CN115146537A - Atmospheric pollutant emission estimation model construction method and system based on power consumption - Google Patents
Atmospheric pollutant emission estimation model construction method and system based on power consumption Download PDFInfo
- Publication number
- CN115146537A CN115146537A CN202210816008.XA CN202210816008A CN115146537A CN 115146537 A CN115146537 A CN 115146537A CN 202210816008 A CN202210816008 A CN 202210816008A CN 115146537 A CN115146537 A CN 115146537A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- time
- model
- estimation model
- 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
- 239000003344 environmental pollutant Substances 0.000 title claims abstract description 85
- 231100000719 pollutant Toxicity 0.000 title claims abstract description 85
- 238000010276 construction Methods 0.000 title claims description 6
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 9
- 230000001419 dependent effect Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 238000012795 verification Methods 0.000 claims description 59
- 238000005457 optimization Methods 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 6
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 2
- 229930195733 hydrocarbon Natural products 0.000 description 2
- 150000002430 hydrocarbons Chemical class 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 239000000809 air pollutant Substances 0.000 description 1
- 231100001243 air pollutant Toxicity 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for constructing an atmospheric pollutant emission estimation model based on power consumption, and relates to the technical field of pollutant emission estimation. The method comprises the following steps: acquiring and establishing a data set according to enterprise attribute information, enterprise power consumption, atmospheric pollutant emission and meteorological conditions; matching and acquiring time-by-time power data and time-by-time online monitoring atmospheric pollutant emission data of corresponding enterprises according to the enterprise name, time and space information; establishing and training a machine learning model by taking online monitoring emission of pollutants as a dependent variable and taking information such as enterprise power consumption, time indicator variables, weather and enterprise attributes as independent variables to obtain an initial estimation model; and optimizing the initial estimation model by taking the statistics such as the decision coefficient, the root-mean-square error, the normalized deviation and the like as evaluation indexes to obtain an optimal estimation model. The method optimizes the estimation model, obviously improves the estimation accuracy, and can estimate the atmospheric pollutant emission of enterprises of different scales in multiple industries.
Description
Technical Field
The invention relates to the technical field of pollutant emission estimation, in particular to a method and a system for constructing an atmospheric pollutant emission estimation model based on power consumption.
Background
The industry is one of main emission sources of pollutants such as nitrogen oxides, sulfur dioxide, smoke dust, non-methane total hydrocarbons and the like, and estimation of pollutant emission amount of enterprises in various industries is of great importance to pollution prevention and control.
In order to master the emission condition of industrial source atmospheric pollutants, a typical city (such as a metropolis) aims at key industrial enterprises, and an online pollutant monitoring system is arranged at key positions of a boiler flue, a combustion chamber, a chimney port and the like. The on-line monitoring system is a system for continuously monitoring pollutant parameters in real time, and is mainly used for monitoring indexes such as flue gas, nitrogen oxide, sulfur dioxide, non-methane total hydrocarbon and the like. However, due to the influence of practical factors, a large number of enterprise emission conditions still cannot be monitored on line, so that the research utilizes the existing online monitoring data to train a machine learning model and estimates the enterprise pollutant emission conditions without installing online monitoring equipment.
In the existing pollutant emission estimation research, the pollutant emission amount is estimated based on the time sequence data and characteristic research of the pollutant emission. The learners improve the wavelet neural network model to predict the pollutant emission of the thermal power plant, optimize the feature extraction method and improve the input feature data performance of the neural network. There are studies to apply Long Short Term Memory (LSTM) network algorithms in deep learning to thermal power plant pollutant emission prediction. However, there are still some problems in the prior art:
(1) The method only aims at certain enterprises (such as thermal power plants, gas stations, civil aircrafts and the like) with pollutant emission data, and can not be expanded to enterprises without pollutant emission online monitoring equipment;
(2) Only internal information (such as the operating power of a combustion engine of a thermal power station and the natural gas mass flow of the combustion engine) such as pollutant emission, enterprise operating conditions and the like is utilized, and external information such as seasons, industrial conditions and the like is not considered.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, embodiments of the present invention provide a method and a system for constructing an atmospheric pollutant emission estimation model based on power consumption, which optimize the estimation model, significantly improve estimation accuracy, and accurately estimate pollutant emissions of enterprises of different scales in multiple industries.
The embodiment of the invention is realized by the following steps:
in a first aspect, an embodiment of the present invention provides a method for constructing an atmospheric pollutant emission estimation model based on power consumption, including the following steps:
acquiring and establishing a data set according to enterprise attribute information, enterprise power consumption, atmospheric pollutant emission and meteorological conditions;
matching and acquiring time-by-time power data and time-by-time online monitoring emission data of corresponding enterprises according to enterprise names, time and space information in the enterprise information;
the online pollutant monitoring and emission data are used as dependent variables, enterprise power consumption data, time and enterprise attribute information are used as independent variables to construct a machine learning model, and the machine learning model is trained on the basis of a data set to obtain an initial estimation model;
to determine the coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
In order to solve the technical problems that the estimation of enterprises without pollutant emission monitoring cannot be carried out and the estimation is inaccurate because external information such as seasons, industries, meteorological conditions and the like is not considered in the prior art, the invention establishes an enterprise pollutant emission estimation model based on the data of multiple aspects such as enterprise power consumption data, enterprise information, pollutant emission data, meteorological environment data and the like, adds an independent variable of power consumption into the estimation model, expands the estimation range from individual enterprises in individual industries to all enterprises capable of obtaining the power consumption, estimates the pollutant emission of enterprises in different scales in multiple industries by using the generally covered data of the power consumption, and is favorable for realizing the fine management of enterprise emission and pollution prevention and control; external environment variables such as meteorological factors and seasons are added, an estimation model is optimized, and estimation accuracy is improved.
Based on the first aspect, in some embodiments of the present invention, the method for constructing the model for estimating the amount of atmospheric pollutants emitted based on electricity consumption further includes the following steps:
and selecting the optimal estimation model in the data set according to a plurality of preset verification angles and performing performance verification on the optimal estimation model according to the verification set.
Based on the first aspect, in some embodiments of the present invention, the method for selecting the optimal estimation model in the data set according to a plurality of preset verification angles and performing performance verification on the optimal estimation model according to the verification set includes the following steps:
respectively selecting a verification set corresponding to each angle in the data set according to a preset sample verification angle, a preset month verification angle, a preset time verification angle and a preset enterprise verification angle;
and respectively carrying out performance verification on the optimal estimation model based on the verification set of each selected angle.
Based on the first aspect, in some embodiments of the present invention, the method for constructing the model for estimating the amount of atmospheric pollutants emitted based on electricity consumption further includes the following steps:
and carrying out time series inspection on the enterprise power consumption data and the pollutant emission data, and removing missing values and abnormal values to obtain target enterprise power consumption data and target pollutant emission data.
In a second aspect, an embodiment of the present invention provides a model building system for estimating an amount of atmospheric pollutants based on power consumption, including a data obtaining module, a hourly data module, a model building module, a linear model module, and a model optimizing module, where:
the data acquisition module is used for acquiring and establishing a data set according to the enterprise attribute information, the enterprise power consumption, the atmospheric pollutant emission and the meteorological conditions;
the time-by-time data module is used for matching and acquiring time-by-time electric power data and time-by-time online monitoring emission data of the corresponding enterprise according to the enterprise name, time and space information in the enterprise information;
the model building module is used for building a machine learning model by taking pollutant online monitoring emission data as a dependent variable and taking enterprise power consumption data, time and enterprise attribute information as independent variables, and training the machine learning model based on a data set to obtain an initial estimation model;
a model optimization module for determining a coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
In order to solve the technical problems that in the prior art, the estimation of enterprises without pollutant emission monitoring cannot be carried out and the estimation is inaccurate because external information such as seasons, industries, meteorological conditions and the like is not considered, the system realizes the accurate estimation of the pollutant emission of each enterprise through the cooperation of a data acquisition module, a time-by-time data module, a model construction module, a linear model module, a model optimization module and other modules; establishing an enterprise pollutant emission estimation model based on the data of multiple aspects such as enterprise power consumption data, enterprise information, pollutant emission data, meteorological environment data and the like, adding an independent variable of power consumption into the estimation model, expanding the estimation range from individual enterprises in individual industries to all enterprises capable of acquiring power consumption, estimating the pollutant emission of enterprises in different scales of multiple industries by using the commonly covered data of power consumption, and contributing to the realization of fine management of enterprise emission and pollution prevention and control; external environment variables such as meteorological factors and seasons are added, an estimation model is optimized, and estimation accuracy is improved.
Based on the second aspect, in some embodiments of the present invention, the system for constructing an atmospheric pollutant emission amount estimation model based on electricity consumption further includes a verification module, configured to select an optimal estimation model from the data set according to a plurality of preset verification angles and perform performance verification on the optimal estimation model according to the verification set.
The embodiment of the invention at least has the following advantages or beneficial effects:
the embodiment of the invention provides a method and a system for constructing an atmospheric pollutant emission estimation model based on power consumption, aiming at solving the technical problems that in the prior art, an enterprise without pollutant emission monitoring can not be estimated, and the estimation is inaccurate because external information such as seasons, industries, meteorological conditions and the like is not considered; external environment variables such as meteorological factors and seasons are added, an estimation model is optimized, and estimation accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a method for constructing an atmospheric pollutant emission estimation model based on power consumption according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a model building system for estimating the amount of atmospheric pollutants based on power consumption according to an embodiment of the present invention.
Icon: 100. a data acquisition module; 200. a time-by-time data module; 300. a model building module; 400. a model optimization module; 500. and a verification module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
In the description of the embodiments of the present invention, "a plurality" means at least 2.
Examples
As shown in fig. 1, in a first aspect, an embodiment of the present invention provides a method for constructing an atmospheric pollutant emission estimation model based on power consumption, including the following steps:
s1, acquiring and establishing a data set according to enterprise attribute information, enterprise power consumption, atmospheric pollutant emission and meteorological conditions;
the enterprise information comprises basic information such as enterprise names and enterprise attributes, the meteorological data comprises data of six aspects such as temperature (T), atmospheric pressure (P), east-west wind speed (U), north-south wind speed (V), dew point temperature (D) and planet boundary layer height (PB), the meteorological data can be obtained from an external database, the spatial resolution is 0.25 degrees, the time resolution is 1 hour, and the data are subjected to spatial interpolation by normal transformation and cooperation kriging combined with altitude and processed to 1km grid. The enterprise power consumption data can be obtained from an external database, the time resolution is 1 hour, and the grid is processed to 1km according to the enterprise data. The pollutant emission data can be obtained from an external database, the time resolution is 1 hour, and the data is processed to 1km grids according to enterprise data. And performing a time series check on the power data and the emission data to remove missing values and abnormal values.
S2, matching and obtaining time-by-time electric power data and time-by-time online monitoring emission data of corresponding enterprises according to enterprise names, time and space information in the enterprise information;
s3, using online pollutant monitoring and emission data as dependent variables, using enterprise power consumption data, time and enterprise attribute information as independent variables to construct a machine learning model, and training the machine learning model based on a data set to obtain an initial estimation model;
s4, determining the coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
In order to solve the technical problems that the estimation of enterprises without online pollutant monitoring and emission monitoring can not be carried out and the estimation is inaccurate because external information such as seasons, the industries, and the like are not considered in the prior art, the online pollutant monitoring and emission estimation method based on the online pollutant monitoring and emission monitoring system based on the power consumption data of the enterprises, the attribute information of the enterprises, the online pollutant monitoring and emission data, and the like establishes an online pollutant monitoring and emission estimation model of the enterprises, adds an independent variable of the power consumption into the estimation model, expands the estimation range from individual enterprises in individual industries to all enterprises capable of acquiring the power consumption, estimates the online pollutant monitoring and emission of the enterprises in different scales in multiple industries by using the generally covered data of the power consumption, and is favorable for realizing the fine management of enterprise emission and pollution prevention and control; external environment variables such as seasons, the affiliated industries and the like are added, the estimation model is optimized, and the estimation accuracy is improved.
As shown in fig. 1, according to the first aspect, in some embodiments of the present invention, the method for constructing the model for estimating the amount of exhaust air pollutants based on electric power consumption further includes the following steps:
and S5, selecting in the data set according to a plurality of preset verification angles and performing performance verification on the optimal estimation model according to the verification set.
Further, respectively selecting a verification set corresponding to each angle in the data set according to a preset sample verification angle, a month verification angle, a time verification angle and an enterprise verification angle; and respectively carrying out performance verification on the optimal estimation model based on the verification set of each selected angle.
Based on the sample: randomly extracting 20% of data as a verification set, and taking the other 80% of data as training sets to train models; on a month basis: selecting data of the last 5 days of each month as a verification set, and taking the rest data as a training set; based on time: taking the last 20% of data in the time sequence as a verification set, and taking the other 80% of data as a training set; based on the enterprise: all enterprises are divided into 9 industries, one enterprise is selected as a verification set each time, and other enterprise data of the industry are used as training sets to conduct cross verification. In order to ensure the estimation effect of the estimation model, the estimation performance of the model is evaluated based on a plurality of verification angles such as samples, months, time, enterprises and the like, a verification result is generated, and then the model is conveniently adjusted according to the verification result in the follow-up process, so that the estimation model with the most accurate estimation effect is obtained.
Based on the first aspect, in some embodiments of the present invention, the method for constructing the model for estimating the amount of atmospheric pollutants emitted based on electricity consumption further includes the following steps:
and carrying out time series inspection on the enterprise power consumption data and the pollutant emission data, and removing missing values and abnormal values to obtain target enterprise power consumption data and target pollutant emission data.
In order to ensure the accuracy of data, avoid carrying out invalid processing on redundant and miscellaneous data, carry out time series inspection on enterprise power consumption data and pollutant discharge data, reject incomplete data and abnormal data of disappearance to obtain accurate data, so that carry out accurate estimation analysis in the follow-up.
As shown in fig. 2, in a second aspect, an embodiment of the present invention provides a model building system for estimating an amount of atmospheric pollutants based on power consumption, including a data obtaining module 100, a hourly data module 200, a model building module 300, and a model optimizing module 400, wherein:
the data acquisition module 100 is used for acquiring and establishing a data set according to enterprise attribute information, enterprise power consumption, atmospheric pollutant emission and meteorological conditions;
the hourly data module 200 is configured to obtain hourly power data and hourly online monitoring emission data of the corresponding enterprise according to the enterprise name, time and space information in the enterprise information in a matching manner;
the model building module 300 is used for building a machine learning model by taking pollutant online monitoring emission data as a dependent variable, taking enterprise power consumption data, time and enterprise attribute information as independent variables, and training the machine learning model based on a data set to obtain an initial estimation model;
a model optimization module 400 for determining a coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
In order to solve the technical problems that in the prior art, an enterprise without pollutant emission monitoring cannot be estimated, and estimation is inaccurate due to the fact that external information such as seasons, industries and meteorological conditions is not considered, the system realizes accurate estimation of pollutant emission of each enterprise through cooperation of modules such as a data acquisition module 100, a time-by-time data module 200, a model construction module 300, a linear model module 400 and a model optimization module 400; establishing an enterprise pollutant emission estimation model based on the data of multiple aspects such as enterprise power consumption data, enterprise information, pollutant emission data, meteorological environment data and the like, adding an independent variable of power consumption into the estimation model, expanding the estimation range from individual enterprises in individual industries to all enterprises capable of acquiring power consumption, estimating the pollutant emission of enterprises in different scales of multiple industries by using the commonly covered data of power consumption, and contributing to the realization of fine management of enterprise emission and pollution prevention and control; external environment variables such as meteorological factors and seasons are added, an estimation model is optimized, and estimation accuracy is improved.
As shown in fig. 2, according to the second aspect, in some embodiments of the present invention, the system for constructing an estimation model of atmospheric pollutant emissions based on electricity consumption further includes a verification module 500, configured to select an optimal estimation model from a data set according to a plurality of preset verification angles and perform performance verification on the optimal estimation model according to the verification set.
In order to ensure the estimation effect of the estimation model, the performance effect of the model is verified from a plurality of angles such as samples, months, time, enterprises and the like through the verification module 500 to generate a verification result, so that the model can be conveniently adjusted according to the verification result in the follow-up process to obtain the estimation model with the most accurate estimation effect.
In the embodiments provided in the present application, it should be understood that the disclosed method, system and method may be implemented in other ways. The method and system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (6)
1. A method for constructing an atmospheric pollutant emission estimation model based on power consumption is characterized by comprising the following steps:
acquiring and establishing a data set according to enterprise attribute information, enterprise power consumption, atmospheric pollutant emission and meteorological conditions;
matching and acquiring time-by-time power data and time-by-time online monitoring emission data of corresponding enterprises according to enterprise names, time and space information in the enterprise information;
the online pollutant monitoring and emission data are used as dependent variables, the enterprise power consumption data, time and enterprise attribute information are used as independent variables to construct a machine learning model, and the machine learning model is trained on the basis of a data set to obtain an initial estimation model;
to determine the coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
2. The method for constructing the model for estimating the amount of atmospheric pollutants emitted based on electric power consumption according to claim 1, further comprising the steps of:
and selecting the optimal estimation model in the data set according to a plurality of preset verification angles and performing performance verification on the optimal estimation model according to the verification set.
3. The method for constructing the model for estimating the amount of atmospheric pollutants emitted based on electric power consumption according to claim 2, wherein the method for selecting the optimal estimation model from the data set according to a plurality of preset verification angles and verifying the performance of the optimal estimation model according to the verification set comprises the following steps:
respectively selecting a verification set corresponding to each angle in the data set according to a preset sample verification angle, a month verification angle, a time verification angle and an enterprise verification angle;
and respectively carrying out performance verification on the optimal estimation model based on the verification set of each selected angle.
4. The method for constructing the model for estimating the emission amount of atmospheric pollutants based on electric power consumption according to claim 1, further comprising the following steps of:
and carrying out time series inspection on the enterprise power consumption data and the pollutant emission data, and removing missing values and abnormal values to obtain target enterprise power consumption data and target pollutant emission data.
5. The utility model provides an atmospheric pollutants emission estimates model construction system based on power consumption, its characterized in that includes data acquisition module, hourly data module, model construction module and model optimization module, wherein:
the data acquisition module is used for acquiring and establishing a data set according to the enterprise attribute information, the enterprise power consumption, the atmospheric pollutant emission and the meteorological conditions;
the time-by-time data module is used for matching and acquiring time-by-time electric power data and time-by-time online monitoring emission data of the corresponding enterprise according to the enterprise name, time and space information in the enterprise information;
the model building module is used for building a machine learning model by taking pollutant online monitoring emission data as a dependent variable, taking enterprise power consumption data, time and enterprise information as independent variables, and training the machine learning model based on a data set to obtain an initial estimation model;
a model optimization module for determining a coefficient R 2 And the root mean square error RMSE and the normalized deviation MNB are used as evaluation indexes to optimize the initial estimation model to obtain an optimal estimation model.
6. The system for constructing an atmospheric pollutant emission quantity estimation model based on electricity consumption according to claim 5, further comprising a verification module for selecting the optimal estimation model from the data set according to a plurality of preset verification angles and performing performance verification on the optimal estimation model according to the verification set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210816008.XA CN115146537A (en) | 2022-07-12 | 2022-07-12 | Atmospheric pollutant emission estimation model construction method and system based on power consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210816008.XA CN115146537A (en) | 2022-07-12 | 2022-07-12 | Atmospheric pollutant emission estimation model construction method and system based on power consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115146537A true CN115146537A (en) | 2022-10-04 |
Family
ID=83411797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210816008.XA Pending CN115146537A (en) | 2022-07-12 | 2022-07-12 | Atmospheric pollutant emission estimation model construction method and system based on power consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115146537A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840793A (en) * | 2022-12-12 | 2023-03-24 | 四川大学 | Meteorological space normalization method and system based on random forest |
| CN115879726A (en) * | 2022-12-23 | 2023-03-31 | 中国环境科学研究院 | Method for mutually optimizing and screening power consumption and emission data of enterprise |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| CN111832814A (en) * | 2020-07-01 | 2020-10-27 | 北京工商大学 | Air pollutant concentration prediction method based on graph attention machine mechanism |
| CN114169424A (en) * | 2021-12-03 | 2022-03-11 | 国网浙江省电力有限公司杭州供电公司 | Discharge capacity prediction method based on k nearest neighbor regression algorithm and electricity utilization data |
| CN114169574A (en) * | 2021-11-11 | 2022-03-11 | 国网冀北电力有限公司唐山供电公司 | Method for predicting atmospheric pollution through industrial operation power index |
-
2022
- 2022-07-12 CN CN202210816008.XA patent/CN115146537A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| CN111832814A (en) * | 2020-07-01 | 2020-10-27 | 北京工商大学 | Air pollutant concentration prediction method based on graph attention machine mechanism |
| CN114169574A (en) * | 2021-11-11 | 2022-03-11 | 国网冀北电力有限公司唐山供电公司 | Method for predicting atmospheric pollution through industrial operation power index |
| CN114169424A (en) * | 2021-12-03 | 2022-03-11 | 国网浙江省电力有限公司杭州供电公司 | Discharge capacity prediction method based on k nearest neighbor regression algorithm and electricity utilization data |
Non-Patent Citations (1)
| Title |
|---|
| 吴力波;周阳;陈海波;杨增辉;: "基于智能电网大数据的工业企业大气污染排放特征研究" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840793A (en) * | 2022-12-12 | 2023-03-24 | 四川大学 | Meteorological space normalization method and system based on random forest |
| CN115840793B (en) * | 2022-12-12 | 2024-05-07 | 四川大学 | Meteorological space normalization method and system based on random forest |
| CN115879726A (en) * | 2022-12-23 | 2023-03-31 | 中国环境科学研究院 | Method for mutually optimizing and screening power consumption and emission data of enterprise |
| CN115879726B (en) * | 2022-12-23 | 2023-10-31 | 中国环境科学研究院 | Enterprise production condition and emission monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418609B (en) | Surface-grid-point-based accurate tracing method for secondary atmospheric pollution | |
| CN115146537A (en) | Atmospheric pollutant emission estimation model construction method and system based on power consumption | |
| CN111985567B (en) | Automatic pollution source type identification method based on machine learning | |
| CN115358332A (en) | Atmospheric pollution tracing method for multi-source data | |
| CN110489785A (en) | A kind of online Source Apportionment of atmosphere pollution and system | |
| KR102100739B1 (en) | Method for predicting fine dust occurrence of target area | |
| Chiwewe et al. | Machine learning based estimation of Ozone using spatio-temporal data from air quality monitoring stations | |
| CN116011317B (en) | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion | |
| CN108802856B (en) | AI-based source data dynamic correction and forecast system and working method thereof | |
| CN115420854B (en) | Atmospheric pollutant tracing method based on forward and backward model combination | |
| CN116626233A (en) | Air pollution tracing method based on multi-source data fusion, terminal and storage medium | |
| CN115438848A (en) | PM based on deep mixed graph neural network 2.5 Long-term concentration prediction method | |
| CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
| CN107767081B (en) | Method and device for evaluating atmospheric environmental impact of coal-fired power plant | |
| CN114036736A (en) | Cause and effect network learning method based on local granger cause and effect analysis | |
| Cheng et al. | A synoptic weather-typing approach to project future daily rainfall and extremes at local scale in Ontario, Canada | |
| CN114118613A (en) | Coking soil pollution space distribution prediction optimization method and system | |
| CN114252463A (en) | Urban atmospheric particulate source analysis method | |
| CN109615239B (en) | Urban air quality assessment method based on social network media data | |
| Saramud et al. | A new approach to multi-version decision-making to improve the reliability of environmental monitoring parameters | |
| CN114792057A (en) | AIS data-based high-precision air quality model ship emission list processing method | |
| CN114722635A (en) | Layout method of atmospheric pollutant monitoring sensors in chemical industrial park | |
| Karaca et al. | Application of inductive learning: air pollution forecast in Istanbul, Turkey | |
| Wahid et al. | Computational intelligence estimation of natural background ozone level and its distribution for air quality modelling and emission control | |
| CN114527235B (en) | Real-time quantitative detection method for emission intensity |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221004 |
|
| RJ01 | Rejection of invention patent application after publication |