Allocation metering method and device for carbon emission measurement and calculation, computer equipment and medium

Abstract

The invention relates to the technical field of carbon emission, and discloses an apportionment metering method and device for carbon emission calculation, computer equipment and a medium, and the method comprises the steps: collecting real-time monitoring data and external access data of a combined heat and power generation system, and extracting feature vectors from the real-time monitoring data and the external access data; calculating the information entropy of each feature in the feature vectors based on the feature vectors, and determining the weight of each feature based on the information entropy of each feature; obtaining a plurality of basic apportionment models from a preset basic apportionment model library; determining the weight of each basic sharing model based on the weight of each feature and a preset fuzzy rule base; and calculating electric power carbon emission and thermal energy carbon emission based on each basic apportionment model and the corresponding weight. According to the method, a multi-model dynamic fusion mechanism is adopted, the limitation of a traditional single method is broken through, the weight of each model is dynamically allocated through the entropy weight method, optimal allocation is achieved in combination with the preset fuzzy rule base, and accurate electric power carbon emission and thermal energy carbon emission are obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emissions, and particularly to an apportionment measurement method, device, computer equipment and medium for carbon emission measurement. Background Art

[0002] A combined heat and power (CHP) system improves energy efficiency by simultaneously producing electricity and heat, but the problem of carbon emission apportionment in it is complex. The traditional apportionment methods have the following problems: Method singularity: relying on a single apportionment standard and not considering multi-dimensional factors. Static calculation: unable to dynamically adapt to real-time changes such as fuel type, equipment efficiency, and operating conditions. Strong data dependence: manual input of data is prone to errors, lacking real-time performance and accuracy. Lack of traceability: it is difficult for traditional methods to verify the transparency and fairness of the apportionment results in the CHP system, resulting in the problem that carbon emission measurement and apportionment cannot be accurately achieved for heat supply and power generation in the CHP system. Summary of the Invention

[0003] In view of this, the present invention provides an apportionment measurement method, device, computer equipment and medium for carbon emission measurement to solve the problem that carbon emission measurement and apportionment cannot be accurately achieved for heat supply and power generation in the CHP system.

[0004] In the first aspect, the present invention provides an apportionment measurement method for carbon emission measurement, and the method includes:

[0005] Collect real-time monitoring data and externally accessed data of the CHP system, and extract feature vectors from the real-time monitoring data and externally accessed data;

[0006] Calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature;

[0007] Obtain a plurality of basic apportionment models from a preset basic apportionment model library;

[0008] Determine the weight of each basic apportionment model based on the weight of each feature and a preset fuzzy rule library;

[0009] Calculate the carbon emissions of electricity and heat based on each basic apportionment model and the corresponding weight.

[0010] A method for allocating and measuring carbon emissions provided by the present invention calculates the information entropy of each feature in the feature vector based on the feature vector, and determines the weight of each feature based on the information entropy of each feature; obtains multiple basic allocation models from a preset basic allocation model library, adopts a multi-model dynamic fusion mechanism to break through the limitations of traditional single methods, dynamically allocates the weights of each model through the entropy weight method, and combines a preset fuzzy rule library to achieve optimal allocation, obtaining accurate carbon emissions from electricity and heat, and solving the problem that it is impossible to accurately measure and allocate carbon emissions for heating and power generation in a cogeneration system.

[0011] In an optional implementation manner, the real-time monitoring data includes the heat-electricity ratio, the equipment load rate, and the fuel carbon emission factor, and the externally connected data includes the heat / electricity market price ratio and the policy constraint coefficient;

[0012] Extract feature vectors from the real-time monitoring data and the externally connected data, including:

[0013] Take the heat-electricity ratio, the equipment load rate, the fuel carbon emission factor, the heat / electricity market price ratio, and the policy constraint coefficient as multiple features;

[0014] After normalizing each feature, a feature vector is obtained.

[0015] Beneficial effects

[0016] In an optional implementation manner, calculating the information entropy of each feature in the feature vector based on the feature vector, and determining the weight of each feature based on the information entropy of each feature, includes:

[0017] Calculate the probability that the value of each feature in the feature vector is a preset value;

[0018] Calculate the information entropy of each feature based on the probability;

[0019] Calculate the weight of each feature based on the information entropy of each feature.

[0020] A method for allocating and measuring carbon emissions provided by the present invention calculates the probability that the value of each feature in the feature vector is a preset value; calculates the information entropy of each feature based on the probability; achieves the purpose of calculating the weight of each feature based on the information entropy of each feature, providing conditions for subsequent determination of the weights of each basic allocation model.

[0021] In an optional implementation manner, obtaining multiple basic allocation models from a preset basic allocation model library, includes:

[0022] Obtain a first basic allocation model based on the heat method, a second basic allocation model based on the equivalent electricity method, and a third basic allocation model based on the economic value method from the preset basic allocation model library.

[0023] In an alternative embodiment, the first basic apportionment model based on the calorimetric method includes: a first power carbon emission sub-model and a first heat energy carbon emission sub-model; the second basic apportionment model based on the equivalent electricity method includes: a second power carbon emission sub-model and a second heat energy carbon emission sub-model; the third basic apportionment model based on the economic value method includes: a third power carbon emission sub-model and a third heat energy carbon emission sub-model.

[0024] A method for apportioning and measuring carbon emissions provided by the present invention realizes a multi-model dynamic fusion mechanism by determining the basic apportionment sub-models of power emissions and heat energy emissions, breaking through the limitations of traditional single apportionment methods.

[0025] In an alternative embodiment, the preset fuzzy rule base includes IF-THEN rules;

[0026] Determining the weights of each basic apportionment model based on the weights of each feature and the preset fuzzy rule base includes:

[0027] Determining the weights of the first power carbon emission sub-model, the second power carbon emission sub-model, and the third power carbon emission sub-model respectively based on the weights of each feature and the IF-THEN rules;

[0028] Determining the weights of the first heat energy carbon emission sub-model, the second heat energy carbon emission sub-model, and the third heat energy carbon emission sub-model respectively based on the weights of each feature and the IF-THEN rules.

[0029] In an alternative embodiment, calculating power carbon emissions and heat energy carbon emissions based on each basic apportionment model and its corresponding weight includes:

[0030] Calculating power carbon emissions based on the first power carbon emission sub-model and its corresponding weight, based on the second power carbon emission sub-model and its corresponding weight, and based on the third power carbon emission sub-model and its corresponding weight;

[0031] Calculating heat energy carbon emissions based on the first heat energy carbon emission sub-model and its corresponding weight, based on the second heat energy carbon emission sub-model and its corresponding weight, and based on the third heat energy carbon emission sub-model and its corresponding weight.

[0032] A method for apportioning and measuring carbon emissions provided by the present invention uses historical data to train a model, predicts the optimal apportionment strategy under different working conditions, reduces manual intervention, achieves the purpose of accurately calculating power carbon emissions and heat energy carbon emissions, and has high processing efficiency.

[0033] In a second aspect, the present invention provides an apparatus for apportioning and measuring carbon emissions, and the apparatus includes:

[0034] A data acquisition and feature vector extraction module, which is used to collect real-time carbon emission monitoring data and externally connected data, and extract feature vectors from the real-time carbon emission monitoring data and the externally connected data;

[0035] A weight determination module, which is used to calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature;

[0036] A basic apportionment model acquisition module, which is used to obtain multiple basic apportionment models from a preset basic apportionment model library;

[0037] A basic apportionment model weight determination module, which is used to determine the weight of each basic apportionment model based on the weight of each feature and a preset fuzzy rule library;

[0038] A carbon emission apportionment measurement module, which is used to calculate the electricity carbon emission and heat energy carbon emission based on each basic apportionment model and the corresponding weight.

[0039] Thirdly, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the carbon emission measurement and apportionment method according to the first aspect or any corresponding embodiment thereof.

[0040] Fourthly, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the carbon emission measurement and apportionment method according to the first aspect or any corresponding embodiment thereof.

[0041] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the carbon emission measurement and apportionment method according to the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0042] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 is a flowchart of the carbon emission measurement and apportionment method according to an embodiment of the present invention;

[0044] Figure 2 is a flowchart of another carbon emission measurement and apportionment method according to an embodiment of the present invention;

[0045] Figure 3 It is a schematic flowchart of another method for allocating and measuring carbon emissions according to an embodiment of the present invention;

[0046] Figure 4 It is a structural block diagram of an apparatus for allocating and measuring carbon emissions according to an embodiment of the present invention;

[0047] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0048] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] According to an embodiment of the present invention, an embodiment of a method for allocating and measuring carbon emissions is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0050] In this embodiment, a method for allocating and measuring carbon emissions is provided, which can be used in a cogeneration system. The cogeneration system includes a data acquisition layer, an intelligent allocation core algorithm layer, a blockchain evidence storage and verification layer, and a visualization and decision support layer. Figure 1 It is a flowchart of the method for allocating and measuring carbon emissions according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0051] Step S101, collect real-time monitoring data and externally accessed data of the cogeneration system, and extract feature vectors from the real-time monitoring data and the externally accessed data.

[0052] Specifically, the real-time monitoring data and externally connected data of the cogeneration system are collected through the data acquisition layer. The data acquisition layer includes primary data acquisition and secondary data acquisition. Primary data acquisition mainly aims at directly obtaining real-time monitoring data through physical probes and sensors, such as parameters like carbon dioxide concentration, flue gas flow rate, temperature, humidity, pressure, thermoelectric ratio, equipment load rate, and fuel carbon emission factor. Secondary data acquisition refers to the data accessed through external database interfaces, that is, externally connected data, such as parameters like grid dispatching data, heat network demand data, heat / electricity market price ratio, and policy constraint coefficient.

[0053] Feature vectors are obtained through data processing of the real-time monitoring data and externally connected data.

[0054] Step S102: Calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature.

[0055] Specifically, Information Entropy is a basic concept in information theory, used to quantify the uncertainty or randomness of information, aiming to solve the problem of quantitative measurement of information.

[0056] The intelligent sharing core algorithm layer includes a dynamic weight allocation mechanism. Through the dynamic weight allocation mechanism of the intelligent sharing core algorithm layer, the information entropy of each feature in the feature vector is calculated based on the feature vector, and the weight of each feature is determined based on the information entropy of each feature.

[0057] Step S103: Obtain multiple basic sharing models from the preset basic sharing model library.

[0058] Specifically, the intelligent sharing core algorithm layer also includes a basic sharing model library. In the basic sharing model library, there are basic sharing models based on the heat method, basic sharing models based on the equivalent electricity method, and basic sharing models based on the economic value method.

[0059] Step S104: Determine the weight of each basic sharing model based on the weight of each feature and the preset fuzzy rule library.

[0060] Specifically, the preset fuzzy rule library includes IF-THEN rules. The entropy weight method and IF-THEN rules are used to determine the weight of each basic sharing model according to the real-time working conditions. For example:

[0061] IF the thermoelectric ratio > 2 AND the remaining carbon quota < 10% THEN increase the weight of the basic sharing model based on the equivalent electricity method.

[0062] IF the heat price volatility > 15% THEN increase the weight of the basic sharing model based on the economic value method.

[0063] Step S105: Calculate the electricity carbon emissions and heat carbon emissions based on each basic sharing model and the corresponding weights.

[0064] Specifically, calculate the product of each basic sharing model and the corresponding weight and then sum them up to obtain the electricity carbon emission data and the heat carbon emission data respectively.

[0065] The sharing measurement method for carbon emission calculation provided in this embodiment calculates the information entropy of each feature in the feature vector based on the feature vector, and determines the weight of each feature based on the information entropy of each feature; obtains multiple basic sharing models from the preset basic sharing model library, adopts a multi-model dynamic fusion mechanism, breaks through the limitations of traditional single methods, dynamically allocates the weights of each model through the entropy weight method, and combines the preset fuzzy rule library to achieve optimal sharing, obtaining accurate electricity carbon emissions and heat carbon emissions, and solving the problem that carbon emission measurement and sharing cannot be accurately achieved for heat supply and power generation in a cogeneration system.

[0066] In this embodiment, a sharing measurement method for carbon emission calculation is provided, which can be used in a cogeneration system. The cogeneration system includes a data acquisition layer, an intelligent sharing core algorithm layer, a blockchain deposit and verification layer, and a visualization and decision support layer. Figure 2 It is a flowchart of the sharing measurement method for carbon emission calculation according to an embodiment of the present invention. As Figure 2 shown, the process includes the following steps:

[0067] Step S201: Collect the real-time monitoring data and external access data of the cogeneration system, and extract the feature vector from the real-time monitoring data and external access data.

[0068] Specifically, the real-time monitoring data includes the heat-electricity ratio (Q h / Q e ), the equipment load rate (%), and the fuel carbon emission factor (unit: kgCO / MJ). The external access data includes the heat / electricity market price ratio (Vh / Ve) and the policy constraint coefficient. The policy constraint coefficient can be a carbon quota limit. The above step S201 includes:

[0069] Step S2011: Take the heat-electricity ratio, the equipment load rate, the fuel carbon emission factor, the heat / electricity market price ratio, and the policy constraint coefficient as multiple features.

[0070] Step S2012: After normalizing and standardizing each feature, obtain the feature vector.

[0071] Specifically, normalize the obtained features according to the relevant normalization standard formula to obtain the feature vector. The specific normalization formula is a mature technology and will not be elaborated here.

[0072] The final eigenvector is expressed by the formula: X = [x1, x2,..., xn], where x1, x2,..., xn represent characteristics such as the heat-electricity ratio, equipment load rate, fuel carbon emission factor, heat / electricity market price ratio, and policy constraint coefficient, respectively.

[0073] Step S202: Calculate the information entropy of each feature in the eigenvector based on the eigenvector, and determine the weight of each feature based on the information entropy of each feature.

[0074] Specifically, the above step S202 includes:

[0075] Step S2021: Calculate the probability that each feature takes a preset value in the eigenvector.

[0076] Specifically, based on each normalized vector, calculate the probability that each feature takes a preset value in the eigenvector. The formula is expressed as:

[0077]

[0078] where p ij is the probability, x ij is each eigenvalue in the eigenvector, i represents a certain feature (such as the heat-electricity ratio, load rate, heat / electricity market price ratio (V h / V e ), and jj represents different historical feature data under a certain feature. In this embodiment, the heat-electricity ratio, load rate, and heat / electricity market price ratio are mainly considered for calculation.

[0079] Step S2022: Calculate the information entropy of each feature based on the probability.

[0080] Specifically, the formula for calculating the information entropy of each feature based on the probability is as follows:

[0081]

[0082] where: E j is the information entropy of each feature, and m represents the number of different eigenvector ps.

[0083] Step S2023: Calculate the weight of each feature based on the information entropy of each feature.

[0084] Specifically, the formula for calculating the weight of each feature based on the information entropy of each feature is as follows:

[0085]

[0086] where w j is the weight of each feature, reflecting the importance of each feature.

[0087] Step S203: Obtain multiple basic allocation models from a preset basic allocation model library.

[0088] Specifically, the above-mentioned step S202 includes:

[0089] Step a: Obtain a first basic allocation model based on the heat method, a second basic allocation model based on the equivalent electricity method, and a third basic allocation model based on the economic value method from the preset basic allocation model library.

[0090] Among them, the first basic allocation model based on the heat method includes: a first power carbon emission sub-model and a first heat energy carbon emission sub-model; the second basic allocation model based on the equivalent electricity method includes: a second power carbon emission sub-model and a second heat energy carbon emission sub-model; the third basic allocation model based on the economic value method includes: a third power carbon emission sub-model and a third heat energy carbon emission sub-model.

[0091] The formulas of each sub-model are as follows:

[0092] a1. In the heat method, the power carbon emission of the first power carbon emission sub-model and the heat energy carbon emission of the first heat energy carbon emission sub-model h The formula is expressed as follows:

[0093]

[0094] Among them, Q e and Q h respectively represent the heat value of power output and the heat value of heat energy output, with the unit of MJ.

[0095] a2. In the equivalent electricity method,

[0096] First, calculate the equivalent electricity, and the formula is as follows:

[0097]

[0098] Among them, η ref represents the power generation efficiency of the reference power plant.

[0099] Determine the power carbon emission of the second power carbon emission sub-model e and the heat energy carbon emission of the second heat energy carbon emission sub-model e based on the equivalent electricity, and the formula is expressed as follows:

[0100]

[0101] Among them, E e represents the unit standard coal power generation of the cogeneration unit.

[0102] a3. In the economic value method, the formulas of the third power carbon emission sub-model and the third heat energy carbon emission sub-model are expressed as follows:

[0103]

[0104] Among them, V e and V h respectively represent the market price of electricity and the market price of heat energy.

[0105] Step S204, determine the weight of each basic sharing model based on the weight of each feature and the preset fuzzy rule base. For details, please refer to Figure 1 Step S104 of the illustrated embodiment, which will not be elaborated here.

[0106] Step S205, calculate the carbon emissions of electricity and the carbon emissions of heat energy based on each basic sharing model and the corresponding weight. For details, please refer to Figure 1 Step S105 of the illustrated embodiment, which will not be elaborated here.

[0107] The sharing measurement method for carbon emission measurement provided in this embodiment calculates the probability that the value of each feature in the feature vector is a preset value; calculates the information entropy of each feature based on the probability; achieves the purpose of calculating the weight of each feature based on the information entropy of each feature, provides conditions for determining the weight of each basic sharing model subsequently, and realizes a multi-model dynamic fusion mechanism by determining the basic sharing sub-models of electricity emissions and heat energy emissions, breaking through the limitations of traditional single sharing methods.

[0108] In this embodiment, a sharing measurement method for carbon emission measurement is provided, which can be used in a cogeneration system. The cogeneration system includes a data acquisition layer, an intelligent sharing core algorithm layer, a blockchain evidence storage and verification layer, and a visualization and decision support layer. Figure 3 is a flowchart of the sharing measurement method for carbon emission measurement according to an embodiment of the present invention. As Figure 3 shown, the process includes the following steps:

[0109] Step S301, collect the real-time monitoring data and external access data of the cogeneration system, and extract the feature vector from the real-time monitoring data and external access data. For details, please refer to Figure 2 Step S201 of the illustrated embodiment, which will not be elaborated here.

[0110] Step S302, calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature. For details, please refer to Figure 2 Step S202 of the illustrated embodiment, which will not be elaborated here.

[0111] Step S303, obtain multiple basic sharing models from the preset basic sharing model library. For details, please refer to Figure 2 Step S203 of the illustrated embodiment, which will not be elaborated here.

[0112] Step S304: Determine the weights of each basic sharing model based on the weights of each feature and the preset fuzzy rule base.

[0113] Specifically, the preset fuzzy rule base includes IF-THEN rules, and the above step S304 includes:

[0114] Step S3041: Determine the weights of the first power carbon emission sub-model, the second power carbon emission sub-model, and the third power carbon emission sub-model respectively based on the weights of each feature and the IF-THEN rules.

[0115] Specifically, the weights corresponding to the three features of the thermoelectric ratio, the load rate, and the heat / electricity market price ratio are: w h , w e , w v , respectively serving as the weight coefficients of the sub-models, and the sum of the three weights = 1;

[0116] For example, the calculation method of power carbon emissions: Power carbon emissions = w h · The first power carbon emission sub-model + w e · The second power carbon emission sub-model + w v · The third power carbon emission sub-model = w h · Power carbon emissions h + w e · Power carbon emissions e + w v · Power carbon emissions v .

[0117] Step S3042: Determine the weights of the first heat energy carbon emission sub-model, the second heat energy carbon emission sub-model, and the third heat energy carbon emission sub-model respectively based on the weights of each feature and the IF-THEN rules.

[0118] Specifically, for fuzzy logic adjustment, the IF-THEN rule is adopted:

[0119] IF the thermoelectric ratio > 2 AND the remaining carbon quota < 10% THEN increase the weight of the equivalent electricity method.

[0120] IF the heat price volatility > 15% THEN increase the weight of the economic value method.

[0121] Output the final model weight W = [w h , w e , w v , satisfying sumW = 1, that is, Σw h , w e , w v = 1.

[0122] Exemplarily, if the IF thermoelectric ratio > 2 AND the hotspot volatility > 15% THEN w v +0.2.

[0123] Output weight: W = [w h , w e , w v = W = [0.3 (calorimetric method), 0.2 (equivalent electric method), 0.5 (economic value method)].

[0124] Step S305, calculate the electricity carbon emissions and heat carbon emissions based on each basic allocation model and the corresponding weights.

[0125] Specifically, the above step S305 includes:

[0126] Step S3051, calculate the electricity carbon emissions based on the first electricity carbon emission sub-model and its corresponding weight, based on the second electricity carbon emission sub-model and its corresponding weight, and based on the third electricity carbon emission sub-model and its corresponding weight.

[0127] Specifically, electricity carbon emissions = w h · The first electricity carbon emission sub-model + w e · The second electricity carbon emission sub-model + w v · The third electricity carbon emission sub-model = w h · Electricity carbon emissions h + w e · Electricity carbon emissions e + w v · Electricity carbon emissions v .

[0128] Step S3052, calculate the heat carbon emissions based on the first heat carbon emission sub-model and its corresponding weight, based on the second heat carbon emission sub-model and its corresponding weight, and based on the third heat carbon emission sub-model and its corresponding weight.

[0129] Specifically, heat carbon emissions = w h · The first heat carbon emission sub-model + w e · The second heat carbon emission sub-model + w v · The third heat carbon emission sub-model = w h · Heat carbon emissions h + w e · Heat carbon emissions e + w v · Heat carbon emissions v .

[0130] It should be noted that after calculating the electricity carbon emissions and heat carbon emissions, the allocation results are transmitted to the blockchain evidence storage and verification layer and the visualization and decision support layer. The blockchain technology of the blockchain evidence storage and verification layer is used to enhance data security and reliability. The hash value of the allocation results is uploaded to the blockchain to ensure data transparency and audit traceability, and to solve the problem of insufficient credibility of traditional methods. The allocation results are displayed in real time on the visualization and decision support layer.

[0131] The allocation measurement method for carbon emission measurement provided in this embodiment uses historical data to train a model, predicts the optimal allocation strategy under different working conditions, reduces manual intervention, achieves the purpose of accurately calculating electricity carbon emissions and heat carbon emissions, and has high processing efficiency.

[0132] As one or more specific application embodiments of the present invention, the allocation measurement method for carbon emission measurement provided by the present invention is further described in detail as follows:

[0133] (1) Data collection can be divided into primary data collection and secondary data collection. Primary data mainly refers to real-time monitoring data directly obtained through physical probes and sensors, such as parameters like carbon dioxide concentration, flue gas flow rate, temperature, humidity, pressure, thermoelectric ratio, equipment load rate, and fuel carbon emission factor. Secondary data collection refers to data accessed through an external database interface, that is, externally accessed data, such as accessing grid dispatching data, heat network demand data, heat / electricity market price ratio, and policy constraint coefficient and other parameters.

[0134] (2) Intelligent allocation core algorithm layer: mainly includes a basic allocation model library, a dynamic weight allocation mechanism, a machine learning optimization module, and algorithm correction. Through multi-model fusion and dynamic optimization mechanism, accurate allocation of carbon emissions is achieved, integrating the advantages of various allocation models such as the comprehensive heat method, equivalent electricity method, and economic value method, and dynamically allocating weights to cope with complex working conditions. The specific steps are as follows:

[0135] 2.1 Basic allocation model library: The system internally sets the following classic models as basic allocation models, including:

[0136] Heat method:

[0137]

[0138] In the equivalent electricity method, first calculate the equivalent electricity, and the formula is as follows:

[0139]

[0140] Economic value method:

[0141]

[0142] 2.2 Dynamic Weight Allocation Mechanism: Adaptive Hybrid Weighting (AHW) is adopted, combining the entropy weight method and fuzzy logic control to dynamically adjust the weights of each basic sharing model. The specific steps are as follows:

[0143] 2.2.1 Feature Extraction: Extract the feature vector X = [x1, x2,..., xn], including: heat-electricity ratio (Qh / Qe), equipment load rate (%), fuel carbon emission factor (kgCO / MJ), heat / electricity market price ratio (Vh / Ve), and policy constraint coefficient (such as carbon quota limit).

[0144] 2.2.2 Calculate the Initial Weight by Entropy Weight Method:

[0145] Based on each normalized vector, calculate the probability that the value of each feature in the feature vector is a preset value. The formula is expressed as:

[0146]

[0147] The formula for calculating the information entropy of each feature based on the probability is as follows:

[0148]

[0149] The formula for calculating the weight of each feature based on the information entropy of each feature is as follows:

[0150]

[0151] 2.3 Fuzzy Logic Dynamic Correction: Define a fuzzy rule base (such as IF-THEN rules) to adjust the weights according to the real-time working conditions:

[0152] Example rules:

[0153] IF the heat-electricity ratio > 2 AND the remaining carbon quota < 10% THEN increase the weight of the equivalent electricity method.

[0154] IF the heat price volatility > 15% THEN increase the weight of the economic value method.

[0155] Output the final model weight W = [w h , w e , w v , satisfying sumW = 1, that is, ∑w h , w e , w v = 1.

[0156] 2.4 Fusion of Sharing Results:

[0157] Electricity carbon emission = w h · The first electricity carbon emission sub-model + w e· The second power carbon emission sub-model + w v · The third power carbon emission sub-model = w h · Power carbon emission h + w e · Power carbon emission e + w v · Power carbon emission v 。

[0158] Thermal energy carbon emission = w h · The first thermal energy carbon emission sub-model + w e · The second thermal energy carbon emission sub-model + w v · The third thermal energy carbon emission sub-model = w h · Thermal energy carbon emission h + w e · Thermal energy carbon emission e + w v · Thermal energy carbon emission v 。

[0159] Among them, · represents product calculation.

[0160] Taking a certain gas CHP plant during the peak heating period in winter as an example, the heat price increases and the heat-electricity ratio rises to 3:1.

[0161] 1. The extracted feature vector is:

[0162] X = [heat-electricity ratio = 3, equipment load rate = 95%, heat-electricity volatility (current heat price / market heat price) = +20%, carbon quota remaining = 5%].

[0163] 2. Entropy weight method calculation:

[0164] According to historical data, the weights of the heat-electricity ratio and heat price volatility are relatively high (w j = 0.4, 0.3).

[0165] 3. Fuzzy logic adjustment:

[0166] Trigger rule: IF heat-electricity ratio > 2 AND hot spot volatility > 15% THEN w v + 0.2.

[0167] Output weight:

[0168] W = [w h , w e , w v = W = [0.3 (heat method), 0.2 (equivalent electricity method), 0.5 (economic value method)].

[0169] The apportionment measurement method for carbon emission measurement provided by the embodiments of the present invention breaks through the limitations of traditional single apportionment methods, dynamically allocates the weights of each model through the entropy weight method, realizes optimal apportionment in combination with real-time working conditions, predicts the optimal apportionment strategy under different working conditions, and reduces manual intervention.

[0170] In this embodiment, an apportionment measurement device for carbon emission measurement is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0171] This embodiment provides an apportionment measurement device for carbon emission measurement, as Figure 4 shown, including:

[0172] A data acquisition and feature vector extraction module 401, configured to acquire real-time carbon emission monitoring data and externally connected data, and extract feature vectors from the real-time carbon emission monitoring data and the externally connected data.

[0173] A weight determination module 402, configured to calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature.

[0174] A basic apportionment model acquisition module 403, configured to acquire a plurality of basic apportionment models from a preset basic apportionment model library.

[0175] A basic apportionment model weight determination module 404, configured to determine the weight of each basic apportionment model based on the weight of each feature and a preset fuzzy rule library.

[0176] A carbon emission apportionment measurement module 405, configured to calculate electric power carbon emissions and heat energy carbon emissions based on each basic apportionment model and the corresponding weight.

[0177] In some alternative implementation manners, the real-time monitoring data includes the thermoelectric ratio, the equipment load rate, and the fuel carbon emission factor, and the externally connected data includes the heat / electricity market price ratio and the policy constraint coefficient; the data acquisition and feature vector extraction module 401 includes:

[0178] A feature extraction unit, configured to use the thermoelectric ratio, the equipment load rate, the fuel carbon emission factor, the heat / electricity market price ratio, and the policy constraint coefficient as multiple features.

[0179] A normalization unit, configured to perform normalization on each feature to obtain a feature vector.

[0180] In some alternative implementation manners, the weight determination module 402 includes:

[0181] A probability calculation unit for calculating the probability that each feature takes a preset value in the feature vector.

[0182] An information entropy calculation unit for calculating the information entropy of each feature based on the probability.

[0183] A weight calculation unit for calculating the weight of each feature based on the information entropy of each feature.

[0184] In some alternative embodiments, the basic apportionment model acquisition module 403 includes:

[0185] A basic apportionment model acquisition unit for obtaining a first basic apportionment model based on the heat method, a second basic apportionment model based on the equivalent electricity method, and a third basic apportionment model based on the economic value method from a preset basic apportionment model library. Among them, the first basic apportionment model based on the heat method includes: a first power carbon emission sub-model and a first heat energy carbon emission sub-model; the second basic apportionment model based on the equivalent electricity method includes: a second power carbon emission sub-model and a second heat energy carbon emission sub-model; the third basic apportionment model based on the economic value method includes: a third power carbon emission sub-model and a third heat energy carbon emission sub-model.

[0186] In some alternative embodiments, the preset fuzzy rule base includes IF-THEN rules; the basic apportionment model weight determination module 404 includes:

[0187] A power carbon emission sub-model weight calculation unit for respectively determining the weights of the first power carbon emission sub-model, the second power carbon emission sub-model, and the third power carbon emission sub-model based on the weight of each feature and the IF-THEN rules.

[0188] A heat energy carbon emission sub-model weight calculation unit for respectively determining the weights of the first heat energy carbon emission sub-model, the second heat energy carbon emission sub-model, and the third heat energy carbon emission sub-model based on the weight of each feature and the IF-THEN rules.

[0189] In some alternative embodiments, the carbon emission apportionment measurement module 405 includes:

[0190] A power carbon emission calculation unit for calculating the power carbon emission based on the first power carbon emission sub-model and its corresponding weight, based on the second power carbon emission sub-model and its corresponding weight, and based on the third power carbon emission sub-model and its corresponding weight.

[0191] A heat energy carbon emission calculation unit for calculating the heat energy carbon emission based on the first heat energy carbon emission sub-model and its corresponding weight, based on the second heat energy carbon emission sub-model and its corresponding weight, and based on the third heat energy carbon emission sub-model and its corresponding weight.

[0192] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding above embodiments, and will not be elaborated here.

[0193] The carbon emission measurement and sharing metering device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0194] An embodiment of the present invention also provides a computer device having the above Figure 4 shown carbon emission measurement and sharing metering device.

[0195] Please refer to Figure 5 , Figure 5 is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As Figure 5 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 5 Taking one processor 10 as an example in

[0196] The processor 10 can be a central processor, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0197] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0198] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device and the like. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0199] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memory.

[0200] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 5 Taking connection through a bus as an example.

[0201] The input device 30 can receive input digital or character information, and generate key signal inputs related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light-emitting diode, a display, and a plasma display. In some alternative embodiments, the display device may be a touch screen.

[0202] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0203] A part of the present invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the methods and / or technical solutions according to the present invention can be called or provided. Those skilled in the art should be able to understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0204] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A carbon emission measurement and allocation method, characterized in that: The method comprises: Collecting real-time monitoring data and external access data of the cogeneration system, and extracting feature vectors from the real-time monitoring data and the external access data; Calculating the information entropy of each feature in the feature vector based on the feature vector, and determining the weight of each feature based on the information entropy of each feature; Obtain multiple basic allocation models from a preset basic allocation model library; Determine the weight of each basic allocation model based on the weight of each feature and a preset fuzzy rule base; Electricity carbon emissions and thermal energy carbon emissions are calculated based on each basic allocation model and corresponding weights.

2. The method according to claim 1, characterized in that The real-time monitoring data includes heat-to-electricity ratio, equipment load rate and fuel carbon emission factor, and the external access data includes heat / electricity market price ratio and policy constraint coefficient; Extracting feature vectors from the real-time monitoring data and the external access data includes: taking the heat-to-electricity ratio, equipment load factor, fuel carbon emission factor, heat / electricity market price ratio and policy constraint coefficient as multiple features; Each feature is normalized to obtain a feature vector.

3. The method according to claim 1, characterized in that Calculating the information entropy of each feature in the feature vector based on the feature vector, and determining the weight of each feature based on the information entropy of each feature, including: Calculate the probability that each feature takes a preset value in the feature vector; Calculate the information entropy of each feature based on the probability; The weight of each feature is calculated based on the information entropy of each feature.

4. The method according to claim 1, characterized in that The step of obtaining multiple basic allocation models from a preset basic allocation model library includes: A first basic allocation model based on a heat method, a second basic allocation model based on an equivalent electricity method, and a third basic allocation model based on an economic value method are obtained from a preset basic allocation model library.

5. The method according to claim 4, characterized in that The first basic allocation model based on the heat method includes: a first electricity carbon emission sub-model and a first thermal energy carbon emission sub-model; the second basic allocation model based on the equivalent electricity method includes: a second electricity carbon emission sub-model and a second thermal energy carbon emission sub-model; the third basic allocation model based on the economic value method includes: a third electricity carbon emission sub-model and a third thermal energy carbon emission sub-model.

6. The method according to claim 5, characterized in that The preset fuzzy rule base includes IF-THEN rules; The step of determining the weight of each basic allocation model based on the weight of each feature and a preset fuzzy rule base includes: Determine the weight of the first electricity carbon emission sub-model, the weight of the second electricity carbon emission sub-model, and the weight of the third electricity carbon emission sub-model based on the weight of each feature and the IF-THEN rule; The weight of the first thermal energy carbon emission sub-model, the weight of the second thermal energy carbon emission sub-model and the weight of the third thermal energy carbon emission sub-model are determined respectively based on the weight of each feature and the IF-THEN rule.

7. The method according to claim 6, characterized in that The calculation of electricity carbon emissions and thermal energy carbon emissions based on each basic allocation model and corresponding weights includes: Calculate electricity carbon emissions based on a first electricity carbon emission sub-model and its corresponding weights, based on a second electricity carbon emission sub-model and its corresponding weights, and based on a third electricity carbon emission sub-model and its corresponding weights; Thermal energy carbon emissions are calculated based on the first thermal energy carbon emission sub-model and its corresponding weights, based on the second thermal energy carbon emission sub-model and its corresponding weights, and based on the third thermal energy carbon emission sub-model and its corresponding weights.

8. A carbon emission measurement and apportionment device, characterized in that: The device comprises: A data collection and feature vector extraction module, used to collect carbon emission real-time monitoring data and external access data, and extract feature vectors from the carbon emission real-time monitoring data and external access data; A weight determination module, used to calculate the information entropy of each feature in the feature vector based on the feature vector, and determine the weight of each feature based on the information entropy of each feature; A basic allocation model acquisition module is used to acquire multiple basic allocation models from a preset basic allocation model library; A basic allocation model weight determination module, used to determine the weight of each basic allocation model based on the weight of each feature and a preset fuzzy rule library; The carbon emission allocation and metering module is used to calculate electricity carbon emissions and thermal energy carbon emissions based on each basic allocation model and corresponding weights.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the carbon emission measurement and allocation method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the carbon emission measurement and allocation method according to any one of claims 1 to 7.

Images