CN115455811A - Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning - Google Patents
Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning Download PDFInfo
- Publication number
- CN115455811A CN115455811A CN202211024480.6A CN202211024480A CN115455811A CN 115455811 A CN115455811 A CN 115455811A CN 202211024480 A CN202211024480 A CN 202211024480A CN 115455811 A CN115455811 A CN 115455811A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic power
- reinforcement learning
- digital twinning
- learning
- deep reinforcement
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000002787 reinforcement Effects 0.000 title claims abstract description 39
- 238000010248 power generation Methods 0.000 claims abstract description 39
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 18
- 238000013473 artificial intelligence Methods 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 241000209527 Arum Species 0.000 claims 1
- 235000006481 Colocasia esculenta Nutrition 0.000 claims 1
- 239000003795 chemical substances by application Substances 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Photovoltaic Devices (AREA)
Abstract
A photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning comprises the following steps: firstly, performing digital twinning on the ground landform shape of a photovoltaic base in a selected site by a digital twinning technology; secondly, performing digital twinning on cloud layers in the meteorological data through deep learning; then carrying out digital twinning on the meteorological data; and finally, performing simulation learning on the digital twin BIM model and the data stream through a deep reinforcement learning technology, and dynamically learning a set of strategy method for arranging the solar cell panel and a real-time dynamic adjustment method. The photovoltaic power generation base solar panel distribution method solves the problems that the photovoltaic power generation base solar panel distribution, the environmental factors and the influence of the photovoltaic power generation panel have larger randomness and volatility under different time and space scales.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to a photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning.
Background
With the gradual exhaustion of fossil fuel energy and the serious problem of environmental pollution, the development and utilization of clean energy such as wind energy and solar energy become mainstream research trends in the world, and wind power generation and solar power generation in China account for about 17% of the total power generation, thereby providing an important basis for the development of clean energy. Further development of solar energy is a new research trend. However, under the influence of the arrangement of the solar panels of the photovoltaic power generation base, environmental factors and the photovoltaic power generation panels, the photovoltaic power generation has larger randomness and fluctuation under different time and space scales, and the effective improvement of the position arrangement of the photovoltaic power generation solar panels and the prejudgment of the influence factors become an important research direction.
As one of the very important technologies in the modern times, the artificial intelligence technology has been widely applied in various industries, and particularly, a deep reinforcement learning method in the aspect of artificial intelligence field decision making has been widely researched in the field of decision making. The Google company quickly promotes the development of deep reinforcement learning after releasing AlphaGo, and lays an important foundation for the decision in the cognitive intelligence field. The digital twin makes full use of actual physical equipment and sensor data, simulates multiple processes, and is rapidly developed in a power system.
Disclosure of Invention
Aiming at the defects in the prior art, the invention designs an efficient solar panel arrangement method of a photovoltaic power generation base based on digital twinning and deep reinforcement learning; the problem of the arrangement of photovoltaic power generation base panel, environmental factor and photovoltaic power generation board self influence, have great randomness and volatility under different time and space scales is solved.
In order to achieve the purpose, the technical scheme adopted by the invention comprises the following specific steps:
a photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning comprises the following steps:
s1, performing digital twinning on the ground geomorphic shape of the photovoltaic base selected by the site through a digital twinning technology;
s2, performing digital twinning on a cloud layer in meteorological data through deep learning;
s3, performing digital twinning on meteorological data;
and S4, performing simulation learning on the digital twin BIM model and the data stream through a deep reinforcement learning technology, and dynamically learning a set of strategy method for arranging the solar cell panel and a real-time dynamic adjustment method.
Further, in step S1, the landform method of the digital twin photovoltaic power generation base includes: through 64 lines of laser radar equipment, utilize the unmanned aerial vehicle of big jiang to take photo by plane to the landform, combine the data of taking photo by plane and some cloud data to carry out digital twin to the landform and landform of photovoltaic base through the modeling, with the virtual mapping of actual physical object to photovoltaic power generation information system in.
Further, in step S2, the cloud cluster in the meteorological data is subjected to a digital twinning method through deep learning: carrying out intelligent image recognition on the height, the cloud cluster shape and the cloud cluster thickness of an aerial cloud cluster by using a camera arranged on a ground photovoltaic base through an artificial intelligence method, deducing the shielding shape of a ground photovoltaic solar panel through height reflection, modeling BIM (building information modeling) in the process, and digitally twinning into a photovoltaic power generation information system;
the method comprises the steps of determining the irradiance influence on the solar cell panel according to the height and the shape of the cloud cluster, calculating the influence area of the cloud cluster on the ground according to the size of the cloud cluster in the air and ground height information, and dynamically adjusting the angle of the solar cell panel in the corresponding area.
Preferably, the artificial intelligence method comprises one or a combination of a neural network and a convolutional neural network method.
Further, in step S3, the weather data includes irradiance, rainfall information, and ambient temperature, and the twin of the weather data refers to digital twin of the sensing and detection result of the weather data by using the existing ground sensor into the photovoltaic power generation information system, or secondary twin of the data by using the weather department into the photovoltaic power generation information system.
Further, in the step S4, the data stream is simulated and learned through a deep reinforcement learning method, and the solar panel arrangement strategy and the real-time dynamic adjustment strategy are found, which means that a set of installation angle strategy suitable for the local illumination condition angle is dynamically learned according to the terrain and the landform of the digital twin in the step S1, and a large-scale photovoltaic solar panel angle adjustment strategy is performed according to the digital twin factors in real time.
Further, the area of influence formula of the cloud cluster on the ground is as follows:
in formula 1, cloud images are identified by a CNN method, and the area and height L of S1 are respectively calculated 1 ,L 2
Further, in step S4, the objective of deep reinforcement learning is to continuously perform interactive learning through an intelligent agent and an environment (photovoltaic cell panel), so that the solar cell panel finally sends out the maximum electric quantity value, and the whole learning objective mathematical expression of the reinforcement learning is as follows:
in order for an agent to learn a set of completion strategies, the reward generated for each interaction is typically measured using a state value function and a state-behavior value function, where the mathematical expressions of the state value function and the state-behavior value function are:
setting a reasonable incentive mechanism according to influence factors, and setting a reward function by taking the maximum electric quantity value EV (Electron Volt) sent by the solar panel per minute as a main reward index, wherein the reward function is mathematically expressed as follows:
R＝α*EV+N(0，1)。
in conclusion, due to the adoption of the technical scheme, the beneficial technical effects of the invention are as follows:
the invention discloses a photovoltaic power station battery board arrangement method based on digital twinning and deep reinforcement learning. In the arrangement of solar panels in a photovoltaic power generation base, geographic factors, weather and the like of site selection of the base are important factors influencing the power generation efficiency, and most of the existing methods concentrate on the improvement of the electrical efficiency. According to the method, a depth reinforcement learning technology based on digital twinning and an artificial intelligence method is used for carrying out digital twinning on site selection landform and topographic features and meteorological data of a photovoltaic power generation base, and data flow simulation learning is carried out through the depth reinforcement learning technology, so that a set of strategy method for arranging the solar cell panel and a real-time dynamic adjusting method are obtained. The method provides a new idea for electric power digital construction and decision, and is a potential leading-edge digital electric power technical method.
Drawings
FIG. 1 is a flow chart of solar panel arrangement in a photovoltaic power generation base
FIG. 2 is a diagram of the influence factors of cloud cluster on photovoltaic power generation base in digital twin
FIG. 3 is a diagram of depth reinforcement learning for dynamically adjusting the arrangement and angle of a solar cell panel
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the embodiment, a set of solar panel arrangement method and dynamic adjustment strategy for the photovoltaic power generation base are obtained by combining digital twinning and depth reinforcement learning.
The specific embodiments described herein are merely illustrative of the relevant invention and are not intended to be limiting. It should be noted that some features in the implementation process may be combined with each other, and the following detailed description is provided:
fig. 1 is a flow chart of arrangement of solar panels in a photovoltaic power generation base. The whole body is composed of four parts, and specifically comprises:
the digital twin photovoltaic power generation base landform and topography of the step S101 means that data scanning modeling is carried out on the landform and topography of a photovoltaic power generation base to be selected through 64-line laser radar equipment, and data are synchronously sent to a photovoltaic power generation management system to serve as important source data for adjusting visualization of the visual photovoltaic power generation base and a dynamic photovoltaic solar panel; meanwhile, the landform is one of important influence factors of the angle of installing the photovoltaic solar panel.
The cloud cluster in the digital twin meteorological data in step S201 is to photograph the cloud cluster in the air through a camera installed in a ground photovoltaic power generation base, identify the shape and thickness of the cloud cluster through an artificial intelligence method such as a neural network and a convolutional neural network method, determine the influence of irradiance on the solar cell panel on one hand, calculate the size of the area of influence of the cloud cluster on the ground according to the size of the cloud cluster in the air and ground height information through inverse mapping, and dynamically adjust the angle of the solar cell panel in the corresponding area.
The rainfall information and the environmental temperature in the digital twin meteorological data in the step S301 mean that relevant data of information systems of governments and all meteorological departments are extracted, or sensor data of a photovoltaic power generation base are digitally twinned into a photovoltaic power generation management system, and a foundation is laid for dynamically adjusting the angle and the installation angle of the solar cell panel in the step S401.
The step S401 of performing simulation learning on the data stream through a deep reinforcement learning method to find a solar panel arrangement strategy and a real-time dynamic adjustment strategy means that a set of installation angle strategies suitable for local illumination condition angles is dynamically learned according to the terrain and features of digital twins in the step S101 and a large-scale photovoltaic solar panel angle adjustment strategy is performed in real time according to digital twins factors.
Fig. 2 is a graph of influence factors of cloud clusters on a photovoltaic power generation base in digital twins, and an influence area formula of the cloud clusters on the ground is as follows:
through a CNN method, cloud images are identified, and the area and the heights l1 and l2 of the S1 are respectively calculated
FIG. 3 is a diagram of dynamically adjusting the arrangement and angle of a solar panel by deep reinforcement learning, which is a strategy of dynamically learning and adjusting the angle of a photovoltaic solar panel by a deep reinforcement learning method; the reinforcement learning agent is a parameter set consisting of an artificial neural network, and the acquisition of observation values is that the agent acquires surrounding environmental factors including landform, cloud cluster, fortune illumination and rainfall information; the action value refers to the angle between the solar panel and the ground, the angle between the solar panel and the sun and the current value of the output adjustment angle of the solar panel motor. The reward is an electric quantity value produced by the solar cell panel after dynamic adjustment, and the influence of the adjustment angle on the electric quantity value is also included.
The target of deep reinforcement learning is through the intelligent agent and the continuous interactive learning of environment (photovoltaic cell board), finally makes solar cell panel send the biggest electric quantity value, and the learning target mathematical expression of whole reinforcement learning is:
in order for an agent to learn a set of completion strategies, the reward generated by each interaction is usually measured using a state-value function and a state-behavior-value function, where the mathematical expressions of the state-value function and the state-behavior-value function are:
according to the reasonable incentive mechanism set by the influence factors, the invention sets the reward function by taking the maximum electric quantity value EV (Electron Volt) sent by the solar panel per minute as the main reward index, and the mathematical expression is as follows:
R＝α*EV+N(0，1)
the method comprises the steps of taking 4 state space input quantities of landform, cloud cluster, fortune illumination and rainfall information as state input quantities of deep reinforcement learning, taking 3 action space input quantities of current values of an angle between a solar cell panel and the ground, an angle between the solar cell panel and the sun and an output adjustment angle of a solar cell panel motor as action input quantities of a deep reinforcement learning intelligent body to carry out modeling, carrying out reinforcement learning intelligent body interactive learning through a set reward function to obtain a control angle voltage value with maximized power generation efficiency, dynamically learning a set of installation angle strategy suitable for local illumination condition angles and carrying out large-scale photovoltaic solar cell panel angle adjustment strategy according to digital twin factors in real time.
The above-described preferred embodiments of the invention are not intended to be limiting, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A photovoltaic power station battery board arrangement method based on digital twinning and deep reinforcement learning is characterized by comprising the following steps:
s1, performing digital twinning on the ground geomorphic shape of the photovoltaic base selected by the site through a digital twinning technology;
s2, performing digital twinning on a cloud layer in meteorological data through deep learning;
s3, performing digital twinning on meteorological data;
and S4, performing simulation learning on the digital twin BIM model and the data stream through a deep reinforcement learning technology, and dynamically learning a set of strategy method for arranging the solar cell panel and a real-time dynamic adjustment method.
2. The digital twinning and deep reinforcement learning-based photovoltaic power station panel arrangement method according to claim 1, characterized in that in step S1: the landform and landform method of the digital twin photovoltaic power generation base comprises the following steps: through 64 line laser radar equipment to utilize big ARUM unmanned aerial vehicle to take photo by plane to the geomorphy, combine to take photo by plane data and some cloud data to carry out the digital twin to the geomorphy and geomorphy of photovoltaic base through the modeling, with the virtual mapping of actual physical object in the photovoltaic power generation information system.
3. The digital twinning and deep reinforcement learning-based photovoltaic power station panel arrangement method according to claim 1, characterized in that in step S2: the cloud cluster in the meteorological data is subjected to a digital twinning method through deep learning: the method comprises the steps that a camera installed on a ground photovoltaic base is utilized, intelligent image recognition is conducted on the height, the shape and the thickness of a cloud cluster in the air through an artificial intelligence method, the shielding shape of a ground photovoltaic solar panel is deduced through height reflection, BIM modeling is conducted in the process, and the number is twinned into a photovoltaic power generation information system;
the method comprises the steps of determining the irradiance influence on the solar cell panel according to the height and the shape of the cloud cluster, calculating the influence area of the cloud cluster on the ground according to the size of the cloud cluster in the air and ground height information, and dynamically adjusting the angle of the solar cell panel in the corresponding area.
4. The digital twin, deep reinforcement learning based photovoltaic power plant panel arrangement method of claim 3, wherein the artificial intelligence method comprises one or a combination of both of neural network and convolutional neural network methods.
5. The digital twinning-based deep reinforcement learning-based photovoltaic power station panel arrangement method according to claim 1, characterized in that in step S3: the meteorological data comprise irradiance, rainfall information and environmental temperature, and the twinning of the meteorological data means that the meteorological data are subjected to digital twinning to a photovoltaic power generation information system by using the sensing and detection results of the existing ground sensor, or the meteorological department is subjected to secondary twinning to the photovoltaic power generation information system by using data of a meteorological department.
6. The photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning as claimed in claim 1, wherein in the step S4, the data stream is simulated and learned through a deep reinforcement learning method, and a solar battery panel arrangement strategy and a real-time dynamic adjustment strategy are found, which means that according to the landform and topography of the digital twinning in the step S1, a set of installation angle strategy suitable for the local illumination condition angle is dynamically learned, and a large-scale photovoltaic solar battery panel angle adjustment strategy is carried out in real time according to the digital twinning factor.
7. The digital twinning deep reinforcement learning-based photovoltaic power station panel arrangement method according to claim 3, wherein the area of influence formula of the cloud cluster on the ground is as follows:
in formula 1, cloud images are identified by a CNN method, and the area and height L of S1 are respectively calculated 1 ,L 2 。
8. The photovoltaic power station panel arrangement method based on digital twinning and deep reinforcement learning as claimed in claim 1, wherein in the step S4, the objective of deep reinforcement learning is to make the solar panel send out the maximum electric quantity value through continuous interactive learning of an intelligent agent and the environment, and the learning objective mathematical expression of the whole reinforcement learning is as follows:
in order for an agent to learn a set of completion strategies, the reward generated for each interaction is typically measured using a state value function and a state-behavior value function, where the mathematical expressions of the state value function and the state-behavior value function are:
a reasonable incentive mechanism is set according to influence factors, a maximum electric quantity value EV (Electron Volt) sent by the solar panel per minute is used as a main reward index to set a reward function, wherein the reward function is set to be expressed in a mathematical way as follows:
R＝α*EV+N(0，1)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211024480.6A CN115455811A (en) | 2022-08-25 | 2022-08-25 | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211024480.6A CN115455811A (en) | 2022-08-25 | 2022-08-25 | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115455811A true CN115455811A (en) | 2022-12-09 |
Family
ID=84299497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211024480.6A Withdrawn CN115455811A (en) | 2022-08-25 | 2022-08-25 | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115455811A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167531A (en) * | 2023-04-26 | 2023-05-26 | 天津福天科技有限公司 | Photovoltaic power generation prediction method based on digital twin |
| CN116740293A (en) * | 2023-06-13 | 2023-09-12 | 西安速度时空大数据科技有限公司 | Digital twinning-based three-dimensional terrain model acquisition method, device and storage medium |
| 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 |
-
2022
- 2022-08-25 CN CN202211024480.6A patent/CN115455811A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167531A (en) * | 2023-04-26 | 2023-05-26 | 天津福天科技有限公司 | Photovoltaic power generation prediction method based on digital twin |
| CN116740293A (en) * | 2023-06-13 | 2023-09-12 | 西安速度时空大数据科技有限公司 | Digital twinning-based three-dimensional terrain model acquisition method, device and storage medium |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115455811A (en) | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning | |
| CN112100720B (en) | Artificial intelligence city design form layout method for improving wind environment | |
| Zhang et al. | A review of urban energy systems at building cluster level incorporating renewable-energy-source (RES) envelope solutions | |
| Mahmoud et al. | An advanced approach for optimal wind power generation prediction intervals by using self-adaptive evolutionary extreme learning machine | |
| Shuvho et al. | Prediction of solar irradiation and performance evaluation of grid connected solar 80KWp PV plant in Bangladesh | |
| CN103903073B (en) | A kind of micro-capacitance sensor Method for optimized planning containing distributed power source and energy storage and system | |
| CN104200484B (en) | Distributed photovoltaic system ultra-short-term power output prediction method based on cloud cluster characteristic analysis | |
| CN104836259B (en) | Multi-energy resource ship micro-grid real-time energy optimal scheduling method | |
| CN107909211B (en) | Wind field equivalent modeling and optimization control method based on fuzzy c-means clustering algorithm | |
| CN105046374A (en) | Power interval predication method based on nucleus limit learning machine model | |
| CN102254239A (en) | Power grid wind damage early warning system based on micro-landform wind field distribution and typhoon superimposed effect | |
| CN103942736B (en) | A kind of wind power plant multimachine equivalent modeling method | |
| CN110209047B (en) | Photovoltaic power station shelter positioning method based on residual error network | |
| CN116070975B (en) | Park energy management system based on digital twin technology and zero-carbon operation method | |
| US20240054267A1 (en) | Method for planning a layout of a renewable energy site | |
| CN109449987A (en) | The power system simulation method and system of new energy power generation grid-connection | |
| CN108196317A (en) | A kind of Predictive meteorological methods for micro-grid system | |
| CN115617083A (en) | Automatic angle adjusting method for photovoltaic power generation solar cell panel based on PPO algorithm | |
| Kurniawan et al. | Estimation of the monthly global, direct, and diffuse solar radiation in Japan using artificial neural network | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| Kanchana et al. | PV Power Forecasting with Holt-Winters Method | |
| CN111488974B (en) | Ocean wind energy downscaling method based on deep learning neural network | |
| CN117374956A (en) | Short-term prediction method for photovoltaic power generation of comprehensive energy station | |
| CN106600055A (en) | Wind speed prediction method the basis of self excitation threshold autoregression model | |
| CN112101626A (en) | Distributed photovoltaic power generation power prediction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221209 |