CN115496286B - Neural network carbon emission prediction method based on big data environment and application - Google Patents
Neural network carbon emission prediction method based on big data environment and application Download PDFInfo
- Publication number
- CN115496286B CN115496286B CN202211174376.5A CN202211174376A CN115496286B CN 115496286 B CN115496286 B CN 115496286B CN 202211174376 A CN202211174376 A CN 202211174376A CN 115496286 B CN115496286 B CN 115496286B
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- emission data
- data
- prediction
- dynamic
- 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.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 216
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 216
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013507 mapping Methods 0.000 claims abstract description 15
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000007789 gas Substances 0.000 claims description 14
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 230000001105 regulatory effect Effects 0.000 claims description 9
- GQPLMRYTRLFLPF-UHFFFAOYSA-N Nitrous Oxide Chemical compound [O-][N+]#N GQPLMRYTRLFLPF-UHFFFAOYSA-N 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000002485 combustion reaction Methods 0.000 claims description 6
- 238000005265 energy consumption Methods 0.000 claims description 6
- 239000002737 fuel gas Substances 0.000 claims description 5
- 239000002028 Biomass Substances 0.000 claims description 3
- 239000000567 combustion gas Substances 0.000 claims description 3
- 238000000855 fermentation Methods 0.000 claims description 3
- 230000004151 fermentation Effects 0.000 claims description 3
- 239000002803 fossil fuel Substances 0.000 claims description 3
- 230000000968 intestinal effect Effects 0.000 claims description 3
- 239000003345 natural gas Substances 0.000 claims description 3
- 239000001272 nitrous oxide Substances 0.000 claims description 3
- 239000003209 petroleum derivative Substances 0.000 claims description 3
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 claims description 3
- 238000009270 solid waste treatment Methods 0.000 claims description 3
- 238000004065 wastewater treatment Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 24
- 238000006386 neutralization reaction Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Development Economics (AREA)
Abstract
The invention provides a neural network carbon emission prediction method based on a big data environment, which comprises the following steps: s1, acquiring multi-channel carbon emission data through an Internet of things platform network, forming the multi-channel emission data into a corresponding emission data set, and carrying out normalization processing; s2, measuring and calculating offset of carbon emission data, dynamically correcting the data, calculating a corresponding mapping transformation function through a TCN time convolution neural network, S3, acquiring multi-channel carbon emission data fusion through the mapping transformation function, judging a carbon emission prediction interval through a prediction accuracy model, and uploading the carbon emission prediction interval to an Internet of things platform network.
Description
Technical Field
The invention relates to the field of big data analysis, in particular to a neural network carbon emission prediction method and application based on big data environment.
Background
Due to global warming and greenhouse effect, research on carbon emissions and carbon absorption in various fields has been conducted in the society today, so that achieving carbon neutralization and carbon peak to provide theoretical support, how to effectively predict carbon emission mechanisms presents great challenges to those skilled in the art. According to the current situation of research, the use scheduling in the electric power system and the gas field is centralized control type, the response speed to carbon emission is slow through the traditional neural network learning, the total amount of carbon emission cannot be effectively predicted through theoretical data, and the result of carbon emission can be obtained through centralized control type scheduling, but the constraint conditions of external use time, idle state, occupied state and load are less, so that an accurate carbon emission prediction model is difficult to establish. There is a need for a person skilled in the art to solve the corresponding technical problems.
Disclosure of Invention
The invention aims at least solving the technical problems in the prior art, and particularly creatively provides a neural network carbon emission prediction method based on a big data environment.
In order to achieve the above object of the present invention, the present invention provides a neural network carbon emission prediction method based on a big data environment, comprising the steps of:
s1, acquiring multi-channel carbon emission data through an Internet of things platform network, forming the multi-channel emission data into a corresponding emission data set, and carrying out normalization processing;
s2, calculating the offset of the carbon emission data, dynamically correcting the data, calculating a corresponding mapping transformation function through a TCN time convolution neural network,
and S3, acquiring multi-channel carbon emission data fusion through a mapping transformation function, judging a carbon emission prediction interval through a prediction accuracy model, and uploading the carbon emission prediction interval to an Internet of things platform network.
According to the above technical solution, the step S1 preferably includes:
s1-1, acquiring corresponding electric power carbon emission data and gas carbon emission data in an Internet of things platform network, performing objective function calculation according to the carbon emission data,
obtaining a carbon emission objective function P (i) of the output power of the electric power in unit time and the gas power in unit time, training a network node of the electric power and the gas carbon emission through the calculated result,
wherein u is the electric power carbon emission regulating coefficient, A elec Is the power used by the electric power in unit time, v is the carbon emission regulating coefficient of the fuel gas, A gas The power is used for the electric power in unit time, and t is the unit time; and obtaining pre-stored data of carbon emission data according to the network node.
According to the above technical solution, preferably, the S1 further includes:
s1-2, determining probability distribution of carbon emission data according to an objective function,
first, according to the electric power carbon emission data vector b= (B 1 ,b 2 ,...,b m ) T Gas carbon emission data vector c= (C) 1 ,c 2 ,...,c m ) T A probability distribution calculation is performed, wherein the superscript T is transposed,
then, the probability distribution formula obtained is:
the carbon emission probability distribution number k, exp (x) is an exponential function, F (B, C) is a carbon emission energy function, β is a target adjustment coefficient, and L (k) is a distribution scale of a carbon emission target.
According to the above technical solution, the S2 preferably includes:
s2-1, carrying out scale division on the carbon emission data according to probability distribution to form an offset formula of the carbon emission data, and according to the scale formula,
E=a·E 0 +M j lambda, wherein E is a carbon emission scale calculation expression formula, a is a carbon emission scale adjustment coefficient, E 0 For pre-stored corresponding period history carbon emission data, M j Is the real-time carbon emission data accumulated value of j weeks, lambda is the carbon emission factor,
s2-2, calculating a displacement formula of the carbon emission probability distribution through a scale formula,
D=E+ΔE 0 according to the calculation result of the scale formula, the change value delta E of the carbon emission data is recorded through the pre-stored corresponding period history 0 Obtaining a displacement value of carbon emission data;
the offset of the carbon emission data can be obtained according to the displacement value, the offset is calculated by an offset formula,
wherein->The pre-stored corresponding cycle history carbon emission data for all j weeks is summed, divided by the corresponding j weeks.
According to the above technical solution, preferably, the S2 further includes:
s2-3, the offset calculated according to the offset formula of the j axis is required to be readjusted in the dynamic property and the constraint property, and the dynamic constraint is carried out through the constraint condition of the carbon emission data, so that the readjustment of the offset is achieved;
the dynamic formula of the carbon emission data is that,
G=G j +η·P j +Z, where G j Is the energy consumption in the carbon emission data of j weeks, eta is a dynamic regulating factor, P j As an overall variation of the j weeks carbon emission data,
when eta is more than 0, the expression of the dynamic formula of the carbon emission data can reflect the actual numerical value of the dynamic carbon emission data, and when eta is less than or equal to 0, the dynamic formula does not relate to the total variation of the carbon emission data.
According to the above technical solution, preferably, the S2 further includes:
s2-4, training the TCN neural network for the real-time carbon emission data according to the obtained dynamic value of the carbon emission data, training and adjusting the dynamic value in the carbon emission process,
the Gaussian function is adopted to carry out the spatial mapping transformation on the neuron basis function in the neural network to the input carbon emission data dynamic value,
wherein μ is a standard constant of the neuron basis function, G is a dynamic value, H g The subscript g is a positive integer and is used for inputting an increasing sequence number of a dynamic value;
the prediction error of the neural network is derived from the mapping transform,
wherein sigma is a dynamic value Q g Weights, d g And h is a prediction error adjustment parameter and is an adjustment coefficient of a neuron basis function.
According to the above technical solution, the step S3 preferably includes:
s3-1, according to a sequence formed by the dynamic values of the carbon emission data, carrying out carbon emission data statistics according to a data regression model after obtaining a prediction error, judging a carbon emission dynamic change component by actually generating values for the carbon emission data in a carbon emission data prediction interval, so that N is formed energy Can be predicted in advance; and f (x) is a regression model of the prediction process, a training sample is extracted from the carbon emission dynamic value, and the minimum variance standard formed in the carbon emission process is obtained for estimating the prediction precision through prediction error judgment.
According to the above technical solution, preferably, the S3 further includes:
s3-2, wherein the prediction precision formula is as follows
x is the number of training samples and is greater than or equal to 2, s x Predicted training value for carbon emissions, y x For carbon emission observations after training, +.>For the observation mean, epsilon is the confidence,
after calculation according to the prediction accuracy, a prediction confidence interval of the corresponding carbon emission data is given, and energy consumption early warning is carried out on the carbon emission data within the interval range, so that the distribution situation of the carbon emission data is predicted, and the prediction interval is adjusted in real time according to the trained accuracy value.
The invention also discloses an application of the neural network carbon emission prediction method based on the big data environment, which comprises the following steps: prediction of carbon emission data for use in fossil fuel combustion, biomass combustion, petroleum and natural gas system escape, paddy methane, agricultural nitrous oxide, animal intestinal fermentation, solid waste treatment, wastewater treatment processes by the method of claim 1.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
in a certain time period, calculating a mapping transformation function through carbon emission data, and acquiring the correlation degree of carbon emission, so that the deviation of the carbon emission is known, and the dependence on the preference of the carbon emission type under the condition of acquiring the carbon emission data according to the variation degree of the carbon emission data of multiple channels; and obtaining the predicted intensity of carbon emission and the predicted emission frequency of the carbon emission type according to the prediction model, continuously training convergence values through a neural network, and performing the later prediction work of the carbon emission through the prediction accuracy model so as to provide data reference for carbon neutralization.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a general schematic of the present invention;
fig. 2 is a schematic diagram of an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
As shown in fig. 1 and 2, the invention discloses a neural network carbon emission prediction method based on a big data environment, comprising the following steps:
s1, acquiring multi-channel carbon emission data through an Internet of things platform network, forming the multi-channel emission data into a corresponding emission data set, and carrying out normalization processing;
s2, calculating the offset of the carbon emission data, dynamically correcting the data, calculating a corresponding mapping transformation function through a TCN time convolution neural network,
and S3, acquiring multi-channel carbon emission data fusion through a mapping transformation function, judging a carbon emission prediction interval through a prediction accuracy model, and uploading the carbon emission prediction interval to an Internet of things platform network.
The internet of things platform can be connected to corresponding electric power and gas and other data acquisition equipment through a wired or wireless network to perform related data acquisition operation.
According to the above technical solution, the step S1 preferably includes:
s1-1, acquiring corresponding electric power carbon emission data and fuel gas carbon emission data in a cloud network, performing objective function calculation according to the carbon emission data,
obtaining a carbon emission objective function P (i) of the output power of the electric power in unit time and the gas power in unit time, training a network node of the electric power and the gas carbon emission through the calculated result,
wherein u is the electric power carbon emission regulating coefficient, A elec Is the power used by the electric power in unit time, v is the carbon emission regulating coefficient of the fuel gas, A gas The power is used for the electric power in unit time, and t is the unit time; obtaining pre-stored data of carbon emission data according to the network node, so as to divide the discrete data linearly;
s1-2, determining probability distribution of carbon emission data according to an objective function,
first, according to the electric power carbon emission data vector b= (B 1 ,b 2 ,...,b m ) T Gas carbon emission data vector c= (C) 1 ,c 2 ,...,c m ) T A probability distribution calculation is performed, wherein the superscript T is transposed,
then, the probability distribution formula obtained is:
the carbon emission probability distribution sequence number k, exp (x) is an exponential function, F (B, C) is a carbon emission energy function, beta is a target adjustment coefficient, L (k) is a distribution scale of a carbon emission target, the distribution scale can carry out distribution quantification on the data trend of carbon emission, the distribution scale is subjected to parameter adjustment through the target adjustment coefficient, and then normalization processing is carried out, so that the carbon emission data can be converged,
according to the above technical solution, the S2 preferably includes:
s2-1, carrying out scale division on the carbon emission data according to probability distribution to form an offset formula of the carbon emission data, and according to the scale formula,
E=a·E 0 +M j lambda, wherein E is a carbon emission scale calculation expression formula, a is a carbon emission scale adjustment coefficient, E 0 For pre-stored corresponding period history carbon emission data, M j Is the real-time carbon emission data accumulated value of j weeks, lambda is the carbon emission factor,
s2-2, calculating a displacement formula of the carbon emission probability distribution through a scale formula,
D=E+ΔE 0 according to the calculation result of the scale formula, the change value delta E of the carbon emission data is recorded through the pre-stored corresponding period history 0 Obtaining a displacement value of carbon emission data;
the offset of the carbon emission data can be obtained according to the displacement value, the offset is calculated by an offset formula,
wherein->Summing the pre-stored historical carbon emission data for all j weeks, dividing by the corresponding j weeks, 7 days for the week, to obtain a corresponding pre-stored average value of the carbon emission data, passing E 0 Subtracting the average value to obtain the offset of the pre-stored carbon emission data, and adjusting the offset by an adjusting coefficient of a carbon emission scale, wherein the pre-stored carbon emission data is carbon emission data which is collected in real time every week, is stored in an Internet of things platform network and is used for analysis processing;
the period of data acquisition can be extended to one month, one quarter or one year, and timely adjustment is carried out according to the accuracy degree of the data by a user, so that different data prediction requirements are met.
S2-3, the offset calculated according to the offset formula of the j axis is required to be readjusted in the dynamic property and the constraint property, and the dynamic constraint is carried out through the constraint condition of the carbon emission data, so that the readjustment of the offset is achieved;
the dynamic formula of the carbon emission data is that,
G=G j +η·P j +Z, where G j The energy consumption in the carbon emission data of j weeks comprises comprehensive data of electric energy and gas energy, and the total value of the carbon emission in theory can be known through the comprehensive data, so that the carbon emission data actually obtained in j weeks is taken as the basis and source of dynamic regulation, eta is a dynamic regulating factor and P j As an overall variation of the j weeks carbon emission data,
when eta is more than 0, the expression of the dynamic formula of the carbon emission data can represent the actual numerical value of the dynamic carbon emission data, when eta is less than or equal to 0, the dynamic formula does not hold,
s2-4, training the TCN neural network for the real-time carbon emission data according to the acquired carbon emission data dynamic value, training and adjusting the dynamic value in the carbon emission process, so as to prepare for predicting the carbon emission data of the next week,
the Gaussian function is adopted to carry out the spatial mapping transformation on the neuron basis function in the neural network to the input carbon emission data dynamic value,
wherein μ is a standard constant of the neuron basis function, G is a dynamic value, H g The subscript g is a positive integer and is used for inputting an increasing sequence number of a dynamic value;
the prediction error of the neural network is derived from the mapping transform,
wherein sigma is a dynamic value Q g Weights, d g Is the adjustment coefficient of the neuron base function, h is the prediction error adjustment parameter,
after the collected carbon emission data of one week is adjusted according to the dynamic value, the carbon emission data of the previous week is compared with the carbon emission data of the previous week, and the corresponding difference value is subjected to component sequence representation to be used as preparation for carbon emission data prediction;
according to the above technical solution, the step S3 preferably includes:
s3-1, according to a sequence formed by the dynamic values of the carbon emission data, carrying out carbon emission data statistics according to a data regression model after obtaining a prediction error, judging a carbon emission dynamic change component by actually generating values for the carbon emission data in a carbon emission data prediction interval, so that N is formed energy Can be predicted in advance; the regression model of the prediction process is f (x), a training sample is extracted from the carbon emission dynamic value, and the minimum variance standard formed in the carbon emission process is obtained for estimating the prediction precision through prediction error judgment;
s3-2, wherein the prediction precision formula is as follows
x is the number of training samples and is greater than or equal to 2, s x Predicted training value for carbon emissions, y x For carbon emission observations after training, +.>For the observation mean, epsilon is the confidence,
after calculation according to the prediction accuracy, a prediction confidence interval of the corresponding carbon emission data is given, and energy consumption early warning is carried out on the carbon emission data within the interval range, so that the distribution situation of the carbon emission data is predicted, and the prediction interval is adjusted in real time according to the trained accuracy value.
The carbon emission data of electric power and fuel gas are considered for carbon emission, and the carbon emission data in the processes of fossil fuel combustion, biomass combustion, petroleum and natural gas system escape, paddy methane, agricultural nitrous oxide, animal intestinal fermentation, solid waste treatment and wastewater treatment can be acquired, corresponding data content is learned through a neural network, and carbon emission prediction is performed.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents.
Claims (2)
1. The neural network carbon emission prediction method based on the big data environment is characterized by comprising the following steps of:
s1, acquiring multi-channel carbon emission data through an Internet of things platform network, forming the multi-channel emission data into a corresponding emission data set, and carrying out normalization processing;
s1-1, acquiring corresponding electric power carbon emission data and gas carbon emission data in an Internet of things platform network, performing objective function calculation according to the carbon emission data,
obtaining a carbon emission objective function P (i) of the output power of the electric power in unit time and the gas power in unit time, training a network node of the electric power and the gas carbon emission through the calculated result,
wherein u is the electric power carbon emission regulating coefficient, A elec Is the power used by the electric power in unit time, v is the carbon emission regulating coefficient of the fuel gas, A gas The power is used for the electric power in unit time, and t is the unit time; obtaining pre-stored data of carbon emission data according to the network node;
s1-2, determining probability distribution of carbon emission data according to an objective function,
first, according to the electric power carbon emission data vector b= (B 1 ,b 2 ,...,b m ) T Gas carbon emission data vector c= (C) 1 ,c 2 ,...,c m ) T A probability distribution calculation is performed, wherein the superscript T is transposed,
then, the probability distribution formula obtained is:
the carbon emission probability distribution sequence number k, exp (x) is an exponential function, F (B, C) is a carbon emission energy function, beta is a target adjustment coefficient, L (k) is a distribution scale of a carbon emission target, the distribution scale can carry out distribution quantification on the data trend of carbon emission, parameter adjustment is carried out on the distribution scale through the target adjustment coefficient, and then normalization processing is carried out;
s2, measuring and calculating the offset of the carbon emission data, dynamically correcting the data, and calculating a corresponding mapping transformation function through a TCN time convolution neural network;
s2-1, carrying out scale division on the carbon emission data according to probability distribution to form an offset formula of the carbon emission data, and according to the scale formula,
E=a·E 0 +M j lambda, wherein E is a carbon emission scale calculation expression formula, a is a carbon emission scale adjustment coefficient, E 0 For pre-stored corresponding period history carbon emission data, M j Is the real-time carbon emission data accumulated value of j weeks, lambda is the carbon emission factor,
s2-2, calculating a displacement formula of the carbon emission probability distribution through a scale formula,
D=E+ΔE 0 according to the calculation result of the scale formula, the change value delta E of the carbon emission data is recorded through the pre-stored corresponding period history 0 Obtaining a displacement value of carbon emission data;
the offset of the carbon emission data can be obtained according to the displacement value, the offset is calculated by an offset formula,
wherein->Summing all j weeks of pre-stored historical carbon emission data for the corresponding period, divided by the corresponding j weeks;
s2-3, the offset calculated according to the offset formula of the j axis is required to be readjusted in the dynamic property and the constraint property, and the dynamic constraint is carried out through the constraint condition of the carbon emission data, so that the readjustment of the offset is achieved;
the dynamic formula of the carbon emission data is that,
G=G j +η·P j +Z, where G j Is the energy consumption in the carbon emission data of j weeks, eta is a dynamic regulating factor, P j Total variation for j weeks of carbon emission data;
when eta is more than 0, the expression of the dynamic formula of the carbon emission data can reflect the actual numerical value of the dynamic carbon emission data, and when eta is less than or equal to 0, the dynamic formula does not relate to the total variation of the carbon emission data;
s2-4, training the TCN neural network for the real-time carbon emission data according to the obtained dynamic value of the carbon emission data, training and adjusting the dynamic value in the carbon emission process,
the Gaussian function is adopted to carry out the spatial mapping transformation on the neuron basis function in the neural network to the input carbon emission data dynamic value,
wherein μ is a standard constant of the neuron basis function, G is a dynamic value, H g The subscript g is a positive integer and is used for inputting an increasing sequence number of a dynamic value;
the prediction error of the neural network is derived from the mapping transform,
wherein sigma is a dynamic value Q g Weights, d g The adjustment coefficient is the adjustment coefficient of the neuron basis function, and h is the prediction error adjustment parameter;
s3, acquiring multi-channel carbon emission data fusion through a mapping transformation function, judging a carbon emission prediction interval through a prediction accuracy model, and uploading the carbon emission prediction interval to an Internet of things platform network;
s3-1, according to a sequence formed by the dynamic values of the carbon emission data, carrying out carbon emission data statistics according to a data regression model after obtaining a prediction error, judging a carbon emission dynamic change component by actually generating values for the carbon emission data in a carbon emission data prediction interval, so that N is formed energy Can be predicted in advance; the regression model of the prediction process is f (x), a training sample is extracted from the carbon emission dynamic value, and the minimum variance standard formed in the carbon emission process is obtained for estimating the prediction precision through prediction error judgment;
s3-2, wherein the prediction precision formula is as follows
x is the number of training samples and is greater than or equal to 2, s x Predicted training value for carbon emissions, y x For carbon emission observations after training, +.>For the observation mean, epsilon is the confidence,
after calculation according to the prediction accuracy, a prediction confidence interval of the corresponding carbon emission data is given, and energy consumption early warning is carried out on the carbon emission data within the interval range, so that the distribution situation of the carbon emission data is predicted, and the prediction interval is adjusted in real time according to the trained accuracy value.
2. The application of the neural network carbon emission prediction method based on the big data environment is characterized by comprising the following steps:
prediction of carbon emission data for use in fossil fuel combustion, biomass combustion, petroleum and natural gas system escape, paddy methane, agricultural nitrous oxide, animal intestinal fermentation, solid waste treatment, wastewater treatment processes by the method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211174376.5A CN115496286B (en) | 2022-09-26 | 2022-09-26 | Neural network carbon emission prediction method based on big data environment and application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211174376.5A CN115496286B (en) | 2022-09-26 | 2022-09-26 | Neural network carbon emission prediction method based on big data environment and application |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115496286A CN115496286A (en) | 2022-12-20 |
CN115496286B true CN115496286B (en) | 2023-05-05 |
Family
ID=84470434
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211174376.5A Active CN115496286B (en) | 2022-09-26 | 2022-09-26 | Neural network carbon emission prediction method based on big data environment and application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115496286B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115965160B (en) * | 2023-01-18 | 2023-08-08 | 中国长江三峡集团有限公司 | Data center energy consumption prediction method and device, storage medium and electronic equipment |
CN117033927B (en) * | 2023-07-14 | 2024-07-12 | 中国建筑科学研究院有限公司 | Subway station carbon emission real-time monitoring, predicting and analyzing method |
CN116681315B (en) * | 2023-08-03 | 2023-11-21 | 南京农业大学 | Method, device, equipment and storage medium for estimating net emission of greenhouse gases |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425099B (en) * | 2013-07-16 | 2014-08-06 | 广东工业大学 | Embedded carbon emission monitoring and detecting system implemented in vulcanization procedures |
CN106529732A (en) * | 2016-11-18 | 2017-03-22 | 国网山东省电力公司电力科学研究院 | Carbon emission efficiency prediction method based on neural network and random frontier analysis |
DE102017219408A1 (en) * | 2017-10-30 | 2019-05-02 | Robert Bosch Gmbh | Method for optimizing a nitrogen oxide emission and a carbon dioxide emission of an internal combustion engine |
CN109740301A (en) * | 2019-03-14 | 2019-05-10 | 华北电力大学 | A kind of accounting method of the Gas Generator Set carbon emission amount based on BP neural network |
KR102400093B1 (en) * | 2020-09-04 | 2022-05-18 | 인하대학교 산학협력단 | System for predicting carbon dioxide emission from construction equipment using artificial neural network analysis and method thereof |
CN114239928A (en) * | 2021-11-29 | 2022-03-25 | 国网北京市电力公司 | Carbon emission prediction method and device, storage medium and processor |
CN114240005B (en) * | 2022-02-24 | 2022-06-03 | 国网浙江省电力有限公司信息通信分公司 | Carbon emission prediction method and device based on multidimensional reference quantity and time series |
CN114742294A (en) * | 2022-04-09 | 2022-07-12 | 广州网文三维数字技术有限公司 | Neural network algorithm for carbon emission prediction |
-
2022
- 2022-09-26 CN CN202211174376.5A patent/CN115496286B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115496286A (en) | 2022-12-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115496286B (en) | Neural network carbon emission prediction method based on big data environment and application | |
Tan et al. | Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning | |
CN112817354B (en) | Livestock and poultry house cultivation environment temperature prediction control system and regulation and control method thereof | |
CN109062053A (en) | A kind of denitration spray ammonia control method based on multivariate calibration | |
CN112396220B (en) | Optimized scheduling method for wind power-containing and demand side resources based on scene reduction | |
CN114742294A (en) | Neural network algorithm for carbon emission prediction | |
CN116341796A (en) | Energy consumption monitoring and evaluating system and method | |
CN111047091B (en) | Lasso and RNN-based provincial energy utilization efficiency prediction method | |
Liu et al. | Electric energy substitution potential prediction based on logistic curve fitting and improved BP neural network algorithm | |
CN113359435B (en) | Correction method for dynamic working condition data of thermal power generating unit | |
CN107247994B (en) | Fuzzy modeling method for desulfurization efficiency of tray tower desulfurization device | |
CN111461297B (en) | Solar irradiation quantity optimization prediction algorithm based on MPC and ELM neural network | |
CN110909492B (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
CN117251672A (en) | Regional industry multi-dimensional energy carbon emission calculation method and device based on electric power data | |
CN116757078A (en) | Method and system for measuring flow velocity of pulverized coal based on acting force | |
CN110826794A (en) | Power plant coal consumption reference value rolling prediction method and device based on PSO (particle swarm optimization) SVM (support vector machine) | |
CN115081681B (en) | Wind power prediction method based on propset algorithm | |
CN107464015B (en) | Short-term load with fusing mechanism and electric quantity prediction method based on electricity utilization behavior | |
CN111242359B (en) | Solar radiation online dynamic prediction method based on data drift | |
Yao et al. | The analysis of the energy consumption of Chinese manufacturing based on the combination forecasting model | |
CN112699600A (en) | Thermal power operating parameter and NOxAnalysis method for bias between emission concentrations | |
Zhu et al. | Control method of outlet moisture content of tobacco primary processing based on TVA-TCN-MPC | |
Xue | Research on two-sided combined forecasting method of economic supply and demand based on big data analysis | |
CN116050482A (en) | Rural area electric energy substitution potential prediction method | |
CN115906620A (en) | Short-term prediction method for load carbon emission rate |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |