CN115994613A - Carbon emission monitoring method based on electric carbon model, terminal and storage medium - Google Patents
Carbon emission monitoring method based on electric carbon model, terminal and storage medium Download PDFInfo
- Publication number
- CN115994613A CN115994613A CN202211406192.7A CN202211406192A CN115994613A CN 115994613 A CN115994613 A CN 115994613A CN 202211406192 A CN202211406192 A CN 202211406192A CN 115994613 A CN115994613 A CN 115994613A
- Authority
- CN
- China
- Prior art keywords
- model
- carbon emission
- data
- carbon
- industry
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a carbon emission monitoring method based on an electric carbon model, a terminal and a storage medium, which relate to the field of carbon monitoring, and are used for collecting economic data and energy consumption data in a monitoring area, collecting industry yield data and electricity consumption data in the monitoring industry and splitting and interpolating the collected data; selecting regional variables for constructing an error correction model, constructing the error correction model, measuring and calculating regional carbon emission, and verifying and optimizing measured regional carbon emission data; an ARDL model is constructed, the industrial carbon emission is calculated, and the calculated industrial carbon emission data is verified and optimized. The invention utilizes macroscopic economic data and energy consumption data to establish an electric-carbon conversion model, and monitors regional carbon emission and industry carbon emission. The relation between carbon emission and power consumption in each key industry is searched, so that the evolution trend of the carbon emission is reasonably predicted, and a reference suggestion is provided for carbon emission reduction work.
Description
Technical Field
The invention relates to the field of carbon monitoring, in particular to a carbon emission monitoring method based on an electric carbon model, a terminal and a storage medium.
Background
Currently, carbon emission prediction models are broadly divided into two categories based on different theoretical basis, different perspectives and different prediction concepts: one type is cost analysis and economic model, which comprises a top-down model (such as a macroscopic metering economic model, an input-output model and a computable general balance model), a bottom-up model (such as an engineering economic calculation model, a dynamic energy optimization model and an energy system simulation model), and a mixed model (such as a GLOBAL2100 model, a NEMS model and the like); the other is comprehensive analysis-comprehensive model (such as comprehensive evaluation model of climate change).
As described above, the current prediction method for carbon emission is various, has a simple model, a complex model, a model based on environmental research, and a commonly applicable prediction model, and the prediction results of different models are different, which indicates that the complexity of the carbon emission influencing factors is a great challenge for developing prediction.
And the modeling process of the comprehensive evaluation model needs to collect a large amount of data, manually screen and identify the data, find valuable data, build a corresponding model, and have a certain difficulty in application and popularization because more manpower and material resources are required for the process of predicting the carbon emission. Common comprehensive evaluation models, such as LEAP models and IPAC models, are not wide in application range, and are difficult to meet the prediction of the carbon emission in areas and industries, so that the accuracy and precision of the prediction result of the current carbon emission prediction model are difficult to guarantee.
Disclosure of Invention
The invention provides a carbon emission monitoring method based on an electric carbon model, which can ensure the accuracy and precision of a predicted result by constructing a regional carbon emission data prediction model and an industry carbon emission data prediction model.
The carbon emission monitoring method based on the electric carbon model comprises the following steps:
collecting economic data and energy consumption data in a monitoring area, collecting industry yield data and electricity consumption data in the monitoring industry, and splitting and interpolating the collected data;
selecting regional variables for constructing an error correction model, constructing the error correction model, measuring and calculating regional carbon emission, and verifying and optimizing measured regional carbon emission data;
and thirdly, selecting industry variables for constructing an ARDL model, constructing the ARDL model, measuring and calculating the industrial carbon emission, and verifying and optimizing the measured and calculated industrial carbon emission data.
Further, the macro economic data includes: GDP data, demographic data, and industry yield data;
the energy consumption data includes: regional energy consumption data and power consumption data.
In the second step, the annual energy consumption data is input as a dependent variable, the annual electricity consumption is input as an explanatory variable, and the stability is checked based on the collected economic data and the energy consumption data in the monitoring area.
It should be further noted that, the method for constructing the error correction model in the second step includes:
performing ADF unit root test on the area variable to distinguish whether the area variable is a 1 st order single integral variable or not, and whether the time sequence data is stable or not;
two groups of variables with 1-order single integer are adopted, and an EG two-step method is adopted to construct an error correction model;
the EG two-step method is to take a lag first-order residual term as an error correction term into an equilibrium equation to obtain a final form of an error correction model ECM:
ΔY t ＝β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t
wherein DeltaYt represents the increment of energy consumption in t years, deltaXt represents the increment of electricity consumption in t years, yt-1 represents the energy consumption in t-1 years, and Xt-1 represents the electricity consumption in t-1 years;
the coefficient lambda <0 of the error correction term is the force for measuring the adjustment of the short-term fluctuation of the energy consumption to the long-term balance.
The method is further characterized in that based on the constructed error correction model, the annual energy consumption level of the area is predicted by utilizing the area electricity consumption data, and the area carbon emission is obtained by combining the standard coal emission factor, and the method comprises the following steps:
obtaining a regional annual energy consumption predicted value Y by using an error correction model t ；
Y t ＝Y t-1 +β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t
Calculating regional carbon emission based on the carbon emission factor library;
E t ＝C p *Y t
wherein C is p Is the standard coal emission factor.
In the third step, the industry yield sequence after season adjustment is used as a dependent variable to be input, the industry electricity consumption sequence is used as an explanatory variable to be input, and a bivariate ARDL model is constructed;
the ARDL model is in the form of:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q
(wherein p and q are each Y t ，X t Hysteresis order of (2)
Wherein Y is t For t years of industrial yield, X t For the power consumption of industry in the t year, p and q are Y respectively t And X t Is a hysteresis order of (2);
a multivariate ARDL model was also constructed, the form was as follows:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q +α 0 Z t +α 1 Z t-1 +α 2 Z t-2 +...+α s Z t-s
(wherein p, q, s are each Y t ，X t ，Z t Hysteresis order of (2)
Wherein Y is t For t years of industrial yield, X t For the power consumption of the industry of the year t, Z t For the GDP of the industry of the t year, p, q and s are Y respectively t、 X t、 Z t Is a hysteresis order of (2).
It should be further noted that, in the third step, the hysteresis order is also determined;
the following modes are adopted: firstly setting a maximum hysteresis order of a model, performing OLS regression on the model, judging the significance of the coefficient, if the model is not significant, rejecting the model and then re-performing OLS regression until the coefficient of the final period is not significant to 0;
AIC/BIC information criteria are also configured; AIC and BIC are red pool information criterion value and Bayesian information criterion value respectively, in order to demonstrate the punishment applied by adding variable to the model;
and (3) performing white noise test on the residual error of the ARDL model, and if the residual error is not white noise, expanding the hysteresis period number until the available information in the residual error is extracted.
It should be further noted that, in the third step, the industry carbon emission measurement and calculation uses an ARDL model to obtain a yield predicted value Yt;
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q
(wherein p and q are each Y t ，X t Hysteresis order of (2)
Screening product carbon emission factors of key industries to calculate carbon emission levels of the industries based on seasonal factors and a carbon emission factor library;
E t ＝C p *S t *Y t 。
the invention also provides a terminal comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the carbon emission monitoring method based on the electric carbon model when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the carbon emission monitoring method based on an electrical carbon model.
From the above technical scheme, the invention has the following advantages:
the carbon emission monitoring method based on the electric carbon model provided by the invention utilizes historical electric power, energy and carbon emission data to establish an electric-carbon conversion model, and monitors regional carbon emission and industrial carbon emission. And constructing an error correction model by using regional electricity data, searching for the relation between carbon emission and electricity consumption, constructing a bivariate ARDL model by using key industry electricity data, and monitoring the relation between carbon emission and electricity consumption of each key industry so as to reasonably predict the evolution trend of the carbon emission and provide a reference suggestion for carbon emission reduction work.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an embodiment of a carbon emission monitoring method based on an electrical carbon model;
FIG. 2 is a flow chart of a carbon emission monitoring method based on an electrical carbon model;
FIG. 3 shows the trend of TCI sequence and original sequence after adjustment of X-12.
Detailed Description
As shown in fig. 1 and 2, the present invention provides a schematic representation provided in an electric carbon model-based carbon emission monitoring method that can acquire and process associated data based on artificial intelligence techniques, merely by way of illustration of the basic concepts of the present invention. The carbon emission monitoring method utilizes a digital computer or a machine controlled by the digital computer to simulate, extend and expand the intelligence of a person, sense the environment, acquire knowledge and use the knowledge to acquire the theory, the method, the technology and the application device of the optimal result.
The technology with a hardware level in the carbon emission monitoring method of the invention also has a software level technology. Hardware-level technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The technology of the software layer comprises a computer visual angle technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The carbon emission monitoring method is based on the technology of artificial neural network, confidence network, reinforcement learning, transfer learning, induction learning, teaching learning and the like, and a prediction model is constructed to realize carbon emission monitoring of a monitoring area and monitoring industry.
The carbon emission monitoring method based on the electric carbon model is applied to one or more terminals, wherein the terminals are equipment capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware comprises, but is not limited to, a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable gate array (Field-Programmable Gate Array, FPGA), a digital processor (Digital Signal Processor, DSP), an embedded equipment and the like.
The terminal may be any electronic product that can interact with a user, such as a personal computer, tablet, smart phone, personal digital assistant (Personal Digital Assistant, PDA), interactive web tv (Internet Protocol Television, IPTV).
The terminal may also include network devices and/or user devices. Wherein the network device includes, but is not limited to, a single network server, a server group composed of a plurality of network servers, or a Cloud based Cloud Computing (Cloud Computing) composed of a large number of hosts or network servers.
The network in which the terminal is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), and the like.
The carbon emission monitoring method based on the electric carbon model of the present invention will be described in detail with reference to fig. 1 to 2, and the carbon emission monitoring method may be applied to carbon emission monitoring of some areas, such as an administrative area or an industrial area in a city, an area where a factory is located, or an area defined by a user. And the method can also analyze carbon emission of one industry, such as carbon emission monitoring of the steel industry, nonferrous metal exploitation processing industry and chemical industry. Evaluating whether a region or industry carbon emissions meets specifications has a positive effect on achieving a carbon spike.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1-2, a flowchart of a method for monitoring carbon emission based on an electric carbon model in an embodiment is shown, the method comprising:
s101, collecting economic data and energy consumption data in a monitoring area, collecting industry yield data and electricity consumption data in the monitoring industry, and splitting and interpolating the collected data;
in particular, the data of the present invention includes macro-economic data and energy consumption data. The macro economic data include GDP, population, industry output and the like, and the energy consumption data comprise regional energy consumption, power consumption and other main product energy consumption data. The method also relates to industry yield data and electricity consumption data, and specific data can be obtained according to actual needs.
The invention also splits the acquired data, namely, the data set is primarily divided into two types of model training sets and verification sets according to the characteristics of data quality, frequency, missing degree and the like.
If the data is missing, the invention can interpolate the data. In the invention, the previous year data is generally easy to obtain, the integrity of the data is also good, and for few quarterly or monthly missing data, the method based on seasons and the like is used for completing, and the method of linear interpolation, virtual variable setting and the like is used for simple processing.
S102, selecting regional variables for constructing an error correction model, constructing the error correction model, measuring and calculating regional carbon emission, and verifying and optimizing measured regional carbon emission data;
in the embodiment of the invention, the model variable is selected firstly, and the selected model variable is determined according to the set target of the model and the actual demand. The electric carbon model is set for searching a long-term equilibrium relation between the total regional energy consumption and the electric power consumption, so that the annual energy consumption is considered to be input as a dependent variable, the annual electricity consumption is considered to be input as an explanatory variable, and the stability is checked based on the economic data and the energy consumption data set which are collected in the previous step and related to the regional energy consumption. In order to improve the interpretability of the model, more variables, such as regional GDP speed-increasing variables, can be also included, and the synergistic relationship among the multiple variables is checked to analyze more factors influencing the energy consumption level.
In the process of constructing the error correction model, in order to establish a long-term equilibrium relationship between energy consumption and power consumption, the error correction model is constructed by utilizing inter-variable cooperative check, and the error correction model measures the correction trend of short-term fluctuation of a horizontal value between variables with the cooperative relationship in a long term, and is mainly applied to the field of macroscopic economic prediction.
The method comprises the following specific steps:
1. firstly, performing ADF unit root test on two groups of variables, namely annual energy consumption and annual electricity consumption, extracted from a data set to distinguish whether the two variables are 1-order single integral variables or not, and whether time sequence data are stable or not, which is the premise of constructing an error correction model;
2. the method has two groups of variables with 1-order single integer, and an error correction model can be constructed by adopting EG two-step method or Johanson synergistic test.
The EG two-step method is mainly aimed at the mutual coordination test between the bivariate of the I (1), OLS regression is directly carried out on the bivariate to obtain an OLS residual error, white noise test is carried out on the residual error, and if the residual error passes, the regression equation is a long-term equilibrium equation. Taking the lag first-order residual term as an error correction term into an equilibrium equation, and obtaining the final form of an error correction model ECM:
ΔY t ＝β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t
wherein DeltaYt represents the increment of energy consumption in t years, deltaXt represents the increment of electricity consumption in t years, yt-1 represents the energy consumption in t-1 years (last year), xt-1 represents the electricity consumption in t-1 years (last year), and the coefficient (lambda < 0) of the error correction term can measure the force of adjusting the short-term fluctuation of the energy consumption to the long-term balance.
In the Johanson coordination method in the embodiment, a coordination relation between energy consumption and power consumption is found through the inspection of a coordination rank, and a vector error correction model is further constructed through a vector system (VRA).
The regional annual energy consumption level can be predicted by using regional power consumption data through the constructed error correction model, and the regional carbon emission can be obtained by combining the standard coal emission factors, and the method mainly comprises the following steps:
and obtaining the regional annual energy consumption predicted value Yt by using an error correction model.
Y t ＝Y t-1 +β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t 。
The invention can calculate regional carbon emission based on the carbon emission factor library.
E t ＝C p *S t *Y t
Wherein C is p Is the standard coal emission factor.
The method is used for verifying and optimizing the measured and calculated regional carbon emission data, and model verification is to utilize a data verification set of a model to verify the accuracy of the model; and secondly, based on the carbon emission data published by government authorities, the problems of excessive identification, setting deviation and the like possibly existing in the model are corrected.
The invention also optimizes regional carbon emission data. Tuning includes expansion of model variables and periodic updates of hysteresis to ensure accuracy of model predictions.
The acquired data is also updated. The method can update the data of the original variables of the model according to the time sequence frequency required by the model, and analyze and adjust the new time sequence in seasons. Typically, quarterly or monthly data is updated in units of years.
And thirdly, selecting industry variables for constructing an ARDL model, constructing the ARDL model, measuring and calculating the industrial carbon emission, and verifying and optimizing the measured and calculated industrial carbon emission data.
According to the method, the regional carbon emission calculation is performed, the carbon emission calculation can be performed according to the requirement for specific industries, and the test verification is performed after a model is built in a targeted mode by selecting sample data.
When the industry variable for constructing the ARDL model is selected, the long-term equilibrium relation between the industry yield sequence and the electricity consumption sequence is discovered based on the important industry yield and electricity consumption data. Considering that the industrial yield has obvious seasonal characteristics, the analysis of the same-ratio trend is difficult to carry out, firstly, the influence of seasonal factors is removed by using a seasonal adjustment method, the data noise is reduced, and the time trend of the sequence is displayed;
secondly, in order to reduce the influence of the interpretation variable (industrial electricity consumption and the like) of the lag infinity period on the current period value of the sequence, the invention takes the industrial yield sequence after season adjustment as dependent variable input, takes the industrial electricity consumption sequence as interpretation variable input, and constructs a bivariate ARDL model (autoregressive distribution lag model). The ARDL model contains both lag terms of the interpreted variables and lag terms of the interpreted variables, and is commonly used for time series analysis, and the basic form is:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +…+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +…+γ q X t-q
(wherein p and q are each Y t ，X t Hysteresis order of (2)
Wherein Y is t For t years of industrial yield, X t For the power consumption of industry in the t year, p and q are Y respectively t And X t Is a hysteresis order of (2). In order to improve the interpretability of the model, more variables such as industry GDP, population, other variables of industry and the like can be included besides the electric quantity, and a multi-element ARDL model is constructed in the following form:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +…+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +…+γ q X t-q +α 0 Z t +α 1 Z t-1 +α 2 Z t-2 +…+α s Z t-s
(wherein p, q, s are each Y t ，x t ，z t Hysteresis order of (2)
Wherein Y is t For t years of industrial yield, X t For the power consumption of the industry of the year t, Z t For the t year industry GDP (or other variables), p, q and s are Y respectively t 、X t 、Z t Is a hysteresis order of (2).
In the process of constructing the ARDL model, the sequence is influenced by the interpretation variable of the lag infinity. Therefore, improvement based on the error correction model is needed to construct the ARDL model. The method mainly comprises the following steps:
1. firstly, season adjustment is carried out on a yield sequence and a power consumption sequence with seasonal factors, and common methods are a regression method, a moving average method, a SEATS, a decomposition method, X-12 arima and the like. The regression method and the moving average method have more limiting factors, and the X-12 arima method can flexibly process extreme values, and the original sequence is pushed forward and pushed backward to be expanded by utilizing the arima modeling method, so that the application is wider.
The basic principle is based on the idea of 'centralized moving average', the span of the moving average is set according to the actual seasonal trend, and finally the seasonal adjustment factor is obtained. The invention uses a 4-phase moving average for quarter data and a 12-phase moving average for month data.
2. The output sequence and the electricity consumption sequence adjusted by the X-12 arima method only have time trend and irregular variation items, and seasonal factors are removed, and the basic form is as follows:
Y t ＝T t +C t +I t or Y t ＝T t *C t *I t
(wherein T t 、C t 、I t Trend term, period term and irregular variation term of time series Yt respectively
The X-12 method generally considers that the time series has two forms (addition or multiplication) as above, and in the field of socioeconomic, a multiplication form is often used to represent the time series. The TCI sequence after season adjustment can better show long-term trend, plays a role in smoothing or eliminating season fluctuation on the original sequence, and enables the season or month data to be synchronously compared.
Taking the white spirit yield data from 1 month 2002 to 12 months 2021 as an example, as shown in fig. 3, the trend of the TCI sequence and the original sequence after adjustment by X-12 is shown in the graph. It is obvious that the TCI sequence subjected to season adjustment smoothens the noise of the original sequence, and the trend of the original sequence is better displayed.
3. The key of constructing the ARDL model is to select a proper hysteresis order and ensure that the model residual is white noise.
The method of determining the hysteresis order is generally as follows: one is the sequential t-principle (general-specific sequential T rule). Firstly, setting a maximum hysteresis order of a model, performing OLS regression on the model, and rejecting the model after the final period by examining the significance of the coefficient of the final period if the model is not significant, and re-performing OLS regression until the coefficient of the final period is not significant to 0;
and secondly, AIC/BIC information criterion method. AIC and BIC are red pool information criterion value and Bayesian information criterion value respectively, in order to demonstrate the punishment applied because of the model increases the variable, the smaller AIC, the more rational to demonstrate model setting and variable selection;
thirdly, white noise detection is carried out on the residual error of the model, if the residual error is not white noise, the hysteresis period number is properly enlarged until the available information in the residual error is extracted. In the above manner, if a selection conflict occurs, the most lagging period is generally selected in a conservative strategy.
The method for measuring and calculating the regional carbon emission comprises the following steps:
1. and obtaining a yield predicted value Yt by using the ARDL model.
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q
(wherein p and q are each Y t ，X t Hysteresis order of (2)
2. Based on seasonal factors and a carbon emission factor library, the carbon emission factors (such as steel, nonferrous metals, chemical industry and the like) of products in the key industries are screened, and the carbon emission level in the key industries can be calculated.
E t ＝C p *S t *Y t
(wherein C p 、S t 、Y t The carbon emission factor, the seasonal factor and the predicted yield value of the product are respectively
The method for verifying and optimizing the measured and calculated industrial carbon emission data comprises the following steps:
1. verifying the ARDL model is to utilize a data verification set of the model to verify the accuracy of the model; and (3) comparing and analyzing based on published carbon emission data, and correcting problems such as excessive identification, setting deviation and the like possibly existing in the model.
2. The invention also adjusts parameters of the ARDL model. The method specifically comprises the steps of expanding model variables and periodically updating the hysteresis period so as to ensure the accuracy of model prediction.
3. Industry data is also updated. According to the time sequence frequency required by the model, the data of the original variable of the model is updated, and the new time sequence is subjected to seasonal analysis and adjustment.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The present invention provides the elements and algorithm steps of the examples described in the embodiments disclosed in the carbon emission monitoring method based on the electric carbon model, which can be implemented in electronic hardware, computer software, or a combination of both, and in order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described in terms of functions in the above description. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The carbon emission monitoring method based on the electric carbon model is the unit and algorithm steps of the examples described in connection with the embodiments disclosed herein, and can be implemented in electronic hardware, computer software, or a combination of both, and to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described in terms of functionality in the foregoing description. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In a non-transitory computer readable storage medium, a program product is stored that enables a carbon emission monitoring method based on an electrical carbon model. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
In the carbon emission monitoring method, computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or power server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A carbon emission monitoring method based on an electrical carbon model, the method comprising:
collecting economic data and energy consumption data in a monitoring area, collecting industry yield data and electricity consumption data in the monitoring industry, and splitting and interpolating the collected data;
selecting regional variables for constructing an error correction model, constructing the error correction model, measuring and calculating regional carbon emission, and verifying and optimizing measured regional carbon emission data;
and thirdly, selecting industry variables for constructing an ARDL model, constructing the ARDL model, measuring and calculating the industrial carbon emission, and verifying and optimizing the measured and calculated industrial carbon emission data.
2. The method for carbon emission monitoring based on an electric carbon model of claim 1, wherein the macro-economic data comprises: GDP data, demographic data, and industry yield data;
the energy consumption data includes: regional energy consumption data and power consumption data.
3. The method for carbon emission monitoring based on an electric carbon model as claimed in claim 1,
and step two, inputting annual energy consumption data as dependent variables, inputting annual electricity consumption as explanatory variables and performing stability test based on the collected economic data and energy consumption data in the monitoring area.
4. The method for monitoring carbon emissions based on an electric carbon model of claim 1, wherein the constructing an error correction model in the second step comprises:
performing ADF unit root test on the area variable to distinguish whether the area variable is a 1 st order single integral variable or not, and whether the time sequence data is stable or not;
two groups of variables with 1-order single integer are adopted, and an EG two-step method is adopted to construct an error correction model;
the EG two-step method is to take a lag first-order residual term as an error correction term into an equilibrium equation to obtain a final form of an error correction model ECM:
ΔY t ＝β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t
wherein DeltaYt represents the increment of energy consumption in t years, deltaXt represents the increment of electricity consumption in t years, yt-1 represents the energy consumption in t-1 years, and Xt-1 represents the electricity consumption in t-1 years;
the coefficient lambda of the error correction term is less than 0, and the coefficient lambda is the force for measuring the adjustment of the short-term fluctuation of the energy consumption to the long-term balance.
5. The carbon emission monitoring method based on an electric carbon model according to claim 4, wherein the regional carbon emission is obtained by predicting regional annual energy consumption level based on the constructed error correction model and using regional power consumption data and combining standard coal emission factors, and the steps of:
obtaining a regional annual energy consumption predicted value Y by using an error correction model t ；
Y t ＝Y t-1 +β 1 ΔX t -λ(Y t-1 -α 0 -α 1 X t-1 )+ε t
Calculating regional carbon emission based on the carbon emission factor library;
E t ＝C p *Y t
wherein C is p Is the standard coal emission factor.
6. The method for carbon emission monitoring based on an electric carbon model as claimed in claim 1,
step three, inputting the industry yield sequence after season adjustment as a dependent variable, and inputting the industry electricity consumption sequence as an explanatory variable to construct a bivariate ARDL model;
the ARDL model is in the form of:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q
wherein p and q are each Y t ，X t Hysteresis order of Y t For t years of industrial yield, X t For the power consumption of industry in the t year, p and q are Y respectively t And X t Is a hysteresis order of (2);
a multivariate ARDL model was also constructed, the form was as follows:
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q +α 0 Z t +α 1 Z t-1 +α 2 Z t-2 +...+α s Z t-s
wherein p, q, s are each Y t ，X t ，Z t Hysteresis order of Y t For t years of industrial yield, X t For the power consumption of the industry of the year t, Z t For the GDP of the industry of the t year, p, q and s are Y respectively t 、X t 、Z t Is a hysteresis order of (2).
7. The method for carbon emission monitoring based on an electric carbon model of claim 6, wherein in step three, a hysteresis order is also determined;
the following modes are adopted: firstly setting a maximum hysteresis order of a model, performing OLS regression on the model, judging the significance of the coefficient, if the model is not significant, rejecting the model and then re-performing OLS regression until the coefficient of the final period is not significant to 0;
AIC/BIC information criteria are also configured; AIC and BIC are red pool information criterion value and Bayesian information criterion value respectively, in order to demonstrate the punishment applied by adding variable to the model;
and (3) performing white noise test on the residual error of the ARDL model, and if the residual error is not white noise, expanding the hysteresis period number until the available information in the residual error is extracted.
8. The method for carbon emission monitoring based on an electric carbon model as claimed in claim 6,
in the third step, the industrial carbon emission measurement and calculation is to calculate a yield predicted value Yt by using an ARDL model;
Y t ＝β 0 +β 1 Y t-1 +β 2 Y t-2 +...+β p Y t-p +γ 0 X t +γ 1 X t-1 +γ 2 X t-2 +...+γ q X t-q
screening product carbon emission factors of key industries to calculate carbon emission levels of the industries based on seasonal factors and a carbon emission factor library;
E t ＝C p *S t *Y t 。
9. a terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the carbon emission monitoring method based on an electric carbon model as claimed in any one of claims 1 to 8 when the program is executed.
10. A non-transitory computer readable storage medium, having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the carbon emission monitoring method based on an electrical carbon model as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406192.7A CN115994613A (en) | 2022-11-10 | 2022-11-10 | Carbon emission monitoring method based on electric carbon model, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406192.7A CN115994613A (en) | 2022-11-10 | 2022-11-10 | Carbon emission monitoring method based on electric carbon model, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115994613A true CN115994613A (en) | 2023-04-21 |
Family
ID=85989502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211406192.7A Pending CN115994613A (en) | 2022-11-10 | 2022-11-10 | Carbon emission monitoring method based on electric carbon model, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994613A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992265A (en) * | 2023-09-22 | 2023-11-03 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN117273276A (en) * | 2023-10-10 | 2023-12-22 | 南方电网能源发展研究院有限责任公司 | Carbon emission monitoring method and device based on electric power data |
-
2022
- 2022-11-10 CN CN202211406192.7A patent/CN115994613A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992265A (en) * | 2023-09-22 | 2023-11-03 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN116992265B (en) * | 2023-09-22 | 2024-01-09 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN117273276A (en) * | 2023-10-10 | 2023-12-22 | 南方电网能源发展研究院有限责任公司 | Carbon emission monitoring method and device based on electric power data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115994613A (en) | Carbon emission monitoring method based on electric carbon model, terminal and storage medium | |
| Perla et al. | Equilibrium imitation and growth | |
| Wang et al. | Forecasting the monthly iron ore import of China using a model combining empirical mode decomposition, non-linear autoregressive neural network, and autoregressive integrated moving average | |
| CN109376953B (en) | Medium-and-long-term electric quantity prediction method and system | |
| Zeng et al. | A novel multivariate grey model for forecasting the sequence of ternary interval numbers | |
| CN113205207A (en) | XGboost algorithm-based short-term power consumption load fluctuation prediction method and system | |
| Sanyal et al. | Calibrating building energy models using supercomputer trained machine learning agents | |
| Cordova et al. | Combined electricity and traffic short-term load forecasting using bundled causality engine | |
| CN111310981A (en) | Reservoir water level trend prediction method based on time series | |
| CN112418921A (en) | Power demand prediction method, device, system and computer storage medium | |
| CN116822997B (en) | Real-time carbon emission accounting method and device considering green power | |
| CN112148557A (en) | Method for predicting performance index in real time, computer equipment and storage medium | |
| Lee et al. | A bottom-up model of industrial energy system with positive mathematical programming | |
| Cai et al. | Model uncertainty and energy technology policy: The example of induced technical change | |
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| Ruan et al. | Estimating demand flexibility using Siamese LSTM neural networks | |
| CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
| CN111967652B (en) | Double-layer collaborative real-time correction photovoltaic prediction method | |
| JP6628700B2 (en) | Weather information forecasting device and power demand forecasting device | |
| CN115309052B (en) | Online correction method for industrial real-time data time sequence prediction result | |
| CN113449933B (en) | Regional medium-term load prediction method and device based on clustering electric quantity curve decomposition | |
| JPH0922402A (en) | Estimating method for daily maximum power demanded | |
| JPH09233700A (en) | Method of evaluating reliability on estimation of day maximum demand power | |
| CN114971736A (en) | Power metering material demand prediction method and device, electronic equipment and storage medium | |
| CN114154697A (en) | House maintenance resource prediction method and device, computer equipment and storage medium |
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 |