CN117634933B - Carbon emission data prediction method and device - Google Patents
Carbon emission data prediction method and device Download PDFInfo
- Publication number
- CN117634933B CN117634933B CN202410107976.2A CN202410107976A CN117634933B CN 117634933 B CN117634933 B CN 117634933B CN 202410107976 A CN202410107976 A CN 202410107976A CN 117634933 B CN117634933 B CN 117634933B
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- period
- data
- user
- key characteristic
- 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.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 157
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 157
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000009826 distribution Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 32
- 238000003860 storage Methods 0.000 claims description 18
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 16
- 238000005265 energy consumption Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 239000003245 coal Substances 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000000556 factor analysis Methods 0.000 claims description 8
- 239000003345 natural gas Substances 0.000 claims description 8
- 239000007787 solid Substances 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009467 reduction Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000004132 cross linking Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 238000000540 analysis of variance Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012886 linear function Methods 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
- 230000003287 optical effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of carbon emission analysis, and particularly provides a carbon emission data prediction method and device, comprising the following steps: taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network; and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model. The invention fully utilizes the advantages of large electric power data and ensures the comprehensiveness and real-time performance of the data. Through precise characteristic analysis, key characteristics affecting carbon emission can be accurately extracted, so that a solid foundation is laid for the establishment of a subsequent carbon emission prediction model.
Description
Technical Field
The invention relates to the technical field of carbon emission analysis, in particular to a carbon emission data prediction method and device.
Background
Real-time, accurate and efficient carbon emission monitoring, metering and prediction are the basis for recognizing the current emission situation and making an emission reduction path. The current carbon emission monitoring system mainly relies on analyzing primary energy consumption of regional coal, petroleum, natural gas and the like, and has the problems of long period, slow updating, difficult management and control, no digitization and the like, so that the construction of an energy consumption and carbon emission monitoring and metering system based on power consumption data is needed urgently, and the economic and efficient carbon emission prediction technology of typical users is formed by utilizing the coupling characteristics of power and carbon emission, the accuracy, instantaneity and full-scene coverage characteristics of the power data, so that the full life cycle tracking of the carbon emission is realized.
The method for predicting the carbon emission mainly comprises an emission factor method, a material balance algorithm, an actual measurement method and the like, wherein the emission factor method has the widest application range and the most common application, however, the accuracy of the emission factor is difficult to meet the requirement of an energy unit.
Disclosure of Invention
In order to overcome the above drawbacks, the present invention provides a method and apparatus for predicting carbon emission data.
In a first aspect, there is provided a carbon emission data prediction method including:
Taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
Preferably, the key characteristic data affecting carbon emission includes: various energy consumption, product output, geographic position and weather data of the region.
Further, when the user is a non-productive unit, the key characteristic data affecting carbon emission includes: flow of people.
Further, the non-productive units include: commercial buildings, office buildings, medical buildings, educational buildings.
Further, the various energy sources include at least one of the following: electric power, coal, natural gas, thermal power.
Preferably, the determining of the key characteristic data affecting carbon emission includes:
Adopting a factor analysis method to analyze the correlation between the historical carbon emission data of the user and each preset type of data;
the preset type data having a first n-th large correlation with the user's historical carbon emission data is determined as key feature data affecting carbon emission.
Preferably, the training process of the pre-trained long-short-term memory network comprises the following steps:
constructing training data by using the user power data of the history period t, the key characteristic data and the power data which influence the carbon emission in the period before the history period t and the key characteristic data which influence the carbon emission in the period after the history period t;
and training an initial long-period memory network by using the training data to obtain the pre-trained long-period memory network, wherein T is [1, T ], and T is the total number of historical periods.
Preferably, the training process of the pre-trained autoregressive distributed hysteresis model comprises:
The method comprises the steps that user power data of a history period t, key characteristic data influencing carbon emission in a period before the history period t and power data are input into a pre-trained long-short-period memory network, and key characteristic data influencing carbon emission in a period after the history period t, which is output by the pre-trained long-short-period memory network, are obtained;
constructing training data by utilizing key characteristic data influencing carbon emission in a period after the history period t, carbon emission in the history period t and carbon emission in a period after the history period t;
And training an initial autoregressive distribution hysteresis model by using the training data to obtain the pretrained autoregressive distribution hysteresis model, wherein T is [1, T ], and T is the total number of historical time periods.
In a second aspect, there is provided a carbon emission data prediction apparatus including:
The first analysis module is used for taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network to obtain key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
And the second analysis module is used for taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as the input of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
In a third aspect, there is provided a computer device comprising: one or more processors;
the processor is used for storing one or more programs;
The carbon emission data prediction method is implemented when the one or more programs are executed by the one or more processors.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored, which when executed, implements the carbon emission data prediction method.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
The invention provides a carbon emission data prediction method and device, comprising the following steps: taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network; and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model. The invention fully utilizes the advantages of large electric power data and ensures the comprehensiveness and real-time performance of the data. By means of precise feature analysis, key features affecting carbon emission can be accurately extracted, so that a solid foundation is laid for the establishment of a subsequent carbon emission prediction model, carbon emission data prediction accuracy is improved, and carbon emission data prediction time is shortened.
Further, the present invention reveals the cross-linking between data and the major factors affecting carbon emissions. For the acquired data, the invention reveals the transverse relation among the data, especially the influence characteristics between the energy consumption data and the carbon emission data through factor analysis, and lays a foundation for the carbon emission prediction by using the sample library of the invention.
Drawings
FIG. 1 is a flow chart showing the main steps of a carbon emission data prediction method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a carbon emission data prediction method according to an embodiment of the present invention.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As disclosed in the background, real-time, accurate, efficient carbon emission monitoring, metering, and prediction are the basis for recognizing the current state of emissions and establishing emission reduction routes. The current carbon emission monitoring system mainly relies on analyzing primary energy consumption of regional coal, petroleum, natural gas and the like, and has the problems of long period, slow updating, difficult management and control, no digitization and the like, so that the construction of an energy consumption and carbon emission monitoring and metering system based on power consumption data is needed urgently, and the economic and efficient carbon emission prediction technology of typical users is formed by utilizing the coupling characteristics of power and carbon emission, the accuracy, instantaneity and full-scene coverage characteristics of the power data, so that the full life cycle tracking of the carbon emission is realized.
The method for predicting the carbon emission mainly comprises an emission factor method, a material balance algorithm, an actual measurement method and the like, wherein the emission factor method has the widest application range and the most common application, however, the accuracy of the emission factor is difficult to meet the requirement of an energy unit.
In order to improve the above problems, the present invention provides a method and apparatus for predicting carbon emission data, including: taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network; and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model. The invention fully utilizes the advantages of large electric power data and ensures the comprehensiveness and real-time performance of the data. By means of precise feature analysis, key features affecting carbon emission can be accurately extracted, so that a solid foundation is laid for the establishment of a subsequent carbon emission prediction model, carbon emission data prediction accuracy is improved, and carbon emission data prediction time is shortened.
Further, the present invention reveals the cross-linking between data and the major factors affecting carbon emissions. For the acquired data, the invention reveals the transverse relation among the data, especially the influence characteristics between the energy consumption data and the carbon emission data through factor analysis, and lays a foundation for the carbon emission prediction by using the sample library of the invention.
The above-described scheme is explained in detail below.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a carbon emission data prediction method according to an embodiment of the present invention. As shown in fig. 1, the carbon emission data prediction method in the embodiment of the present invention mainly includes the following steps:
Step S101: taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
step S102: and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
Wherein the key characteristic data affecting carbon emissions includes: various energy consumption, product output, geographic position and weather data of the region.
In one embodiment, when the user is a non-productive unit, the key characteristic data affecting carbon emissions includes: flow of people.
In one embodiment, the non-productive unit comprises: commercial buildings, office buildings, medical buildings, educational buildings.
In one embodiment, the various types of energy sources include at least one of the following: electric power, coal, natural gas, thermal power.
In this embodiment, the emission amount of carbon dioxide is a linear function of the consumption amount of various energy sources, so that an accurate emission amount of CO 2 can be obtained as long as the consumption amount of various energy sources can be accurately predicted. However, in practice, the real-time performance of the acquisition of various energy consumption data is different, the power consumption can be conveniently acquired in real time, and the acquisition of fossil energy consumption has certain hysteresis. Therefore, the invention provides a two-step prediction method, which uses the historical data of the power data and other energy sources (such as coal, natural gas and the like) to predict the current consumption condition of other energy sources, and predicts the carbon emission condition according to the power data and the predicted energy source data. The first step adopts a long-short-term memory network (LongShort Term Memory, LSTM) method based on deep learning, and the second step adopts an autoregressive distribution hysteresis (AutoRegression Distributed Lags, ARDL) method based on time series. As shown in fig. 2.
In this embodiment, the determining of the key characteristic data affecting carbon emission includes:
Adopting a factor analysis method to analyze the correlation between the historical carbon emission data of the user and each preset type of data;
the preset type data having a first n-th large correlation with the user's historical carbon emission data is determined as key feature data affecting carbon emission.
In one embodiment, the factor analysis is a statistical method that merges multiple related features into fewer integrated features. The invention can obtain the comprehensive score through the factor score/variance contribution rate, thereby obtaining the characteristics with larger influence. The factor analysis adopts an analysis of variance method, which data in the data set has the largest contribution to the total carbon emission, a plurality of data with the largest influence on the carbon emission can be determined according to a given threshold value, the data are taken as main factors, other factors which do not play a main role are ignored, and only selected main factors are considered in the later data acquisition, so that the data dimension reduction is realized, and the data acquisition and storage cost is reduced.
For example, table 1 gives an example of the root variance ratio of the features of one different energy type. It can be seen that the cumulative variance ratio of the electric power, coal and natural gas reaches more than 99%, which means that the contribution rate of the three factors to the carbon emission exceeds 99%, so that the threshold value can be selected to be 99%, and the three factors can be selected, and only the three data can be acquired during the later operation data acquisition, thereby reducing the data acquisition quantity and the storage space consumption.
TABLE 1
In this embodiment, the training process of the pre-trained long-short-term memory network includes:
constructing training data by using the user power data of the history period t, the key characteristic data and the power data which influence the carbon emission in the period before the history period t and the key characteristic data which influence the carbon emission in the period after the history period t;
and training an initial long-period memory network by using the training data to obtain the pre-trained long-period memory network, wherein T is [1, T ], and T is the total number of historical periods.
In this embodiment, the training process of the pre-trained autoregressive distributed hysteresis model includes:
The method comprises the steps that user power data of a history period t, key characteristic data influencing carbon emission in a period before the history period t and power data are input into a pre-trained long-short-period memory network, and key characteristic data influencing carbon emission in a period after the history period t, which is output by the pre-trained long-short-period memory network, are obtained;
constructing training data by utilizing key characteristic data influencing carbon emission in a period after the history period t, carbon emission in the history period t and carbon emission in a period after the history period t;
And training an initial autoregressive distribution hysteresis model by using the training data to obtain the pretrained autoregressive distribution hysteresis model, wherein T is [1, T ], and T is the total number of historical time periods.
In one specific embodiment, the carbon accounting database is used for carbon emissions and energy consumption data from the cement industry in 1996-2016 for 21 years, group 651. The following four predictive models were tested separately:
1. predicting CO 2 emission directly by using an LSTM method according to the power consumption data;
2. Predicting CO 2 emission directly by ARDL method according to the power consumption data;
3. Using a twice LSTM approach, the first to predict coal consumption from power consumption, the second to predict CO 2 emissions from power consumption and predicted coal consumption;
4. The two-step prediction method provided by the invention is used for predicting coal consumption according to power consumption by using an LSTM method for the first time and predicting CO 2 emission by using a ARDL method for power consumption and predicted coal consumption for the second time.
The prediction error and calculated time comparison results are shown in Table 2 below:
TABLE 2
From the results in the table it can be seen that:
1. When the power data is directly used to predict the CO 2 emissions data, the method 1 using LSTM is better than the method 2ARDL method, but the calculation time is much longer than the method 2.
2. The prediction error of method 3 is significantly better than methods 1 and 2, and the calculation time is substantially 2 times that of method 1.
3. Method 4, the present method, has far less prediction error than methods 1 and 2, is substantially equivalent to method 3, but has far less computation time than method 3.
Example 2
Based on the same inventive concept, the present invention also provides a carbon emission data prediction apparatus, comprising:
The first analysis module is used for taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network to obtain key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
And the second analysis module is used for taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as the input of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
Preferably, the key characteristic data affecting carbon emission includes: various energy consumption, product output, geographic position and weather data of the region.
Further, when the user is a non-productive unit, the key characteristic data affecting carbon emission includes: flow of people.
Further, the non-productive units include: commercial buildings, office buildings, medical buildings, educational buildings.
Further, the various energy sources include at least one of the following: electric power, coal, natural gas, thermal power.
Preferably, the determining of the key characteristic data affecting carbon emission includes:
Adopting a factor analysis method to analyze the correlation between the historical carbon emission data of the user and each preset type of data;
the preset type data having a first n-th large correlation with the user's historical carbon emission data is determined as key feature data affecting carbon emission.
Preferably, the training process of the pre-trained long-short-term memory network comprises the following steps:
constructing training data by using the user power data of the history period t, the key characteristic data and the power data which influence the carbon emission in the period before the history period t and the key characteristic data which influence the carbon emission in the period after the history period t;
and training an initial long-period memory network by using the training data to obtain the pre-trained long-period memory network, wherein T is [1, T ], and T is the total number of historical periods.
Preferably, the training process of the pre-trained autoregressive distributed hysteresis model comprises:
The method comprises the steps that user power data of a history period t, key characteristic data influencing carbon emission in a period before the history period t and power data are input into a pre-trained long-short-period memory network, and key characteristic data influencing carbon emission in a period after the history period t, which is output by the pre-trained long-short-period memory network, are obtained;
constructing training data by utilizing key characteristic data influencing carbon emission in a period after the history period t, carbon emission in the history period t and carbon emission in a period after the history period t;
And training an initial autoregressive distribution hysteresis model by using the training data to obtain the pretrained autoregressive distribution hysteresis model, wherein T is [1, T ], and T is the total number of historical time periods.
Example 3
Based on the same inventive concept, the invention also provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processor, digital signal processor (DIGITAL SIGNAL Processor, DSP), application specific integrated circuit (Application SpecificIntegrated Circuit, ASIC), off-the-shelf Programmable gate array (Field-Programmable GATEARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular to load and execute one or more instructions within a computer storage medium to implement the corresponding method flow or corresponding functions to implement the steps of a carbon emission data prediction method in the above embodiments.
Example 4
Based on the same inventive concept, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a computer device, for storing programs and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of a carbon emission data prediction method in the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (11)
1. A method for predicting carbon emission data, the method comprising:
Taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network, and obtaining key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
and taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as inputs of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
2. The method of claim 1, wherein the key characteristic data affecting carbon emissions comprises: various energy consumption, product output, geographic position and weather data of the region.
3. The method of claim 2, wherein the key characteristic data affecting carbon emissions when the user is a non-productive unit comprises: flow of people.
4. The method of claim 3, wherein the non-productive units comprise: commercial buildings, office buildings, medical buildings, educational buildings.
5. The method of claim 2, wherein the types of energy sources include at least one of: electric power, coal, natural gas, thermal power.
6. The method of claim 1, wherein the determination of key characteristic data affecting carbon emissions comprises:
Adopting a factor analysis method to analyze the correlation between the historical carbon emission data of the user and each preset type of data;
the preset type data having a first n-th large correlation with the user's historical carbon emission data is determined as key feature data affecting carbon emission.
7. The method of claim 1, wherein the training process of the pre-trained long-short term memory network comprises:
constructing training data by using the user power data of the history period t, the key characteristic data and the power data which influence the carbon emission in the period before the history period t and the key characteristic data which influence the carbon emission in the period after the history period t;
training an initial long-period memory network by using training data to obtain a pre-trained long-period memory network, wherein T is E [1, T ], and T is the total number of history periods.
8. The method of claim 1, wherein the training process of the pre-trained autoregressive distributed hysteresis model comprises:
The method comprises the steps that user power data of a history period t, key characteristic data influencing carbon emission in a period before the history period t and power data are input into a pre-trained long-short-period memory network, and key characteristic data influencing carbon emission in a period after the history period t, which is output by the pre-trained long-short-period memory network, are obtained;
constructing training data by utilizing key characteristic data influencing carbon emission in a period after the history period t, carbon emission in the history period t and carbon emission in a period after the history period t;
and training an initial autoregressive distribution hysteresis model by using training data to obtain a pre-trained autoregressive distribution hysteresis model, wherein T is E [1, T ], and T is the total number of historical time periods.
9. A carbon emission data prediction apparatus, characterized in that the apparatus comprises:
The first analysis module is used for taking current power data of a user, key characteristic data influencing carbon emission in a history period and the power data as inputs of a pre-trained long-short-period memory network to obtain key characteristic data influencing carbon emission in a user prediction period output by the pre-trained long-short-period memory network;
And the second analysis module is used for taking the key characteristic data affecting the carbon emission in the user prediction period and the carbon emission in the history period as the input of a pre-trained autoregressive distribution hysteresis model to obtain the carbon emission in the user prediction period output by the pre-trained autoregressive distribution hysteresis model.
10. A computer device, comprising: one or more processors;
the processor is used for storing one or more programs;
The carbon emission data prediction method according to any one of claims 1 to 8 is implemented when the one or more programs are executed by the one or more processors.
11. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when executed, implements the carbon emission data prediction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410107976.2A CN117634933B (en) | 2024-01-26 | 2024-01-26 | Carbon emission data prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410107976.2A CN117634933B (en) | 2024-01-26 | 2024-01-26 | Carbon emission data prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117634933A CN117634933A (en) | 2024-03-01 |
| CN117634933B true CN117634933B (en) | 2024-05-07 |
Family
ID=90035902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410107976.2A Active CN117634933B (en) | 2024-01-26 | 2024-01-26 | Carbon emission data prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117634933B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563028A (en) * | 2020-05-15 | 2020-08-21 | 周毅 | Data center task scale prediction method based on time series data analysis |
| CN111598289A (en) * | 2020-03-30 | 2020-08-28 | 国网河北省电力有限公司 | Distributed optimization method of integrated energy system considering LSTM photovoltaic output prediction |
| CN115907222A (en) * | 2022-12-26 | 2023-04-04 | 中能融合智慧科技有限公司 | Carbon emission prediction method and system |
| CN116861776A (en) * | 2023-06-30 | 2023-10-10 | 天津大学 | Near real-time carbon emission calculation method based on electric-energy-carbon correlation model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102346188B1 (en) * | 2020-04-08 | 2021-12-31 | 상명대학교산학협력단 | method for forecasting power demanding and apparatus adopting the method |
-
2024
- 2024-01-26 CN CN202410107976.2A patent/CN117634933B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598289A (en) * | 2020-03-30 | 2020-08-28 | 国网河北省电力有限公司 | Distributed optimization method of integrated energy system considering LSTM photovoltaic output prediction |
| CN111563028A (en) * | 2020-05-15 | 2020-08-21 | 周毅 | Data center task scale prediction method based on time series data analysis |
| CN115907222A (en) * | 2022-12-26 | 2023-04-04 | 中能融合智慧科技有限公司 | Carbon emission prediction method and system |
| CN116861776A (en) * | 2023-06-30 | 2023-10-10 | 天津大学 | Near real-time carbon emission calculation method based on electric-energy-carbon correlation model |
Non-Patent Citations (3)
| Title |
|---|
| High Temperature Superheater Wall Temperature Prediction Method Based on ARLD-LSTM Recurrent Neural Network;Kai Zhu等;《2022 4th International Conference on Electrical Engineering and Control Technologies》;20221231;第197-203页 * |
| Impact of COVID-19 on electricity energy consumption: A quantitative analysis on electricity;Zonghan Li等;《International Journal of Electrical Power and Energy Systems》;20220225;第140卷;第108084（1-16）页 * |
| 基于LSTM+MIDAS 深度学习模型的电力需求预测;洪小林;《能源与环保》;20210630;第43卷(第6期);第229-235页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117634933A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215442B (en) | Method, system, device and medium for predicting short-term load of power system | |
| CN105205570A (en) | Power grid power sale quantity prediction method based on season time sequence analysis | |
| CN111754024A (en) | Power industry time sequence prediction method and device based on regression analysis | |
| CN103268519A (en) | Electric power system short-term load forecast method and device based on improved Lyapunov exponent | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN113554213A (en) | Natural gas demand prediction method, system, storage medium and equipment | |
| JP2024077563A (en) | Method, system and storage medium for forecasting ultra-short-term water levels of reservoirs taking into account the effects of dynamic water storage capacity | |
| CN114498619A (en) | Wind power prediction method and device | |
| JP2022510667A (en) | Methods and equipment for predicting energy consumption | |
| CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
| CN111582630A (en) | Method and system for determining low-voltage transformer area line loss rate evaluation value | |
| CN113590682B (en) | Power grid power failure window period generation method and device, electronic equipment and storage medium | |
| CN117634933B (en) | Carbon emission data prediction method and device | |
| CN113902260A (en) | Information prediction method, information prediction device, electronic equipment and medium | |
| CN111026624B (en) | Fault prediction method and device of power grid information system | |
| CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
| CN114417549B (en) | Digital twin object field data processing system based on super computer | |
| CN112766535B (en) | Building load prediction method and system considering load curve characteristics | |
| WO2022222230A1 (en) | Indicator prediction method and apparatus based on machine learning, and device and storage medium | |
| CN112116216B (en) | New energy consumption evaluation method and system based on multiple objects and multiple dimensions | |
| CN114759579A (en) | Power grid active power optimization control system, method and medium based on data driving | |
| CN112668784A (en) | Regional macro economy prediction model and method based on big data | |
| CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
| CN114036823B (en) | Power transformer load control method and device based on coding-decoding and memory mechanism | |
| CN112085459B (en) | Wind power project investment estimation method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |