CN116167531A - Photovoltaic power generation prediction method based on digital twin - Google Patents
Photovoltaic power generation prediction method based on digital twin Download PDFInfo
- Publication number
- CN116167531A CN116167531A CN202310456291.4A CN202310456291A CN116167531A CN 116167531 A CN116167531 A CN 116167531A CN 202310456291 A CN202310456291 A CN 202310456291A CN 116167531 A CN116167531 A CN 116167531A
- Authority
- CN
- China
- Prior art keywords
- power generation
- photovoltaic power
- digital twin
- model
- data
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005286 illumination Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000013499 data model Methods 0.000 abstract description 4
- 210000004027 cell Anatomy 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000000306 component Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 238000012706 support-vector machine 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a photovoltaic power generation prediction method based on digital twin, which aims to improve the efficiency and reliability of photovoltaic power generation. The method comprises the following steps: firstly, constructing a digital twin model through a physical model and a data model of a photovoltaic power generation system, and updating the digital twin model through monitoring collected data of the photovoltaic power generation system in real time; secondly, combining weather forecast data and historical weather data to establish a weather digital twin model, wherein the weather digital twin model comprises an illumination intensity model and a temperature model, and optimizing the model in a real-time updating mode; the digital twin model and the meteorological digital twin model are combined to construct a digital twin body for predicting the power generation capacity of the photovoltaic power generation system, and the digital twin body comprises an simulator, a data collector and a predictor. Experiments prove that the photovoltaic power generation prediction method based on digital twin has high prediction accuracy, and the efficiency and reliability of photovoltaic power generation can be effectively improved.
Description
Technical Field
The invention relates to the field of photovoltaic power generation, in particular to a photovoltaic power generation prediction method based on digital twin.
Background
With the increasing increase of global energy crisis, photovoltaic power generation is a novel clean, renewable, noiseless and pollution-free energy source, and has become one of main choices for developing renewable energy sources and coping with climate change by governments at home and abroad. However, since photovoltaic power generation has instability and volatility and has a large influence on external factors such as illumination, air temperature and the like, accurate prediction of photovoltaic power generation amount has important significance for safe and stable operation and optimal management of photovoltaic power generation.
Digital twinning is a method for finely modeling a physical system into a digital twin body based on physical, mathematical modeling and simulation technology and realizing comprehensive monitoring, prediction and optimization of the physical system by means of various data, algorithms and tools. In the photovoltaic power generation prediction, a digital twin technology is utilized to carry out mathematical modeling and simulation on solar illumination, a photovoltaic panel and an inverter, model parameters are continuously optimized according to historical data and real-time data, and the change trend of photovoltaic power generation in a future time period is predicted.
The traditional photovoltaic power generation prediction methods are mainly based on mathematical models, such as ARIMA, SVM and the like, and can better predict the output of photovoltaic power generation, but the traditional photovoltaic power generation prediction methods are poor in performance when dealing with complex conditions such as weather changes and the like due to the fact that the traditional photovoltaic power generation prediction methods depend on historical data and physical models. The invention provides a photovoltaic power generation prediction method based on digital twin, and aims to solve the defects of the traditional method through a digital twin technology.
Disclosure of Invention
The technical problems to be solved are as follows:
the traditional photovoltaic power generation prediction method is mainly based on meteorological data, but the accuracy of the method is affected by the quality and quantity of the meteorological data, the prediction accuracy is low, and the prior art lacks a simple and easy-to-use prediction method with good accuracy.
The technical scheme is as follows:
the invention provides a photovoltaic power generation prediction method based on digital twin, which comprises the following steps:
step 1: the digital twin model of the photovoltaic power generation system is built by collecting real-time operation data, current, voltage and temperature parameters and structure and position information of the photovoltaic power station of the photovoltaic power generation system. The acquisition equipment of the real-time operation data comprises an illumination intensity sensor, an ambient temperature sensor, a wind speed sensor, a current sensor and a voltage sensor.
Step 2: the digital twin model is updated by monitoring the collected data of the photovoltaic power generation system in real time, and the updated digital twin model can more accurately reflect the actual running condition of the photovoltaic power generation system. And the data of the photovoltaic power generation system which is monitored and collected in real time is simultaneously sent to a data collector in the digital twin body.
Step 3: the weather forecast data and the historical weather data are combined, a weather digital twin model is built, a numerical model of a weather system is built through the weather data and a machine learning algorithm on the digital twin model, and weather conditions and change trends are accurately predicted. The meteorological digital twin model data are simultaneously transmitted to a data collector in the digital twin body.
Step 4: the meteorological digital twin model is optimized in a real-time updating mode to reflect real-time weather conditions, the time interval for updating the digital twin model and the meteorological digital twin model in real time can be adjusted according to actual conditions, and the method for optimizing the meteorological digital twin model comprises the steps of updating meteorological data, adjusting a machine learning algorithm, including a neural network, a support vector machine and a random forest.
Step 5: the digital twin model of the photovoltaic power generation system and the meteorological digital twin model are combined to construct a digital twin body, and the digital twin body comprises an simulator, a data acquisition device and a predictor, so that the power generation capacity of the photovoltaic power generation system is predicted, and the efficiency and the reliability of photovoltaic power generation are improved. The data collector receives the photovoltaic power generation system data, the weather forecast data and the historical meteorological data which are collected in a real-time monitoring mode.
And 6, the photovoltaic power generation prediction result based on digital twin is presented through a human-computer interface and can be compared and evaluated with the actual power generation.
The beneficial effects are that:
the invention has the advantages that the digital twin technology can quickly generate the historical data, and solves the problem of insufficient historical data of the traditional method; the digital twin body predictor can accurately simulate the photovoltaic power generation output conditions under various meteorological conditions, so that the prediction accuracy is improved; the digital twin body can be calibrated continuously, and stability and accuracy of a prediction result are guaranteed.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a photovoltaic power generation prediction method based on digital twin, which comprises the following steps:
step 1: and a digital twin model of the photovoltaic power generation system is constructed by collecting real-time operation data of the photovoltaic power generation system, current and voltage parameters and structure and position information of the photovoltaic power station. The digital twin model digitally models the running condition, structure and performance characteristics of an actual physical system on a computer, and is based on digital replication of an actual photovoltaic power generation system.
The digital twin model consists of a simulation model and a data model of the photovoltaic power generation system. The simulation model is the core of a digital twin model and comprises a photovoltaic cell panel model and an inverter model; the data model is a key component of the digital twin model, and the accuracy of photovoltaic power generation prediction is improved by simulating the actual output of the photovoltaic power generation system through data. The real time simulation of the photovoltaic power generation system is realized by establishing a simulation model and a data model, and the monitoring, the prediction and the optimization of the real physical system are realized.
Step 2: the collected photovoltaic power generation system data is monitored in real time to update the digital twin model, and the updated digital twin model can more accurately reflect the actual running condition of the photovoltaic power generation system.
Step 3: the weather forecast data and the historical weather data are combined to establish a weather digital twin model comprising weather parameters such as environment, illumination intensity, temperature and the like, so that the weather condition of the region where the photovoltaic power generation system is located can be accurately reflected. The weather forecast data and the historical weather data of the weather digital twin model are analyzed and processed through a support vector regression algorithm, and weather conditions and weather changes are predicted.
The support vector regression algorithm creates a distance on both sides of the linear function, the distance is a tolerance deviation of the empirical value set manually, no loss is calculated for all samples falling into the interval band, only the support vector will affect the function model, and the optimized model is obtained by minimizing the total loss and maximizing the interval.
Step 4: the meteorological data is updated in real time, and the meteorological digital twin model is optimized, including updating the meteorological data and adjusting a machine learning algorithm to reflect real-time weather conditions more accurately. The collected meteorological data is cleaned, processed and analyzed to ensure the accuracy and the integrity of the data, modeling is carried out aiming at specific meteorological parameters, temperature, humidity and wind speed, and verification is carried out after a numerical model is established to verify the accuracy and the reliability of the model. The verification method comprises cross verification and error analysis, and the model is further improved and optimized through verification results, so that the prediction capability and stability of the model are improved.
Step 5: the digital twin model and the meteorological digital twin model of the photovoltaic power generation system are combined to construct a digital twin body to predict the power generation capacity of the photovoltaic power generation system, so that the efficiency and the reliability of photovoltaic power generation are improved.
The digital twin body is a key component of the invention and mainly comprises an simulator, a predictor and a data collector.
The simulator is a core algorithm model of a digital twin body, and aims to simulate the actual output condition of the photovoltaic power generation system. The simulator is established according to external data such as meteorological data, illumination intensity and temperature, and is calculated by combining internal data such as a photovoltaic cell panel model and an inverter model.
In the specific implementation process, the simulator models the output of the photovoltaic cell panel by adopting a polynomial regression algorithm, and a polynomial function capable of accurately predicting the output of the photovoltaic cell panel is obtained by analyzing and fitting historical data. Meanwhile, the simulator also adopts a neural network algorithm to model the whole output of the photovoltaic power generation system, and a neural network model capable of accurately predicting the output of the photovoltaic power generation system is obtained through learning and training historical data. Finally, the two are combined to form a prediction model which can simultaneously consider the output of the photovoltaic cell panel and the photovoltaic power generation system, and the accuracy and the reliability of prediction are improved.
The photovoltaic cell panel model is established based on an empirical formula, and the output power of the photovoltaic cell panel is obtained through calculation by simulating meteorological data, illumination intensity, temperature, wind speed and characteristic parameters of the photovoltaic cell panel, and the area, power, conversion efficiency, current and voltage of the photovoltaic cell panel. When the model is built, the output change of the photovoltaic cell panel under different meteorological conditions is considered, and for n groups of samples
A polynomial regression algorithm is selected to build a model: />
Wherein y is the output power of the photovoltaic panel, x is one of characteristic parameters such as temperature, wind speed, illumination intensity, current, voltage and the like,
is a regression equation constant term, +.>
Is a partial regression coefficient. Fitting is carried out according to the historical data, so that an accurate photovoltaic cell panel output power prediction model is obtained.
The inverter model is built based on the operation characteristics of the inverter and mainly comprises parameters such as inverter efficiency, input voltage range, output voltage range and the like. By adopting the neural network algorithm to establish the inverter model, the output power of the inverter can be accurately predicted.
The predictor is another core component of the digital twin body, and aims to predict the output condition of the photovoltaic power generation system for a period of time in the future based on the results of the simulator and the data collector. The predictor can calculate according to the weather data, the external data such as illumination intensity and temperature and the like by combining the results of the simulator and the data collector, and the actual power generation amount of the photovoltaic power generation system in a future period of time is obtained. The predictor is mainly modeled by adopting a neural network algorithm, and a neural network model capable of accurately predicting the output of the photovoltaic power generation system is obtained through learning and training historical data. In the design of neural network models, taking into account the nonlinearity and time-varying nature of photovoltaic power generation systems, a multi-layer perceptron model with a depth and width is employed, and multi-layer perceptrons (MLP, multilayer Perceptron) are a type of feed-forward artificial neural network model that map multiple data sets of an input onto a single output data set, including an input layer, a hidden layer, and an output layer. The input layer receives weather data and characteristic parameters of the photovoltaic power generation system in the history and future period, and information such as illumination intensity, temperature, photovoltaic panel area, input and output voltage of the inverter and the like; the hidden layer adopts ReLU (Rectified Linear Unit) activation function, has a plurality of neuron nodes, and can perform nonlinear feature extraction and complex relation modeling; the output layer adopts a linear activation function to output predicted photovoltaic power generation.
In the training and optimizing of the neural network model, regularization and batch standardization technologies are adopted, and the prediction precision and generalization capability of the model are improved. The regularization technology comprises L1 regularization and L2 regularization, so that the overfitting risk of the model can be effectively reduced; batch normalization can speed up the convergence rate of the model and improve the stability of the model.
In the model training process, a random gradient descent (SGD, stochastic Gradient Descent) algorithm is adopted for parameter optimization, and meanwhile, an early-stop technology is adopted to prevent the model from being over-fitted during training. In order to improve the prediction accuracy of the model, a cross-validation technology is also adopted to evaluate the model and select the optimal super-parameter combination.
The neural network formula and calculation process are as follows:
input layer: and receiving weather data and characteristic parameters of a photovoltaic power generation system in the history and future time, such as illumination intensity, temperature, photovoltaic panel area, input and output voltage of an inverter and the like.
Hidden layer: nonlinear feature extraction and complex relational modeling can be performed using ReLU (Rectified Linear Unit) activation functions with multiple neuron nodes. Assuming that the hidden layer has m neurons in total, the input of the jth neuron is:
wherein x is i Is the ith feature of the input layer, w ij Is the weight between the ith feature and the jth neuron, b j Is the bias term for the jth neuron. The output is:
max represents the larger value of the input sum 0, i.e. the ReLU function.
Output layer: and outputting the predicted photovoltaic power generation amount by adopting a linear activation function. Assuming that the output layer has only one neuron, its inputs are:
w j is the weight between the jth neuron and the output layer, b is the bias term of the output layer, and outputs: a=z.
Model training and optimization: parameter optimization is performed using a random gradient descent algorithm (SGD), wherein the loss function uses a mean square error (MSE, mean Squared Error) function. And meanwhile, regularization processing is carried out by adopting an L1 regularization technology and an L2 regularization technology so as to avoid the occurrence of the over-fitting phenomenon. The convergence speed of the model is accelerated and the stability of the model is improved by adopting a batch standardization technology.
The prediction process comprises the following steps: and inputting meteorological data to be predicted and characteristic parameters of the photovoltaic power generation system, and calculating through a neural network model to obtain predicted photovoltaic power generation capacity.
In conclusion, the neural network formula and the calculation process of the photovoltaic power generation prediction method based on digital twin are simple and clear, and effective support and guidance can be provided for practical application.
And 6, the predicted result is presented through a human-computer interface and is compared and evaluated with the actual power generation amount.
And applying the established neural network model to an actual photovoltaic power generation scene for verification. And the model is adjusted and optimized by comparing the difference between the predicted result and the actual output result, so that the prediction precision and reliability are improved. And after model verification is completed, the model is used for photovoltaic power generation prediction for a period of time in the future. According to future meteorological data and characteristic parameters of the photovoltaic power generation system, the prediction model can accurately predict the output condition of the photovoltaic power generation system, and effective reference information is provided and presented through a human-computer interface.
Claims (7)
1. The photovoltaic power generation prediction method based on digital twinning is characterized by comprising the following steps of: step 1: the method comprises the steps of constructing a digital twin model of the photovoltaic power generation system, wherein the digital twin model is built by collecting real-time operation data of the photovoltaic power generation system and structure and position information of a photovoltaic power station; step 2: updating the digital twin model by monitoring the collected data of the photovoltaic power generation system in real time, so that the running condition and performance of the photovoltaic power generation system are reflected more accurately; step 3: establishing a meteorological digital twin model, wherein the meteorological digital twin model comprises weather forecast data and historical meteorological data and reflects weather conditions of a region where a photovoltaic power generation system is located; step 4: optimizing the meteorological digital twin model in a real-time updating mode; step 5: the digital twin model is combined with a digital twin body constructed by the meteorological digital twin model to predict photovoltaic power generation, and a prediction result is generated; and 6, comparing and evaluating the predicted result with the actual power generation amount.
2. The photovoltaic power generation prediction method based on digital twin according to claim 1, wherein the photovoltaic power generation system data collected by real-time monitoring comprises real-time operation data of photovoltaic cell panel current, voltage, inverter input current, voltage and output power, and the real-time operation data is fed back to a digital twin model.
3. The digital twin-based photovoltaic power generation prediction method according to claim 1, wherein the weather forecast data and the historical weather data for establishing the weather digital twin model comprise illumination intensity, ambient temperature and wind speed, and are analyzed and processed through a machine learning algorithm.
4. The method for predicting the photovoltaic power generation based on the digital twin according to claim 1, wherein the time interval for updating the digital twin model and the meteorological digital twin model in real time can be adjusted according to actual conditions.
5. The method for predicting photovoltaic power generation based on digital twinning according to claim 1, wherein the method for optimizing the meteorological digital twinning model comprises the steps of updating meteorological data and adjusting a machine learning algorithm.
6. The method for predicting photovoltaic power generation based on digital twinning according to claim 1, wherein the predicted result can be compared and evaluated with the actual power generation amount.
7. The method for predicting photovoltaic power generation based on digital twinning according to claim 1, wherein the prediction result can be presented through a human-machine interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310456291.4A CN116167531A (en) | 2023-04-26 | 2023-04-26 | Photovoltaic power generation prediction method based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310456291.4A CN116167531A (en) | 2023-04-26 | 2023-04-26 | Photovoltaic power generation prediction method based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116167531A true CN116167531A (en) | 2023-05-26 |
Family
ID=86422283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310456291.4A Pending CN116167531A (en) | 2023-04-26 | 2023-04-26 | Photovoltaic power generation prediction method based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167531A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595395A (en) * | 2023-07-14 | 2023-08-15 | 中国人民解放军空军预警学院 | Inverter output current prediction method and system based on deep learning |
| CN116961575A (en) * | 2023-09-21 | 2023-10-27 | 中国电建集团贵阳勘测设计研究院有限公司 | Tea light complementary photovoltaic power station monitoring system and method based on digital twin |
| CN117407773A (en) * | 2023-12-14 | 2024-01-16 | 山东捷瑞数字科技股份有限公司 | Digital twinning-based method, system and equipment for predicting icing state of fan blade |
| CN117522156A (en) * | 2023-10-17 | 2024-02-06 | 江苏尚诚能源科技有限公司 | Distributed photovoltaic prediction evaluation method and system based on big data analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566435A (en) * | 2012-02-17 | 2012-07-11 | 冶金自动化研究设计院 | Performance prediction and fault alarm method for photovoltaic power station |
| CN107256437A (en) * | 2017-05-15 | 2017-10-17 | 内蒙古电力(集团)有限责任公司 | A kind of photovoltaic plant ultra-short term irradiation level Forecasting Methodology and system |
| CN113821931A (en) * | 2021-09-26 | 2021-12-21 | 上海海事大学 | Method and system for predicting output power of fan |
| CN115455811A (en) * | 2022-08-25 | 2022-12-09 | 国网甘肃省电力公司电力科学研究院 | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning |
| CN115965132A (en) * | 2022-12-15 | 2023-04-14 | 国网重庆市电力公司丰都供电分公司 | Distributed photovoltaic digital twin system power prediction method based on GA-BP neural network |
-
2023
- 2023-04-26 CN CN202310456291.4A patent/CN116167531A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566435A (en) * | 2012-02-17 | 2012-07-11 | 冶金自动化研究设计院 | Performance prediction and fault alarm method for photovoltaic power station |
| CN107256437A (en) * | 2017-05-15 | 2017-10-17 | 内蒙古电力(集团)有限责任公司 | A kind of photovoltaic plant ultra-short term irradiation level Forecasting Methodology and system |
| CN113821931A (en) * | 2021-09-26 | 2021-12-21 | 上海海事大学 | Method and system for predicting output power of fan |
| CN115455811A (en) * | 2022-08-25 | 2022-12-09 | 国网甘肃省电力公司电力科学研究院 | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning |
| CN115965132A (en) * | 2022-12-15 | 2023-04-14 | 国网重庆市电力公司丰都供电分公司 | Distributed photovoltaic digital twin system power prediction method based on GA-BP neural network |
Non-Patent Citations (4)
| Title |
|---|
| 卢冬冬，等: ""基于天气预报的光伏发电预测研究"", 《技术研发》, no. 15, pages 43 - 44 * |
| 孙运志，等: ""大数据分析下太阳能发电优化模型研究"", 《数据信息与智能》, pages 86 - 101 * |
| 王江元，等: ""基于太阳辐照强度的光伏发电功率预测"", 《中国可再生能源学会2011年学术年会论文（太阳能）》, pages 1 - 4 * |
| 黑白好的角色: ""数字孪生与GIS：解读物理世界，开启智能未来 "", pages 1 - 2, Retrieved from the Internet <URL:https://baijiahao.***.com/s?id=1763676368286303224&wfr=spider&for=pc> * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595395A (en) * | 2023-07-14 | 2023-08-15 | 中国人民解放军空军预警学院 | Inverter output current prediction method and system based on deep learning |
| CN116595395B (en) * | 2023-07-14 | 2023-09-22 | 中国人民解放军空军预警学院 | Inverter output current prediction method and system based on deep learning |
| CN116961575A (en) * | 2023-09-21 | 2023-10-27 | 中国电建集团贵阳勘测设计研究院有限公司 | Tea light complementary photovoltaic power station monitoring system and method based on digital twin |
| CN116961575B (en) * | 2023-09-21 | 2023-12-01 | 中国电建集团贵阳勘测设计研究院有限公司 | Tea light complementary photovoltaic power station monitoring system and method based on digital twin |
| CN117522156A (en) * | 2023-10-17 | 2024-02-06 | 江苏尚诚能源科技有限公司 | Distributed photovoltaic prediction evaluation method and system based on big data analysis |
| CN117407773A (en) * | 2023-12-14 | 2024-01-16 | 山东捷瑞数字科技股份有限公司 | Digital twinning-based method, system and equipment for predicting icing state of fan blade |
| CN117407773B (en) * | 2023-12-14 | 2024-06-18 | 山东捷瑞数字科技股份有限公司 | Digital twinning-based method, system and equipment for predicting icing state of fan blade |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734331B (en) | Short-term photovoltaic power generation power prediction method and system based on LSTM | |
| CN116167531A (en) | Photovoltaic power generation prediction method based on digital twin | |
| CN110766212B (en) | Ultra-short-term photovoltaic power prediction method for historical data missing electric field | |
| CN113128793A (en) | Photovoltaic power combination prediction method and system based on multi-source data fusion | |
| CN110909919A (en) | Photovoltaic power prediction method of depth neural network model with attention mechanism fused | |
| CN108280551A (en) | A kind of photovoltaic power generation power prediction method using shot and long term memory network | |
| CN111222674A (en) | Short-term photovoltaic power generation capacity prediction method based on long-term and short-term memory neural network | |
| CN108399470B (en) | Indoor PM2.5 prediction method based on multi-example genetic neural network | |
| CN113537582B (en) | Photovoltaic power ultra-short-term prediction method based on short-wave radiation correction | |
| Shah et al. | A novel prediction error-based power forecasting scheme for real pv system using pvusa model: A grey box-based neural network approach | |
| CN116757057A (en) | Air quality prediction method based on PSO-GA-LSTM model | |
| CN115796004A (en) | Photovoltaic power station ultra-short term power intelligent prediction method based on SLSTM and MLSTNet models | |
| CN114444660A (en) | Short-term power load prediction method based on attention mechanism and LSTM | |
| CN115115125A (en) | Photovoltaic power interval probability prediction method based on deep learning fusion model | |
| CN112101626A (en) | Distributed photovoltaic power generation power prediction method and system | |
| CN112183877A (en) | Photovoltaic power station fault intelligent diagnosis method based on transfer learning | |
| Wibawa et al. | Long Short-Term Memory to Predict Unique Visitors of an Electronic Journal | |
| CN113449847B (en) | Offshore wind power rolling prediction method considering second-level time series wind speed change | |
| CN114429248A (en) | Transformer apparent power prediction method | |
| CN114757330A (en) | Urban instantaneous water consumption prediction method based on LSTM | |
| CN110956304A (en) | Distributed photovoltaic power generation capacity short-term prediction method based on GA-RBM | |
| Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
| CN111967660B (en) | Ultra-short-term photovoltaic prediction residual error correction method based on SVR | |
| CN112036672B (en) | New energy power generation ultra-short term power prediction method and system based on iterative correction | |
| CN112232714B (en) | Deep learning-based risk assessment method for distribution network under incomplete structural parameters |
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 |