CN113610287A - Optical power forecasting method and device, computer equipment and storage medium - Google Patents
Optical power forecasting method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113610287A CN113610287A CN202110851492.5A CN202110851492A CN113610287A CN 113610287 A CN113610287 A CN 113610287A CN 202110851492 A CN202110851492 A CN 202110851492A CN 113610287 A CN113610287 A CN 113610287A
- Authority
- CN
- China
- Prior art keywords
- forecast
- optical power
- ith
- target time
- forecasting
- 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
- 230000003287 optical effect Effects 0.000 title claims abstract description 210
- 238000013277 forecasting method Methods 0.000 title claims description 16
- 238000010801 machine learning Methods 0.000 claims abstract description 73
- 238000012937 correction Methods 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010248 power generation Methods 0.000 abstract description 21
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012417 linear regression Methods 0.000 description 6
- 230000005855 radiation Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000003550 marker Substances 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/10—Control of fluid heaters characterised by the purpose of the control
- F24H15/144—Measuring or calculating energy consumption
- F24H15/152—Forecasting future energy consumption
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/20—Control of fluid heaters characterised by control inputs
- F24H15/262—Weather information or forecast
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/40—Control of fluid heaters characterised by the type of controllers
- F24H15/414—Control of fluid heaters characterised by the type of controllers using electronic processing, e.g. computer-based
-
- 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
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Power Engineering (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Secondary Cells (AREA)
Abstract
The application discloses a method and a device for forecasting optical power, computer equipment and a storage medium, and relates to the technical field of photovoltaic power generation. The method comprises the following steps: acquiring n forecast data aiming at a target time interval, wherein the n forecast data are respectively from n meteorological sources, and n is a positive integer greater than 1; calling a forecasting model, wherein the forecasting model comprises: the optical power prediction layer comprises n machine learning processing modules; inputting ith forecast data aiming at a target time interval into an ith machine learning processing module in the optical power forecasting layer to obtain ith reference forecast optical power aiming at the target time interval, wherein i is a positive integer not greater than n; inputting the 1 st reference forecast optical power to the nth reference forecast optical power aiming at the target time interval into the optical power correction layer to obtain the corrected forecast optical power aiming at the target time interval. According to the embodiment of the application, the forecasting level of each meteorological source can be maximally excavated, and the forecasting precision of the optical power is improved.
Description
Technical Field
The present application relates to the field of photovoltaic power generation technologies, and in particular, to a method and an apparatus for forecasting optical power, a computer device, and a storage medium.
Background
Photovoltaic power generation is a power generation method in which the output light power is closely related to meteorological conditions.
At present, photovoltaic power generation enterprises generally input forecast data of a meteorological source into a machine learning model based on a single machine learning model so as to output forecasted luminous power, and forecasting accuracy is not good enough.
Disclosure of Invention
The embodiment of the application provides a method and a device for forecasting optical power, computer equipment and a storage medium, which can maximally excavate the forecasting level of each meteorological source, thereby improving the forecasting precision of the optical power. The technical scheme is as follows.
According to an aspect of the present application, there is provided an optical power forecasting method, the method including:
acquiring n forecast data aiming at a target time interval, wherein the n forecast data are respectively from n meteorological sources, and n is a positive integer greater than 1;
invoking a forecasting model, the forecasting model comprising: the device comprises an optical power prediction layer and an optical power correction layer, wherein the optical power prediction layer comprises n machine learning processing modules;
inputting ith forecast data aiming at the target time interval into an ith machine learning processing module in the optical power forecasting layer to obtain ith reference forecast optical power aiming at the target time interval, wherein i is a positive integer not greater than n;
inputting the 1 st reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer to obtain a corrected forecast optical power for the target time interval.
According to an aspect of the present application, there is provided an optical power forecasting apparatus, the apparatus comprising: the device comprises a forecast data acquisition module, a model calling module, an optical power forecasting module and an optical power correcting module;
the forecast data acquisition module is used for acquiring n pieces of forecast data aiming at a target time interval, wherein the n pieces of forecast data are respectively from n meteorological sources, and n is a positive integer greater than 1;
the model calling module is used for calling a forecasting model, and the forecasting model comprises: the device comprises an optical power prediction layer and an optical power correction layer, wherein the optical power prediction layer comprises n machine learning processing modules;
the optical power forecasting module is used for inputting ith forecast data aiming at the target time interval into an ith machine learning processing module in the optical power forecasting layer to obtain ith reference forecast optical power aiming at the target time interval, wherein i is a positive integer not greater than n;
the optical power correction module is configured to input the 1 st reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer, so as to obtain a corrected forecast optical power for the target time interval.
According to another aspect of the present application, there is provided a computer device comprising: a processor and a memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions that is loaded and executed by the processor to implement a method of optical power forecasting as described above.
According to another aspect of the present application, there is provided a computer readable storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement the optical power forecasting method as described above.
According to another aspect of the application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the optical power forecasting method provided in the above-mentioned alternative implementation.
The technical scheme provided by the embodiment of the application has the following advantages.
The method comprises the steps of acquiring n forecast data from n meteorological sources, processing the n forecast data by using n machine learning processing modules respectively to obtain n reference forecast light powers corresponding to the n meteorological sources, and correcting the n reference forecast light powers by using a light power correction layer to obtain a final corrected forecast light power.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an optical power forecasting system provided by an exemplary embodiment of the present application;
FIG. 2 is a flow chart of a method for optical power forecasting provided by an exemplary embodiment of the present application;
FIG. 3 is a flow chart of a method for optical power forecasting provided by an exemplary embodiment of the present application;
FIG. 4 is a flow chart of a method for optical power forecasting provided by an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram of an optical power forecasting method provided by an exemplary embodiment of the present application;
FIG. 6 is a block diagram of an optical power prediction apparatus provided in an exemplary embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to an exemplary embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The photovoltaic power generation by using the solar energy has the characteristics of low energy density, intermittence, uncertainty and the like, and particularly, the output power of the photovoltaic power generation is closely related to meteorological conditions, so that the power generation characteristics of the photovoltaic power generation are greatly different from those of conventional power.
The grid-connected access of photovoltaic power generation is an important form for realizing large-scale efficient utilization of photovoltaic power generation. Due to the intermittency, uncertainty and uncontrollable property of photovoltaic power generation, when a large-scale and large-capacity photovoltaic power generation system is connected to a power grid, a great challenge is brought to the safe operation of a public power grid.
Therefore, if the light power of the photovoltaic power generation system can be accurately predicted, the uncertainty of the output power of the photovoltaic power generation system is reduced, the acceptance and digestion of the power grid to unstable energy sources can be promoted, and the method has important significance for the safety and stability of grid-connected access operation of the photovoltaic power generation system and economic dispatching of the power grid.
At present, the light power forecast is mainly based on forecast data of a meteorological source, irradiation or light power is used as an optimization target, and single machine learning model modeling is carried out.
Because each meteorological source has its own limitation and structural deviation, how to efficiently exert the advantages of multiple meteorological sources and reduce the deviation of each meteorological source is a great challenge of optical power forecasting.
In the embodiment of the application, the modeling is respectively carried out on each meteorological source, so that the advantages of each meteorological source can be exerted, the deviation of each meteorological source is reduced, and the accuracy of the optical power forecast is improved. Next, an optical power forecasting method provided in the embodiment of the present application is exemplarily described.
Please refer to fig. 1, which illustrates a schematic diagram of an optical power forecasting system according to an embodiment of the present application. The optical power forecasting system may include: a meteorological source 110, computer equipment 120, and a photovoltaic power generation enterprise 130.
The weather source 110 can issue forecast data about the weather, such as issue of predicted irradiance, temperature, rainfall, cloud cover, zenith angle, clear sky index, and weather type, among others. In the embodiment of the present application, the number of the weather sources 110 is at least two, and fig. 1 only illustrates the number of the weather sources 110 as 3. Alternatively, the weather source 110 may include: weather Research and Forecasting models (WRF), deterministic Forecasts provided by The European Central for Medium-Range Weather Forecasts (ECMWF), collective Forecasts provided by The European Central for Central Weather Forecasting center, deterministic Forecasts provided by The Weather sector of International Business machines corporation (IBM), and The like.
The computer device 120 refers to a device capable of transmitting data and performing data processing, such as a server with computing and storage capabilities, or a terminal such as a mobile phone, a tablet computer, a multimedia playing device, a wearable device, and other computer devices. Optionally, when the computer device is a server, the computer device may be one server, a server cluster composed of a plurality of servers, or one cloud computing service center. In the embodiment of the present application, the computer device 120 can obtain the forecast data provided by each of the plurality of weather sources 110, and call the forecast model to process the forecast data, so as to obtain the corrected forecast optical power, and send the corrected forecast optical power to the photovoltaic power generation enterprise 130.
The photovoltaic power generation enterprise 130 is capable of light power forecasting. Optionally, the computer device 120 may be disposed in the photovoltaic power generation enterprise 130, or may be independent from the photovoltaic power generation enterprise 130, which is not limited in this embodiment of the application.
Referring to fig. 2, a flowchart of an optical power forecasting method according to an exemplary embodiment of the present application is shown, where the embodiment of the present application is described by taking a computer device as an example, where the method is applied to the optical power forecasting system shown in fig. 1, and the method includes:
In one possible implementation, the computer device obtains n forecast data for a target time period from n weather sources, respectively.
The target time interval is a time interval in the future after the current time, and the specific duration of the target time interval is not limited in the embodiment of the present application. For example, the target time period may be one day, or half day, or a midday time period, such as 11 am to 13 pm.
A weather source refers to a weather product that can issue weather-related forecast data. In the embodiment of the application, the number of the meteorological sources is multiple, the meteorological sources support the release of multiple forecast data, and the meteorological sources and the forecast data are in one-to-one correspondence. Optionally, the weather sources include at least two of the following weather sources: deterministic forecasts provided by the european mid-term weather forecast center; an ensemble forecast provided by the mid-European weather forecast center; deterministic forecasts provided by International Business machines corporation; weather research and forecasting modes.
Illustratively, the computer device obtains first forecast data from a weather research and forecast model and second forecast data from a deterministic forecast provided by the mid-european weather forecast center. Here, "day ahead" in the day-ahead first forecast data and day-ahead second forecast data means that the target period of the forecast data is 24 hours in the future.
In one possible implementation, after acquiring n forecast data from n weather sources, the computer device invokes the forecast model to process the acquired n forecast data.
The optical power prediction layer in the prediction model is a prediction layer for outputting a reference predicted optical power. In this embodiment of the present application, the optical power prediction layer includes n machine learning processing modules, and the n machine learning modules are configured to process n pieces of prediction data respectively, so as to obtain n pieces of reference prediction optical power. Optionally, any one of the machine learning processing modules includes at least one machine learning processing model.
The optical power correction layer in the prediction model is a correction layer for processing the n reference predicted optical powers to output a corrected predicted optical power.
In one possible implementation, the computer device inputs the 1 st forecast data for the target time period into the 1 st machine learning processing module in the optical power forecast layer, to obtain the 1 st reference forecast optical power for the target time period; inputting the 2 nd forecast data aiming at the target time interval into a 2 nd machine learning processing module in the optical power forecast layer to obtain the 2 nd reference forecast optical power aiming at the target time interval; until the 1 st to nth reference forecast optical powers are obtained.
The reference predicted optical power is a reference predicted value of the predicted optical power obtained after the optical power prediction layer processes. It can be understood that, because different machine learning processing modules are adopted to process the forecast data of different weather sources, the forecast characteristics of different weather sources can be fully considered, and compared with the current processing mode of adopting a single machine learning processing module to process, the forecast accuracy of the reference forecast optical power corresponding to each weather source can be improved.
Step 208, inputting the 1 st reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer to obtain the corrected forecast optical power for the target time interval.
In a possible implementation manner, after n reference predicted optical powers are obtained by n machine learning processing modules in the optical power prediction layer, the computer device inputs the n reference predicted optical powers into the optical power correction layer to obtain a corrected predicted optical power for a target time period.
The corrected predicted optical power is a final predicted value of the predicted optical power obtained by correcting after the optical power correction layer comprehensively considers the n reference predicted optical powers. Optionally, the optical power correction layer includes at least one machine learning model.
In summary, in the method provided in this embodiment, n pieces of forecast data from n weather sources are obtained, the n pieces of forecast data are respectively processed by using n machine learning processing modules, so as to obtain n pieces of reference forecast optical power corresponding to the n weather sources, and the n pieces of reference forecast optical power are corrected by the optical power correction layer to obtain a final corrected forecast optical power, so that a processing manner of optical power forecast is implemented.
In an exemplary embodiment, in order to improve the prediction accuracy of the reference predicted optical power output by the optical power prediction layer, the optical power prediction layer is layered, and the optical power prediction layer includes: the first forecasting layer is adopted to optimize one forecasting parameter in the forecasting data to obtain a more accurate corrected forecasting parameter, and further, the corrected forecasting parameter with higher accuracy can be input into the second forecasting layer so as to forecast the optical power.
Referring to fig. 3, a flowchart of an optical power forecasting method according to an exemplary embodiment of the present application is shown, where the embodiment of the present application is described by taking a computer device as an example, where the method is applied to the optical power forecasting system shown in fig. 1, and the method includes:
step 302, acquiring n forecast data for a target time interval, where the n forecast data are from n weather sources respectively, and n is a positive integer greater than 1.
The implementation of this step refers to step 202, which is not described herein again.
In this embodiment, the optical power prediction layer includes: the first prediction layer and the second prediction layer, correspondingly, the ith machine learning processing module in the n machine learning processing modules comprises: ith present in first prediction layer1A machine learning model, and an ith present in a second prediction layer2A machine learning model. It is understood that the ith1Machine learning model and ith2The machine learning models are different machine learning models that exist at different prediction layers.
Optionally, the type of the machine learning model in the n machine learning processing modules in the optical power prediction layer includes at least one of the following types: an eXtreme Gradient boost (XGB) model; a micro Gradient Boosting Machine (LightGBM) model; a Gradient Boosting Decision Tree (GBDT) model; random Forest (RF) model; a neural network model.
In the present embodiment, the i-th1Machine learning model and ith2The machine learning models may be the same type of machine learning model or different types of machine learning models. Exemplary, i (th)1Machine learning model and ith2The machine learning models are all XGB models. Exemplary, i (th)1The machine learning model is XGB model, i2The machine learning model is a GBDT model.
In one possible implementation, the computer device enters 1 st forecast data for a target time period into 1 st forecast layer1The machine learning model is used for obtaining a 1 st correction forecast parameter aiming at a target time interval; entering forecast data for target time period at forecast 2 in first forecast layer1The machine learning model is used for obtaining a 2 nd correction forecast parameter aiming at the target time interval; until obtaining the 1 st to nth correction forecast parameters.
Wherein the ith correction forecast parameter is passed through the ith1And the machine learning model optimizes one forecast parameter in the ith forecast data to obtain data. It can be understood that, a prediction parameter in the prediction data is optimized through the machine learning model in the first prediction layer to obtain a more accurate corrected prediction parameter, so that the light power can be predicted by using the corrected prediction parameter with higher accuracy.
Optionally, the ith forecast data includes at least one of the following forecast data: the ith forecast irradiation, the ith forecast temperature and the ith forecast time tag. Optionally, the ith forecast data further includes at least one of the following forecast data: the method comprises the following steps of (1) forecasting rainfall, forecasting cloud quality, forecasting zenith angle, forecasting morning and afternoon marker, forecasting clear sky index and forecasting weather type.
Illustratively, the mandatory data in the ith forecast data includes: the ith forecast irradiation, the ith forecast temperature and the ith forecast time label, wherein the selectable data comprises: the method comprises the following steps of (1) forecasting rainfall, forecasting cloud quality, forecasting zenith angle, forecasting morning and afternoon marker, forecasting clear sky index and forecasting weather type.
Wherein, the forecast irradiation refers to the radiation energy of the solar radiation reaching the earth surface in unit area in the target time interval after the absorption, scattering, emission and other actions of the atmosphere, and the unit is watt/square meter (W/m)2). The forecast time label refers to the corresponding forecast time within the target time period. The forecast clear sky index is used for describing the influence of the atmosphere on the solar short wave radiation, and refers to the sun which is incident to the horizontal plane in a target time periodThe ratio of total radiation to astronomical radiation in joules per square meter (J/m)2). The weather type refers to the type of weather in the target period, such as: rainy, sunny, cloudy, etc. The forecast temperature refers to a range of temperatures in degrees celsius (° c) over a target period. The forecasted rainfall refers to a depth in millimeters (mm) at which rainfall accumulates on the water surface within a target period. The forecast cloud cover refers to the number of cloud-obscuring views of the sky in the target time period. The forecast zenith angle refers to the angular distance, in degrees (°), between the celestial body and the zenith over the target time period. The forecast morning and afternoon labels refer to the morning and afternoon attributes of the time within the target time period.
In one possible implementation, the computer device obtains two types of data: inputting the data of the two types into the ith correction forecast parameter in the second forecast layer aiming at the target time interval after the optimization processing of the first forecast layer and the ith intermediate forecast data aiming at the target time interval2The model is machine learned, resulting in the ith reference forecast optical power for the target time period.
Wherein the ith intermediate forecast data is in the ith forecast data for inputting the ith forecast data in the second forecast layer2Data of a machine learning model. That is, the ith intermediate forecast data is part or all of the ith forecast data acquired from the weather source.
Optionally, the ith correction prediction parameter includes an ith correction prediction irradiation. It is understood that the accuracy of the predicted irradiance has a large influence on the accuracy of the predicted optical power, and therefore the description is given here as an example in which the ith correction prediction parameter includes the ith correction prediction irradiance. That is, in step 306, the computer device inputs the forecast data into the first forecast layer, and processes the forecast data using the machine learning model in the first forecast layer with the optimal forecast exposure as the target, so as to obtain a more accurate corrected forecast exposure.
Optionally, the ith intermediate forecast data includes at least one of the following forecast data: the ith forecast exposure and the ith forecast time tags. Optionally, the ith intermediate forecast data further includes at least one of the following forecast data: an ith forecast clear sky index and an ith weather type.
Illustratively, the mandatory data in the ith intermediate forecast data includes: the ith forecast irradiation and ith forecast time labels, optional data: including the ith forecast clear sky index and the ith weather type.
It is understood that, after understanding the technical solutions provided by the embodiments of the present application, a person skilled in the art will easily think that the number of the first prediction layers may be multiple, and multiple first prediction layers are adopted to optimize multiple prediction parameters in the prediction data, so as to obtain more accurate multiple corrected prediction parameters, so as to complete all or part of the functions described in the embodiments of the present application, but all of the functions should fall within the scope of the present application.
The implementation of this step refers to the above step 208, and is not described herein again.
In summary, the method provided in this embodiment layers the optical power prediction layer, where the optical power prediction layer includes: the first forecasting layer is adopted to optimize one forecasting parameter in the forecasting data to obtain a more accurate corrected forecasting parameter, so that the corrected forecasting parameter with higher accuracy can be input into the second forecasting layer, and the optical power with higher forecasting accuracy is predicted.
In an exemplary embodiment, the optical power correction layer includes a regression model.
Referring to fig. 4, a flowchart of an optical power forecasting method according to an exemplary embodiment of the present application is shown, where the embodiment of the present application is described by taking a computer device as an example, where the method is applied to the optical power forecasting system shown in fig. 1, and the method includes:
The implementation of this step refers to step 202, which is not described herein again.
The implementation of this step refers to step 204, which is not described herein again.
The implementation of this step refers to step 206, which is not described herein again.
In a possible implementation manner, after n reference forecast optical powers are obtained by n machine learning processing modules in the optical power forecast layer, the computer device inputs the n reference forecast optical powers into a regression model in the optical power correction layer to perform regression algorithm processing, so as to obtain a corrected forecast optical power for a target time period.
Optionally, the type of the regression model includes at least one of the following types: a Linear Regression (Linear Regression) model; ridge (Ridge) regression model; the Least absolute value shrinkage and Selection (LASSO) regression model.
In summary, in the method provided in this embodiment, the optical power correction layer includes a regression model for performing regression algorithm processing on the n reference predicted optical powers output by the optical power prediction layer, so as to synthesize the n reference predicted optical powers, obtain a final corrected predicted optical power, and improve the accuracy of optical power prediction.
Hereinafter, the optical power forecasting method provided by the present application is exemplarily described with reference to the following embodiments.
In this embodiment, the prediction model includes three layers, a first layer of the prediction model is the first prediction layer in this embodiment, a second layer of the prediction model is the second prediction layer in this embodiment, and a third layer of the prediction model is the optical power correction layer in this embodiment.
As shown in fig. 5, n XGB models are included in the first layer of the prediction model, n being a positive integer greater than 1, the XGB models in the first layer of the prediction model aiming at optimizing the prediction irradiation. The meteorological sources 1 to n are n meteorological sources, and each meteorological source inputs corresponding forecast data to the corresponding XGB model, such as: the meteorological source 1 inputs 1 st forecast data into a corresponding XGB model; and (4) inputting nth forecast data into the corresponding XGB model by the meteorological source n. Each XGB model outputs a corrected forecast exposure, such as: outputting the 1 st corrected forecast irradiation by the XGB model corresponding to the meteorological source 1; and outputting the nth corrected forecast irradiation by the XGB model corresponding to the meteorological source n.
Also included in the second layer of the prediction model are n XGB models, the XGB models in the second layer of the prediction model aiming at optimizing the predicted optical power. Input data for the ith XGB model in the second layer of the forecasting model includes: and the ith corrected forecast irradiation obtained by the first layer of the forecast model and ith intermediate forecast data in the ith forecast data corresponding to the meteorological source i. Such as: input data for the 1 st XGB model in the second layer of the forecasting model includes: 1, correcting and forecasting irradiation and 1 st intermediate forecasting data; the input data for the nth XGB model in the second layer of the forecasting model comprises: the nth corrected forecast irradiation and nth intermediate forecast data. Each XGB model outputs a reference predicted optical power, such as: the XGB model corresponding to the meteorological source 1 outputs the 1 st reference forecast optical power; and the XGB model corresponding to the meteorological source n outputs the nth reference forecast optical power.
And the third layer of the forecasting model comprises 1 linear regression model, and the linear regression model is used for performing linear regression operation on n reference forecasting light powers respectively corresponding to the n meteorological sources obtained by the second layer of the forecasting model to obtain the final corrected forecasting light power as a result of light power forecasting.
It is to be understood that the above method embodiments may be implemented individually or in combination, and the present application is not limited thereto.
The following are embodiments of the apparatus of the present application, and for details that are not described in detail in the embodiments of the apparatus, reference may be made to corresponding descriptions in the above method embodiments, and details are not described herein again.
Fig. 6 shows a schematic structural diagram of an optical power forecasting apparatus provided by an exemplary embodiment of the present application. The apparatus may be implemented as all or part of a computer device in software, hardware or a combination of both, the apparatus comprising: a forecast data acquisition module 601, a model calling module 602, an optical power forecasting module 603 and an optical power correction module 604;
the forecast data acquiring module 601 is configured to acquire n pieces of forecast data for a target time period, where the n pieces of forecast data are respectively from n weather sources, and n is a positive integer greater than 1;
the model invoking module 602 is configured to invoke a forecasting model, where the forecasting model includes: the device comprises an optical power prediction layer and an optical power correction layer, wherein the optical power prediction layer comprises n machine learning processing modules;
the optical power forecasting module 603 is configured to input ith forecast data for the target time interval into an ith machine learning processing module in the optical power forecasting layer, so as to obtain an ith reference forecast optical power for the target time interval, where i is a positive integer no greater than n;
the optical power correction module 604 is configured to input the 1 st reference predicted optical power to the nth reference predicted optical power for the target time interval into the optical power correction layer, so as to obtain a corrected predicted optical power for the target time interval.
In an alternative embodiment, the optical power prediction layer comprises: the first prediction layer and the second prediction layer, the ith machine learning processing module in the optical power prediction layer includes: the first isIth in forecast layer1Machine learning model and ith in the second prediction layer2A machine learning model;
the optical power forecasting module 603 is configured to input ith forecast data for the target time period into the ith forecast layer1The machine learning model is used for obtaining the ith correction forecast parameter aiming at the target time interval; inputting the ith modified forecast parameter and ith intermediate forecast data for the target time period into the ith forecast layer2A machine learning model to obtain an ith reference forecast optical power for the target time period, the ith intermediate forecast data being in the ith forecast data for inputting the ith in the second forecast layer2Data of a machine learning model.
In an alternative embodiment, the ith correction prediction parameter comprises an ith correction prediction irradiance.
In an alternative embodiment, the ith intermediate forecast data comprises at least one of the following forecast data: the ith forecast exposure and the ith forecast time tags.
In an optional embodiment, the ith intermediate forecast data further comprises at least one of the following forecast data: an ith forecast clear sky index and an ith weather type.
In an alternative embodiment, the ith forecast data includes at least one of the following forecast data: the ith forecast irradiation, the ith forecast temperature and the ith forecast time tag.
In an optional embodiment, the ith forecast data further comprises at least one of the following forecast data: the method comprises the following steps of (1) forecasting rainfall, forecasting cloud quality, forecasting zenith angle, forecasting morning and afternoon marker, forecasting clear sky index and forecasting weather type.
In an optional embodiment, the optical power correction layer comprises a regression model;
the optical power correction module 604 is configured to input the first to nth reference predicted optical powers for the target time interval into the regression model in the optical power correction layer for performing regression algorithm processing, so as to obtain the corrected predicted optical power for the target time interval.
In an alternative embodiment, the type of the regression model includes at least one of the following types: a linear regression model; a ridge regression model; the minimum absolute value shrinks and the regression model is selected.
In an alternative embodiment, the meteorological sources include at least two of the following meteorological sources: deterministic forecasts provided by the european mid-term weather forecast center; an ensemble forecast provided by the mid-European weather forecast center; deterministic forecasts provided by International Business machines corporation; weather research and forecasting modes.
In an optional embodiment, the type of the machine learning model in the n machine learning processing modules in the optical power prediction layer includes at least one of the following types: an extreme gradient lifting model; a micro-gradient lifting machine model; a gradient boosting decision tree model; a random forest model; a neural network model.
Fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application. Specifically, the method comprises the following steps: the computer device 700 includes a Central Processing Unit (CPU) 701, a system Memory 704 including a Random Access Memory (RAM) 702 and a Read-Only Memory (ROM) 703, and a system bus 705 connecting the system Memory 704 and the CPU 701. The computer device 700 also includes a basic input/output system (I/O system) 706 for facilitating information transfer between devices within the computer, and a mass storage device 707 for storing an operating system 713, application programs 714, and other program modules 715.
The basic input/output system 706 includes a display 708 for displaying information and an input device 709, such as a mouse, keyboard, etc., for user account entry of information. Wherein the display 708 and the input device 709 are connected to the central processing unit 701 through an input/output controller 710 connected to the system bus 705. The basic input/output system 706 may also include an input/output controller 710 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, an input/output controller 710 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 707 is connected to the central processing unit 701 through a mass storage controller (not shown) connected to the system bus 705. The mass storage device 707 and its associated computer-readable media provide non-volatile storage for the computer device 700. That is, the mass storage device 707 may include a computer-readable medium (not shown) such as a hard disk or a Compact Disc-Only Memory (CD-ROM) drive.
Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash Memory or other solid state Memory technology, CD-ROM, Digital Versatile Disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage, or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 704 and mass storage device 707 described above may be collectively referred to as memory.
According to various embodiments of the present application, the computer device 700 may also operate as a remote computer connected to a network via a network, such as the Internet. That is, the computer device 700 may be connected to the network 712 through the network interface unit 711 connected to the system bus 705, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 711.
The present application further provides a computer-readable storage medium, having at least one instruction, at least one program, code set, or set of instructions stored therein, which is loaded and executed by a processor to implement the optical power forecasting method provided by the above method embodiments.
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the optical power forecasting method provided in the above-mentioned alternative implementation.
It should be understood that reference to "a plurality" herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
It will be understood by those skilled in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The present application is intended to cover various modifications, alternatives, and equivalents, which may be included within the spirit and scope of the present application.
Claims (10)
1. An optical power forecasting method, the method comprising:
acquiring n forecast data aiming at a target time interval, wherein the n forecast data are respectively from n meteorological sources, and n is a positive integer greater than 1;
invoking a forecasting model, the forecasting model comprising: the device comprises an optical power prediction layer and an optical power correction layer, wherein the optical power prediction layer comprises n machine learning processing modules;
inputting ith forecast data aiming at the target time interval into an ith machine learning processing module in the optical power forecasting layer to obtain ith reference forecast optical power aiming at the target time interval, wherein i is a positive integer not greater than n;
inputting the 1 st reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer to obtain a corrected forecast optical power for the target time interval.
2. The method of claim 1, wherein the optical power prediction layer comprises: the first prediction layer and the second prediction layer, the ith machine learning processing module in the optical power prediction layer includes: ith in the first prediction layer1Machine learning model and ith in the second prediction layer2A machine learning model;
inputting ith forecast data for the target time period into an ith machine learning model in the optical power forecast layer to obtain an ith reference forecast optical power for the target time period, including:
entering ith forecast data for the target time period into the ith forecast layer1The machine learning model is used for obtaining the ith correction forecast parameter aiming at the target time interval;
inputting the ith modified forecast parameter and ith intermediate forecast data for the target time period into the ith forecast layer2A machine learning model to obtain an ith reference forecast optical power for the target time period, the ith intermediate forecast data being in the ith forecast data for inputting the ith in the second forecast layer2Data of a machine learning model.
3. The method of claim 2,
the ith correction forecast parameter comprises ith correction forecast irradiation.
4. The method according to claim 2, wherein the ith intermediate forecast data comprises at least one of the following forecast data:
the ith forecast exposure and the ith forecast time tags.
5. The method according to claim 4, wherein the ith intermediate forecast data further comprises at least one of the following forecast data:
an ith forecast clear sky index and an ith weather type.
6. The method according to any one of claims 1 to 5, wherein the ith forecast data comprises at least one of the following forecast data:
the system comprises an ith forecast irradiation, an ith forecast temperature, an ith forecast time label, an ith forecast rainfall, an ith forecast cloud cover, an ith forecast zenith angle, an ith forecast morning and afternoon mark, an ith forecast clear sky index and an ith weather type.
7. The method of any of claims 1 to 5, wherein the optical power correction layer comprises a regression model;
inputting the first reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer to obtain a corrected forecast optical power for the target time interval, including:
inputting the first reference forecast optical power to the nth reference forecast optical power for the target time interval into the regression model in the optical power correction layer for regression algorithm processing, and obtaining the corrected forecast optical power for the target time interval.
8. An optical power prediction apparatus, characterized in that the apparatus comprises: the device comprises a forecast data acquisition module, a model calling module, an optical power forecasting module and an optical power correcting module;
the forecast data acquisition module is used for acquiring n pieces of forecast data aiming at a target time interval, wherein the n pieces of forecast data are respectively from n meteorological sources, and n is a positive integer greater than 1;
the model calling module is used for calling a forecasting model, and the forecasting model comprises: the device comprises an optical power prediction layer and an optical power correction layer, wherein the optical power prediction layer comprises n machine learning processing modules;
the optical power forecasting module is used for inputting ith forecast data aiming at the target time interval into an ith machine learning processing module in the optical power forecasting layer to obtain ith reference forecast optical power aiming at the target time interval, wherein i is a positive integer not greater than n;
the optical power correction module is configured to input the 1 st reference forecast optical power to the nth reference forecast optical power for the target time interval into the optical power correction layer, so as to obtain a corrected forecast optical power for the target time interval.
9. A computer device, characterized in that the computer device comprises: a processor and a memory, said memory having stored therein at least one instruction, at least one program, set of codes or set of instructions, which is loaded and executed by said processor to implement the optical power forecasting method according to any of claims 1 to 7.
10. A computer readable storage medium, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the storage medium, loaded and executed by a processor to implement the optical power forecasting method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110851492.5A CN113610287A (en) | 2021-07-27 | 2021-07-27 | Optical power forecasting method and device, computer equipment and storage medium |
| PCT/SG2022/050533 WO2023009070A2 (en) | 2021-07-27 | 2022-07-26 | Method and apparatus for forecasting optical power, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110851492.5A CN113610287A (en) | 2021-07-27 | 2021-07-27 | Optical power forecasting method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610287A true CN113610287A (en) | 2021-11-05 |
Family
ID=78305622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110851492.5A Pending CN113610287A (en) | 2021-07-27 | 2021-07-27 | Optical power forecasting method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113610287A (en) |
| WO (1) | WO2023009070A2 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079306A (en) * | 2022-05-23 | 2022-09-20 | 远景智能国际私人投资有限公司 | Lightning forecasting method, device, equipment, storage medium and computer program product |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101769788A (en) * | 2009-12-29 | 2010-07-07 | 青海国泰节能技术研究院 | Method for forecasting optical output power and electric energy production of photovoltaic power station |
| CN102411729A (en) * | 2011-11-04 | 2012-04-11 | 国电南京自动化股份有限公司 | Wind power prediction method based on adaptive linear logic network |
| CN109543721A (en) * | 2018-11-05 | 2019-03-29 | 中国科学院寒区旱区环境与工程研究所 | A kind of solar irradiance ultra-short term forecasting procedure under fine with occasional clouds weather condition |
| CN110263998A (en) * | 2019-06-19 | 2019-09-20 | 大唐（赤峰）新能源有限公司 | Multi-source numerical weather forecast set bilayer modification method |
| CN111091138A (en) * | 2019-11-14 | 2020-05-01 | 远景智能国际私人投资有限公司 | Irradiation forecast processing method and stacked generalization model training method and device |
| CN111369070A (en) * | 2020-03-13 | 2020-07-03 | 西安理工大学 | Envelope clustering-based multimode fusion photovoltaic power prediction method |
| CN111507512A (en) * | 2020-04-10 | 2020-08-07 | 阳光电源股份有限公司 | Method and device for correcting photovoltaic ultra-short-term predicted power |
| WO2021080107A1 (en) * | 2019-10-22 | 2021-04-29 | (주)한국해양기상기술 | Learning method and testing method for generating high-resolution weather and climate data, and testing method and testing apparatus using same |
| CN112906757A (en) * | 2021-01-29 | 2021-06-04 | 广东晨兴智能科技有限公司 | Model training method, optical power prediction method, device, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169683A (en) * | 2017-06-30 | 2017-09-15 | 上海电力学院 | A kind of grid-connected photovoltaic power station short term power combination forecasting method of variable weight coefficient |
| CN109583467A (en) * | 2018-10-11 | 2019-04-05 | 中国电力科学研究院有限公司 | A kind of electric power meteorological data fusion method and system |
| CN112418558B (en) * | 2020-12-07 | 2022-03-11 | 天津大学 | Total radiation correction method based on multi-source meteorological forecast |
| CN113408785B (en) * | 2021-05-20 | 2023-04-07 | 上海晨翘智能科技有限公司 | Method, device, equipment and storage medium for predicting optical power |
-
2021
- 2021-07-27 CN CN202110851492.5A patent/CN113610287A/en active Pending
-
2022
- 2022-07-26 WO PCT/SG2022/050533 patent/WO2023009070A2/en unknown
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101769788A (en) * | 2009-12-29 | 2010-07-07 | 青海国泰节能技术研究院 | Method for forecasting optical output power and electric energy production of photovoltaic power station |
| CN102411729A (en) * | 2011-11-04 | 2012-04-11 | 国电南京自动化股份有限公司 | Wind power prediction method based on adaptive linear logic network |
| CN109543721A (en) * | 2018-11-05 | 2019-03-29 | 中国科学院寒区旱区环境与工程研究所 | A kind of solar irradiance ultra-short term forecasting procedure under fine with occasional clouds weather condition |
| CN110263998A (en) * | 2019-06-19 | 2019-09-20 | 大唐（赤峰）新能源有限公司 | Multi-source numerical weather forecast set bilayer modification method |
| WO2021080107A1 (en) * | 2019-10-22 | 2021-04-29 | (주)한국해양기상기술 | Learning method and testing method for generating high-resolution weather and climate data, and testing method and testing apparatus using same |
| CN111091138A (en) * | 2019-11-14 | 2020-05-01 | 远景智能国际私人投资有限公司 | Irradiation forecast processing method and stacked generalization model training method and device |
| CN111369070A (en) * | 2020-03-13 | 2020-07-03 | 西安理工大学 | Envelope clustering-based multimode fusion photovoltaic power prediction method |
| CN111507512A (en) * | 2020-04-10 | 2020-08-07 | 阳光电源股份有限公司 | Method and device for correcting photovoltaic ultra-short-term predicted power |
| CN112906757A (en) * | 2021-01-29 | 2021-06-04 | 广东晨兴智能科技有限公司 | Model training method, optical power prediction method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杨银国;李博;谭嫣;朱誉;熊欢;: "改进型小波神经网络在风光功率预测中的应用研究", 信息技术, no. 02, 20 February 2020 (2020-02-20), pages 106 - 110 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079306A (en) * | 2022-05-23 | 2022-09-20 | 远景智能国际私人投资有限公司 | Lightning forecasting method, device, equipment, storage medium and computer program product |
| CN115079306B (en) * | 2022-05-23 | 2023-12-05 | 远景智能国际私人投资有限公司 | Lightning prediction method, device, apparatus, storage medium and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023009070A3 (en) | 2023-05-25 |
| WO2023009070A2 (en) | 2023-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Al-Dahidi et al. | Assessment of artificial neural networks learning algorithms and training datasets for solar photovoltaic power production prediction | |
| Kim et al. | Daily prediction of solar power generation based on weather forecast information in Korea | |
| Dvorkin et al. | Wind generation as a reserve provider | |
| Narayan et al. | Exploring the boundaries of Solar Home Systems (SHS) for off-grid electrification: Optimal SHS sizing for the multi-tier framework for household electricity access | |
| Peng et al. | Uncertainty management in power system operation | |
| US20150241892A1 (en) | Predictive smart grid re-structuring based on expected load and power generation | |
| Amjady et al. | A new hybrid iterative method for short‐term wind speed forecasting | |
| Rahimiyan et al. | Real‐time energy management of a smart virtual power plant | |
| Xiong et al. | Two‐stage adjustable robust optimisation for unit commitment under uncertainty | |
| Akhlaghi et al. | Efficient operation of residential solar panels with determination of the optimal tilt angle and optimal intervals based on forecasting model | |
| US20220376499A1 (en) | System and method for load and source forecasting for increasing electrical grid component longevity | |
| Shi et al. | Multistage robust energy management for microgrids considering uncertainty | |
| US9773303B2 (en) | Prediction system for short-term solar irradiance and method for operating the same | |
| Khare et al. | Optimal sizing of a grid integrated solar photovoltaic system | |
| CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
| Saberi et al. | Probabilistic congestion driven network expansion planning using point estimate technique | |
| CN113570126A (en) | Method, device and system for predicting power generation power of photovoltaic power station | |
| CN113610287A (en) | Optical power forecasting method and device, computer equipment and storage medium | |
| CN115730755A (en) | Method, device, terminal equipment and medium for realizing path planning of double-carbon target | |
| Bai et al. | Improved Markov‐chain‐based ultra‐short‐term PV forecasting method for enhancing power system resilience | |
| Nikoobakht et al. | Integrated transmission and storage systems investment planning hosting wind power generation: continuous‐time hybrid stochastic/robust optimisation | |
| US11842303B2 (en) | Method for processing irradiation forecast, method for training stacked generalization model, and apparatuses thereof | |
| CN113408785B (en) | Method, device, equipment and storage medium for predicting optical power | |
| Zhu et al. | Multi‐time‐scale robust economic dispatching method for the power system with clean energy | |
| Hasan et al. | Neural network-based solar irradiance forecast for peak load management of grid-connected microgrid with photovoltaic distributed generation |
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 |