CN117313992A - Carbon emission factor updating method considering multi-energy-flow community load - Google Patents
Carbon emission factor updating method considering multi-energy-flow community load Download PDFInfo
- Publication number
- CN117313992A CN117313992A CN202311173108.6A CN202311173108A CN117313992A CN 117313992 A CN117313992 A CN 117313992A CN 202311173108 A CN202311173108 A CN 202311173108A CN 117313992 A CN117313992 A CN 117313992A
- Authority
- CN
- China
- Prior art keywords
- energy
- carbon emission
- load
- community
- cchp
- 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
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 107
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000006870 function Effects 0.000 claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 16
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 48
- 238000006243 chemical reaction Methods 0.000 claims description 30
- 238000010521 absorption reaction Methods 0.000 claims description 27
- 230000005611 electricity Effects 0.000 claims description 26
- 239000007789 gas Substances 0.000 claims description 26
- 239000003345 natural gas Substances 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000010248 power generation Methods 0.000 claims description 15
- 238000001816 cooling Methods 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 230000005284 excitation Effects 0.000 claims description 12
- 238000010438 heat treatment Methods 0.000 claims description 9
- 239000002699 waste material Substances 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 4
- 239000006096 absorbing agent Substances 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000003245 coal Substances 0.000 claims description 3
- 238000002485 combustion reaction Methods 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 claims description 3
- 238000009472 formulation Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 231100000719 pollutant Toxicity 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000003507 refrigerant Substances 0.000 claims description 3
- 238000005057 refrigeration Methods 0.000 claims description 3
- 239000002904 solvent Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000009834 vaporization Methods 0.000 claims description 3
- 230000008016 vaporization Effects 0.000 claims description 3
- 230000000241 respiratory effect Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Power Engineering (AREA)
- Bioinformatics & Cheminformatics (AREA)
Abstract
The invention discloses a carbon emission factor updating method considering the load of a multi-energy-flow community, which comprises the following steps: step one: acquiring load demands of communities in the current month and a predicted value of a clean energy capacity interval, and performing interval oversampling on the predicted value to acquire a large number of predicted samples; step two: modeling a community function device; step three: designing a model loss function to obtain an optimal energy scheduling plan at each moment under each prediction sample; step four: calculating time-varying dynamic carbon emission factors of all samples, and constructing a self-adaptive fuzzy neural network; step five: and training and learning the self-adaptive fuzzy neural network based on the source load prediction data set, and applying the trained network to updating the actual dynamic carbon emission factor. The modeling is performed on the comprehensive energy community, the actual carbon emission of the community can be rapidly and accurately calculated, and the community is effectively stimulated to carry out reliable management measures for carbon emission.
Description
[ field of technology ]
The invention relates to the technical field of comprehensive management of load energy sources, in particular to the technical field of a carbon emission factor updating method considering the load of a multi-energy-flow community.
[ background Art ]
Because of the proposal of 'carbon reaching peak, carbon neutralization' target, renewable energy source becomes the main force army in urban electricity energy source, and the comprehensive energy community plays an important role in the process of realizing 'double carbon' target by means of the technical means of multi-energy complementation, demand response and the like. The method has the advantages that the carbon emission of the comprehensive energy community is rapidly and accurately measured and calculated, the multi-energy potential evaluation and influence factor analysis of 'source charge storage and charging' can be realized, the resource scheduling feedback is carried out so as to effectively reduce the carbon emission of the community, and the energy consumption and the environmental cost in the community are reduced while the transparency of the carbon emission of the community is realized.
The most common of existing carbon emission calculation methods is the emission factor method, i.e., carbon emission calculation based on fossil energy usage. However, for a comprehensive energy community, the energy supply modes of all the time periods are various and frequently changed, the fixed carbon emission factors cannot quickly and accurately calculate the actual carbon emission of the community, and forward feedback cannot be generated for energy regulation and control in the community, so that the calculation of the carbon emission is fuzzy, and the community cannot be effectively stimulated to carry out reliable management measures on the carbon emission.
[ invention ]
The invention aims to solve the problems in the prior art, and provides a carbon emission factor updating method considering the load of a multi-energy community, which models a typical comprehensive energy community, focuses on the running cost and the environmental cost of the community in each period, so as to acquire a dynamic load carbon emission factor updating mode under normal operation of the community, and can calculate the carbon emission amount based on the community load amount in different periods quickly and accurately.
In order to achieve the above object, the present invention provides a carbon emission factor updating method considering the load of a multi-energy stream community, comprising the steps of:
step one: acquiring load demands of communities in the current month and a predicted value of a clean energy capacity interval, and performing interval oversampling on the predicted value to acquire a large number of predicted samples;
step two: modeling a community function device: considering an energy supply device owned by a typical comprehensive energy community, wherein the energy supply device comprises photovoltaic, wind power clean energy, an electric refrigerator, an absorption refrigerator, a gas boiler and a combined heat and power generation device, and a mathematical model is built aiming at a main energy supply device;
step three: designing a model loss function, and carrying out iterative solution on the model based on the prediction samples and a heuristic algorithm to obtain an optimal energy scheduling plan at each moment under each prediction sample: to achieve optimal energy regulation, a cost F of energy is established E Cost of operation and maintenance F U And carbon emission cost F C The specific formula is as follows: min f=f E +F U +F C The method comprises the steps of carrying out a first treatment on the surface of the In order to ensure the stable operation of the energy system, setting load balance constraint and external energy purchasing constraint;
step four: calculating time-varying dynamic carbon emission factors of all samples, and constructing a self-adaptive fuzzy neural network;
step five: and training and learning the self-adaptive fuzzy neural network based on the source load prediction data set, and applying the trained network to updating the actual dynamic carbon emission factor.
Preferably, the specific process of the first step is as follows: obtaining electricity, cold and heat load demands of communities at each moment in month and clean energy productivityThe section prediction value is set to be E (t) = { E min (t),E max (t)}、C(t)={C min (t),C max (t)}、H(t)={H min (t),H max (t)}、E ce (t)={E ce min (t),E ce max (t) } (t=0, 1,2 …, 23), oversampling boundary prediction values by adopting an SMOTE algorithm or a bordure-SMOTE algorithm, obtaining prediction samples of a large amount of load demands and clean energy power generation amounts which can effectively represent a month change trend, taking the prediction samples obtained by the oversampling as a source load prediction data set of the month, and setting the prediction samples as a source load prediction data set of the monthN represents the total number of the prediction samples obtained after oversampling, and the clean energy sources comprise photovoltaic power generation and wind power generation.
Preferably, modeling of the primary energy supply device in the second step:
the combined cooling, heating and power generation can simultaneously generate heat, electricity and cooling load by inputting natural gas, and input energy sources can be fully utilized, and an energy supply output model can be expressed as follows:
wherein G is CCHP (t) is the amount of natural gas consumed by CCHP at time t; e (E) CCHP (t)、H CCHP (t)、C CCHP (t) is the electric, thermal and cold power output by CCHP at time t;the conversion efficiency of gas-to-electricity conversion, gas-to-heat conversion and gas-to-cold conversion is realized for CCHP; />The minimum power of CCHP electricity generation, heat and cold respectively,maximum power of CCHP electricity generation, heat and cold respectively;
the gas boiler is energy supply equipment for converting chemical energy into heat energy by utilizing energy sources such as natural gas, when the heat demand is high, CCHP is difficult to meet the heat load energy supply demand, and the gas boiler is taken as an auxiliary heating device to complement the residual heat shortage, and an energy supply output model can be expressed as follows:
wherein G is GB (t) is the natural gas amount consumed by the gas boiler at the moment t, H GB (t) is the thermal power output by the gas boiler at the moment t,the conversion efficiency of gas-to-heat conversion is realized for the gas-fired boiler; />The minimum and maximum output power of the gas boiler are respectively;
the working principle of the absorption refrigerator is that as the temperature is continuously increased, the concentration of the cooling solvent is increased along with the temperature and gradually flows into the absorber, meanwhile, steam enters the condenser to release energy and is converted into liquid water, the liquid water flows into the evaporator to generate vaporization reaction to absorb huge heat of coal water so as to achieve the refrigerating effect, and the refrigerating capacity generated by the absorption refrigerator is shown in the following formula:
wherein H is AC (t) is the thermal power consumed by the absorption refrigerator at time t, C AC (t) is the cold power output by the absorption refrigerator at the moment t,the conversion efficiency of heat to cold is realized for the absorption refrigerator; />The minimum and maximum output power of the absorption refrigerator are respectively;
the electric refrigerator has the advantages of less pollutant emission, stable and reliable operation, simple and convenient modulation and the like, so that the electric refrigerator has higher application rate in a combined cooling heating and power micro-grid system; in a multi-energy-flow community, the electric refrigerator can be used as auxiliary refrigeration to effectively promote clean energy consumption and reduce carbon emission, and the electric refrigerator runs stably and is simple and convenient to regulate and control, so that the electric refrigerator has higher application rate in various micro-grid systems; the cooling capacity of the electric refrigerant is calculated as follows:
wherein E is EC (t) is the electric power consumed by the electric refrigerator at the moment t, C EC (t) is the cold power output by the electric refrigerator at the moment t,the conversion efficiency of electric conversion to cold is realized for the absorption refrigerator; />The minimum and the maximum output power of the electric refrigerator respectively.
Preferably, the energy cost in the third step refers to the actual cost spent by the community in purchasing electricity and gas from the external network, and the clean energy waste cost calculation formula is as follows:
wherein g (t) and e (t) are the prices of natural gas (Yuan/m) at t 3 ) And grid purchase price (Yuan/KWh), E other (t) is the electricity generated in the community at the moment t is insufficient, so that the electricity quantity required to be additionally purchased from the power grid is E cut (t) clean energy waste power, ω being a clean energy waste penalty factor;
the operation and maintenance cost is mainly the cost generated by mechanical productivity loss, manual inspection, maintenance and the like, is normally positively related to the equipment productivity, and has the following calculation formula:
in the formula, v CCHP 、v GB 、v AC 、v EC Respectively CCHP, gas boiler and respiration type systemUnit maintenance cost (Yuan/KWh) of the refrigerator and the electric refrigerator;
the carbon emission cost calculation mode of each period of the multi-energy flow community is as follows:
wherein lambda is g 、λ e Carbon emission coefficient (kg/m) of natural gas combustion 3 ) The electricity generation carbon emission coefficient (kg/KWh) of the power grid, c is the carbon trade unit price (yuan/kg) of the carbon trade market;
the load balance constraint is that electric, thermal and cold loads exist in the energy system of the multi-energy community, and the load supply and demand balance relation is as follows:
E(t)+E EC (t)=E CCHP (t)+E ce (t)+E other (t)
H(t)+H AC (t)=H CCHP (t)+H GB (t)
C(t)=C CCHP (t)+C AC (t)+C EC (t)
the external energy purchasing constraint is that in order to ensure that the upper power grid and the air network can safely and stably operate, the maximum transmission efficiency limit of the energy supply channel cannot be exceeded when energy purchasing is carried out, and therefore the external energy purchasing constraint is set as follows:
in the method, in the process of the invention,minimum and maximum limits for power grid purchase; />Minimum and maximum limits for purchasing natural gas for a systemAnd (5) preparing.
Preferably, the specific process of the fourth step is as follows: inputting the obtained source load prediction data set into the built model based on the set objective function and condition constraint, and adopting a particle swarm algorithm or other heuristic algorithms to carry out iterative solution to obtain a regulation and control mode of the multi-energy community energy under the minimum cost of the month;
the natural gas purchase amount of each predicted sample in each period under the control mode obtained by solving is as followsThe electricity purchasing quantity of the power grid is>The carbon emission amount corresponding to each period can be expressed as:
in order to couple the relation between multiple kinds of load and carbon emission, a dynamic load carbon emission factor epsilon which can be changed with time is proposed i (t) the calculation is as follows:
in order to fit the corresponding association relation between the dynamic load carbon emission factors and the source load data, the dynamic carbon emission factors are accurately updated based on the actual source load data, and an adaptive fuzzy neural network is built to learn the obtained source load prediction data set and the dynamic load carbon emission factors corresponding to the samples; the self-adaptive fuzzy neural network combines a fuzzy reasoning mechanism and a neural network prediction idea, and optimizes various membership functions and fuzzy rule parameters contained in hidden nodes by utilizing a parallel self-learning means of the neural network, so that the reasoning performance of the traditional fuzzy reasoning system is greatly improved, and the parameter formulation difficulty of the fuzzy system is effectively reduced.
Preferably, the steps ofThe specific process is as follows: inputting a source load prediction data set and dynamic load carbon emission factors corresponding to all samples into a designed self-adaptive fuzzy neural network for training and testing; in order to reduce updating effect deviation caused by unreasonable data division, a cross-validation training method is adopted, an original data set is divided into K groups randomly and averagely, each subset data is respectively used as a validation set, the rest of K-1 group subset data are used as training sets, K self-adaptive fuzzy neural networks for updating the dynamic load carbon emission factors are obtained, and the actual updating value of the dynamic load carbon emission factors is finally obtained by using the comprehensive results of the K self-adaptive fuzzy neural networks:
the self-adaptive fuzzy neural network has five layers, namely an input layer, a membership function layer, a rule layer, a defuzzification layer and an output layer, and the self-adaptive fuzzy neural network has the following functions of the current time and the previous t a Load demand and photoelectric capacity of each hour are used as network input, and dynamic carbon emission factors at the current moment are used as output;
the input layer mainly connects each node with the input quantity component directly, and the connected input quantity is transmitted to the second layer as a new input quantity; the input layer parameters are the load demand at the current moment and the clean energy productivity E (t), C (t), H (t) and E ce (t) and the previous t a Load demand, clean energy production E (t-1), C (t-1), H (t-1), E for several hours ce (t-1)……E(t-t a )、C(t-t a )、H(t-t a )、E ce (t-t a );
The membership function layer mainly designs a proper membership function for input parameters to realize input fuzzification; because the load demand is relatively gentle, it is blurred with a gaussian function:
wherein mu is jk As a fuzzy membership function, x j For input ofParameters; a, a jk And b jk The expected standard deviation of the Gaussian function is the parameter to be optimized; j represents the j-th input parameter, k represents the k-th fuzzy subset, k sum For the set maximum number of fuzzy subsets;
the clean energy capacity has large variation amplitude and larger instability, so that the clean energy capacity is blurred by adopting a trigonometric function:
wherein a is jk ,b jk C jk The membership function parameters to be optimized are obtained;
the rule layer mainly performs fuzzy product on the input of each neuron, each neuron represents a fuzzy rule, and the total fuzzy number is set as n sum The excitation intensity calculation formula of each fuzzy rule is:
and then, carrying out normalization calculation on the excitation intensity of each rule, and inputting the excitation intensity into the next layer:
the defuzzification layer mainly carries out overall defuzzification processing to enable output to be an accurate result, and the output quantity of each fuzzy rule can be accurately processed based on the excitation strength of the fuzzy rule of the upper layer:
in p n0 ,p n1 ,…,p n4 (t a +1) is the deblurring function f to be optimized n An internal parameter;
the output layer is used for summarizing and calculating the final output of the whole grid:
in order to realize reverse gradient training learning of a network, a loss function of the network needs to be designed:
where ε is the actual value of the dynamic carbon emission factor.
The invention has the beneficial effects that:
the method aims at the comprehensive energy communities with various energy supply modes and frequent change in each period, can rapidly and accurately calculate the actual carbon emission of the communities, and can generate forward feedback for energy regulation and control in the communities, so that the communities are effectively stimulated to carry out reliable management measures on carbon emission.
The features and advantages of the present invention will be described in detail by way of example with reference to the accompanying drawings.
[ description of the drawings ]
FIG. 1 is a schematic diagram of an exemplary integrated energy community energy system for a carbon emission factor update method that accounts for multi-energy community load in accordance with the present invention;
FIG. 2 is a block diagram of an adaptive fuzzy neural network of the carbon emission factor updating method taking into account the load of the multi-energy-flow community according to the present invention;
FIG. 3 is a flow chart of a dynamic load carbon emission factor update method of the carbon emission factor update method taking into account the load of the multi-energy-flow community according to the present invention.
In fig. 2, from left to right, an input layer, a membership function layer, a rule layer, a defuzzification layer, and an output layer are provided.
[ detailed description ] of the invention
Referring to fig. 1,2 and 3, the present invention includes the following steps:
step one: acquiring load demands of communities in the current month and a predicted value of a clean energy capacity interval, and performing interval oversampling on the predicted value to acquire a large number of predicted samples;
step two: modeling a community function device: considering an energy supply device owned by a typical comprehensive energy community, wherein the energy supply device comprises photovoltaic, wind power clean energy, an electric refrigerator, an absorption refrigerator, a gas boiler and a combined heat and power generation device, and a mathematical model is built aiming at a main energy supply device;
step three: designing a model loss function, and carrying out iterative solution on the model based on the prediction samples and a heuristic algorithm to obtain an optimal energy scheduling plan at each moment under each prediction sample: to achieve optimal energy regulation, a cost F of energy is established E Cost of operation and maintenance F U And carbon emission cost F C The specific formula is as follows: min f=f E +F U +F C The method comprises the steps of carrying out a first treatment on the surface of the In order to ensure the stable operation of the energy system, setting load balance constraint and external energy purchasing constraint;
step four: calculating time-varying dynamic carbon emission factors of all samples, and constructing a self-adaptive fuzzy neural network;
step five: and training and learning the self-adaptive fuzzy neural network based on the source load prediction data set, and applying the trained network to updating the actual dynamic carbon emission factor.
The working process of the invention comprises the following steps:
the invention relates to a carbon emission factor updating method considering the load of a multi-energy-flow community, which is described with reference to the accompanying drawings in the working process.
The carbon emission factor updating method considering the load of the multi-energy-flow community comprises the following steps:
step one, obtaining the interval prediction value of the power, cold and heat load demands and the capacity of clean energy (photovoltaic power generation, wind power generation and the like) of the community at each moment in the month, and setting the interval prediction value as E (t) = { E min (t),E max (t)}、C(t)={C min (t),C max (t)}、H(t)={H min (t),H max (t)}、E ce (t)={E cemin (t),E cemax (t) } (t=0, 1,2., 23). Using SMOTE or Borderline-SMOThe TE method is used for realizing oversampling on the boundary predicted value, obtaining predicted samples of a large amount of load demands and clean energy power generation capacity which can effectively represent the month change trend, taking the predicted samples obtained by oversampling as a source load predicted data set of the month, and setting the predicted data set asN represents the total number of prediction samples obtained after oversampling.
Step two, considering energy supply devices owned by a typical comprehensive energy community, such as photovoltaic, wind power clean energy, an electric refrigerator, an absorption refrigerator, a gas boiler and a combined heat and power generation, and building a mathematical model aiming at the energy supply devices. The exemplary community energy system is schematically illustrated in FIG. 1.
Modeling a main energy supply device in the method:
combined heat and power (Combined Cooling Heating and Power, CCHP)
The CCHP can simultaneously generate heat, electricity and cold load by inputting natural gas, can fully utilize input energy, and an energy supply output model can be expressed as:
wherein G is CCHP (t) is the natural gas amount consumed by CCHP at time t, E CCHP (t)、H CCHP (t)、C CCHP (t) is the electric, thermal and cold power output by CCHP at the moment t,the conversion efficiency of gas-to-electricity conversion, gas-to-heat conversion and gas-to-cold conversion is realized for CCHP. />The minimum power of CCHP electricity generation, heat and cold respectively,maximum power of CCHP electricity generation, heat and cold respectively.
(1) Gas Boiler (Gas Boiler, GB)
The gas-fired boiler is an energy supply device for converting chemical energy into heat energy by utilizing energy sources such as natural gas, and when the heat demand is high, the CCHP is generally difficult to meet the heat load energy supply demand, and the gas-fired boiler is used as an auxiliary heating device to complement the surplus heat deficiency. The energy output model can be expressed as:
wherein G is GB (t) is the natural gas amount consumed by the gas boiler at the moment t, H GB (t) is the thermal power output by the gas boiler at the moment t,the conversion efficiency of gas-to-heat is realized for the gas boiler. />The minimum output power and the maximum output power of the gas boiler are respectively.
(2) Absorption refrigerator (Absorption Chillers, AC)
The working principle of the absorption refrigerator is that as the temperature is continuously increased, the concentration of the cooling solvent is increased along with the temperature and gradually flows into the absorber, meanwhile, steam enters the condenser to release energy and is converted into liquid water, the liquid water flows into the evaporator to generate vaporization reaction to absorb huge heat of coal water so as to achieve the refrigerating effect, and the refrigerating capacity generated by the absorption refrigerator is shown in the following formula:
wherein H is AC (t) is the thermal power consumed by the absorption refrigerator at time t, C AC (t) is the cold power output by the absorption refrigerator at the moment t,for absorption refrigerationThe machine realizes the conversion efficiency of heat conversion into cold. />The minimum and the maximum output power of the absorption refrigerator are respectively.
(3) Electric refrigerator (Electric Chiller, EC)
The electric refrigerator has the advantages of less pollutant emission, stable and reliable operation, simple and convenient modulation and the like, so the electric refrigerator has higher application rate in a combined cooling heating and power type micro-grid system. In a multi-energy-flow community, the electric refrigerator can be used as auxiliary refrigeration to effectively promote clean energy consumption and reduce carbon emission, and the electric refrigerator is stable in running and simple and convenient to regulate and control, so that the electric refrigerator has higher application rate in various micro-grid systems. The cooling capacity of the electric refrigerant is calculated as follows:
wherein E is EC (t) is the electric power consumed by the electric refrigerator at the moment t, C EC (t) is the cold power output by the electric refrigerator at the moment t,the conversion efficiency of electric conversion to cold is realized for the absorption refrigerator. />The minimum and the maximum output power of the electric refrigerator respectively.
Step three, in order to realize optimal energy regulation, the energy cost F needs to be established and considered E Cost of operation and maintenance F U And carbon emission cost F C The specific formula is as follows:
min F=F E +F U +F C (5)
(1) Cost of energy consumption
The energy consumption cost refers to the actual cost spent by the community in purchasing electricity and gas from the external network, and the clean energy waste cost is calculated by the following formula:
wherein g (t) and e (t) are the prices of natural gas (Yuan/m) at t 3 ) And grid purchase price (Yuan/KWh), E other (t) is the electricity generated in the community at the moment t is insufficient, so that the electricity quantity required to be additionally purchased from the power grid is E cut For clean energy waste power, ω is a clean energy waste penalty factor.
(2) Cost of operation and maintenance
The system operation maintenance cost is mainly the cost generated by mechanical productivity loss, manual inspection, maintenance and the like, and is normally positively related to the equipment productivity, and the calculation formula is as follows:
in the formula, v CCHP 、υ GB 、v AC、 υ EC The unit maintenance cost (Yuan/KWh) of CCHP, gas boiler, respiratory refrigerator and electric refrigerator is respectively.
(3) Carbon emission cost
The carbon emission cost calculation mode of each period of the multi-energy flow community is as follows:
wherein lambda is g 、λ e Carbon emission coefficient (kg/m) of natural gas combustion 3 ) And the electricity generation carbon emission coefficient (kg/KWh) of the power grid, and c is the carbon trade unit price (yuan/kg) of the carbon trade market.
In order to ensure stable operation of the energy system, load balance constraints and external energy purchasing constraints need to be set.
(1) Load balancing constraints:
the energy system of the multi-energy-flow community has electric, thermal and cold loads, and the load supply and demand balance relation is as follows:
(2) External energy purchasing constraints:
in order to ensure that the upper power grid and the air grid can safely and stably operate, the maximum transmission efficiency limit of the energy supply channel cannot be exceeded when energy purchase is performed, and therefore the external energy purchase constraint is set as follows:
in the method, in the process of the invention,minimum and maximum limits for power grid purchase; />Minimum and maximum limits for natural gas purchase for systems.
And step four, inputting the obtained source load prediction data set into the built model based on the set objective function and condition constraint, and adopting a particle swarm algorithm or other heuristic algorithms to carry out iterative solution so as to obtain the multi-energy-flow community energy regulation and control mode under the minimum cost of the month. The natural gas purchase amount of each predicted sample in each period under the control mode obtained by solving is as followsThe electricity purchasing quantity of the power grid is>The carbon emission amount corresponding to each period can be expressed as:
in order to couple the relation between various loads and carbon emission, the invention providesDynamic load carbon emission factor epsilon that can vary with time i (t) the calculation is as follows:
in order to fit the corresponding association relation between the dynamic load carbon emission factors and the source load data and achieve accurate updating of the dynamic carbon emission factors based on actual source load data, the invention builds the self-adaptive fuzzy neural network (Adaptive Network based Fuzzy Inference System, ANFIS) to learn the obtained source load prediction data set and the dynamic load carbon emission factors corresponding to all samples. The self-adaptive fuzzy neural network combines a fuzzy reasoning mechanism and a neural network prediction idea, and optimizes various membership functions and fuzzy rule parameters contained in hidden nodes by utilizing a parallel self-learning means of the neural network, so that the reasoning performance of the traditional fuzzy reasoning system is greatly improved, and the parameter formulation difficulty of the fuzzy system is effectively reduced.
The self-adaptive fuzzy neural network built by the invention has five layers, namely an input layer, a membership function layer, a rule layer, a defuzzification layer and an output layer, as shown in figure 2. The network uses the current time and the previous t a (taking t) a =2) load demand, photovoltaic capacity for a time of hour as network input, and dynamic carbon emission factor at the current moment as output.
(1) Input layer
The layer mainly connects each node directly with the input quantity component, and the connected input quantity is transmitted to the second layer as a new input quantity. The input layer parameters are the load demand at the current moment and the clean energy productivity E (t), C (t), H (t) and E ce (t) and the previous t a Load demand, clean energy production E (t-1), C (t-1), H (t-1), E for several hours ce (t-1)……E(t-t a )、C(t-t a )、H(t-t a )、E ce (t-t a )。
(2) Membership function layer
This layer is mainly to design a suitable membership function for the input parameters to achieve input blurring. Because the load demand is relatively gentle, it is blurred with a gaussian function:
wherein mu is jk As a fuzzy membership function, x j Is an input parameter; a, a jk And b jk The expected standard deviation of the Gaussian function is the parameter to be optimized; j represents the j-th input parameter, k represents the k-th fuzzy subset, k sum Let k be the set maximum number of fuzzy subsets sum =3。
The clean energy capacity has large variation amplitude and larger instability, so that the clean energy capacity is blurred by adopting a trigonometric function:
wherein a is jk ,b jk C jk And the membership function parameters to be optimized.
(3) Rule layer
The layer mainly performs fuzzy product on the input of each neuron, each neuron represents a fuzzy rule, and the total fuzzy number is set as n sum The excitation intensity calculation formula of each fuzzy rule is:
and then, carrying out normalization calculation on the excitation intensity of each rule, and inputting the excitation intensity into the next layer:
(4) De-blurring layer
The layer mainly carries out overall defuzzification processing to change output into an accurate result, and the output quantity of each fuzzy rule can be accurately processed based on the excitation strength of the fuzzy rule of the upper layer:
in the middle ofFor deblurring function f to be optimized n Internal parameters.
(5) Output layer
This layer is used to aggregate and calculate the final output of the entire grid:
in order to realize reverse gradient training learning of a network, a loss function of the network needs to be designed:
where ε is the actual value of the dynamic carbon emission factor.
And fifthly, inputting the source load prediction data set and the dynamic load carbon emission factors corresponding to the samples into the designed ANFIS for training and testing. In order to reduce updating effect deviation caused by unreasonable data division, the invention adopts a cross-validation training method, an original data set is divided into K (K=10) groups randomly and averagely, each subset data is respectively used as a validation set, the rest K-1 groups of subset data are used as a training set, K ANFISs for updating the dynamic load carbon emission factor are obtained, and the actual updating value of the dynamic load carbon emission factor is finally obtained by using the comprehensive result of the K ANFISs.
In the actual use process, the load demand and the predicted value of the clean energy output at the current moment and the previous t can be obtained a And (5) inputting the historical data of the moment into the trained ANFIS of the current month to obtain the dynamic load carbon emission factor of the current moment. In the subsequent carbon emission calculation, the actual carbon emission in the period can be calculated directly based on the real-time total load and the dynamic load carbon emission factor updated based on the actual data, the calculated dynamic load carbon emission factor can be applicable to communities of the same type, and the carbon emission conditions of different energy consumption devices can be quantitatively analyzed based on the load usage amount due to the fact that the emission factor is coupled with various load information, so that the transparency of carbon emission flow is realized. The implementation flow chart of the method is shown in fig. 3.
The above embodiments are illustrative of the present invention, and not limiting, and any simple modifications of the present invention fall within the scope of the present invention.
Claims (6)
1. A carbon emission factor updating method considering the load of a multi-energy-flow community is characterized in that: the method comprises the following steps:
step one: acquiring load demands of communities in the current month and a predicted value of a clean energy capacity interval, and performing interval oversampling on the predicted value to acquire a large number of predicted samples;
step two: modeling a community function device: considering an energy supply device owned by a typical comprehensive energy community, wherein the energy supply device comprises photovoltaic, wind power clean energy, an electric refrigerator, an absorption refrigerator, a gas boiler and a combined heat and power generation device, and a mathematical model is built aiming at a main energy supply device;
step three: designing a model loss function, and carrying out iterative solution on the model based on the prediction samples and a heuristic algorithm to obtain an optimal energy scheduling plan at each moment under each prediction sample: to achieve optimal energy regulation, a cost F of energy is established E Cost of operation and maintenance F U And carbon emission cost F C The specific formula is as follows: min f=f E +F U +F C The method comprises the steps of carrying out a first treatment on the surface of the To ensure stable operation of energy systemSetting load balance constraint and external energy purchasing constraint;
step four: calculating time-varying dynamic carbon emission factors of all samples, and constructing a self-adaptive fuzzy neural network;
step five: and training and learning the self-adaptive fuzzy neural network based on the source load prediction data set, and applying the trained network to updating the actual dynamic carbon emission factor.
2. The carbon emission factor updating method considering the load of the multi-stream community as claimed in claim 1, wherein: the specific process of the first step is as follows: obtaining the interval predicted value of the power, cold and heat load demands and clean energy productivity of the community at each moment in the month, and setting the interval predicted value as E (t) = { E min (t),E max (t)}、C(t)={C min (t),C max (t)}、H(t)={H min (t),H max (t)}、E ce (t)={E ce min (t),E ce max (t) } (t=0, 1,2 …, 23), oversampling boundary prediction values by adopting an SMOTE algorithm or a bordure-SMOTE algorithm, obtaining prediction samples of a large amount of load demands and clean energy power generation amounts which can effectively represent a month change trend, taking the prediction samples obtained by the oversampling as a source load prediction data set of the month, and setting the prediction samples as a source load prediction data set of the monthN represents the total number of the prediction samples obtained after oversampling, and the clean energy sources comprise photovoltaic power generation and wind power generation.
3. The carbon emission factor updating method considering the load of the multi-stream community as claimed in claim 1, wherein: modeling of the main energy supply device in the second step:
the combined cooling, heating and power generation can simultaneously generate heat, electricity and cooling load by inputting natural gas, and input energy sources can be fully utilized, and an energy supply output model can be expressed as follows:
wherein G is CCHP (t) is the amount of natural gas consumed by CCHP at time t; e (E) CCHP (t)、H CCHP (t)、C CCHP (t) is the electric, thermal and cold power output by CCHP at time t;the conversion efficiency of gas-to-electricity conversion, gas-to-heat conversion and gas-to-cold conversion is realized for CCHP; />The minimum power of CCHP electricity generation, heat and cold respectively,maximum power of CCHP electricity generation, heat and cold respectively;
the gas boiler is energy supply equipment for converting chemical energy into heat energy by utilizing energy sources such as natural gas, when the heat demand is high, CCHP is difficult to meet the heat load energy supply demand, and the gas boiler is taken as an auxiliary heating device to complement the residual heat shortage, and an energy supply output model can be expressed as follows:
wherein G is GB (t) is the natural gas amount consumed by the gas boiler at the moment t, H GB (t) is the thermal power output by the gas boiler at the moment t,the conversion efficiency of gas-to-heat conversion is realized for the gas-fired boiler; />The minimum and maximum output power of the gas boiler are respectively;
the working principle of the absorption refrigerator is that as the temperature is continuously increased, the concentration of the cooling solvent is increased along with the temperature and gradually flows into the absorber, meanwhile, steam enters the condenser to release energy and is converted into liquid water, the liquid water flows into the evaporator to generate vaporization reaction to absorb huge heat of coal water so as to achieve the refrigerating effect, and the refrigerating capacity generated by the absorption refrigerator is shown in the following formula:
wherein H is AC (t) is t time absorption systemThermal power consumed by the chiller, C AC (t) is the cold power output by the absorption refrigerator at the moment t,the conversion efficiency of heat to cold is realized for the absorption refrigerator; />The minimum and maximum output power of the absorption refrigerator are respectively;
the electric refrigerator has the advantages of less pollutant emission, stable and reliable operation, simple and convenient modulation and the like, so that the electric refrigerator has higher application rate in a combined cooling heating and power micro-grid system; in a multi-energy-flow community, the electric refrigerator can be used as auxiliary refrigeration to effectively promote clean energy consumption and reduce carbon emission, and the electric refrigerator runs stably and is simple and convenient to regulate and control, so that the electric refrigerator has higher application rate in various micro-grid systems; the cooling capacity of the electric refrigerant is calculated as follows:
wherein E is EC (t) is the electric power consumed by the electric refrigerator at the moment t, C EC (t) is the cold power output by the electric refrigerator at the moment t,the conversion efficiency of electric conversion to cold is realized for the absorption refrigerator; />The minimum and the maximum output power of the electric refrigerator respectively.
4. The carbon emission factor updating method considering the load of the multi-stream community as claimed in claim 1, wherein: the energy cost in the third step refers to the actual cost spent by the community in purchasing electricity and gas from the external network, and the clean energy waste cost calculation formula is as follows:
wherein g (t) and e (t) are the prices of natural gas (Yuan/m) at t 3 ) And grid purchase price (Yuan/KWh), E other (t) is the electricity generated in the community at the moment t is insufficient, so that the electricity quantity required to be additionally purchased from the power grid is E cut (t) clean energy waste power, ω being a clean energy waste penalty factor;
the operation and maintenance cost is mainly the cost generated by mechanical productivity loss, manual inspection, maintenance and the like, is normally positively related to the equipment productivity, and has the following calculation formula:
in the formula, v CCHP 、v GB 、v AC 、v EC Unit maintenance costs (yuan/KWh) of CCHP, gas boiler, respiratory refrigerator, electric refrigerator, respectively;
the carbon emission cost calculation mode of each period of the multi-energy flow community is as follows:
wherein lambda is g 、λ e Carbon emission coefficient (kg/m) of natural gas combustion 3 ) The electricity generation carbon emission coefficient (kg/KWh) of the power grid, c is the carbon trade unit price (yuan/kg) of the carbon trade market;
the load balance constraint is that electric, thermal and cold loads exist in the energy system of the multi-energy community, and the load supply and demand balance relation is as follows:
E(t)+E EC (t)=E CCHP (t)+E ce (t)+E other (t)
H(t)+H AC (t)=H CCHP (t)+H GB (t)
C(t)=C CCHP (t)+C AC (t)+C EC (t)
the external energy purchasing constraint is that in order to ensure that the upper power grid and the air network can safely and stably operate, the maximum transmission efficiency limit of the energy supply channel cannot be exceeded when energy purchasing is carried out, and therefore the external energy purchasing constraint is set as follows:
in the method, in the process of the invention,minimum and maximum limits for power grid purchase; />Minimum and maximum limits for natural gas purchase for systems.
5. The carbon emission factor updating method considering the load of the multi-stream community as claimed in claim 1, wherein: the specific process of the fourth step is as follows: inputting the obtained source load prediction data set into the built model based on the set objective function and condition constraint, and adopting a particle swarm algorithm or other heuristic algorithms to carry out iterative solution to obtain a regulation and control mode of the multi-energy community energy under the minimum cost of the month;
the natural gas purchase amount of each predicted sample in each period under the control mode obtained by solving is as followsThe electricity purchasing quantity of the power grid is>The carbon emission amount corresponding to each period can be expressed as:
in order to couple the relation between multiple kinds of load and carbon emission, a dynamic load carbon emission factor epsilon which can be changed with time is proposed i (t) the calculation is as follows:
in order to fit the corresponding association relation between the dynamic load carbon emission factors and the source load data, the dynamic carbon emission factors are accurately updated based on the actual source load data, and an adaptive fuzzy neural network is built to learn the obtained source load prediction data set and the dynamic load carbon emission factors corresponding to the samples; the self-adaptive fuzzy neural network combines a fuzzy reasoning mechanism and a neural network prediction idea, and optimizes various membership functions and fuzzy rule parameters contained in hidden nodes by utilizing a parallel self-learning means of the neural network, so that the reasoning performance of the traditional fuzzy reasoning system is greatly improved, and the parameter formulation difficulty of the fuzzy system is effectively reduced.
6. The carbon emission factor updating method considering the load of the multi-stream community as claimed in claim 1, wherein: the specific process of the fifth step is as follows: inputting a source load prediction data set and dynamic load carbon emission factors corresponding to all samples into a designed self-adaptive fuzzy neural network for training and testing; in order to reduce the update effect deviation caused by unreasonable data division, a cross-validation training method is adopted to divide the original data set into KAnd taking each subset data as a verification set and the rest K-1 subset data as training sets to obtain K self-adaptive fuzzy neural networks for updating the dynamic load carbon emission factors, and finally obtaining actual updated values of the dynamic load carbon emission factors by using the comprehensive results of the K self-adaptive fuzzy neural networks:
the self-adaptive fuzzy neural network has five layers, namely an input layer, a membership function layer, a rule layer, a defuzzification layer and an output layer, and the self-adaptive fuzzy neural network has the following functions of the current time and the previous t a Load demand and photoelectric capacity of each hour are used as network input, and dynamic carbon emission factors at the current moment are used as output;
the input layer mainly connects each node with the input quantity component directly, and the connected input quantity is transmitted to the second layer as a new input quantity; the input layer parameters are the load demand at the current moment and the clean energy productivity E (t), C (t), H (t) and E ce (t) and the previous t a Load demand, clean energy production E (t-1), C (t-1), H (t-1), E for several hours ce (t-1)……E(t-t a )、C(t-t a )、H(t-t a )、E ce (t-t a );
The membership function layer mainly designs a proper membership function for input parameters to realize input fuzzification; because the load demand is relatively gentle, it is blurred with a gaussian function:
wherein mu is jk As a fuzzy membership function, x j Is an input parameter; a, a jk And b jk The expected standard deviation of the Gaussian function is the parameter to be optimized; j represents the j-th input parameter, k represents the k-th fuzzy subset, k sum For the set maximum number of fuzzy subsets;
the clean energy capacity has large variation amplitude and larger instability, so that the clean energy capacity is blurred by adopting a trigonometric function:
wherein a is jk ,b jk C jk The membership function parameters to be optimized are obtained;
the rule layer mainly performs fuzzy product on the input of each neuron, each neuron represents a fuzzy rule, and the total fuzzy number is set as n sum The excitation intensity calculation formula of each fuzzy rule is:
and then, carrying out normalization calculation on the excitation intensity of each rule, and inputting the excitation intensity into the next layer:
the defuzzification layer mainly carries out overall defuzzification processing to enable output to be an accurate result, and the output quantity of each fuzzy rule can be accurately processed based on the excitation strength of the fuzzy rule of the upper layer:
in p n0 ,p n1 ,…,For deblurring function f to be optimized n An internal parameter;
the output layer is used for summarizing and calculating the final output of the whole grid:
in order to realize reverse gradient training learning of a network, a loss function of the network needs to be designed:
where ε is the actual value of the dynamic carbon emission factor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311173108.6A CN117313992A (en) | 2023-09-12 | 2023-09-12 | Carbon emission factor updating method considering multi-energy-flow community load |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311173108.6A CN117313992A (en) | 2023-09-12 | 2023-09-12 | Carbon emission factor updating method considering multi-energy-flow community load |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117313992A true CN117313992A (en) | 2023-12-29 |
Family
ID=89287537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311173108.6A Pending CN117313992A (en) | 2023-09-12 | 2023-09-12 | Carbon emission factor updating method considering multi-energy-flow community load |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117313992A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117575175A (en) * | 2024-01-15 | 2024-02-20 | 国网浙江省电力有限公司 | Carbon emission evaluation method, device, electronic equipment and storage medium |
-
2023
- 2023-09-12 CN CN202311173108.6A patent/CN117313992A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117575175A (en) * | 2024-01-15 | 2024-02-20 | 国网浙江省电力有限公司 | Carbon emission evaluation method, device, electronic equipment and storage medium |
CN117575175B (en) * | 2024-01-15 | 2024-03-29 | 国网浙江省电力有限公司 | Carbon emission evaluation method, device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yang et al. | Indirect multi-energy transactions of energy internet with deep reinforcement learning approach | |
CN108206543B (en) | Energy router based on energy cascade utilization and operation optimization method thereof | |
CN111355230B (en) | Optimized scheduling method and system for comprehensive energy system | |
CN112633571B (en) | Ultra-short-term load prediction method based on LSTM in source network load interaction environment | |
CN108471119B (en) | Prediction control method for three-phase imbalance dynamic power flow model of power distribution network containing smart community | |
CN117313992A (en) | Carbon emission factor updating method considering multi-energy-flow community load | |
CN107492886A (en) | A kind of power network monthly electricity purchasing scheme optimization method containing wind-powered electricity generation under Regional Electric Market | |
CN114357782A (en) | Comprehensive energy system optimization scheduling method considering carbon source sink effect | |
Yang et al. | Optimal energy operation strategy for we-energy of energy internet based on hybrid reinforcement learning with human-in-the-loop | |
CN114219195A (en) | Regional comprehensive energy capacity optimization control method | |
Xiao et al. | Optimal scheduling of regional integrated energy system considering multiple uncertainties and integrated demand response | |
Liu et al. | Optimal planning design of a district-level integrated energy system considering the impacts of multi-dimensional uncertainties: A multi-objective interval optimization method | |
CN112131712B (en) | Multi-objective optimization method and system for multi-energy system on client side | |
CN116663820A (en) | Comprehensive energy system energy management method under demand response | |
CN116432824A (en) | Comprehensive energy system optimization method and system based on multi-target particle swarm | |
CN110991764B (en) | Day-ahead rolling optimization method for comprehensive energy system | |
CN113762650A (en) | Optimization method and system for distributed prediction of power grid | |
CN114611772B (en) | Multi-agent reinforcement learning-based multi-microgrid system collaborative optimization method | |
Li et al. | Intraday multi-objective hierarchical coordinated operation of a multi-energy system | |
CN115795992A (en) | Park energy Internet online scheduling method based on virtual deduction of operation situation | |
CN108734419B (en) | Blast furnace gas scheduling system modeling method based on knowledge migration | |
CN113158547B (en) | Regional comprehensive energy system optimal configuration method considering economy and reliability | |
CN112883630B (en) | Multi-microgrid system day-ahead optimization economic dispatching method for wind power consumption | |
Zhou et al. | Multi-objective optimization and decision making for integrated energy system using STA and fuzzy TOPSIS | |
CN113673738A (en) | Comprehensive energy system optimal configuration method based on supply and demand response and adjustable scene |
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 |