CN115564314A - Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation - Google Patents
Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation Download PDFInfo
- Publication number
- CN115564314A CN115564314A CN202211480198.9A CN202211480198A CN115564314A CN 115564314 A CN115564314 A CN 115564314A CN 202211480198 A CN202211480198 A CN 202211480198A CN 115564314 A CN115564314 A CN 115564314A
- Authority
- CN
- China
- Prior art keywords
- power plant
- carbon
- hypergraph
- thermal power
- new energy
- 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 100
- 238000005259 measurement Methods 0.000 title claims abstract description 59
- 238000005457 optimization Methods 0.000 title claims abstract description 39
- 238000005265 energy consumption Methods 0.000 title claims abstract description 20
- 230000008447 perception Effects 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 18
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 61
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 58
- GQPLMRYTRLFLPF-UHFFFAOYSA-N Nitrous Oxide Chemical compound [O-][N+]#N GQPLMRYTRLFLPF-UHFFFAOYSA-N 0.000 claims description 56
- 239000013598 vector Substances 0.000 claims description 40
- 239000003546 flue gas Substances 0.000 claims description 33
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 29
- 239000001569 carbon dioxide Substances 0.000 claims description 29
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 28
- 239000001272 nitrous oxide Substances 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 239000007789 gas Substances 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004134 energy conservation Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 7
- 230000002596 correlated effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 239000013604 expression vector Substances 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 239000000779 smoke Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000010792 warming Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012360 testing method 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
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation, which belongs to the technical field of carbon emission measurement systems and comprises a data measurement module and an information acquisition module, wherein the data measurement module and the information acquisition module are both connected with a power plant knowledge perception hypergraph module, the power plant knowledge perception hypergraph module is connected with a knowledge perception hypergraph convolution operation block, and the knowledge perception hypergraph convolution operation block is connected with a recommendation module. When regional carbon emission measurement is carried out, the system and the method insert the self capacity and equipment information of the thermal power plant, the energy-saving emission-reducing technical level information, the capacity information of the new energy power plant and the knowledge sensing hypergraph of the equipment into a regional carbon emission measurement system, solve the problem that the prior measurement system recommends the new energy power plant coordinated and cooperated with the thermal power plant and the new energy ratio thereof, recommends cold start due to sparsity of basic data, and can effectively utilize the characteristic attribute knowledge sensing hypergraph of the thermal power plant and the new energy power plant.
Description
Technical Field
The invention relates to a measuring system, in particular to an intelligent measuring system for regional carbon emission based on low-carbon energy consumption optimization cooperation, and belongs to the technical field of carbon emission measuring systems.
Background
Because of global warming, low-carbon production is being implemented globally, various energy-saving and emission-reducing technologies are utilized to control the emission of greenhouse gases, in order to avoid the aggravation of global warming, as the country with the largest world carbon emission, the China supports the optimization development area to firstly realize the carbon emission peak value, deepens various low-carbon test points, implements the demonstration engineering of the near-zero carbon emission area, the thermal power plant is taken as a main carbon dioxide emission enterprise, particularly, low-carbon energy consumption, cooperative optimization and reasonable configuration of energy use are highlighted, a regional carbon emission measurement system of the thermal power plant needs to measure carbon emission in time to assist carbon emission accounting of the thermal power plant, carbon emission accounting methods commonly used in the thermal power plant in China mainly comprise a carbon emission factor method, an actual measurement monitoring method and a material balance algorithm, wherein the actual measurement monitoring method is to measure the flow, flow rate and concentration of the discharged gas through a monitoring instrument or a continuous metering facility, according to the classification of measuring instruments, the actual measurement monitoring method is divided into an artificial measurement method and a continuous monitoring method based on smoke emission, the former carries out short-time measurement at a reserved chimney measuring point by carrying handheld equipment, the latter can realize continuous measurement, the actual measurement monitoring method has few influence parameters and high data accuracy, however, when regional carbon emission measurement is performed in such a monitoring mode, the capacity, the equipment information, the energy-saving emission-reduction technical level information of the thermal power plant and the capacity and the equipment information of each new energy power plant in the region are not combined, so that the new energy power plant which realizes carbon emission optimization and the new energy ratio can not be accurately recommended to the thermal power plant, and the recommended cold start problem can be caused by the sparsity of the new energy power plant and the basic data sample of the recommended ratio.
In order to facilitate the thermal power plant and the new energy power plant to achieve the aim of low-carbon energy utilization collaborative optimization in the region, the invention provides a regional carbon emission intelligent measurement system based on low-carbon energy utilization collaborative optimization, based on the inspiration of the existing knowledge graph neural network recommendation system sparsity and cold start problem solution, when regional carbon emission measurement is carried out, the regional carbon emission intelligent measurement system is used for introducing the self-productivity and equipment information of the thermal power plant, the energy-saving emission-reduction technical level information, the new energy power plant capacity information and the knowledge perception hypergraph of the equipment into the regional carbon emission measurement system, the problem of cold start recommendation caused by basic data sparsity when the existing measurement system recommends the new energy power plant coordinated with the thermal power plant and the new energy ratio of the new energy power plant is solved, the characteristic attribute knowledge perception hypergraph of the thermal power plant and the new energy power plant can be effectively utilized and integrated into the vector representation of each thermal power plant and the new energy power plant, and the potential relation between the given target power plant and the new energy power plant is enriched.
Disclosure of Invention
The invention mainly aims to solve the problem that the conventional measurement system recommends a collaborative optimization new energy power plant to a thermal power plant and recommends cold start due to sparsity of basic data when recommending a collaborative optimization new energy ratio to the new energy power plant, and provides an intelligent measurement system for regional carbon emission based on low-carbon energy consumption optimization collaboration.
The purpose of the invention can be achieved by adopting the following technical scheme:
the utility model provides a regional carbon discharges wisdom measurement system based on low carbon can be optimized in coordination, includes data measurement module and information acquisition module, data measurement module with information acquisition module all is connected with power plant's knowledge perception hypergraph module, power plant's knowledge perception hypergraph module is connected with knowledge perception hypergraph convolution operation block, knowledge perception hypergraph convolution operation block is connected with recommending module, recommending module is connected with prediction module, prediction module includes carbon emission module, optimization module and training loss module, carbon emission module with data measurement module links to each other, more than the effect of module is:
a data measurement module: the device is used for measuring the flow, flow speed and concentration of the exhaust gas measured by each thermal power plant chimney;
the information acquisition module: the system is used for acquiring the generator set information, the capacity and the energy-saving and emission-reducing technical level of the thermal power plant and is also used for acquiring the capacity and the generator set information of a new energy power plant;
the power plant knowledge perception hypergraph module: constructing a hypergraph of a thermal power plant and a hypergraph of a new energy power plant;
a knowledge-aware hypergraph convolution operation block: performing convolution calculation on the hypergraph of the thermal power plant and the hypergraph of each new energy power plant to obtain a single vector of the hypergraph of the thermal power plant and a single vector corresponding to the hypergraph of each new energy power plant, performing inner product calculation on the single vector of each thermal power plant and the single vectors of all the new energy power plants, and performing nonlinear transformation to obtain cooperation scores of the thermal power plant and all the new energy power plants, wherein the cooperation scores represent the probability of performing new energy coordination distribution on the thermal power plant and the new energy power plants;
a recommendation module: the cooperation scores are arranged in a descending order from big to small, and one or more new energy power plants corresponding to the cooperation scores which are ranked at the top are output;
a prediction module: the system is used for predicting the carbon emission of the thermal power plant by using the carbon emission parameters acquired by the data measurement module, optimizing the carbon emission index of unit energy production through the supply and cooperative distribution of the unit energy production and the new energy power plant capacity, and performing convergence calculation by combining the loss of the recommendation model;
a carbon emission module: predicting and calculating the carbon emission of the thermal power plant through the weighted sum of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index, wherein the carbon emission prediction formula of the thermal power plant is as follows:
in the formula:is used as a predicted value of the carbon emission of the thermal power plant,the monthly average carbon emission of the thermal power plant is taken as the basic carbon emission of the thermal power plant for the basic carbon emission of the thermal power plant,、andthe carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index are respectively taken as the weight of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index according to the volume percentage of the three gases in the flue gas discharged by each thermal power plant,、andcarbon monoxide emission index, carbon dioxide emission index and nitrous oxide emission index;
wherein: the carbon monoxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the carbon monoxide concentration, the carbon dioxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the carbon dioxide concentration, the nitrous oxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the nitrous oxide concentration, and the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index are expressed by the following formulas:
(1) Carbon monoxide emission index formula:
in the formula:the emission amount of the smoke is the amount of the smoke,the discharge speed of the flue gas is set as the discharge speed of the flue gas,the concentration of carbon monoxide in the flue gas;
(2) Carbon dioxide emission index formula:
(3) Nitrous oxide emission index equation:
an optimization module: calculating the recommended coordination distribution rate of the new energy power plant according to the carbon emission prediction quantity, wherein the coordination distribution rate of the new energy power plant is in negative correlation with a standard carbon emission index and in positive correlation with the predicted carbon emission quantity of the thermal power plant, and the formula of the coordination distribution rate is as follows:
a training loss module: for calculating the loss of the recommended model training process.
As a further scheme of the invention, the power plant knowledge sensing hypergraph module is used for horizontally constructing an initial hypergraph and a 2-K-order knowledge sensing hypergraph of a thermal power plant in time by utilizing information, capacity, energy conservation and emission reduction of a generating set of the thermal power plant, wherein K is an integer larger than 1, the initial hypergraph is used for being physically combined with a new energy power plant in a cooperative relationship with the thermal power plant, an entity node of a next-order knowledge sensing hypergraph is the characteristic information of the new energy power plant or the new energy power plant corresponding to the entity combining point of the previous-order knowledge sensing hypergraph, and entity nodes of two adjacent-order knowledge sensing hypergraphs respectively correspond to the characteristic information of the new energy power plant and the new energy power plant so as to construct the thermal power plant hypergraph and the new energy power plant hypergraph.
As a further scheme of the invention, the knowledge sensing hypergraph convolution operation block comprises a field convolution operation block and a hypergraph convolution operation block connected with the field convolution operation block, the field convolution operation block is used for processing each initial hypergraph and each knowledge sensing hypergraph of a target thermal power plant hypergraph and each new energy power plant to obtain a single vector of each hypergraph on the target thermal power plant hypergraph and each new energy power plant hypergraph, the hypergraph convolution operation block is used for processing single vectors of all hypergraphs of the thermal power plant hypergraph to obtain a unique single vector of the target thermal power plant, and is also used for processing single vectors of all knowledge sensing hypergraphs of the new energy power plant to obtain a unique single vector of the new energy power plant.
As a further aspect of the present invention, the operation method of the domain convolution operation block includes: and putting the entity vectors in the K-order super edges and the K-order super edges of the thermal power plant or the entity vectors in the K-order super edges and the K-order super edges of the new energy power plant into a one-dimensional convolution to generate a transformation matrix, and then performing replacement and weighting operation on the entity vectors in the K-order super edges by using the transformation matrix to obtain a plurality of transformed super edge vectors of the thermal power plant or the new energy power plant.
As a further scheme of the present invention, the operation method of the super-edge convolution operation block is: and performing summation operation on a plurality of embedded parts in the thermal power plant representation set by using a one-dimensional convolution and a summation aggregator, performing maximum calculation on a plurality of embedded execution elements in the thermal power plant representation set by using a pooling aggregator, and splicing the plurality of embedded parts into the thermal power plant representation set by using a splicing aggregator.
As a further scheme of the invention, the power plant knowledge perception hypergraph module and the knowledge perception hypergraph operation block select the same number of negative samples and positive samples for each thermal power plant, wherein the new energy power plant which accords with thermal power plant collaborative optimization of low-carbon energy utilization is used as a positive sample, the new energy power plant which does not accord with thermal power plant collaborative optimization of low-carbon energy utilization is used as a negative sample, the thermal power plant trains the candidate new energy power plant collaborative score value model to ensure the effectiveness of the training, and the training loss module defines a loss function of the thermal power plant to the candidate new energy power plant collaborative score value model as a difference between cross entropy loss of the training loss module and cross entropy loss of the negative sample, and the norm of an L2 regularization term of the parameterized model.
As a further aspect of the present invention, the data measurement module includes a flow sensor, a flow rate sensor, a carbon dioxide concentration sensor, a carbon monoxide concentration sensor, and a nitrous oxide sensor.
The invention has the beneficial technical effects that: according to the intelligent regional carbon emission measurement system based on low-carbon energy consumption optimization cooperation, the data measurement module and the information acquisition module are used for acquiring the power generation characteristic information and the carbon emission characteristic information of a thermal power plant, meanwhile, the power generation characteristic information of a new energy power plant is acquired, the thermal power plant knowledge sensing hypergraph composed of hypergraph edges and the new energy power plant hypergraph are acquired through the power plant knowledge sensing hypergraph module, the high-order correlation of the thermal power plant, the new energy power plant and an entity in a knowledge graph is constructed by using the knowledge sensing hypergraph convolution operation block, the thermal power plant hypergraph and each new energy power plant hypergraph are used for carrying out convolution operation to effectively aggregate different neighbors in the new energy power plant neighborhood and simultaneously retain the relationship information in the new energy power plant neighborhood, and the cooperation scores of the thermal power plant and all the new energy power plants are obtained, the collaborative scores can be sorted from time to time through the arrangement of the recommending module, and then a list of new energy power plants corresponding to one or more collaborative scores at the top of the ranking is output, when the existing measuring system recommends a collaborative new energy power plant and a new energy ratio thereof to the thermal power plant, the problem of recommending cold start due to basic data sparsity is solved, a characteristic attribute knowledge perception hypergraph of the thermal power plant and the new energy power plant can be effectively utilized, the collaborative new energy power plant is integrated into vector representation of each thermal power plant and the new energy power plant, the potential relation between a given target power plant and the new energy power plant is enriched, meanwhile, the new energy power plant suitable for collaborative optimization of carbon emission indexes is recommended, and the accuracy of recommending the collaborative new energy power plant to the thermal power plant is improved.
Drawings
FIG. 1 is a block diagram of the components of a regional carbon emission intelligent measurement system based on low carbon energy consumption optimization synergy according to the invention.
Detailed Description
In order to make the technical solutions of the present invention more clear and definite for those skilled in the art, the present invention is further described in detail below with reference to the examples and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1, the wisdom measurement system is discharged to regional carbon based on low carbon is with ability optimization synergy that this embodiment provided, including data measurement module and information acquisition module, data measurement module with information acquisition module all is connected with power plant's knowledge perception hypergraph module, power plant's knowledge perception hypergraph module is connected with knowledge perception hypergraph convolution operation block, knowledge perception hypergraph convolution operation block is connected with recommendation module, recommendation module is connected with prediction module, prediction module includes carbon emission module, optimization module and training loss module, carbon emission module with data measurement module links to each other, above the effect of module is:
a data measurement module: the device is used for measuring the flow, flow speed and concentration of the exhaust gas measured by each thermal power plant chimney;
the information acquisition module: the system is used for acquiring the generator set information, the capacity and the energy-saving and emission-reducing technical level of the thermal power plant and is also used for acquiring the capacity and the generator set information of a new energy power plant;
power plant knowledge perception hypergraph module: constructing a hypergraph of a thermal power plant and a hypergraph of a new energy power plant;
a knowledge-aware hypergraph convolution operation block: performing convolution calculation on the hypergraph of the thermal power plant and the hypergraph of each new energy power plant to obtain a single vector of the hypergraph of the thermal power plant and a single vector corresponding to the hypergraph of each new energy power plant, performing inner product calculation on the single vector of each thermal power plant and the single vectors of all the new energy power plants, and performing nonlinear transformation to obtain cooperation scores of the thermal power plant and all the new energy power plants, wherein the cooperation scores represent the probability of performing new energy coordination distribution on the thermal power plant and the new energy power plants;
a recommendation module: and (4) performing descending order on the cooperation scores from large to small, and outputting one or more new energy power plants corresponding to the cooperation scores at the top.
A prediction module: the system is used for predicting the carbon emission of the thermal power plant by using the carbon emission parameters acquired by the data measurement module, optimizing the carbon emission index of unit energy production through the supply and cooperative distribution of the unit energy production and the new energy power plant capacity, and then performing convergence calculation by combining the loss of the recommendation model;
a carbon emission module: the carbon emission amount of the thermal power plant is predicted and calculated through the weighted sum of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index, and the carbon emission amount prediction formula of the thermal power plant is as follows:
in the formula:is used as a predicted value of the carbon emission of the thermal power plant,the monthly average carbon emission of the thermal power plant is taken as the basic carbon emission of the thermal power plant for the basic carbon emission of the thermal power plant,、andthe carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index are respectively taken as the weight of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index according to the volume percentage of the three gases in the flue gas discharged by each thermal power plant,、andcarbon monoxide emission index, carbon dioxide emission index and nitrous oxide emission index;
wherein: the carbon monoxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the carbon monoxide concentration, the carbon dioxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the carbon dioxide concentration, the nitrous oxide emission index is positively correlated with the flue gas emission flow, the flue gas emission speed and the nitrous oxide concentration, and the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index are expressed by the following formulas:
(1) Carbon monoxide emission index formula:
in the formula:the amount of the discharged flue gas is the amount of the discharged flue gas,the discharge speed of the flue gas is set as the discharge speed of the flue gas,the concentration of carbon monoxide in the flue gas;
(2) Carbon dioxide emission index formula:
(3) Nitrous oxide emission index equation:
an optimization module: calculating the recommended coordination distribution rate of the new energy power plant according to the carbon emission prediction quantity, wherein the coordination distribution rate of the new energy power plant is in negative correlation with a standard carbon emission index and in positive correlation with the predicted carbon emission quantity of the thermal power plant, and the formula of the coordination distribution rate is as follows:
a training loss module: for calculating the loss of the recommended model training process.
The method comprises the steps of collecting power generation characteristic information and carbon emission characteristic information of a thermal power plant through a data measurement module and an information collection module, collecting power generation characteristic information of a new energy power plant, building high-order correlation of the thermal power plant, the new energy power plant and an entity in a knowledge map through a power plant knowledge perception hypergraph module, and building high-order correlation of the thermal power plant, the new energy power plant and the entity in the knowledge map through a knowledge perception hypergraph module of the thermal power plant, effectively aggregating different neighbors in a neighborhood of the new energy power plant and simultaneously keeping relationship information in the neighborhood of the new energy power plant by using a convolution operation method of the hypergraph of the thermal power plant and each hypergraph of the new energy power plant to obtain cooperation scores of the thermal power plant and all new energies.
The power plant knowledge perception hypergraph module is used for generating set information of a thermal power plant, capacity and energy conservation and emission reduction to build an initial hypergraph and a 2-K-order knowledge perception hypergraph of the thermal power plant in time and horizontally, wherein K is set to be an integer larger than 1, the initial hypergraph is combined with a new energy power plant in a cooperative relationship with the thermal power plant to perform entity combination, entity nodes of the next-order knowledge perception hypergraph are feature information of the new energy power plant or the new energy power plant corresponding to the previous-order knowledge perception hypergraph entity combination points, and entity nodes of two adjacent-order knowledge perception hypergraph correspond to feature information of the new energy power plant and the new energy power plant respectively, so that the thermal power plant hypergraph and the new energy power plant hypergraph are built.
Through the creation of the hypergraph of the thermal power plant and the hypergraph of the new energy power plant, multiple hyperedges can be constructed for the thermal power plant and the new energy power plant, the high-order correlation of information of the thermal power plant and the new energy power plant is enriched, and single vector representation of all the hyperedges of the thermal power plant and each new energy power plant is formed.
Knowledge perception hypergraph convolution operation piece include the field convolution operation piece and with the super limit convolution operation piece that the field convolution operation piece links to each other, every initial super limit and every knowledge perception super limit that the field convolution operation piece is used for handling target thermal power plant hypergraph and every new energy power plant obtain the single vector of every super limit on target thermal power plant hypergraph and every new energy power plant hypergraph, super limit convolution operation piece is used for handling the single vector of all super limits of thermal power plant hypergraph, obtains the only single vector of target thermal power plant, still is used for handling the single vector of all knowledge perception super limits of new energy power plant, obtains the only single vector of new energy power plant. The operation method of the field convolution operation block comprises the following steps: and putting the entity vectors in the K-order super edges and the K-order super edges of the thermal power plant or the entity vectors in the K-order super edges and the K-order super edges of the new energy power plant into a one-dimensional convolution to generate a transformation matrix, and then performing replacement and weighting operation on the entity vectors in the K-order super edges by using the transformation matrix to obtain a plurality of transformed super edge vectors of the thermal power plant or the new energy power plant. The operation method of the super-edge convolution operation block comprises the following steps: and performing summation operation on a plurality of embedded units in the thermal power plant representation set by using a one-dimensional convolution and a summation aggregator, performing maximum calculation on a plurality of embedded execution elements in the thermal power plant representation set by using a pooling aggregator, and splicing the plurality of embedded units into the thermal power plant representation set by using a splicing aggregator.
Through the setting of the field convolution operation block and the super-edge convolution operation block, the final single expression vector of the thermal power plant and the new energy power plant can be generated conveniently by utilizing the expression vectors of the thermal power plant and all the new energy power plants, and the cooperation score of the thermal power plant for each new energy power plant can be obtained.
The power plant knowledge perception hypergraph module and the knowledge perception hypergraph operation block select the same number of negative samples and positive samples for each thermal power plant, wherein the new energy power plant which accords with thermal power plant collaborative optimization low-carbon energy consumption is used as a positive sample, the new energy power plant which does not accord with thermal power plant collaborative optimization low-carbon energy consumption is used as a negative sample, the thermal power plant is trained on a candidate new energy power plant collaborative score value model, the effectiveness of training is guaranteed, a training loss module defines a loss function of the thermal power plant on the candidate new energy power plant collaborative score value model as a positive sample, the difference between cross entropy loss of the training loss module and the cross entropy loss of the negative sample is added with the norm of an L2 regularization term parameterized by the model.
Training through negative sample and positive sample can let the numerical model of thermal power plant to candidate new forms of energy power plant cooperation score obtain the intensive training, improves the accuracy of model, guarantees the training effect of model.
The data measurement module comprises a flow sensor, a flow rate sensor, a carbon dioxide concentration sensor, a carbon monoxide concentration sensor and a nitrous oxide sensor.
Through the setting of each sensor of data measurement module, can conveniently acquire the carbon emission measured data of each thermal power plant, and then when being convenient for provide data basis for the carbon emission accounting of each thermal power plant, provide the basic data of recommendation for the thermal power plant selects cooperation new forms of energy power plant.
In summary, in this embodiment, according to the intelligent measurement system for regional carbon emission based on low-carbon energy consumption optimization synergy of this embodiment, multiple hyperedges can be constructed for the thermal power plant and the new energy power plant through creation of the thermal power plant hypermap and the new energy power plant hypermap, high-order correlations of information of the thermal power plant and the new energy power plant are enriched, and single vector representation of all the hyperedges of the thermal power plant and each new energy power plant is formed. Through the setting of the field convolution operation block and the super-edge convolution operation block, the final single expression vector of the thermal power plant and the new energy power plant can be generated conveniently by utilizing the expression vectors of the thermal power plant and all the new energy power plants, and the cooperation score of the thermal power plant for each new energy power plant can be obtained. Through the training of the negative sample and the positive sample, the thermal power plant can be enabled to fully train the candidate new energy power plant collaborative scoring numerical model, the accuracy of the model is improved, and the training effect of the model is guaranteed. Through the setting of each sensor of data measurement module, can conveniently acquire the carbon emission measured data of each thermal power plant, and then when being convenient for provide data basis for the carbon emission accounting of each thermal power plant, provide the basic data of recommendation for the thermal power plant selects cooperation new forms of energy power plant.
The above description is only a further embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution of the present invention and its idea within the scope of the present invention.
Claims (10)
1. The utility model provides a regional carbon emission wisdom measurement system based on low carbon is with ability optimization is cooperative, includes data measurement module and information acquisition module, its characterized in that: the data measurement module with the information acquisition module all is connected with power plant's knowledge perception hypergraph module, power plant's knowledge perception hypergraph module is connected with knowledge perception hypergraph convolution operation block, knowledge perception hypergraph convolution operation block is connected with the recommendation module, the recommendation module is connected with the prediction module, the prediction module includes carbon emission module, optimization module and training loss module, carbon emission module with the data measurement module links to each other.
2. The intelligent regional carbon emission measurement system based on low carbon energy use optimization synergy of claim 1, wherein the carbon emission module: the carbon emission amount of the thermal power plant is predicted and calculated through the weighted sum of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index, and the carbon emission amount prediction formula of the thermal power plant is as follows:
(ii) a In the formula:is used as a predicted value of the carbon emission of the thermal power plant,the monthly average carbon emission of the thermal power plant is taken as the basic carbon emission of the thermal power plant,、andthe carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index are respectively taken as the weight of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index according to the volume percentage of the three gases in the flue gas discharged by each thermal power plant,、andrespectively carbon monoxide emission index, carbon dioxide emission index and nitrous oxide emission index.
3. The intelligent regional carbon emission measurement system based on low carbon energy consumption optimization synergy of claim 1, wherein the formula of the carbon monoxide emission index, the carbon dioxide emission index and the nitrous oxide emission index is as follows:
(1) Carbon monoxide emission index formula:
(ii) a In the formula:the amount of the discharged flue gas is the amount of the discharged flue gas,in order to obtain the discharge speed of the flue gas,the concentration of carbon monoxide in the flue gas;
(2) Carbon dioxide emission index formula:
(3) Nitrous oxide emission index equation:
4. The intelligent regional carbon emission measurement system based on low carbon energy use optimization synergy of claim 1, wherein the optimization module: calculating the recommended coordination distribution rate of the new energy power plant according to the carbon emission prediction quantity, wherein the coordination distribution rate of the new energy power plant is in negative correlation with a standard carbon emission index and in positive correlation with the predicted carbon emission quantity of the thermal power plant, and the formula of the coordination distribution rate is as follows:
5. The intelligent regional carbon emission measurement system based on low-carbon energy consumption optimization and coordination as claimed in claim 1, wherein the power plant knowledge perception hypergraph module utilizes the power plant generating set information, the capacity, the energy conservation and emission reduction of a thermal power plant to construct an initial hypergraph and a 2-K-order knowledge perception hypergraph of the thermal power plant in time and horizontally, wherein K is an integer larger than 1, the initial hypergraph is utilized to combine with a new energy power plant having a cooperative relationship with the thermal power plant for entity combination, an entity node of a next-order knowledge perception hypergraph is the feature information of the new energy power plant or the new energy power plant corresponding to the entity combination point of the previous-order knowledge perception hypergraph, and entity nodes of two adjacent-order knowledge perception hypergraphs respectively correspond to the feature information of the new energy power plant and the new energy power plant, so as to construct the thermal power plant hypergraph and the new energy power plant hypergraph.
6. The intelligent regional carbon emission measurement system based on low carbon energy consumption optimization synergy of claim 5, wherein the knowledge-aware hypergraph convolution operation block comprises a field convolution operation block and a hypergraph convolution operation block connected with the field convolution operation block, the field convolution operation block is used for processing each initial hypergraph and each knowledge-aware hypergraph of a target thermal power plant hypergraph and each new energy power plant, single vectors of each hypergraph on the target thermal power plant hypergraph and each new energy power plant hypergraph are obtained, the hypergraph convolution operation block is used for processing single vectors of all the hypergraphs of the thermal power plant hypergraph, the single vectors of the target thermal power plant are obtained, the single vectors of all the knowledge-aware hypergraphs of the new energy power plant are further used for processing the single vectors of the new energy power plant, and the only single vector of the new energy power plant is obtained.
7. The intelligent regional carbon emission measurement system based on low carbon energy consumption optimization cooperation of claim 6, wherein the operation method of the domain convolution operation block is as follows: and putting the entity vectors in the K-order super edges and the K-order super edges of the thermal power plant or the entity vectors in the K-order super edges and the K-order super edges of the new energy power plant into a one-dimensional convolution to generate a transformation matrix, and then performing replacement and weighting operation on the entity vectors in the K-order super edges by using the transformation matrix to obtain a plurality of transformed super edge vectors of the thermal power plant or the new energy power plant.
8. The intelligent regional carbon emission measurement system based on low carbon energy consumption optimization synergy of claim 6, wherein the operation method of the super-edge convolution operation block is as follows: and performing summation operation on a plurality of embedded units in the thermal power plant representation set by using a one-dimensional convolution and a summation aggregator, performing maximum calculation on a plurality of embedded execution elements in the thermal power plant representation set by using a pooling aggregator, and splicing the plurality of embedded units into the thermal power plant representation set by using a splicing aggregator.
9. The intelligent regional carbon emission measurement system based on low-carbon energy consumption optimization and coordination as claimed in claim 1, wherein the power plant knowledge perception hypergraph module and the knowledge perception hypergraph operation block select the same number of negative samples and positive samples for each thermal power plant, wherein a new energy power plant meeting the requirement of the thermal power plant for collaborative optimization of low-carbon energy consumption is used as a positive sample, a new energy power plant not meeting the requirement of the thermal power plant for collaborative optimization of low-carbon energy consumption is used as a negative sample, a candidate new energy power plant collaborative score value model is trained by the thermal power plant, effectiveness of training is guaranteed, and the training loss module defines a loss function of the candidate new energy power plant collaborative score value model by the thermal power plant as a difference between cross entropy loss of the training loss module and cross entropy loss of the negative samples, and a norm of an L2 regularization term of the model parameterization is added.
10. The intelligent regional carbon emission measurement system based on low carbon energy consumption optimization synergy of claim 1, wherein the data measurement module comprises a flow sensor, a flow rate sensor, a carbon dioxide concentration sensor, a carbon monoxide concentration sensor and a nitrous oxide sensor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211480198.9A CN115564314A (en) | 2022-11-24 | 2022-11-24 | Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation |
PCT/CN2022/136045 WO2024108641A1 (en) | 2022-11-24 | 2022-12-01 | Regional carbon emission smart measurement system based on low-carbon energy consumption optimization collaboration |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211480198.9A CN115564314A (en) | 2022-11-24 | 2022-11-24 | Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115564314A true CN115564314A (en) | 2023-01-03 |
Family
ID=84770164
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211480198.9A Pending CN115564314A (en) | 2022-11-24 | 2022-11-24 | Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115564314A (en) |
WO (1) | WO2024108641A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116756203A (en) * | 2023-06-13 | 2023-09-15 | 淮阴工学院 | Knowledge graph driving cold chain logistics equipment type selection method and device based on carbon emission reduction target |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107491882A (en) * | 2017-08-24 | 2017-12-19 | 华北电力大学(保定) | A kind of construction method of thermal power plant's electric power green color index model |
CN110955834B (en) * | 2019-11-27 | 2023-07-07 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
CN113282868A (en) * | 2020-02-20 | 2021-08-20 | 赫普能源环境科技股份有限公司 | Online monitoring system and calculation and analysis method for degree electric carbon emission intensity of thermal power plant |
CN112613602A (en) * | 2020-12-25 | 2021-04-06 | 神行太保智能科技(苏州)有限公司 | Recommendation method and system based on knowledge-aware hypergraph neural network |
CN113887827B (en) * | 2021-10-25 | 2024-06-14 | 国网安徽省电力有限公司电力科学研究院 | Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
CN114744684A (en) * | 2022-04-24 | 2022-07-12 | 国网浙江省电力有限公司 | Novel low-carbon economic regulation and control method for power system |
-
2022
- 2022-11-24 CN CN202211480198.9A patent/CN115564314A/en active Pending
- 2022-12-01 WO PCT/CN2022/136045 patent/WO2024108641A1/en unknown
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116756203A (en) * | 2023-06-13 | 2023-09-15 | 淮阴工学院 | Knowledge graph driving cold chain logistics equipment type selection method and device based on carbon emission reduction target |
CN116756203B (en) * | 2023-06-13 | 2024-06-11 | 淮阴工学院 | Knowledge graph driving cold chain logistics equipment type selection method and device based on carbon emission reduction target |
Also Published As
Publication number | Publication date |
---|---|
WO2024108641A1 (en) | 2024-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Coupling efficiency measurement and spatial correlation characteristic of water–energy–food nexus in China | |
CN103853106B (en) | A kind of energy consumption Prediction Parameters optimization method of building energy supplied equipment | |
Chen et al. | Study on spatio-temporal changes and driving factors of carbon emissions at the building operation stage-A case study of China | |
Wang et al. | Assessing the performance of industrial water resource utilization systems in China based on a two-stage DEA approach with game cross efficiency | |
CN103440528B (en) | Thermal power unit operation optimization method and device based on power consumption analysis | |
Sun et al. | Improved energy performance evaluating and ranking approach for office buildings using Simple-normalization, Entropy-based TOPSIS and K-means method | |
Liu et al. | The calculation of productivity factor for ecological footprints in China: A methodological note | |
Liu et al. | The calculation of equivalence factor for ecological footprints in China: a methodological note | |
CN115564314A (en) | Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation | |
Azizi | A note on data envelopment analysis with missing values: an interval DEA approach | |
CN112968441A (en) | Power grid planning method applied to large-scale wind power base | |
Lei et al. | Prediction method of energy consumption for high building based on LMBP neural network | |
CN108647483A (en) | A kind of SCR inlet NO based on fuzzy tree modeling methodXThe flexible measurement method of concentration | |
CN117422004B (en) | Carbon potential prediction method and system based on neural network | |
CN113673892B (en) | Energy consumption monitoring system and method for green building | |
Xiong | Uncertainty evaluation of the coordinated development of urban human settlement environment and economy in Changsha city | |
Li et al. | Study on the regional differences and promotion models of green technology innovation performance in China: Based on entropy weight method and fuzzy set-qualitative comparative analysis | |
CN111126827A (en) | Input-output accounting model construction method based on BP artificial neural network | |
Gao et al. | A prediction approach on energy consumption for public buildings using mind evolutionary algorithm and bp neural network | |
Zhang et al. | Water-energy-food nexus efficiency and its factor analysis in China: A dynamic series-loop DDF model | |
Yang et al. | The impact of quality of life on industrial and agricultural production and environmental efficiency in China's provinces | |
CN113704978B (en) | Urban ring man-water coupling simulation method and system based on social hydrology | |
CN114298492B (en) | Method for predicting and evaluating biomass energy development suitability based on economic development change | |
Li et al. | Spatial-temporal evolution of the coupling state of agricultural socio-ecologo-economic system in North China Plain | |
Tang | Research on Sustainable Development of Beijing City Based on Ecological Footprint 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 |