CN111967689A - Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network - Google Patents
Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network Download PDFInfo
- Publication number
- CN111967689A CN111967689A CN202010921151.6A CN202010921151A CN111967689A CN 111967689 A CN111967689 A CN 111967689A CN 202010921151 A CN202010921151 A CN 202010921151A CN 111967689 A CN111967689 A CN 111967689A
- Authority
- CN
- China
- Prior art keywords
- model
- neural network
- power generation
- wind power
- regression
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 38
- 238000010248 power generation Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012417 linear regression Methods 0.000 title claims abstract description 22
- 238000004088 simulation Methods 0.000 claims abstract description 4
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000001134 F-test Methods 0.000 claims description 2
- 238000000692 Student's t-test Methods 0.000 claims description 2
- 230000001419 dependent effect Effects 0.000 claims description 2
- 238000012353 t test Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 239000013598 vector Substances 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
Due to the characteristics of volatility, indirection and randomness of wind power generation, a lot of challenges are brought to the aspects of operation planning, dispatching scheme and the like of the utilization of the wind power energy at present. The invention provides a novel mixing system and a method for predicting day-ahead (day-ahead) power output of a wind power generation system based on daily weather prediction data. The method combines the traditional multiple linear regression and the artificial neural network model, screens more important weather prediction input variables by a step-by-step linear regression method by adopting a hybrid modeling method, and feeds the screened weather prediction variables into the artificial neural network model, thereby generating a complex model to predict the power output quantity of the wind power generation system. The complex model simulation result provided by the invention shows that the performance of the complex model is better than that of other corresponding single-stage models, and the complex model can be applied to realize the power output prediction of the wind power generation system in a region with the condition of monitoring meteorological data.
Description
Technical Field
The invention relates to the technical field of output prediction of a wind power generation system, in particular to a complex model and a method for predicting output of a photovoltaic power generation system by combining multivariate linear regression, step linear regression and an artificial neural network.
Background
Different from a conventional power supply, the wind power generation almost completely depends on real-time weather conditions, and the wind power generation has the characteristics of fluctuation, indirection and randomness due to the weather which changes randomly. Because the power generation, power transmission and power consumption of the power system need to be kept balanced in real time, and the large-scale grid connection of new energy sources such as wind power generation and the like brings more and more pressure to the operation of a power grid. With the increasing occupation ratio of wind power generation in the power system, the importance of wind power generation prediction is more and more prominent, and the more accurate the prediction result is, the more the operating efficiency and stability of the power system can be greatly increased. The invention provides a method for predicting the power output quantity of a wind power generation system by combining the traditional multivariate linear regression sum and an artificial neural network model, screening more important weather prediction input variables by a step-by-step linear regression method by adopting a hybrid modeling method, and then feeding the screened weather prediction variables into the artificial neural network model so as to generate a complex model.
Currently, there are various methods for predicting the power generation of a wind power generation system, including physical methods and statistical calculation methods. The physics approach takes the wind power system power production as a function of some independent variable depending on its physical properties, such as turbine size, wind speed and direction, and blade specifications, and many physical models derive from the conventional wind power production equivalent aiming to achieve as close as possible to the circuit load situation of the local wind level. The statistical prediction method relies on historical data for prediction to perform regression analysis, time series analysis and artificial intelligence analysis on the historical data to predict the power of the wind power generation system, and comprises methods such as an autoregressive model and a Support Vector Machine (SVM). An Artificial Neural Network (ANN) is also widely used for nonlinear modeling for predicting wind power generation output based on meteorological data variables and for predicting the amount of power generation of a wind power generation system in the future. The key advantage of the prediction method based on the artificial neural network is that a model designer can select a plurality of input values in sequence to improve the prediction accuracy, and the prediction accuracy of the output of the wind power generation system can be greatly improved by using a multivariate linear regression and the mixed model of the prediction method of the artificial neural network and the screening of the distributed linear regression. The invention provides a novel and optimal energy output prediction model of a wind power generation system in the future, reduces the number of climate variables input by the model, and combines multiple linear regression and ANN technology. The present invention takes into account a large number of meteorological parameters that may affect the output power of a wind power system. The influence of each meteorological parameter is evaluated by adopting a step-by-step linear Regression (Stepwise Regression) method, the final prediction of the power generation amount of the wind power generation system is generated by using meteorological input variables ANN in a complex model, and the aim of generating an accurate ANN prediction output value by using less calculation work is fulfilled by ensuring that only those input variables which have great influence on the output of the model are selected in the model.
Disclosure of Invention
The invention provides a complex model and a method for predicting the output of a wind power generation system by combining multiple linear regression, stepwise regression and an artificial neural network. The whole complex mixed model process comprises the steps of weather data collection, distributed linear regression recognition of the most relevant input value, optimal neural network configuration determination, artificial neural network training data set, regression post-processing, model simulation after training, calculation of statistical operation relevant parameters, output prediction of the generated energy of the wind power generation system and the like, and is shown in figure 1.
Drawings
FIG. 1 is a flow chart of a wind power generation prediction complex model according to an embodiment of the present invention.
FIG. 2 is a flow chart of model input and output used in an embodiment of the present invention.
FIG. 3 is a diagram of a feedforward neural network in an embodiment of the present invention.
FIG. 4 is a diagram of a generalized recurrent neural network in an embodiment of the present invention.
Detailed Description
In order to make the content, the purpose, the features and the advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative effort belong to the scope of the protection specification of the present invention, and the relevant steps in the embodiments of the present invention are as follows.
The method comprises the following steps: collecting relevant weather data of a specified area and a specified time span required by a prediction model, wherein the relevant weather data comprises: average/highest/lowest atmospheric pressure, average/highest/lowest humidity, average/highest/lowest temperature, average/highest/lowest wind speed, average/highest/lowest wind direction, average/highest/lowest rainfall, average/highest/lowest characteristic time period wind clockwise intensity, and specific time period wind direction variation, as shown in fig. 2.
Step two: screening by a regression method, and identifying the most relevant weather input value; stepwise linear regression is a method of fitting a regression model, by the formula:
fitting the relevant variables, wherein the selection of the predictor variables is performed by an automated program, wherein Y is the photovoltaic output (dependent variable) to be predicted, XiWeather data (independent variables) representing K changes (where 1. ltoreq. i. ltoreq.k), β i
For the regression coefficient of the calculated independent variable, beta0Is the predictor variable for the offset value and e is the residual term. In each fitting step, according to some predetermined statistical criterion: (Including adjusted R2Standard Error (SE), mean adjusted deviation (MAPE), sum of the squares of the residuals expected (PRESS), etc.) take the form of a series of F-tests or t-tests, adding or subtracting variables to or from a set of explanatory variables (including forward and reverse stepwise regression); according to the method, the wind power system power generation output quantity and eight weather related data are fitted through step-by-step linear regression, and the most relevant weather input value is identified to the next step of model operation according to the preset standard (containing 1-8 weather data).
Step three: and determining the optimized neural network configuration by adjusting the parameters of the artificially designed network. The design of the artificial neural network includes determining the number of input layers, the number of neurons in the hidden and output layers and associated weights, biases, activities and normal distribution characteristics. Depending on the arrangement of neurons and their activity, several network architectures may be formed. (claim 4) the present invention applies two architectures of Feed Forward Neural Network (FFNN) and Generalized Regression Neural Network (GRNN) to the prediction of photovoltaic output power. (claim 5) FFNN is a complex multivariate linear regression that links each neuron in the previous layer together to all neurons in the next layer, as shown in fig. 3; data moves through the hidden layer in only one direction from the input layer to the output layer. To specify a target, the feed-forward reach network is trained using past historical data over a specified period of time for a time having a predetermined error range. During training, the connections adjust the weights between neurons so that the network output matches the desired target. Generalized recurrent neural networks are probabilistic based networks that can perform the task of regression rather than classification. The generalized recurrent neural network comprises four layers, with the reaction neuron layer and the recurrent layer located between the input and output layers, as shown in FIG. 4; the number of the reaction neural layers is equal to the number of samples in the design data set. The regression layer has an additional linear function neuron compared to the output layer and the response neural layer, this additional neuron is used to calculate the probability density, while the remaining units are used to calculate the output. And feedforward neural network based on multiple linear regressionIn contrast, it does not require iterative training and can input and output vectors directly from training data. Inputting the data screened in the second step into two neural networks, and analyzing the adjusted R2Standard deviation (SE), mean adjusted deviation (MAPE), predicted residual sum of squares (PRESS), etc., selecting a single neural network model or a mixture of two neural network models, and setting a data distribution proportion between the models. Through data training, the number of model input layers, the number of neurons in hidden layers and output layers, associated weights, deviations, activities, normal distribution characteristics and other indexes are selected, regression analysis post-processing is carried out, and the output value of a training set is compared with the power generation amount of a wind power generation system of an actual training set.
Step four: and (5) after the training in the third step is completed, model simulation calculation of the artificial neural network with set parameters is given, and the generated energy of the wind power generation system in the future 24 hours is predicted.
Step five: and calculating relevant statistical data of the model operation, recording the statistical data, monitoring the model operation condition and adjusting the test regression process of the model parameters in time.
Step six: and outputting and recording the predicted wind power generation capacity.
The invention provides a set of mixed complex prediction system by comprehensively applying prediction calculation means such as step linear regression, feedforward neural network, generalized regression neural network and the like and considering various weather data independent variables. The method is characterized in that a step-by-step linear regression method is used for screening input values, the running time of an integral model is reduced, two neural network calculation modes are comprehensively used for accurately predicting the generated energy of the wind power generation system, and a set of system for obtaining effective prediction data is provided for comprehensively applying wind energy and guaranteeing the stability and safety of the power consumption of the integral power grid.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. The invention discloses a model and a method for wind power generation prediction by combining multivariate and step linear regression and an artificial neural network, which are characterized by comprising the following steps of: specifying a time span of relevant weather data for a specified region as needed in collecting the predictive model, including: average/highest/lowest atmospheric pressure, average/highest/lowest humidity, average/highest/lowest temperature, average/highest/lowest wind speed, average/highest/lowest wind direction, average/highest/lowest rainfall, average/highest/lowest characteristic time period wind clockwise strength and specific time period wind direction variation.
2. The invention is also characterized in that it comprises identifying the most relevant weather input values by regression method screening; stepwise linear regression is a method of fitting a regression model, by the formula:
fitting the relevant variables, wherein the selection of the predictor variables is performed by an automated program, wherein Y is the photovoltaic output (dependent variable) to be predicted, XiWeather data (independent variables) representing K changes (where 1. ltoreq. i. ltoreq.k), β i
For the regression coefficient of the calculated independent variable, beta0Is a predictor variable for the offset value, e is a residual term, and in each fitting step, according to some predetermined statistical criterion (including adjusted R2Standard Error (SE), mean adjusted deviation (MAPE), sum of the squares of the residuals expected (PRESS), etc.) take the form of a series of F-tests or t-tests, adding or subtracting variables to or from a set of explanatory variables (including forward and reverse stepwise regression).
3. The method is also characterized in that the generation output quantity of the wind power system and the eight weather related data are fitted through step-by-step linear regression, and the most relevant weather input value is identified to the next step of model operation according to the preset standard (containing 1-8 weather data).
4. The invention is also characterized in that the optimized neural network configuration is determined by adjusting parameters of an artificial design network, the design of the artificial neural network comprises determining the number of input layers, the number of neurons in hidden layers and output layers and associated weights, deviations, activities and normal distribution characteristics, and several network architectures can be formed depending on the arrangement of the neurons and their activities.
5. The invention is also characterized in that the invention applies two architectures of a feed-forward neural network (FFNN) and a Generalized Regression Neural Network (GRNN) to the prediction of the photovoltaic output power.
6. The invention is also characterized by screening the data to two neural networks, by analyzing the adjusted R2Selecting a single neural network model or a mixed two neural network models and setting data distribution proportion between the models, selecting indexes such as the number of model input layers, the number of neurons in hidden layers and output layers and correlation weights, deviation, activity and normal distribution characteristics through data training, carrying out regression analysis post-processing, and comparing the output value of a training set with the power generation capacity of a wind power generation system of an actual training set.
7. The method is also characterized in that the generated energy of the wind power generation system in the future 24 hours is predicted through model simulation calculation of the artificial neural network with given set parameters, then the relevant statistical data of the model operation is calculated and recorded, the model operation condition is monitored, and the test regression process of the model parameters is adjusted in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921151.6A CN111967689A (en) | 2020-09-04 | 2020-09-04 | Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921151.6A CN111967689A (en) | 2020-09-04 | 2020-09-04 | Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967689A true CN111967689A (en) | 2020-11-20 |
Family
ID=73392169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010921151.6A Pending CN111967689A (en) | 2020-09-04 | 2020-09-04 | Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967689A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529298A (en) * | 2020-12-11 | 2021-03-19 | 北京邮电大学 | Method, apparatus, electronic device, and medium for predicting power load |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124003A (en) * | 2017-04-28 | 2017-09-01 | 北京天诚同创电气有限公司 | Wind power plant wind energy Forecasting Methodology and equipment |
| US20200057175A1 (en) * | 2018-08-17 | 2020-02-20 | Nec Laboratories America, Inc. | Weather dependent energy output forecasting |
| CN111191854A (en) * | 2020-01-10 | 2020-05-22 | 上海积成能源科技有限公司 | Photovoltaic power generation prediction model and method based on linear regression and neural network |
-
2020
- 2020-09-04 CN CN202010921151.6A patent/CN111967689A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124003A (en) * | 2017-04-28 | 2017-09-01 | 北京天诚同创电气有限公司 | Wind power plant wind energy Forecasting Methodology and equipment |
| US20200057175A1 (en) * | 2018-08-17 | 2020-02-20 | Nec Laboratories America, Inc. | Weather dependent energy output forecasting |
| CN111191854A (en) * | 2020-01-10 | 2020-05-22 | 上海积成能源科技有限公司 | Photovoltaic power generation prediction model and method based on linear regression and neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529298A (en) * | 2020-12-11 | 2021-03-19 | 北京邮电大学 | Method, apparatus, electronic device, and medium for predicting power load |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191854A (en) | Photovoltaic power generation prediction model and method based on linear regression and neural network | |
| Saloux et al. | Forecasting district heating demand using machine learning algorithms | |
| CN105631558A (en) | BP neural network photovoltaic power generation system power prediction method based on similar day | |
| CN111369070A (en) | Envelope clustering-based multimode fusion photovoltaic power prediction method | |
| Chuentawat et al. | The comparison of PM2. 5 forecasting methods in the form of multivariate and univariate time series based on support vector machine and genetic algorithm | |
| CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
| Kolhe et al. | GA-ANN for short-term wind energy prediction | |
| CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
| CN113689049A (en) | Complex model and method for predicting carbon emission of enterprise by combining multivariate linear regression step-by-step linear regression and artificial neural network | |
| CN108876163A (en) | The transient rotor angle stability fast evaluation method of comprehensive causality analysis and machine learning | |
| CN106649479A (en) | Probability graph-based transformer state association rule mining method | |
| CN116070769A (en) | Ultra-short-term wind power plant power multi-step interval prediction modularization method and device thereof | |
| CN111815039A (en) | Weekly scale wind power probability prediction method and system based on weather classification | |
| CN114757104A (en) | Construction method of series gate group water transfer engineering hydraulic real-time regulation model based on data driving | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN115829145A (en) | Photovoltaic power generation capacity prediction system and method | |
| CN115764870A (en) | Multivariable photovoltaic power generation power prediction method and device based on automatic machine learning | |
| CN117439101B (en) | Intelligent network for interaction of new energy and flexible load in power grid | |
| CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
| CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN111967689A (en) | Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network | |
| CN113240217A (en) | Photovoltaic power generation prediction method and device based on integrated prediction model | |
| CN112488443A (en) | Method and system for evaluating utilization rate of power distribution equipment based on data driving | |
| CN108492013A (en) | A kind of manufacture system scheduling model validation checking method based on quality control |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201120 |