CN112819225A - Carbon market price prediction method based on BP neural network and ARIMA model - Google Patents
Carbon market price prediction method based on BP neural network and ARIMA model Download PDFInfo
- Publication number
- CN112819225A CN112819225A CN202110136613.8A CN202110136613A CN112819225A CN 112819225 A CN112819225 A CN 112819225A CN 202110136613 A CN202110136613 A CN 202110136613A CN 112819225 A CN112819225 A CN 112819225A
- Authority
- CN
- China
- Prior art keywords
- carbon
- model
- value
- market price
- prediction
- 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 111
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 36
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 7
- 238000007637 random forest analysis Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 239000003245 coal Substances 0.000 claims description 3
- 239000000295 fuel oil Substances 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 239000003345 natural gas Substances 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000003921 oil Substances 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 230000007246 mechanism Effects 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 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
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a carbon market price prediction method based on a BP neural network and an ARIMA model, which comprises the steps of obtaining a carbon market price influence factor data sequence in a set time range, screening main influence factors of the carbon market price based on a random forest model to obtain an input data sequence of a subsequent model, inputting the input data sequence into the BP neural network and the ARIMA model respectively, obtaining a carbon price intermediate prediction result by using the two methods respectively, optimizing a weight coefficient by using a differential evolution algorithm, and performing linear weighted combination by using the optimal weight coefficient to obtain a more accurate carbon price prediction result and higher precision of the BP-ARIMA model. The invention not only can provide a new method for the research of the price of the abundant carbon market, but also can provide beneficial reference for a policy maker to explore a carbon market stability mechanism and investors to actively participate in carbon financial market trading and avoid the carbon market risk.
Description
Technical Field
The invention belongs to the technical field of electric power, and particularly relates to a carbon market price prediction method based on a BP neural network and an ARIMA model.
Background
In recent years, with the continuous development of economy, environmental problems such as carbon dioxide emission and the like become more serious, and the problem of carbon emission is emphasized in various parts of the world. China is establishing a nationwide carbon trading platform to enhance the activity of carbon trading, and the key for establishing the carbon trading platform is solving the problem of how to price the carbon emission right, and the price of the carbon market directly influences the scale of the carbon trading market. The research on carbon market price prediction can not only provide a new method for the abundant carbon market price, but also provide beneficial references for policy makers to explore a carbon market stability mechanism and investors to actively participate in carbon financial market trading and avoid carbon market risks. However, in consideration of the inherent high complexity of the carbon market price, the prediction of the carbon market price by using a single prediction model inevitably generates prediction errors, resulting in inaccuracy of the prediction result. In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problems, a carbon market price prediction method based on a BP neural network and an ARIMA model is provided, and beneficial references are provided for policy makers to explore a carbon market stability mechanism and investors to actively participate in carbon financial market trading and avoid carbon market risks.
The technical scheme is as follows: the invention discloses a carbon market price prediction method based on a BP neural network and an ARIMA model, which specifically comprises the following steps:
(1) acquiring a carbon market price influence factor data sequence within a set time range;
(2) screening main influence factors of the carbon market price based on a random forest model to obtain an input data sequence of a subsequent model;
(3) inputting the input data sequence into a BP neural network model and an ARIMA model respectively, and obtaining a carbon value intermediate prediction result by using the two methods respectively;
(4) and optimizing the weight coefficient by using a differential evolution algorithm, and performing linear weighted combination by using the optimal weight coefficient to obtain a high-precision carbon value prediction result of the BP-ARIMA model.
Further, carbon market price influencing factors include: fuel oil prices, coal prices, oil prices, and natural gas prices.
Further, the step (2) is realized as follows:
changing the variable value in the carbon value influence factor sequence in the Gaussian white noise increasing mode, and calculating the error outside the bag on the model training set; the out-of-bag error is unbiased estimation of the prediction error, the more the out-of-bag error is, the more important the carbon value influence factor is proved to be, so that the importance degree distribution of the carbon value influence factor sequence is obtained, the carbon value influence factor sequence is further screened, and the factors which have smaller influence on the carbon value in the model are removed;
importance F of variable t on model training settComprises the following steps:wherein T is a carbon market price influencing factor data sequence obtained by the model, EoobFor errors outside the original bag of the model, EoobtThe out-of-bag error of the model after white noise is added to the value of the variable t.
Further, the step (4) comprises the steps of:
(41) population initialization: setting lambda as a weight coefficient of a carbon value prediction result of the ARIMA model, and setting l-lambda as a weight coefficient of a carbon value prediction result of the BP neural network, wherein the combined prediction model only has one parameter lambda; randomly generating L values with the length of 1 according to the range of the lambda, wherein each value is an individual in the population;
(42) calculating a fitness value: selecting a combined carbon value prediction result and a carbon value actual value to carry out mean square error calculation, wherein the obtained error value is a fitness value, and sequentially calculating the fitness values of all individuals in the current population;
(43) the specific linear weighted combination mode is as follows: y ═ λ Y1+(1-λ)Y2Wherein Y is the final predicted result of carbon number, Y1Carbon number prediction for ARIMA model, Y2And lambda is a weight coefficient of the carbon valence prediction result of the BP model.
Further, the calculation process of the fitness value in step (42) is as follows:
(421) judging whether the minimum error standard is reached, if so, saving the current individual as the optimal weight coefficient, and if not, performing evolution operation;
(422) carrying out evolution operations such as cross mutation and the like on the individuals, selecting the individuals with smaller fitness values in the evolution process, and eliminating the individuals with larger fitness values;
(423) and judging whether the minimum error standard is reached, if not, returning to the step (422), and if so, stopping the evolution to obtain the optimal weight coefficient lambda of the combined prediction model.
Has the advantages that: compared with the prior art, the invention has the beneficial effects that: 1. the method can solve the problem that the operation process of the model is too complicated because a plurality of carbon value influence factors are directly used as input variables, simultaneously fully considers the inherent high complexity of the carbon value, adopts a linear and nonlinear combined model for prediction, and improves the prediction precision of the carbon value prediction model; 2. the invention not only can provide a new method for the research of the price of the abundant carbon market, but also can provide beneficial reference for a policy maker to explore a carbon market stability mechanism and investors to actively participate in carbon financial market trading and avoid the carbon market risk.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The invention provides a carbon market price prediction method based on a BP neural network and an ARIMA model, which comprises the steps of obtaining a carbon market price influence factor data sequence in a set time range, screening main influence factors of the carbon market price based on a random forest model to obtain an input data sequence of a subsequent model, inputting the input data sequence into the BP neural network and the ARIMA model respectively, obtaining intermediate prediction results by the two methods respectively, optimizing weight coefficients by using a differential evolution algorithm, and performing linear weighted combination by using the optimal weight coefficients to obtain a more accurate prediction result and higher prediction precision of the BP-ARIMA model. As shown in fig. 1, the method specifically comprises the following steps:
step 1: and acquiring a carbon market price influence factor data sequence within a set time range.
Carbon market price influencing factors include: fuel oil prices, coal prices, oil prices, and natural gas prices.
Step 2: and screening main influence factors of the carbon market price based on the random forest model to obtain an input data sequence of a subsequent model.
Changing variable values in the carbon value influence factor sequence in the model by increasing Gaussian white noise, and calculating out-of-bag errors on the model training set, wherein the out-of-bag errors are unbiased estimates of prediction errors, and the more the out-of-bag errors are, the more important the carbon value influence factors are proved to be, so that the importance degree distribution of the carbon value influence factor sequence is obtained, the carbon value influence factor sequence is further screened, and the factors which have small influence on the carbon value in the model are removed.
Importance F of variable t on model training settComprises the following steps:
wherein T is a carbon market price influencing factor data sequence obtained by the model, EoobFor errors outside the original bag of the model, EoobtAdding white noise to the value of the variable tOut-of-bag error of the posterior model.
In order to reduce the complexity of the model, a random forest model is used for screening out main influence factors of carbon number. If many carbon number influencing factors are directly used as input variables, the carbon number influencing factors are not subjected to dimensionality reduction, so that the running process of the model is too complicated.
And step 3: and respectively inputting the input data sequence into a BP neural network model and an ARIMA model, and respectively obtaining an intermediate prediction result by using the two methods.
Due to the inherent high complexity of carbon market price, i.e. linear and non-linear characteristics, prediction errors inevitably occur when a single model is used for carbon market price prediction. Therefore, the BP neural network and the linear model ARIMA which have strong capture capacity on nonlinearity are used for respectively predicting the carbon value, and the carbon value prediction result based on the BP neural network and the carbon value prediction result based on the ARIMA model are obtained.
And 4, step 4: and optimizing the weight coefficient by using a differential evolution algorithm, and performing linear weighted combination by using the optimal weight coefficient to obtain a high-precision carbon value prediction result of the BP-ARIMA model.
(1) Population initialization:
and if lambda is the weight coefficient of the prediction result of the ARIMA model and l-lambda is the weight coefficient of the prediction result of the BP neural network, only one parameter lambda exists in the combined prediction model. Based on the range of λ, L values of length 1 (real number codes) are randomly generated, where each value is an individual in the population.
(2) Calculating a fitness value:
and selecting a combined carbon value prediction result and a carbon value actual value to carry out mean square error calculation, wherein the obtained error value is the fitness value, and sequentially calculating the fitness values of all individuals in the current population.
Specifically, the sequentially calculating the fitness values of all individuals in the current population specifically includes:
1) judging whether the minimum error standard is reached, if the minimum error standard is reached, saving the current individual as the optimal weight coefficient, and if the minimum error standard is not reached, performing evolution operation;
2) carrying out evolution operations such as cross mutation and the like on the individuals, selecting the individuals with smaller fitness values in the evolution process, and eliminating the individuals with larger fitness values;
3) and judging whether the minimum error standard is reached, if the minimum error standard is not reached, returning to the step S522, and if the minimum error standard is not reached, stopping the evolution to obtain the optimal weight coefficient lambda of the combined prediction model.
(3) The specific linear weighted combination mode is as follows: y ═ λ Y1+(1-λ)Y2Wherein Y is the final predicted result of carbon number, Y1Carbon number prediction for ARIMA model, Y2And lambda is a weight coefficient of the carbon valence prediction result of the BP model.
It should be noted that, it is very critical to determine the weight coefficients of each method in the BP-ARIMA model to predict the carbon number by using the BP-ARIMA model and obtain a high-precision prediction result. The existing stage weight distribution method mostly adopts a manual distribution method or a linear regression method, but the performance of a prediction model is not easy to measure and quantify, so that the methods are not very suitable, the calculation process is complex, the weight distribution is unreasonable, the prediction result of a combined model is possibly higher than the result error of a single prediction model, and the differential evolution algorithm is an intelligent calculation method and has the advantages of simple structure, quickness in convergence, convenience in use, high speed, good robustness and the like. And optimizing the weight coefficient of the BP-ARIMA model by using a differential evolution algorithm to obtain the optimal weight coefficient.
The method can solve the problem that the operation process of the model is too complicated because a plurality of carbon price influence factors are directly used as input variables, simultaneously fully considers the inherent high complexity of the carbon price, adopts a linear and nonlinear combined model for prediction, and improves the prediction precision of the electricity price prediction model. The method accurately predicts the clearing electricity price of the power market by establishing the carbon price prediction model, and is favorable for providing meaningful reference for a policy maker to explore a carbon market stability mechanism and investors to actively participate in carbon financial market trading and avoid carbon market risks.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (5)
1. A carbon market price prediction method based on a BP neural network and an ARIMA model is characterized by comprising the following steps:
(1) acquiring a carbon market price influence factor data sequence within a set time range;
(2) screening main influence factors of the carbon market price based on a random forest model to obtain an input data sequence of a subsequent model;
(3) inputting the input data sequence into a BP neural network model and an ARIMA model respectively, and obtaining a carbon value intermediate prediction result by using the two methods respectively;
(4) and optimizing the weight coefficient by using a differential evolution algorithm, and performing linear weighted combination by using the optimal weight coefficient to obtain a high-precision carbon value prediction result of the BP-ARIMA model.
2. The method of claim 1, wherein the carbon market price influencing factors comprise: fuel oil prices, coal prices, oil prices, and natural gas prices.
3. The method for predicting carbon market price based on BP neural network and ARIMA model as claimed in claim 1, wherein the step (2) is realized by the following steps:
changing the variable value in the carbon value influence factor sequence in the Gaussian white noise increasing mode, and calculating the error outside the bag on the model training set; the out-of-bag error is unbiased estimation of the prediction error, the more the out-of-bag error is, the more important the carbon value influence factor is proved to be, so that the importance degree distribution of the carbon value influence factor sequence is obtained, the carbon value influence factor sequence is further screened, and the factors which have smaller influence on the carbon value in the model are removed;
importance F of variable t on model training settComprises the following steps:wherein T is a carbon market price influencing factor data sequence obtained by the model, EoobFor errors outside the original bag of the model, EoobtThe out-of-bag error of the model after white noise is added to the value of the variable t.
4. The BP neural network and ARIMA model-based carbon market price prediction method according to claim 1, wherein the step (4) comprises the steps of:
(41) population initialization: setting lambda as a weight coefficient of a carbon value prediction result of the ARIMA model, and setting l-lambda as a weight coefficient of a carbon value prediction result of the BP neural network, wherein the combined prediction model only has one parameter lambda; randomly generating L values with the length of 1 according to the range of the lambda, wherein each value is an individual in the population;
(42) calculating a fitness value: selecting a combined carbon value prediction result and a carbon value actual value to carry out mean square error calculation, wherein the obtained error value is a fitness value, and sequentially calculating the fitness values of all individuals in the current population;
(43) the specific linear weighted combination mode is as follows: y ═ λ Y1+(1-λ)Y2Wherein Y is the final predicted result of carbon number, Y1Carbon number prediction for ARIMA model, Y2And lambda is a weight coefficient of the carbon valence prediction result of the BP model.
5. The method for predicting carbon market price based on BP neural network and ARIMA model as claimed in claim 4, wherein the fitness value of step (42) is calculated as follows:
(421) judging whether the minimum error standard is reached, if so, saving the current individual as the optimal weight coefficient, and if not, performing evolution operation;
(422) carrying out evolution operations such as cross mutation and the like on the individuals, selecting the individuals with smaller fitness values in the evolution process, and eliminating the individuals with larger fitness values;
(423) and judging whether the minimum error standard is reached, if not, returning to the step (422), and if so, stopping the evolution to obtain the optimal weight coefficient lambda of the combined prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110136613.8A CN112819225A (en) | 2021-02-01 | 2021-02-01 | Carbon market price prediction method based on BP neural network and ARIMA model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110136613.8A CN112819225A (en) | 2021-02-01 | 2021-02-01 | Carbon market price prediction method based on BP neural network and ARIMA model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112819225A true CN112819225A (en) | 2021-05-18 |
Family
ID=75861118
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110136613.8A Pending CN112819225A (en) | 2021-02-01 | 2021-02-01 | Carbon market price prediction method based on BP neural network and ARIMA model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112819225A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393166A (en) * | 2021-07-12 | 2021-09-14 | 阳光电源股份有限公司 | Integrated energy scheduling service system, method, computer device and medium |
CN115860797A (en) * | 2022-12-08 | 2023-03-28 | 国网江苏省电力有限公司南通供电分公司 | Electric quantity demand prediction method suitable for new electricity price reform situation |
CN116228044A (en) * | 2023-05-08 | 2023-06-06 | 华南师范大学 | Mathematical core literacy assessment method and system based on neural network and random forest |
CN117010942A (en) * | 2023-08-11 | 2023-11-07 | 新立讯科技股份有限公司 | Agricultural product sales prediction method and system based on neural network and linear model |
-
2021
- 2021-02-01 CN CN202110136613.8A patent/CN112819225A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393166A (en) * | 2021-07-12 | 2021-09-14 | 阳光电源股份有限公司 | Integrated energy scheduling service system, method, computer device and medium |
CN115860797A (en) * | 2022-12-08 | 2023-03-28 | 国网江苏省电力有限公司南通供电分公司 | Electric quantity demand prediction method suitable for new electricity price reform situation |
CN115860797B (en) * | 2022-12-08 | 2023-07-18 | 国网江苏省电力有限公司南通供电分公司 | Electric quantity demand prediction method suitable for new electricity price reform situation |
CN116228044A (en) * | 2023-05-08 | 2023-06-06 | 华南师范大学 | Mathematical core literacy assessment method and system based on neural network and random forest |
CN117010942A (en) * | 2023-08-11 | 2023-11-07 | 新立讯科技股份有限公司 | Agricultural product sales prediction method and system based on neural network and linear model |
CN117010942B (en) * | 2023-08-11 | 2024-02-20 | 新立讯科技股份有限公司 | Agricultural product sales prediction method and system based on neural network and linear model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112819225A (en) | Carbon market price prediction method based on BP neural network and ARIMA model | |
Wang et al. | Modeling carbon emission trajectory of China, US and India | |
CN112733417B (en) | Abnormal load data detection and correction method and system based on model optimization | |
CN108876132B (en) | Industrial enterprise energy efficiency service recommendation method and system based on cloud | |
CN112950067B (en) | Power consumer electricity consumption efficiency evaluation method based on fuzzy comprehensive evaluation | |
Meng et al. | Forecasting energy consumption based on SVR and Markov model: A case study of China | |
CN110796293A (en) | Power load prediction method | |
CN104865827A (en) | Oil pumping unit oil extraction optimization method based on multi-working-condition model | |
CN115841250A (en) | Electricity charge delinquent risk early warning method and system based on ensemble learning | |
CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
CN115689001A (en) | Short-term load prediction method based on pattern matching | |
CN117422165A (en) | Urban water delivery system water quantity prediction method and system based on low carbon emission | |
CN115345297A (en) | Platform area sample generation method and system based on generation countermeasure network | |
Xiao | Quantitative investment decision model based on PPO algorithm | |
CN114004530A (en) | Enterprise power credit score modeling method and system based on sequencing support vector machine | |
CN113705098A (en) | Air duct heater modeling method based on PCA and GA-BP network | |
CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
CN113361776A (en) | Power load probability prediction method based on user power consumption behavior clustering | |
Yang et al. | Research on the application of GA improved neural network in the prediction of financial crisis | |
CN116883057A (en) | XGBoost-based high-precision power customer marketing channel preference prediction system | |
CN115034618A (en) | Community comprehensive energy system benefit evaluation method based on fuzzy evaluation | |
CN115796327A (en) | Wind power interval prediction method based on VMD (vertical vector decomposition) and IWOA-F-GRU (empirical mode decomposition) -based models | |
CN115526393A (en) | Construction cost prediction method based on transformer project key influence factor screening | |
Xu et al. | A new multivariable grey model and its application to energy consumption in China | |
CN111047108B (en) | Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |