating model parameters are repeated until the optimization goal is achieved; The selection of an execution action includes increasing the carbon emission factor of energy, reducing the carbon emission factor of energy, and not changing the carbon emission factor of energy; the scoring formula for the current action is: ； Among them, Z is the action score, R is the reward obtained, is the discount factor, is the current estimated value, is the current state, For the selected action, The maximum evaluation value of the action selected in the new state; when the score is less than 50 points, the model parameters are updated and the strategy is adjusted immediately; when the score is greater than or equal to 50 points, the current strategy and model parameters are maintained; The strategy adjustment formula is: ； in, is the updated estimated value, is the learning rate, Z is the action score, is the current estimated value; The real-time monitoring and early warning module calculates carbon emissions using the optimized carbon emission factors, transmits the carbon emissions to the monitoring center in real time, sets thresholds for comparison, and warns of abnormal carbon emissions in real time; When abnormal carbon emissions occur, the emission reduction optimization suggestion module matches emission reduction suggestions according to early warning results and automatically generates emission reduction suggestions.

2. A carbon emission accounting system based on measurement as claimed in claim 1, characterized in that: The obtaining of energy consumption data includes obtaining electricity consumption data, natural gas consumption data, water resource consumption data, thermal energy consumption data and renewable energy consumption data; The electricity consumption data includes meter readings, electricity consumption time periods and peak and valley electricity price information; the natural gas consumption data includes meter readings, gas usage time and gas source type; the water resource consumption data includes meter readings, water usage and usage time; the thermal energy consumption data includes the usage of central heating, steam and hot water; the renewable energy consumption data includes the consumption of solar energy, wind energy and nuclear energy.

3. A carbon emission accounting system based on measurement as claimed in claim 2, characterized in that: The energy consumption trend prediction includes preprocessing the acquired energy consumption data, using an autoregressive integrated moving average model in combination with seasonal factors and external variables to build a model, and predicting the energy consumption trend according to the established model; The preprocessing includes using statistical analysis methods to process outliers, filling missing data with interpolation methods, and standardizing energy consumption data of different units; The autoregressive integrated moving average model formula is expressed as: ； in, is the energy consumption data at time point t, t is time, is a constant term, , , , is the coefficient of the autoregressive part, is the error term, , , is the coefficient of the sliding average part, p is the number of autoregressive terms, q is the number of sliding average terms, s is the seasonal period, , For time point , 2. , Energy consumption data, , , For time point , , Energy consumption data of q; The energy consumption trend prediction formula is: ； in, is the prediction for the future k moments, is the predicted value at the time point before the predicted time point, is the prediction formula, is the external variable adopted at time point t.

4. A carbon emission accounting system based on measurement as claimed in claim 3, characterized in that: Generating the preliminary carbon emission factor includes generating the preliminary carbon emission factor according to different energy types and consumption amounts using the preprocessed energy consumption data, and calculating the current carbon emission amount using the energy consumption data and the preliminary carbon emission factor; The formula for generating the preliminary carbon emission factor is expressed as: ； ； in, is the preliminary carbon emission factor, is the baseline emission value of energy, is the carbon emission factor adjustment function, is the energy output, is the climate influencing factor, is the impact factor of socioeconomic data, j is the variable index; The formula for calculating the current carbon emissions is: ； in, is the current carbon emissions, is the energy consumption, is the preliminary carbon emission factor.

5. The carbon emission accounting system based on measurement as claimed in claim 1, characterized in that: The real-time transmission of the carbon emissions to the monitoring center includes: outputting the optimized carbon emission factor according to the model, calculating the carbon emissions by the emission factor, and transmitting the carbon emissions to the monitoring center in real time; Real-time carbon emissions transmission includes encapsulating the calculated carbon emissions into a data packet for transmission, encrypting the data packet using the AES encryption algorithm, generating an encryption key, establishing an encrypted transmission channel between the data sender and the monitoring center using a secure transmission protocol, and confirming whether the server certificate of the monitoring center is valid. The encrypted data packet is sent to the monitoring center through the established encrypted transmission channel. After receiving the encrypted data, the monitoring center uses the corresponding decryption algorithm and key to decrypt the data packet. After decryption, the carbon emissions are verified for integrity using a hash function, and the decrypted and verified carbon emissions are stored in the monitoring center's data warehouse.

6. A carbon emission accounting system based on measurement as claimed in claim 5, characterized in that: The matching of emission reduction suggestions includes setting a carbon emission threshold, comparing the transmitted carbon emission with the carbon emission threshold in real time, making graded warnings for abnormal carbon emission situations through comparison, and matching emission reduction suggestions according to the warning results; The setting of the carbon emission threshold includes setting the daily carbon emission threshold to 500 kg, the weekly carbon emission threshold to 3,000 kg, and the monthly carbon emission threshold to 12,000 kg. When the real-time monitored carbon emissions exceed the set threshold, the alarm mechanism is triggered. When the carbon emissions are between 105% and 110% of the threshold, the carbon emissions are judged to be in the warning range, and the responsible person is notified via SMS to remind him to pay attention to the emission situation; when the carbon emissions are between 110% and 150% of the threshold, the carbon emissions are judged to be in the severe warning range, and an emergency notice is immediately issued for review and response; when the carbon emissions exceed 150%, the carbon emissions are judged to be in the critical warning range, and an emergency notice is sent to require immediate action and on-site inspection; The emission reduction proposals include reducing fossil fuel combustion when carbon emission warnings are triggered, switching to renewable solar and wind energy, improving production processes, and capturing and storing emitted carbon dioxide.

7. A carbon emission accounting system based on measurement as claimed in claim 6, characterized in that: The emission reduction proposals include reducing fossil fuel combustion and switching to renewable solar and wind energy when carbon emission warnings are triggered, improving production processes, and capturing and storing emitted carbon dioxide; The improved production processes include conducting energy audits, evaluating energy consumption and carbon emissions in the current production process, identifying energy waste links, optimizing equipment operating parameters, redesigning production processes, reducing energy-intensive steps, and replacing old and inefficient equipment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a carbon emission accounting system based on measurement according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a carbon emission accounting system based on measurement according to any one of claims 1 to 7 are implemented.

Images