Electric power carbon emission monitoring method, system and device and storage medium

Abstract

The invention is suitable for the technical field of carbon emission monitoring, and provides an electric power carbon emission monitoring method, system and device and a storage medium, and the method comprises the steps: obtaining the carbon emission source data of a power grid enterprise in a plurality of operation scenes; performing knowledge labeling on the carbon emission source data to extract position features, and extracting confidence features from the data after knowledge labeling; enhancing the position feature and the confidence feature by using a double attention mechanism to obtain a target variable; and generating a carbon emission monitoring result corresponding to the target variable according to the constructed index list for carbon emission monitoring of the power grid enterprise. According to the invention, through a data processing mode of extracting the data features and enhancing the features, a complex calculation process is avoided, and a carbon emission result can be generated by comparing the index lists on the basis of the processed data, so that the monitoring efficiency of carbon emission is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring, and in particular to a method, system, device and storage medium for monitoring carbon emission of electricity. Background Art

[0002] Carbon emission monitoring is mainly a process of obtaining accurate emission concentrations, emissions, and carbon sink status data and change trend information of known greenhouse gases, such as ecosystem carbon sinks and impacts, through various means such as numerical simulation, comprehensive observation, and statistical analysis, so as to further carry out relevant work such as climate change response research and management. Carbon emission monitoring mostly calculates carbon emissions through carbon emission concentration monitoring data in exhaust gas and assimilation inversion model. Carbon accounting is to calculate greenhouse gas emissions and absorption according to activity level multiplied by emission factor. At present, carbon emission monitoring mainly involves data such as gas emission intensity, concentration emitted into the environment, and carbon sink status. In view of the low data processing volume involved in carbon emission monitoring and the relatively complex data, the existing clustering algorithm or neural network algorithm is relatively complex to process such data, making the process of outputting monitoring results relatively inefficient.

[0003] In view of this, a method, system, device and storage medium for monitoring carbon emissions from electricity are needed. Summary of the invention

[0004] The embodiment of the present application provides a method for monitoring carbon emissions from electricity, which is used to solve the problem of low process efficiency in outputting monitoring results.

[0005] A first aspect of an embodiment of the present application provides a method for monitoring carbon emissions of electricity, comprising:

[0006] Obtain carbon emission source data of power grid companies in several operating scenarios;

[0007] Extracting location features by performing knowledge annotation on the carbon emission source data, and extracting confidence features from the knowledge annotated data;

[0008] The position feature and the confidence feature are enhanced by using a dual attention mechanism to obtain a target variable;

[0009] The carbon emission monitoring results corresponding to the target variables are generated according to the constructed indicator list for carbon emission monitoring of power grid enterprises.

[0010] Furthermore, extracting location features by performing knowledge annotation on the carbon emission source data includes:

[0011] The single data set and the multiple data sets in the carbon emission source data are screened respectively, and after the single data set is knowledge-annotated, the multiple data sets are knowledge-annotated.

[0012] Furthermore, extracting confidence features from the knowledge-annotated data includes:

[0013] The confidence feature of the target data is extracted by calculating the cosine of the angle between the mean vector of the target data and the mean word vector of the adjacent data in the data set.

[0014] Furthermore, the expression of the confidence feature X extracted from the knowledge-annotated data is as follows:

[0015]

[0016] X = {x1, x2};

[0017] Where: x1 is the correlation feature between the target data and the previous data in the data set, x2 is the correlation feature between the target data and the next data in the data set, and They are the average word vector of the target data, the average word vector of the previous data of the target data in the dataset, and the average word vector of the next data of the target data in the dataset.

[0018] Furthermore, the dual attention mechanism is used to enhance the position feature and the confidence feature to obtain the target variable, including:

[0019] Calculating the attention coefficients of the position features and the confidence features, and determining the target variable based on the attention coefficients;

[0020] The calculation formula of the attention coefficient is as follows:

[0021]

[0022] α ij =softmaxj(α(WT i ,WT j ))=softmaxj;

[0023]

[0024] Where: T is the triple feature representative, GM is the position feature, X is the confidence feature, k is the number of attention features, and w is k is the weight matrix, and α is the attention weight coefficient.

[0025] Furthermore, the carbon emission monitoring results corresponding to the target variables are generated according to the constructed indicator list for carbon emission monitoring of power grid enterprises, including:

[0026] The carbon emission monitoring type corresponding to the target variable is matched according to the constructed indicator list of carbon emission monitoring of power grid enterprises, wherein the indicator list includes the carbon emission monitoring type and the calculation method of the carbon emission amount corresponding to each type.

[0027] Furthermore, the matching of the carbon emission monitoring type corresponding to the target variable includes:

[0028] According to the calculation method of each type of carbon emissions in the indicator list, it is calculated whether each type of carbon emissions is greater than or equal to the set threshold. If so, the corresponding monitoring and early warning information is generated, and the monitoring and early warning information includes the early warning object, early warning time and early warning content.

[0029] A second aspect of an embodiment of the present application provides a system for monitoring carbon emissions of electricity, including:

[0030] A carbon emission source data acquisition unit, used to acquire carbon emission source data of power grid enterprises in several operation scenarios;

[0031] A feature extraction unit, configured to extract location features by performing knowledge annotation on the carbon emission source data, and extract confidence features from the knowledge annotated data;

[0032] A target variable determination unit, used for enhancing the position feature and the confidence feature by using a dual attention mechanism to obtain a target variable;

[0033] The carbon emission monitoring result generating unit is used to generate the carbon emission monitoring result corresponding to the target variable according to the constructed indicator list of carbon emission monitoring of the power grid enterprise.

[0034] A third aspect of an embodiment of the present application provides a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein when the processor executes the computer-readable instructions, the steps of the method for monitoring carbon emissions of electricity as described in any one of the above are implemented.

[0035] A fourth aspect of an embodiment of the present application provides a readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the steps of the method for monitoring carbon emissions of electricity as described in any one of the above are implemented.

[0036] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0037] This application first extracts features from the carbon emission data of the power grid company in several operating scenarios, including location features and confidence features, and then uses the dual attention mechanism to enhance the location features and confidence features to obtain the target variable. Finally, the carbon emission results corresponding to the target variable are generated based on the constructed indicator list for carbon emission monitoring of the power grid company. This application uses a data processing method based on extracting data features to enhance features. The calculation process is simple and avoids complex calculation processes. In addition, carbon emission results can be generated by comparing the indicator list based on the processed data, which effectively improves the efficiency of carbon emission monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of an embodiment of a method for monitoring carbon emissions of electricity in the present invention;

[0039] Figure 2 Schematic diagram of the structure of the double-layer attention mechanism in the present invention;

[0040] Figure 3 This is a structural block diagram of an embodiment of a monitoring system for electric power carbon emissions in the present invention;

[0041] Figure 4 The figure is a structural block diagram of a computer device in the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0043] The monitoring method of electric power carbon emission in this embodiment is used to improve the monitoring efficiency of carbon emission through simple calculation. The implementation method in this embodiment can be implemented in the system, can be implemented in the server, and can also be implemented in the terminal, and the specific details are not clearly limited.

[0044] Embodiment 1

[0045] See also Figure 1 , an embodiment of a method for monitoring carbon emissions of electricity in the present invention comprises the following steps:

[0046] S11. Obtain carbon emission source data of power grid enterprises in several operation scenarios;

[0047] In practical applications, data collection, analysis and processing of the operation process of distribution equipment in power grid companies are necessary processes. Currently, most of the carbon emissions are fed back by obtaining power data. However, not all power data are valid during the acquisition process. Even if the data is pre-processed, there may still be some erroneous data. Therefore, the source data of carbon emissions is directly obtained here.

[0048] In this embodiment, the carbon emission source data contains heterogeneous data and some meaningless data, and the source data needs to be extracted by entity and entity relationship extraction to obtain valid data for the power grid enterprise in several operating scenarios. The several operating scenarios may include various direct carbon emission source data or indirect carbon emission source data in the power grid enterprise's operation and maintenance, inspection, marketing, office and logistics operating scenarios, and the source data may be expressed in different forms and stored in different ways.

[0049] S12. extracting location features by performing knowledge annotation on the carbon emission source data, and extracting confidence features from the knowledge annotated data;

[0050] Specifically, the location features are extracted by knowledge annotation of carbon emission source data, including:

[0051] The single data set and multiple data sets in the carbon emission source data are screened separately, and the multiple data sets are annotated with knowledge after the single data set is annotated with knowledge.

[0052] Assume a single data set D = {d1, d2, ..., d m}, where m is the length of carbon emission source data, d i For the i-th word in the carbon emission source data, the BIO annotation method is used to extract the entity set and entity relationship set, that is, all entity vectors G = (E, R) of the single data set D, where E is the node set corresponding to all entities in the entity data, and R is the geometry of all corresponding edges in the entity relationship data. For the entity vector G, any two entity data nodes and the corresponding triples constitute (h, r, t), where h, t∈E; r∈R.

[0053] Set multiple data sets M = {D1, D2, ..., D n}, where n is the number of carbon emission source data in M, D j is the jth data in the multi-dataset. Similarly, using BIO annotation, all entity data sets can be integrated. E = {E1, E2, ..., E n} and all entity relationship datasets R = {R1, R2, …, R n}. Extract entity relationships from source data one by one to obtain entity set E i The entity and relationship set R iThe corresponding triplet set of entity relations in the , and then all triples are mapped into nodes and edges to form all entity vectors GM = {G1, G2, ..., G n}, thereby completing the data integration of all carbon emission source data.

[0054] Specifically, confidence features are extracted from the knowledge-annotated data, including:

[0055] The confidence feature of the target data is extracted by calculating the cosine of the angle between the mean vector of the target data and the mean word vector of the adjacent data in the data set.

[0056] The expression for extracting confidence feature X from the knowledge-annotated data is as follows:

[0057]

[0058] X = {x1, x2};

[0059] Where: x1 is the correlation feature between the target data and the previous data in the data set, x2 is the correlation feature between the target data and the next data in the data set, and They are the average word vector of the target data, the average word vector of the previous data of the target data in the dataset, and the average word vector of the next data of the target data in the dataset.

[0060] S13. Use the dual attention mechanism to enhance the position features and confidence features to obtain the target variable;

[0061] Specifically, Figure 2 As shown in the figure, the dual attention mechanism is used to enhance the position features and confidence features to obtain the target variables, including:

[0062] Calculate the attention coefficients of the position features and confidence features, and determine the target variable based on the attention coefficients;

[0063] The calculation formula of attention coefficient is as follows:

[0064]

[0065] α ij =softmaxj(α(WT i ,WT j ))=softmaxj;

[0066]

[0067] Where: T is the triple feature representative, GM is the position feature, X is the confidence feature, k is the number of attention features, and w is k is the weight matrix, and α is the attention weight coefficient.

[0068] S14. Generate carbon emission monitoring results corresponding to the target variables based on the constructed indicator list for carbon emission monitoring of power grid enterprises.

[0069] In this embodiment, the constructed indicator list for carbon emission monitoring of power grid enterprises generates carbon emission monitoring results corresponding to target variables, including:

[0070] The carbon emission monitoring type corresponding to the target variable is matched according to the constructed indicator list of carbon emission monitoring of power grid enterprises. The indicator list includes the carbon emission monitoring type and the calculation method of the carbon emission amount corresponding to each type.

[0071] Specifically, the types of carbon emissions monitoring may include the following: network loss carbon emissions, sulfur hexafluoride carbon emissions, office electricity carbon emissions, gas carbon emissions, fuel carbon emissions and heating carbon emissions. The calculation method for each type of carbon emissions in the indicator list is as follows:

[0072] E 网损 =AD 网损 ×EF 电网 ;

[0073] Among them: A 网损 EF is the power loss in transmission and distribution, 电网 is the annual average power supply emission factor of the regional power grid.

[0074] E 六氟化硫 =AD 六氟化硫 ×EF 六氟化硫 ;

[0075] Where: E 六氟化硫 is the emission of sulfur hexafluoride, AD 六氟化硫 is the leakage of sulfur hexafluoride, EF 六氟化硫 The global warming potential of sulfur hexafluoride.

[0076] E 办公用电 =AD 办公用电 ×EF 电网 ;

[0077] Where: E 办公用电 is the office electricity emissions, AD 办公用电 Office electricity consumption.

[0078] E 燃气 =AD 燃气 ×EF 燃气 ;

[0079] Where: E 燃气 is the gas emission, AD 燃气 For gas usage.

[0080] E 燃油 =AD燃油 ×EF 燃油 ;

[0081] Where: E 燃气 is the fuel emission, AD 燃气 is the fuel consumption, EF 燃油 is the carbon emission coefficient of fuel.

[0082] E 供热 =AD 供热 ×EF 供热 ;

[0083] Where: E 供热 is the carbon emissions from heating, AD 供热 is the heating area, EF 供热 is the heating emission coefficient.

[0084] In addition to the carbon emission types listed above, there are other types. Most of them determine carbon emissions based on usage and emission coefficients, which will not be elaborated here.

[0085] After calculating each type of carbon emissions, calculate whether each type of carbon emissions is greater than or equal to the set threshold according to the calculation method of each type of carbon emissions in the indicator list. If so, it means that the carbon emissions exceed the set allowable range, and the corresponding monitoring and early warning information is generated, where the monitoring and early warning information includes the warning object, warning time and warning content.

[0086] The above-mentioned embodiment improves the validity of the data by performing data extraction and feature enhancement on the acquired carbon emission source data, so that the processed data can be used as the basis for monitoring judgment, the calculation process is simple and errors can be reduced.

[0087] Embodiment 2

[0088] See also Figure 3 , an embodiment of a monitoring system for carbon emissions of electricity in the present invention comprises the following steps:

[0089] The carbon emission source data acquisition unit 101 is used to acquire the carbon emission source data of the power grid enterprise in several operation scenarios;

[0090] The feature extraction unit 102 is used to extract location features by performing knowledge annotation on the carbon emission source data, and extract confidence features from the knowledge annotated data;

[0091] A target variable determination unit 103 is used to enhance the position feature and the confidence feature by using a dual attention mechanism to obtain a target variable;

[0092] The carbon emission monitoring result generating unit 104 is used to generate the carbon emission monitoring result corresponding to the target variable according to the constructed indicator list of carbon emission monitoring of the power grid enterprise.

[0093] For the specific definition of the monitoring system, please refer to the definition of the monitoring method above, which will not be repeated here. Each module in the above monitoring system can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0094] Embodiment 3

[0095] See also Figure 4 The present invention provides a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the above method are implemented.

[0096] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0099] It can be understood that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for monitoring carbon emissions from electricity, characterized in that: include: Obtain carbon emission source data of power grid companies in several operating scenarios; Extracting location features by performing knowledge annotation on the carbon emission source data, and extracting confidence features from the knowledge annotated data; The position feature and the confidence feature are enhanced by using a dual attention mechanism to obtain a target variable; The carbon emission monitoring results corresponding to the target variables are generated according to the constructed indicator list for carbon emission monitoring of power grid enterprises.

2. The method for monitoring carbon emissions from electricity according to claim 1, characterized in that: The extracting location features by performing knowledge annotation on the carbon emission source data includes: The single data set and the multiple data sets in the carbon emission source data are screened respectively, and after the single data set is knowledge-annotated, the multiple data sets are knowledge-annotated.

3. The method for monitoring carbon emissions from electricity according to claim 1, characterized in that: The confidence features extracted from the knowledge-annotated data include: The confidence feature of the target data is extracted by calculating the cosine of the angle between the mean vector of the target data and the mean word vector of the adjacent data in the data set.

4. The method for monitoring carbon emissions from electricity according to claim 3, characterized in that: The expression of the confidence feature X extracted from the knowledge-annotated data is as follows: X = {x1, x2}; Where: x1 is the correlation feature between the target data and the previous data in the data set, x2 is the correlation feature between the target data and the next data in the data set, and They are the average word vector of the target data, the average word vector of the previous data of the target data in the dataset, and the average word vector of the next data of the target data in the dataset.

5. The method for monitoring carbon emissions from electricity according to claim 1, characterized in that: The dual attention mechanism is used to enhance the position feature and the confidence feature to obtain the target variable, including: Calculating the attention coefficients of the position features and the confidence features, and determining the target variable based on the attention coefficients; The calculation formula of the attention coefficient is as follows: α ij =softmaxj(α(WT i ,WT j ))=softmaxj; Where: T is the triple feature representative, GM is the position feature, X is the confidence feature, k is the number of attention features, and w is k is the weight matrix, and α is the attention weight coefficient.

6. The method for monitoring carbon emissions from electricity according to claim 1, characterized in that: The step of generating the carbon emission monitoring result corresponding to the target variable according to the constructed indicator list of carbon emission monitoring of the power grid enterprise includes: The carbon emission monitoring type corresponding to the target variable is matched according to the constructed indicator list of carbon emission monitoring of power grid enterprises, wherein the indicator list includes the carbon emission monitoring type and the calculation method of the carbon emission amount corresponding to each type.

7. The method for monitoring carbon emissions from electricity according to claim 6, characterized in that: The carbon emission monitoring type corresponding to the target variable is matched, including: According to the calculation method of each type of carbon emissions in the indicator list, it is calculated whether each type of carbon emissions is greater than or equal to the set threshold. If so, the corresponding monitoring and early warning information is generated, and the monitoring and early warning information includes the early warning object, early warning time and early warning content.

8. A monitoring system for carbon emissions from electricity, characterized in that: include: A carbon emission source data acquisition unit, used to acquire carbon emission source data of power grid enterprises in several operation scenarios; A feature extraction unit, configured to extract location features by performing knowledge annotation on the carbon emission source data, and extract confidence features from the knowledge annotated data; A target variable determination unit, used for enhancing the position feature and the confidence feature by using a dual attention mechanism to obtain a target variable; The carbon emission monitoring result generating unit is used to generate the carbon emission monitoring result corresponding to the target variable according to the constructed indicator list of carbon emission monitoring of the power grid enterprise.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the steps of the method for monitoring carbon emissions of electricity as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the steps of the method for monitoring carbon emissions of electricity as described in any one of claims 1 to 7 are implemented.

Images