CN117763944A - Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data - Google Patents
Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data Download PDFInfo
- Publication number
- CN117763944A CN117763944A CN202311527724.7A CN202311527724A CN117763944A CN 117763944 A CN117763944 A CN 117763944A CN 202311527724 A CN202311527724 A CN 202311527724A CN 117763944 A CN117763944 A CN 117763944A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- data
- target
- electric
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 240
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 236
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000000691 measurement method Methods 0.000 claims abstract description 8
- 238000005265 energy consumption Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 22
- 238000000354 decomposition reaction Methods 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 11
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 5
- 239000007787 solid Substances 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an enterprise carbon emission measurement method, device, equipment and medium based on power data. The method comprises the following steps: acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period; learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data; combining the target power data with a non-electric equipment carbon emission prediction model to obtain target energy carbon emission data corresponding to each non-electric equipment in a preset period; and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data. The method can be used for measuring and calculating the carbon emission from the equipment level to the enterprise level with high efficiency and advanced carbon emission theory, and provides a solid foundation for realizing the double-carbon target.
Description
Technical Field
The application relates to the field of carbon emission and carbon accounting, in particular to an enterprise carbon emission measuring and calculating method, device, equipment and medium based on electric power data.
Background
The carbon emission calculation is a process of quantifying and evaluating the emission of greenhouse gases under different scales of enterprises, industries, cities and the like, can help the enterprises to know the contribution and risk of the enterprises to climate change, and can provide references and support for energy conservation and emission reduction.
Currently, the carbon emission of an enterprise is counted and calculated based on the fuel consumption reported by the artificial measurement of the enterprise, which is time-consuming, labor-consuming and inefficient.
Disclosure of Invention
Based on the foregoing, it is necessary to provide an enterprise carbon emission measurement method, apparatus, device and medium based on electric power data, which can improve the efficiency of carbon emission measurement.
In a first aspect, the present application provides a method for enterprise carbon emission measurement based on electrical data. The method comprises the following steps:
acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period;
based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data;
acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model;
and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
In one embodiment, obtaining target power data corresponding to each electric device in a predetermined period of time includes:
acquiring total target power data of a target subject within a predetermined period of time;
and determining target power data corresponding to the electric equipment in the preset time period according to the total target power data and the trained power decomposition model, wherein the power decomposition model comprises a mapping relation between the total power data of the target main body and the power data of each electric equipment in the target main body.
In one embodiment, the power decomposition model is obtained by:
acquiring total historical power time sequence data of a target main body in a historical period;
and learning from a training sample to obtain an electric power decomposition model, wherein the training sample comprises total historical electric power time sequence data and corresponding records between the historical electric power time sequences respectively corresponding to all electric equipment.
In one embodiment, learning and obtaining the non-consumer carbon emission prediction model from the historical energy carbon emission time sequence data and the historical power time sequence data based on association rules among different devices comprises:
acquiring a corresponding relation data set of each non-electric equipment and electric equipment, wherein the relation data set comprises equipment types, working states, energy consumption and carbon emission data of each equipment in a historical period;
according to the corresponding relation data sets of the non-electric equipment and the electric equipment, adopting an association rule mining algorithm to associate the coupling relation among the equipment to obtain an association rule;
and based on the association rule, learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data.
In one embodiment, the non-powered carbon emission prediction model employs a multiple regression model.
In one embodiment, obtaining target power carbon emission data corresponding to each electric device in a predetermined period according to the target power data includes:
acquiring equipment energy consumption of each electric equipment respectively corresponding to each electric equipment in a preset period according to the target electric power data;
and combining the equipment energy consumption and the carbon emission factor to obtain target electric power carbon emission data corresponding to each electric equipment respectively.
In a second aspect, the present application also provides an enterprise carbon emission measurement device based on the power data. The device comprises:
the acquisition module is used for acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device in a historical period of the target main body;
the construction module is used for learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data based on association rules among different equipment;
the prediction module is used for obtaining target power data corresponding to each electric equipment in a preset time period and obtaining target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model;
and the summarizing module is used for acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the following steps:
acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period;
based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data;
acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model;
and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period;
based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data;
acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model;
and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, performs the steps of:
acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period;
based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data;
acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model;
and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
According to the enterprise carbon emission measuring and calculating method, device, equipment, medium and product based on the electric power data, the historical energy carbon emission time sequence data of each non-electric equipment and the historical electric power time sequence data of each electric equipment of the target main body in the historical period are obtained; based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data; acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model; and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data. According to the method and the device, the non-electric equipment carbon emission prediction model is obtained through the historical energy carbon emission time sequence data of the non-electric equipment and the historical electric power time sequence data of the non-electric equipment, the target energy carbon emission data corresponding to the non-electric equipment can be predicted by combining the target electric power data corresponding to the electric equipment and the non-electric equipment carbon emission prediction model, rapid carbon emission measurement and calculation can be performed based on the electric information of the target main body, the measurement and calculation efficiency is improved, and the advanced carbon emission theory is utilized to realize the carbon emission measurement and calculation from the equipment level to the enterprise level, so that a solid foundation is provided for realizing the double-carbon target.
Drawings
FIG. 1 is an application environment diagram of an enterprise carbon emission measurement method based on power data in one embodiment;
FIG. 2 is a flow chart of an enterprise carbon emission measurement method based on power data in one embodiment;
FIG. 3 is a flow chart of acquiring target power data in one embodiment;
FIG. 4 is a block diagram of an enterprise carbon emission measurement device based on power data in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The method for measuring and calculating the carbon emission of the enterprise based on the electric power data can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may obtain the power data and the carbon emission data related to the target subject and send the data to the server 104, and the server may perform the carbon emission measurement according to the power data and the carbon emission data related to the target subject. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, there is provided an enterprise carbon emission measurement method based on electric power data, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
step 202, acquiring historical energy carbon emission time sequence data of each non-electric equipment and historical power time sequence data of each electric equipment of a target main body in a historical period.
The target subject may include a particular entity such as an enterprise, organization, or factory, among others.
The target main body of the embodiment of the application comprises electric equipment and non-electric equipment, and the embodiment of the application can acquire carbon emission data of each non-electric equipment at each moment in a historical period to obtain historical energy carbon emission time sequence data.
Illustratively, historical energy consumption data for each non-powered device is obtained, which may include historical high power, historical average energy consumption, historical operating time, and the like. According to the fuel type and the fuel efficiency of each non-electric device, a carbon emission coefficient is determined, and historical energy carbon emission time sequence data respectively corresponding to each non-electric device is determined through historical energy consumption data and the carbon emission coefficient respectively corresponding to each non-electric device in a historical period.
According to the method and the device for obtaining the historical power time sequence data of the electric equipment, the historical power time sequence data of the target main body in the historical time period can be obtained, wherein the historical power time sequence data can comprise voltage, current, power and the like of the electric equipment at each historical moment.
And 204, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data based on association rules among different equipment.
The association rule between different devices refers to the coupling relation between each electric device and each non-electric device in the target main body.
The embodiment of the application can determine the coupling relation among different devices based on energy transmission, the topology of the internal power structure of the target main body, the working states and work coordination of the devices, such as energy supply and electric equipment, data acquisition equipment and transmission equipment, mechanical equipment and control equipment, temperature control equipment and air conditioning equipment and the like.
According to the method and the device for predicting the carbon emission of the non-electric equipment, based on association rules among different devices, mapping relations between the carbon emission of the energy source of the specific non-electric equipment and the power data of the electric equipment are learned from historical energy carbon emission time sequence data corresponding to the non-electric equipment respectively and historical power time sequence data corresponding to the electric equipment respectively, and a non-electric equipment carbon emission prediction model is obtained, wherein the non-electric equipment carbon emission prediction model can comprise the mapping relations between the carbon emission of the energy source of the certain non-electric equipment and the power data of the electric equipment at a certain moment.
For example, a multiple regression model may be used to integrate historical energy carbon emission time sequence data corresponding to each non-electric device and historical power time sequence data corresponding to each electric device, and the historical energy carbon emission data of the non-electric device is presumed by the historical power data corresponding to each electric device, where the non-electric device carbon emission prediction model may be expressed as:
Y＝β 0 +β 1 X 1 +β 2 X 2 +...+β n X n +ζ；
wherein Y is carbon emission data of non-electric equipment at a certain moment, X 1 、X 2 、…、X n Is the power data of the electric equipment at a certain moment, beta 0 、β 1 、…、β n Is the regression coefficient and ζ is the error term.
And 206, acquiring target power data corresponding to each electric equipment in a preset time period, and combining the target power data and a non-electric equipment carbon emission prediction model to acquire target energy carbon emission data corresponding to each non-electric equipment in the preset time period.
The predetermined period may be the current period of time or the current time or the time to be predicted.
The method and the device acquire target power data corresponding to each electric equipment in a preset time period, wherein the target power data comprise target voltage, target current, target power and the like of each electric equipment in the preset time period. And (3) adopting a pre-constructed non-electric equipment carbon emission prediction model and combining target power data to obtain target energy carbon emission data corresponding to each non-electric equipment in a preset period.
In one implementation manner, the embodiment of the application may implement monitoring of the target power data corresponding to each electric device by using a non-invasive load monitoring technology, that is, without installing a plurality of measuring devices to obtain the power data of each electric device like a traditional invasive method, the total power data of the target main body is analyzed and decomposed, so as to obtain the power data of each electric device in the target main body. For example, a Non-negative matrix factorization (Non-negative Matrix Factorization, abbreviated as NMF) method may be used to decompose the total power data, and the total power data is represented as a total power matrix, where the total power matrix is decomposed into a plurality of Non-negative component matrices, where each component matrix represents the power load characteristics of a consumer, including information such as power consumption, time, waveform, and the like. By adjusting parameters such as the number, the attribute and the like of the component matrixes, electricity utilization information of different electric equipment can be extracted.
And step 208, acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
According to the embodiment of the application, the target electric power carbon emission data respectively corresponding to the electric equipment in the preset time period can be obtained according to the target electric power data respectively corresponding to the electric equipment in the preset time period, and the equipment energy consumption respectively corresponding to the electric equipment in the preset time period is obtained according to the target electric power data; and combining the equipment energy consumption and the carbon emission factor to obtain target electric power carbon emission data corresponding to each electric equipment respectively.
In one implementation, a non-invasive load monitoring technique is used to monitor the energy consumption of the device in real time, and the target power data corresponding to each electric device is determined through the decomposition of the target main body total power data, so that the target power carbon emission data corresponding to each electric device is monitored, and for continuously operating devices, time series analysis can be performed to predict future energy consumption and carbon emission, for example, the analysis can be predicted through an autoregressive moving average (ARIMA) model or a state space model.
According to the method and the device, after the target electric power carbon emission data corresponding to each electric equipment and the target energy carbon emission data corresponding to each non-electric equipment are obtained, the target electric power carbon emission data and the target energy carbon emission data are combined to determine the total carbon emission data of the target main body.
For example, the target subject total carbon emission data may be expressed as:
wherein C is Total Is total carbon emission of enterprises, C ei And C nej Carbon emissions of the electric equipment and the non-electric equipment are respectively, and m and n are respectively the number of the electric equipment and the non-electric equipment.
In the enterprise carbon emission measuring and calculating method based on the electric power data, the historical energy carbon emission time sequence data of each non-electric equipment and the historical electric power time sequence data of each electric equipment of the target main body in the historical period are obtained; based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data; acquiring target power data corresponding to each electric equipment in a preset time period, and acquiring target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and a non-electric equipment carbon emission prediction model; and acquiring target electric power carbon emission data corresponding to each electric equipment in a preset period according to the target electric power data, and determining target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data. According to the method and the device, the non-electric equipment carbon emission prediction model is obtained through the historical energy carbon emission time sequence data of the non-electric equipment and the historical electric power time sequence data of the non-electric equipment, the target energy carbon emission data corresponding to the non-electric equipment is predicted by combining the target electric power data corresponding to the electric equipment and the non-electric equipment carbon emission prediction model, rapid carbon emission measurement and calculation can be carried out based on the electric information of the target main body, the measurement and calculation efficiency is improved, and the advanced carbon emission theory is utilized to realize the carbon emission measurement and calculation from the equipment level to the enterprise level, so that a solid foundation is provided for realizing the double-carbon target.
In one embodiment, as shown in fig. 3, obtaining target power data corresponding to each electric device in a predetermined period of time includes:
step 302, obtaining total target power data of a target subject within a predetermined period.
Wherein the total target power data includes total power data of the target subject, such as total voltage data, total current data, total power data, and the like.
And step 304, determining target power data corresponding to the electric equipment in the preset time period respectively according to the total target power data and the trained power decomposition model.
The power decomposition model comprises a mapping relation between total power data of the target main body and power data of electric equipment in the target main body.
The power decomposition model of the embodiment of the application is obtained through the following processes: acquiring total historical power time sequence data of a target main body in a historical period; and learning from a training sample to obtain an electric power decomposition model, wherein the training sample comprises total historical electric power time sequence data and corresponding records between the historical electric power time sequences respectively corresponding to all electric equipment.
In this embodiment, the total target power data and the trained power decomposition model are used to determine the target power data corresponding to the electric devices respectively in the predetermined period, so that the equipment-level power data of each electric device can be obtained by decomposing the total power data by using a non-invasive load monitoring technology, the non-invasive load monitoring becomes a solid foundation for the operation of the smart grid, the electric data is deeply analyzed by using a non-invasive load monitoring method under the large background of global climate change, and the carbon emission measuring and calculating technology based on the equipment electric information is provided by using the carbon emission theory, so that the production enterprises can be helped to determine the carbon emission of themselves, realize the low-carbon transformation, and be beneficial to the realization of the double-carbon targets.
In one embodiment, the basic steps of non-invasive load monitoring may include:
step A, data collection and pretreatment: time series data including device load information is collected, and the data is obtained from the total power signal, including power, current and voltage parameters. Preprocessing includes filtering, denoising and data normalization.
And step B, extracting features: extracting from the power signal: peak power characteristics (maximum power consumed by the device during operation), start-up current transient characteristics (current change at device start-up), harmonic characteristics (power line harmonics caused by device operation), duration/period characteristics (time length or periodic pattern of device operation).
Step C, training a machine learning model: using the extracted features and corresponding labels (per device state) a machine learning model (support vector machine) is trained that optimizes the following objective functions:
wherein w is a model parameter, C is a regularization parameter, and ζ i Is the error term for the ith training sample.
Step D, equipment state identification: after training the model, it is used to identify the device status in the new, unlabeled power usage data. The model predicts the load signature for each point in time or window. For example, if we have a set of device state labels, the output of the model is a probability distribution representing the predicted probability for each state, and the state with the highest probability is selected as the predicted result, e.g., P (s|data) = [ P (S) 1 |data),P(s 2 |data),...,P(s m |data)]。
The embodiment of the application can construct a non-invasive load monitoring evaluation index system, evaluate the identification accuracy of the equipment working state, and quantify the identification accuracy of the equipment working state by adopting the accuracy, the recall rate and the F1 score index.
The calculation formula of the Accuracy (Accuracy) is as follows:
the Recall rate (Recall) calculation formula is:
wherein, the calculation formula of the F1 Score (F1 Score) is as follows:
wherein TP (true case), TN (true negative case), FP (false positive case) and FN (false negative case) represent the real case and the predicted case of the device state recognition, respectively.
The embodiment of the application can construct an enterprise carbon emission estimation test and evaluation platform, such as designing an experimental scene, simulating different power disturbance, background noise and sampling frequency, testing the performance of the non-invasive load monitoring algorithm under various conditions, and quantifying evaluation results such as accuracy, error rate and the like so as to determine the reliability and effectiveness of the algorithm.
The embodiment of the application can also be applied to carbon emission test points of multiple types of enterprises, for example, enterprises with different industries and scales are selected for test point application, developed software algorithms and hardware platforms are applied, and real-time carbon emission data are collected. The effectiveness of the algorithm is verified by comparing actual carbon emission data with estimated data and using the estimated index, and the algorithm is iterated and optimized according to feedback, so that the accuracy of carbon emission estimation is improved. By constructing a complete evaluation index system and a test platform and implementing test point application, the performance of the non-invasive load monitoring and carbon emission estimation algorithm is comprehensively evaluated, and the effectiveness and the accuracy of the technologies in practical application are ensured.
In one embodiment, learning and obtaining the non-consumer carbon emission prediction model from the historical energy carbon emission time series data and the historical power time series data based on association rules among different devices comprises: acquiring a corresponding relation data set of each non-electric equipment and electric equipment, wherein the relation data set comprises equipment types, working states, energy consumption and carbon emission data of each equipment in a historical period; according to the corresponding relation data sets of the non-electric equipment and the electric equipment, adopting an association rule mining algorithm to associate the coupling relation among the equipment to obtain an association rule; and based on the association rule, learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data.
According to the method and the device, a relation data set of the working state, carbon emission and the like of each device of a target main body can be firstly obtained, specifically, historical data of a historical period, such as device types, working states, energy consumption, carbon emission data and the like of each device in the historical period, are adopted, and according to the relation data set of each device, coupling relations among the devices are associated by adopting an association rule mining algorithm, so that association rules are obtained.
Illustratively, the coupling relation between the devices is analyzed by adopting an Apriori algorithm, a data association mapping is formed according to association rules between different operating states of the devices, and a support degree (support) and confidence (confidence) calculation formula in the Apriori algorithm comprises:
support(A→B)＝P(A∩B)；
in one embodiment, the carbon emissions of the powered device may be expressed as:
C＝E×F；
where C is the carbon emissions, E is the consumer energy consumption, e.g., kilowatt-hours, and F is the carbon emission factor, representing the carbon emissions produced per unit energy consumption, e.g., kg carbon dioxide/kilowatt-hours.
In one embodiment, the carbon emissions of the non-powered device within the target body may be expressed as:
C i ＝E i ×F i ；
wherein C is i Carbon emission of non-electric equipment, E i Energy consumption of non-electric equipment, F i Carbon emission coefficient of non-electric equipment.
In one embodiment, the total energy consumption of the non-powered devices within the target body may be expressed as:
wherein E is Total Is total energy consumption, P i Power of non-electric equipment, T i Run time, n, is the number of non-powered devices.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an enterprise carbon emission measuring device based on the electric power data, which is used for realizing the enterprise carbon emission measuring method based on the electric power data. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the one or more enterprise carbon emission measurement devices based on electric power data provided below may be referred to the limitation of the enterprise carbon emission measurement method based on electric power data hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 4, there is provided an enterprise carbon emission measurement device based on power data, comprising: an acquisition module 402, a construction module 404, a prediction module 406, and a summary module 408, wherein:
an acquisition module 402, configured to acquire historical energy carbon emission time sequence data of each non-electric device and historical power time sequence data of each electric device in a historical period of the target main body;
the construction module 404 is configured to learn and obtain a non-electric equipment carbon emission prediction model from historical energy carbon emission time sequence data and historical electric power time sequence data based on association rules among different devices;
the prediction module 406 is configured to obtain target power data corresponding to each electric device in a predetermined period, and combine the target power data with a non-electric device carbon emission prediction model to obtain target energy carbon emission data corresponding to each non-electric device in the predetermined period;
and the summarizing module 408 is configured to obtain target electric power carbon emission data corresponding to each electric device in a predetermined period according to the target electric power data, and determine target main body total carbon emission data by combining the target electric power carbon emission data and the target energy carbon emission data.
In one embodiment, prediction module 406, when executing the obtaining target power data corresponding to each powered device within the predetermined period, is configured to: acquiring total target power data of a target subject within a predetermined period of time;
and determining target power data corresponding to the electric equipment in the preset time period according to the total target power data and the trained power decomposition model, wherein the power decomposition model comprises a mapping relation between the total power data of the target main body and the power data of each electric equipment in the target main body.
In one embodiment, prediction module 406 is further configured to: acquiring total historical power time sequence data of a target main body in a historical period; and learning from a training sample to obtain an electric power decomposition model, wherein the training sample comprises total historical electric power time sequence data and corresponding records between the historical electric power time sequences respectively corresponding to all electric equipment.
In one embodiment, the construction module 404, when executing learning from the historical energy carbon emission time series data and the historical power time series data based on association rules between different devices, is configured to: acquiring a corresponding relation data set of each non-electric equipment and electric equipment, wherein the relation data set comprises equipment types, working states, energy consumption and carbon emission data of each equipment in a historical period; according to the corresponding relation data sets of the non-electric equipment and the electric equipment, adopting an association rule mining algorithm to associate the coupling relation among the equipment to obtain an association rule; and based on the association rule, learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data.
In one embodiment, the non-powered carbon emission prediction model employs a multiple regression model.
In one embodiment, summary module 408, when executing the obtaining of target power carbon emission data corresponding to each powered device for a predetermined period of time from the target power data, is configured to: acquiring equipment energy consumption of each electric equipment respectively corresponding to each electric equipment in a preset period according to the target electric power data; and combining the equipment energy consumption and the carbon emission factor to obtain target electric power carbon emission data corresponding to each electric equipment respectively.
The above-described modules in the enterprise carbon emission measurement device based on the electric power data may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing target subject power related data and carbon emission related data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements an enterprise carbon emission measurement method based on power data.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. An enterprise carbon emission measurement method based on electric power data, characterized in that the method comprises the following steps:
acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device of a target main body in a historical period;
based on association rules among different devices, learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data;
acquiring target power data corresponding to each electric equipment in a preset period, and combining the target power data and the non-electric equipment carbon emission prediction model to acquire target energy carbon emission data corresponding to each non-electric equipment in the preset period;
and acquiring target electric power carbon emission data corresponding to each electric equipment in the preset time period according to the target electric power data, and determining the total carbon emission data of the target main body by combining the target electric power carbon emission data and the target energy carbon emission data.
2. The method of claim 1, wherein the obtaining the target power data corresponding to each of the electric devices in the predetermined period of time includes:
acquiring total target power data of the target subject within the predetermined period;
and determining target power data corresponding to the electric equipment respectively in the preset time period according to the total target power data and the trained power decomposition model, wherein the power decomposition model comprises a mapping relation between the total power data of the target main body and the power data of each electric equipment in the target main body.
3. The method according to claim 2, wherein the power decomposition model is obtained by:
acquiring total historical power time sequence data of the target main body in a historical period;
and learning from a training sample to obtain the power decomposition model, wherein the training sample comprises the total historical power time sequence data and corresponding records between the historical power time sequences respectively corresponding to the electric equipment.
4. The method of claim 1, wherein learning the non-powered carbon emission prediction model from the historical energy carbon emission time series data and the historical power time series data based on association rules between different devices comprises:
acquiring a relation data set corresponding to each non-electric equipment and each electric equipment, wherein the relation data set comprises equipment types, working states, energy consumption and carbon emission data of each equipment in a historical period;
according to the relation data sets respectively corresponding to the non-electric equipment and the electric equipment, adopting an association rule mining algorithm to associate the coupling relation among the equipment to obtain the association rule;
and based on the association rule, learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data.
5. The method of any one of claims 1 to 4, wherein the non-powered carbon emission prediction model employs a multiple regression model.
6. The method according to claim 1, wherein the obtaining, according to the target power data, target power carbon emission data corresponding to each of the electric devices in the predetermined period of time includes:
acquiring the equipment energy consumption of each electric equipment respectively corresponding to each electric equipment in the preset time period according to the target electric power data;
and combining the equipment energy consumption and the carbon emission factor to obtain target electric power carbon emission data corresponding to each electric equipment respectively.
7. An enterprise carbon emission measurement device based on electrical data, the device comprising:
the acquisition module is used for acquiring historical energy carbon emission time sequence data of each non-electric device and historical electric power time sequence data of each electric device in a historical period of the target main body;
the construction module is used for learning and obtaining a non-electric equipment carbon emission prediction model from the historical energy carbon emission time sequence data and the historical electric power time sequence data based on association rules among different equipment;
the prediction module is used for obtaining target power data corresponding to each electric equipment in a preset time period and obtaining target energy carbon emission data corresponding to each non-electric equipment in the preset time period by combining the target power data and the non-electric equipment carbon emission prediction model;
and the summarizing module is used for acquiring target electric power carbon emission data corresponding to each electric equipment in the preset time period according to the target electric power data, and determining the total carbon emission data of the target main body by combining the target electric power carbon emission data and the target energy carbon emission data.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311527724.7A CN117763944A (en) | 2023-11-15 | 2023-11-15 | Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311527724.7A CN117763944A (en) | 2023-11-15 | 2023-11-15 | Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117763944A true CN117763944A (en) | 2024-03-26 |
Family
ID=90309490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311527724.7A Pending CN117763944A (en) | 2023-11-15 | 2023-11-15 | Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117763944A (en) |
-
2023
- 2023-11-15 CN CN202311527724.7A patent/CN117763944A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A compound framework for wind speed forecasting based on comprehensive feature selection, quantile regression incorporated into convolutional simplified long short-term memory network and residual error correction | |
| Sun et al. | Short-term performance degradation prediction of a commercial vehicle fuel cell system based on CNN and LSTM hybrid neural network | |
| CN112381673B (en) | Park electricity utilization information analysis method and device based on digital twin | |
| CN113657661A (en) | Enterprise carbon emission prediction method and device, computer equipment and storage medium | |
| CN115471098B (en) | Carbon emission amount acquisition method, carbon emission amount acquisition device, computer device, and storage medium | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| Cui et al. | Improved long short-term memory network based short term load forecasting | |
| Wan et al. | Neural network model comparison and analysis of prediction methods using ARIMA and LSTM models | |
| CN116757465A (en) | Line risk assessment method and device based on double training weight distribution model | |
| Fu et al. | Lithium-ion battery SOH prediction based on VMD-PE and improved DBO optimized temporal convolutional network model | |
| CN118014352A (en) | Dynamic early warning method and device for manufacturing cost of power transformation project based on LIME model | |
| CN117056776A (en) | Carbon emission monitoring method, apparatus, device, medium and computer program product | |
| Liu et al. | Real-time industrial carbon emission estimation with deep learning-based device recognition and incomplete smart meter data | |
| CN113380340A (en) | Training method and device of fly ash concentration prediction model and computer equipment | |
| CN116737681A (en) | Real-time abnormal log detection method and device, computer equipment and storage medium | |
| Sun et al. | Short-Term Exhaust Gas Temperature Trend Prediction of a Marine Diesel Engine Based on an Improved Slime Mold Algorithm-Optimized Bidirectional Long Short-Term Memory—Temporal Pattern Attention Ensemble Model | |
| CN116523001A (en) | Method, device and computer equipment for constructing weak line identification model of power grid | |
| CN116402528A (en) | Power data processing system | |
| CN114819267B (en) | Short-term load prediction method and device, electronic equipment and storage medium | |
| CN117763944A (en) | Method, device, equipment and medium for measuring and calculating enterprise carbon emission based on electric power data | |
| CN107464015B (en) | Short-term load with fusing mechanism and electric quantity prediction method based on electricity utilization behavior | |
| CN115481767A (en) | Operation data processing method and device for power distribution network maintenance and computer equipment | |
| Ji et al. | An Active Learning based Latency Prediction Approach for Neural Network Architecture | |
| Nong | Construction and Simulation of Financial Risk Prediction Model Based on LSTM | |
| Chen et al. | Technique of Feature Extraction Based on Interpretation Analysis for Multilabel Learning in Nonintrusive Load Monitoring With Multiappliance Circumstances |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |