CN114626627A - Monitoring and early warning system for carbon emission in area - Google Patents
Monitoring and early warning system for carbon emission in area Download PDFInfo
- Publication number
- CN114626627A CN114626627A CN202210309529.6A CN202210309529A CN114626627A CN 114626627 A CN114626627 A CN 114626627A CN 202210309529 A CN202210309529 A CN 202210309529A CN 114626627 A CN114626627 A CN 114626627A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- data
- consumption
- module
- trend
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 120
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 119
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 32
- 230000002265 prevention Effects 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 31
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 239000003502 gasoline Substances 0.000 claims description 23
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 20
- 239000007789 gas Substances 0.000 claims description 18
- 238000004140 cleaning Methods 0.000 claims description 12
- 230000005611 electricity Effects 0.000 claims description 11
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 10
- 239000001569 carbon dioxide Substances 0.000 claims description 10
- 230000007774 longterm Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 239000002737 fuel gas Substances 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 18
- 230000008859 change Effects 0.000 abstract description 3
- 230000015654 memory Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008033 biological extinction Effects 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000006386 neutralization reaction Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a monitoring and early warning system for carbon emission in a region, which comprises: the system comprises a data acquisition module, a data processing module, a trend prediction module and a prevention alarm module; the data acquisition module is used for acquiring original data for determining carbon emission in real time; the data processing module is used for processing the original data acquired in real time and calculating carbon emission; the trend prediction module is used for predicting the future trend of carbon emission according to the processed original data and the carbon emission calculation result; the prevention alarm module is used for performing prevention alarm according to the carbon emission trend prediction result. The method not only calculates the carbon emission amount through various types of raw data acquired in real time, but also carries out the future trend development change of each type of data through various types of raw data acquired in real time, and carries out early warning in time after the preset carbon emission development plan is exceeded, so that the real-time monitoring and the advanced early warning of the carbon emission in the area are realized.
Description
Technical Field
The invention belongs to the technical field of intelligent monitoring and early warning, and particularly relates to a monitoring and early warning system for carbon emission in a region.
Background
With global warming, greenhouse gas emissions of carbon dioxide have attracted widespread attention; energy consumption and carbon emission problems become important restriction factors for enterprise development, carbon emission reduction is the core significance of carbon neutralization and the key direction of the target realization, and accurate measurement and comprehensive monitoring of carbon emission are the primary tasks of carbon emission reduction. Although the energy supply side is an important area for carbon emission generation, the production thereof serves for consumption, and the energy consumption side directly or indirectly obtains economic and environmental benefits from high energy consumption and high emission of the energy supply side. Based on the method, in order to balance the supply side responsibility and the consumption side responsibility of the carbon emission and avoid the unfair problem caused by the transfer of the carbon emission responsibility, the accurate measurement and the comprehensive monitoring of the carbon emission at the energy consumption side are enhanced, and a credible data support is provided for a 'double-carbon' target.
However, the distribution of energy statistics tends to have a long time lag (one year or more). For example, the "yearbook for Chinese energy statistics" generally releases the energy statistics data of the previous year in the next year, so that the accounting of the carbon emission data has a time lag of at least one and a half years. In addition, energy activity data is typically only counted on a yearly scale, and only a few countries publish monthly energy statistics. Therefore, carbon emission data sets typically account for national carbon emissions and provide monitoring and forewarning only on an annual scale.
Current carbon emission data sets have failed to meet the higher demands placed on carbon emission monitoring. Under the background of taking climate actions and successively declaring a 'carbon neutralization' plan in various countries around the world, carbon emission data has time lag of one to two years, which means that the carbon emission level cannot be monitored in real time and at high frequency, the latest carbon emission change condition cannot be known, and the action effect of various climate policies cannot be evaluated in time; secondly, annual emission data cannot reflect higher-frequency (day-level or hour-level) carbon emission information, and it is difficult to perform research on finer time granularity on a carbon emission change rule, so that the development trend of carbon emission cannot be predicted in real time.
The LSTM (Long Short-Term Memory network) is a time-cycle neural network and is specially designed for solving the problems of gradient extinction and gradient explosion of RNN. Compared with RNN, LSTM has a unique design structure, which adds an input gate, an output gate and a forgetting gate in a hidden layer, and uses a memory state unit to store and process long-time sequence information, and is very suitable for processing and predicting important events with very long intervals and delays in time sequence.
Therefore, there is a need for a regional carbon emission monitoring and early warning system based on LSTM to solve the above problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides a monitoring and early warning system for carbon emission in a region, relevant data of carbon emission in the region are monitored in real time, so that the carbon emission is calculated in real time, the development trend of each item of data and the development trend of the carbon emission are intelligently predicted in real time in the future, and the real-time calculation and intelligent prediction early warning of the development trend of the carbon emission are really realized.
In order to achieve the above object, the present invention provides a system for monitoring and early warning carbon emission in a region, comprising: the system comprises a data acquisition module, a data processing module, a trend prediction module and a prevention alarm module;
the data acquisition module is used for acquiring original data for determining carbon emission in real time;
the data processing module is used for processing the original data acquired in real time and calculating carbon emission;
the trend prediction module is used for predicting the future trend of the carbon emission according to the processed original data and the carbon emission calculation result;
the prevention alarm module is used for performing prevention alarm according to the carbon emission trend prediction result.
Optionally, the raw data for determining carbon emissions comprises: water consumption, electricity consumption, gas consumption and gasoline consumption.
Optionally, the data processing module includes: a cleaning unit and an accounting unit;
the cleaning unit is used for cleaning the original data;
and the accounting unit is used for performing carbon emission accounting according to the cleaned original data.
Optionally, the manner of cleaning the raw data includes: removing repeated items and abnormal values, supplementing missing values by using a linear interpolation method, and uniformly processing the time resolution of data.
Optionally, the accounting unit obtains the carbon emission through an accounting formula;
the accounting formula is as follows:
carbon dioxide emission (water consumption x 0.91+ electricity consumption x 0.785+ gas consumption x 0.19+ gasoline consumption x 2.7)
The unit of carbon dioxide emission is kilogram, the unit of water consumption is ton, the unit of electricity consumption is degree, the unit of gas consumption is cubic meter, and the unit of gasoline consumption is liter.
Optionally, the trend prediction module comprises: the system comprises a model building unit, a database and a trend prediction unit;
the model building unit is used for building an LSTM neural network;
the database is used for storing the cleaned original data;
the trend prediction unit is used for training the LSTM neural network according to the cleaned original data and predicting the carbon emission trend based on the trained LSTM neural network.
Optionally, the LSTM neural network comprises: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the cleaned original data and sequencing the original data according to a time sequence;
the hidden layer is used for iteratively learning short-range and long-range semantic features of the time series data;
the output layer is used for outputting a prediction result;
the LSTM neural network further comprises LSTM network parameters;
the LSTM network parameters comprise a learning rate, iteration times and stepsize.
Optionally, the trend prediction model comprises: the system comprises a water consumption trend prediction model, a power consumption trend prediction model, a gas consumption trend prediction model, a gasoline consumption trend prediction model and a carbon emission trend prediction model;
the trend prediction module is used for predicting the future trend, including short-term trend prediction, medium-term trend prediction and long-term trend prediction.
Optionally, the precautionary alarm module comprises: the device comprises a water consumption alarm module, a power consumption alarm module, a gas consumption alarm module, a gasoline consumption alarm module and a carbon emission alarm module.
Optionally, after each type of the trend prediction model predicts a future trend, the prediction result is transmitted to each type of corresponding alarm module in the prevention alarm module in real time, and if the prediction result has a deviation from a preset threshold value, the corresponding alarm module alarms;
after any one of the water consumption alarm module, the power consumption alarm module, the fuel gas consumption alarm module and the gasoline consumption alarm module gives an alarm, the carbon emission alarm module gives an alarm at the same time; the more the number of the alarm modules for alarming is, the higher the response level of the carbon emission alarm module for alarming is.
Compared with the prior art, the invention has the following advantages and technical effects:
the method comprises the steps of collecting various kinds of original data of carbon emission in a determined area in real time through a data collection module, and calculating the carbon emission in real time through a carbon emission accounting formula in a data processing module; the method is characterized in that various kinds of raw data collected in real time within a period of time are used as training data to train a network model in a trend prediction module, and the trained network model is used for predicting the future development trend of various kinds of real-time raw data, so that the intelligent prediction, monitoring and early warning of the development trend of carbon emission are truly realized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a schematic structural diagram of a monitoring and early warning system for carbon emission in a region according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
As shown in fig. 1, the present embodiment provides a monitoring and early warning system for carbon emissions in a region, including: the system comprises a data acquisition module, a data processing module, a trend prediction module and a prevention alarm module;
the data acquisition module is used for acquiring original data for determining carbon emission in real time;
the data processing module is used for processing the real-time acquired original data and calculating carbon emission;
the trend prediction module is used for predicting the future trend of the carbon emission according to the processed original data and the carbon emission calculation result;
the prevention alarm module is used for performing prevention alarm according to the carbon emission trend prediction result.
The data processing module comprises: a cleaning unit and an accounting unit;
the cleaning unit is used for cleaning the original data;
and the accounting unit is used for performing carbon emission accounting according to the cleaned original data.
The raw data for determining carbon emissions includes: water consumption, electricity consumption, gas consumption and gasoline consumption.
The method for cleaning the original data comprises the following steps: removing repeated items and abnormal values, supplementing missing values by using a linear interpolation method, and uniformly processing the time resolution of data.
The accounting unit obtains the carbon emission through an accounting formula; the accounting formula is:
carbon dioxide emission (water consumption x 0.91+ electricity consumption x 0.785+ gas consumption x 0.19+ gasoline consumption x 2.7)
The unit of carbon dioxide emission is kilogram, the unit of water consumption is ton, the unit of electricity consumption is degree, the unit of gas consumption is cubic meter, and the unit of gasoline consumption is liter.
The raw data for determining carbon emissions in this embodiment includes at least one of: water, electricity, gas and gasoline, wherein the unit of the original data for determining the carbon emission is the same as the common unit of the object, for example, the unit of electricity is 'degree', the unit of water is 'ton', the unit of gas is 'cubic meter', and the unit of gasoline is 'liter'; the accounting formula is a formula for calculating the carbon emission of gasoline when the gasoline is used in the automobile: because the oil consumption of the automobiles with the same distance and different displacement is different, the carbon emission can be calculated only by converting the distance into the oil consumption according to the oil consumption condition of the automobiles, and the carbon emission of the automobiles with small displacement is less at the same distance. Furthermore, when gasoline is used on an airplane, a short trip of 200 km or less: carbon dioxide emission (kg) is flight kilometers multiplied by 0.275; and (3) traveling in 200-1000 km midway: carbon dioxide emissions (kg) 55+0.105 × (flight kilometer number one 200); long distance travel over 1000 km: the carbon dioxide emission (kg) is flight kilometers × 0.139.
The cleaned original data are substituted into a carbon emission accounting formula for calculation to obtain the real-time carbon emission in the region, the carbon emission in the region can be accounted in real time or near real time to generate a data set of the carbon emission in the region, and the problems that the current data set of the carbon emission has time lag of one year or more and does not have carbon emission data of day level or hour level are solved.
Artificial Intelligence (AI) is a machine learning technique that involves the study, design, and application of intelligent machines. The artificial intelligence models the complex relation among the data through an artificial neural network, and forms more abstract high-level characteristics by combining low-level characteristics, so that the data characteristics are extracted, the artificial intelligence has stronger modeling and reasoning capabilities, and the artificial intelligence can simulate the human brain to work. Unlike the traditional method, artificial intelligence can autonomously learn useful characteristics from data only through training and learning of the own neural network without determining a mathematical equation of a mapping relation between input and output in advance, so that the output result which is closest to the expected output value can be obtained when the input value is given. The artificial neural network is a neural network formed by connecting a large number of processing units, has strong self-learning capability and can automatically summarize the data rule characteristics from the existing data.
In a traditional RNN neural network, an RNN training method is characterized in that time is considered on the basis of a traditional back propagation algorithm, when propagation time is long, residual errors needing to be transmitted back are exponentially reduced, network weight is slowly updated, the long-term memory effect of the RNN cannot be embodied, and at the moment, gradient signals become very tiny and almost zero or are scattered absolutely, so that the problems of gradient loss and gradient explosion in the RNN are caused. Therefore, a memory unit is required to store the memory, and the LSTM model is proposed.
The LSTM (Long Short-Term Memory network) is a time-cycle neural network and is specially designed for solving the problems of gradient extinction and gradient explosion of RNN. Compared with RNN, LSTM has unique design structure, which adds input gate, output gate and forgetting gate (three gates can pass information selectively) in hidden layer, and uses memory state unit to store and process long time sequence information, wherein the memory gate is used to select to forget some past information, the input gate is used to memorize some present information, the information is merged with the present memory through the input gate and the memory gate, and the output gate finally outputs information. LSTM is therefore well suited to handle and predict significant events of very long intervals and delays in time series.
In this embodiment, the trend prediction module includes: the system comprises a model construction unit, a database and a trend prediction unit;
the model building unit is used for building an LSTM neural network; the database is used for storing the cleaned original data; the trend prediction unit is used for training the LSTM neural network according to the cleaned original data and predicting the carbon emission trend based on the trained LSTM neural network.
The trend prediction unit can predict the future trend of the environmental parameters in a short term, a medium term or a long term, wherein the short term refers to 4-48 h, the medium term refers to 2-7 days, and the long term refers to 7-15 days. The intermediate-term and long-term future tendency predictions are not limited to the above-described large and small intervals, but may be set to have a larger interval value than the above-described interval, but the longer the predicted future time is, the larger the corresponding error is.
The LSTM neural network comprises an input layer, a hidden layer and an output layer, wherein the input layer inputs training data; the hidden layer iteratively learns short-range and long-range semantic features of the time series data; the output layer outputs the prediction result. The LSTM network parameters comprise learning rate, iteration times, stepsize and the like, wherein the key network parameter stepsize takes a value between 1 and 24, and the specific value is determined according to the scale of the environmental parameter training data and the actual conditions and requirements.
The database comprises collected cleaned original data within a period of time, the cleaned original data are used as training data to train a trend prediction model, each type of training data in the database needs to be labeled, and the labeling processing mode meets the following requirements:
when stepsize is equal to 1, the labeling processing mode is that training data at the nth + x moment is used as a label of training data at the nth moment; when stepsize is 2, the labeling processing mode is that the training data at the nth + x moment is used as labels of the training data at the nth and the (n-1) th moments; when stepsize is equal to 3, the labeling processing mode is that training data at the nth + x moment is used as labels of environment training data at the nth, the n-1 and the n-2 moments, and the rest is analogized in sequence, wherein x is a prediction step size parameter and takes any integer greater than or equal to 0.
The value of the prediction step length parameter x is related to short-term and medium-term prediction, if the prediction is performed in a short term, the value of x is smaller, if the prediction is performed in a long term, the value of x is larger, and if the prediction is performed in a medium term, the value of x is between the short-term and medium-term. By adjusting the prediction step size parameter x, the development trend of the predicted carbon emission parameter data corresponding to the near or far future time can be obtained. For example, when the value of x is 3 (the time span between the nth and the (n + 1) th moments is set to be 4 hours), the trend prediction model can obtain the development trend of the predicted carbon emission parameter data after 12 hours; when the value of x is 24, the trend prediction model can obtain the development trend of the predicted carbon emission parameter data after 96 hours (namely after 4 days); when x is 72, the trend prediction model can obtain the development trend of the predicted carbon emission parameter data after 12 days.
Each type of training data in the training database is arranged according to a time sequence, wherein the training data at the nth time refers to the mean value of the training data in a certain time period, but not the training data value at a time point. Moreover, the time periods corresponding to the training data at all the moments have the same and uniform interval size. In addition, the time span between the nth and the (n + 1) th time (where n is an arbitrary integer of 0 or more) is preferably 4 or 6 or 8 hours, and the maximum time does not exceed 48 hours.
The trend prediction model comprises: the system comprises a water consumption trend prediction model, a power consumption trend prediction model, a gas consumption trend prediction model, a gasoline consumption trend prediction model and a carbon emission trend prediction model; each type of trend prediction model is obtained by utilizing an LSTM network to perform training learning based on corresponding training data in a database, and the future trend prediction is performed on corresponding real-time original data.
The training process of the LSTM neural network is as follows:
carrying out iterative training by turns by the LSTM neural network, in each round of training, taking training data at the n, n-1, … … and n-stepsize +1 moments as input data, outputting predicted carbon emission parameter data aiming at the n + x moment, matching the predicted environment parameter data at the n + x moment with the actual carbon emission parameter data at the n + x moment, if the matching error does not meet the preset requirement, correcting and adjusting weight parameters of each neural unit of the neural network according to the matching error, continuing taking the training data at the n, n-1, … … and n-stepsize +1 moments as input data, starting the next round of iterative training until the matching error between the predicted carbon emission parameter data at the n + x moment and the actual carbon emission parameter data at the n + x moment is smaller than a specified threshold value, the neural network training is complete.
The trend prediction module and the data processing module are deployed on a computing processing server, the computing processing server needs to meet 64G memory and 4T hard disk space so as to ensure that the artificial intelligent computing processor has enough computing processing capacity and data storage space, and the computing processing server is preferably provided with a plurality of GPUs, so that the requirement of parallel processing computing can be met.
The prevention alarm module includes: the system comprises a water consumption alarm module, a power consumption alarm module, a gas consumption alarm module, a gasoline consumption alarm module and a carbon emission alarm module; the alarm modes are different among different sub-modules.
After each type of trend prediction model predicts the future trend, the prediction result is transmitted to each type of corresponding alarm module in the prevention alarm module in real time, and if the prediction result has deviation from the preset threshold value, the corresponding alarm module gives an alarm; wherein the deviation is beyond an expected carbon emissions schedule, and the predetermined threshold is set based on a current real-time carbon emissions within the region and a future carbon emissions schedule within the region, based on not exceeding a maximum future carbon emissions within the region.
After any one of the water consumption alarm module, the power consumption alarm module, the gas consumption alarm module and the gasoline consumption alarm module gives an alarm, the carbon emission alarm module gives an alarm at the same time; the more the number of the alarm modules for alarming is, the higher the response level of the carbon emission alarm module for alarming is.
The carbon emission is calculated by collecting different original data in real time, the calculation is carried out through the trend prediction module, the development trend of each type of data is predicted, and after the current development trend and the future development trend have deviation, early warning processing can be timely sent out. The carbon emission amount is calculated based on all collected real-time original data, when one type of data development trend gives an alarm, the carbon emission alarm module necessarily gives an alarm at the same time, and when multiple data development trends give an alarm, the alarm level of the carbon emission alarm module is upgraded to remind relevant personnel of paying high attention.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. Regional interior carbon emission's monitoring early warning system, its characterized in that includes: the system comprises a data acquisition module, a data processing module, a trend prediction module and a prevention alarm module;
the data acquisition module is used for acquiring original data for determining carbon emission in real time;
the data processing module is used for processing the original data acquired in real time and calculating carbon emission;
the trend prediction module is used for predicting the future trend of carbon emission according to the processed original data and the carbon emission calculation result;
the prevention alarm module is used for performing prevention alarm according to the carbon emission trend prediction result.
2. The regional carbon emission monitoring and early warning system of claim 1, wherein determining the raw data of carbon emissions comprises: water consumption, electricity consumption, gas consumption and gasoline consumption.
3. The system for monitoring and warning carbon emission in a region according to claim 1, wherein the data processing module comprises: a cleaning unit and an accounting unit;
the cleaning unit is used for cleaning the original data;
and the accounting unit is used for performing carbon emission accounting according to the cleaned original data.
4. The regional carbon emission monitoring and early warning system as claimed in claim 3, wherein the manner of cleaning the raw data comprises: removing repeated items and abnormal values, supplementing missing values by using a linear interpolation method, and uniformly processing the time resolution of data.
5. The system for monitoring and pre-warning carbon emission in a region according to claim 3, wherein the accounting unit obtains the carbon emission amount through an accounting formula;
the accounting formula is as follows:
carbon dioxide emission (water consumption x 0.91+ electricity consumption x 0.785+ gas consumption x 0.19+ gasoline consumption x 2.7)
The unit of carbon dioxide emission is kilogram, the unit of water consumption is ton, the unit of electricity consumption is degree, the unit of gas consumption is cubic meter, and the unit of gasoline consumption is liter.
6. The system of claim 3, wherein the trend prediction module comprises: the system comprises a model building unit, a database and a trend prediction unit;
the model building unit is used for building an LSTM neural network;
the database is used for storing the cleaned original data;
the trend prediction unit is used for training the LSTM neural network according to the cleaned original data and predicting the carbon emission trend based on the trained LSTM neural network.
7. The regional carbon emission monitoring and warning system of claim 6, wherein the LSTM neural network comprises: an input layer, a hidden layer and an output layer;
the input layer is used for inputting the cleaned original data and sequencing the original data according to a time sequence;
the hidden layer is used for iteratively learning short-range and long-range semantic features of the time sequence data;
the output layer is used for outputting a prediction result;
the LSTM neural network further comprises LSTM network parameters;
the LSTM network parameters comprise a learning rate, iteration times and stepsize.
8. The system of claim 7, wherein the trend predictive model comprises: the system comprises a water consumption trend prediction model, a power consumption trend prediction model, a gas consumption trend prediction model, a gasoline consumption trend prediction model and a carbon emission trend prediction model;
the trend prediction module is used for predicting the future trend, including short-term trend prediction, medium-term trend prediction and long-term trend prediction.
9. The system of claim 8, wherein the precaution alarm module comprises: the device comprises a water consumption alarm module, a power consumption alarm module, a gas consumption alarm module, a gasoline consumption alarm module and a carbon emission alarm module.
10. The system for monitoring and pre-warning carbon emission in an area according to claim 9, wherein after the trend prediction model predicts the future trend, the prediction result is transmitted to each corresponding alarm module in the prevention alarm modules in real time, and if the prediction result deviates from a preset threshold value, the corresponding alarm module gives an alarm;
after any one of the water consumption alarm module, the power consumption alarm module, the fuel gas consumption alarm module and the gasoline consumption alarm module gives an alarm, the carbon emission alarm module also gives an alarm at the same time; the more the number of the alarm modules for alarming is, the higher the response level of the carbon emission alarm module for alarming is.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210309529.6A CN114626627A (en) | 2022-03-28 | 2022-03-28 | Monitoring and early warning system for carbon emission in area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210309529.6A CN114626627A (en) | 2022-03-28 | 2022-03-28 | Monitoring and early warning system for carbon emission in area |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114626627A true CN114626627A (en) | 2022-06-14 |
Family
ID=81904047
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210309529.6A Pending CN114626627A (en) | 2022-03-28 | 2022-03-28 | Monitoring and early warning system for carbon emission in area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114626627A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115587218A (en) * | 2022-12-12 | 2023-01-10 | 南方电网数字电网研究院有限公司 | Database construction method suitable for analysis of massive power carbon emission big data |
CN116862738A (en) * | 2023-07-12 | 2023-10-10 | 中冀电力集团股份有限公司 | Energy carbon emission prediction early warning system |
CN116933983A (en) * | 2023-09-19 | 2023-10-24 | 江西财经大学 | Low-carbon emission data monitoring system and method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104658213A (en) * | 2014-12-31 | 2015-05-27 | 中国科学院深圳先进技术研究院 | Internet of things-based method and internet of things-based system for monitoring carbon emission |
CN107832913A (en) * | 2017-10-11 | 2018-03-23 | 微梦创科网络科技(中国)有限公司 | The Forecasting Methodology and system to monitoring data trend based on deep learning |
CN111351664A (en) * | 2020-02-13 | 2020-06-30 | 成都运达科技股份有限公司 | Bearing temperature prediction and alarm diagnosis method based on LSTM model |
CN111445060A (en) * | 2020-03-06 | 2020-07-24 | 华南理工大学珠海现代产业创新研究院 | Community carbon emission monitoring and predicting system and method |
-
2022
- 2022-03-28 CN CN202210309529.6A patent/CN114626627A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104658213A (en) * | 2014-12-31 | 2015-05-27 | 中国科学院深圳先进技术研究院 | Internet of things-based method and internet of things-based system for monitoring carbon emission |
CN107832913A (en) * | 2017-10-11 | 2018-03-23 | 微梦创科网络科技(中国)有限公司 | The Forecasting Methodology and system to monitoring data trend based on deep learning |
CN111351664A (en) * | 2020-02-13 | 2020-06-30 | 成都运达科技股份有限公司 | Bearing temperature prediction and alarm diagnosis method based on LSTM model |
CN111445060A (en) * | 2020-03-06 | 2020-07-24 | 华南理工大学珠海现代产业创新研究院 | Community carbon emission monitoring and predicting system and method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115587218A (en) * | 2022-12-12 | 2023-01-10 | 南方电网数字电网研究院有限公司 | Database construction method suitable for analysis of massive power carbon emission big data |
CN116862738A (en) * | 2023-07-12 | 2023-10-10 | 中冀电力集团股份有限公司 | Energy carbon emission prediction early warning system |
CN116933983A (en) * | 2023-09-19 | 2023-10-24 | 江西财经大学 | Low-carbon emission data monitoring system and method |
CN116933983B (en) * | 2023-09-19 | 2024-01-23 | 江西财经大学 | Low-carbon emission data monitoring system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
CN114626627A (en) | Monitoring and early warning system for carbon emission in area | |
CN110889527B (en) | Electric vehicle charging load prediction method based on LSTM neural network | |
CN110555551A (en) | air quality big data management method and system for smart city | |
Pranolo et al. | Robust LSTM With tuned-PSO and bifold-attention mechanism for analyzing multivariate time-series | |
CN114626628A (en) | Carbon emission accounting system and accounting method thereof | |
Ye et al. | Short-term prediction of available parking space based on machine learning approaches | |
Dong et al. | Ensemble wind speed forecasting system based on optimal model adaptive selection strategy: Case study in China | |
Sen | Time series prediction based on improved deep learning | |
CN114723131A (en) | Mine environment intelligent prediction system based on artificial intelligence | |
Huang et al. | Prediction of solar photovoltaic power generation based on MLP and LSTM neural networks | |
Bişkin et al. | Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks | |
Wu et al. | Two-stage decomposition and temporal fusion transformers for interpretable wind speed forecasting | |
Małek et al. | The use of deep recurrent neural networks to predict performance of photovoltaic system for charging electric vehicles | |
Wu et al. | Interpretable wind speed forecasting with meteorological feature exploring and two-stage decomposition | |
CN109978237A (en) | A kind of area power grid Short Term Load Forecasting System based on fining meteorological data | |
Famoso et al. | A Dependability Neural Network Approach for Short-Term Production Estimation of a Wind Power Plant | |
Ge et al. | Multivariate Two-stage Adaptive-stacking Prediction of Regional Integrated Energy System | |
Wang et al. | A deep learning and ensemble learning based architecture for metro passenger flow forecast | |
Ren et al. | Predicting spacecraft telemetry data by using Grey–Markov model with sliding window and particle swarm optimization | |
Kang et al. | Analysis of failure features of high-speed automatic train protection system | |
Galphade et al. | Intelligent multiperiod wind power forecast model using statistical and machine learning model | |
Gu et al. | Wind power prediction based on VMD-neural network | |
He et al. | Design of explainability module with experts in the loop for visualization and dynamic adjustment of continual learning | |
Yang et al. | Application of mamdani fuzzy system amendment on load forecasting model |
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: 20220614 |
|
RJ01 | Rejection of invention patent application after publication |