CN113689057A - Photovoltaic power generation power prediction method and device - Google Patents
Photovoltaic power generation power prediction method and device Download PDFInfo
- Publication number
- CN113689057A CN113689057A CN202111237428.4A CN202111237428A CN113689057A CN 113689057 A CN113689057 A CN 113689057A CN 202111237428 A CN202111237428 A CN 202111237428A CN 113689057 A CN113689057 A CN 113689057A
- Authority
- CN
- China
- Prior art keywords
- irradiance
- power generation
- real
- daily
- power
- 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
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to the field of photovoltaic power generation, and particularly discloses a method and a device for predicting photovoltaic power generation power, wherein the method comprises the following steps: the method comprises the steps of obtaining real-time photovoltaic data and weather forecast information of a power supply station, obtaining weather type information corresponding to daily irradiance integral according to real-time irradiance, selecting a photovoltaic power generation power prediction model based on the weather forecast information, inputting daily installed capacity and real-time irradiance of a preset period into the selected photovoltaic power generation power prediction model to obtain photovoltaic power generation power at a moment, obtaining historical similar power generation power based on historical installed capacity, daily installed capacity and real-time irradiance, calculating the combination of the photovoltaic power generation power at the moment and the historical similar power generation power to obtain predicted daily power generation, and calculating the percentage of the predicted daily power generation and the real daily power generation to obtain the prediction accuracy of the photovoltaic power generation power. The method for predicting the photovoltaic power generation power realizes the high-efficiency and high-accuracy prediction of the photovoltaic power generation power.
Description
Technical Field
The invention relates to the field of photovoltaic power generation, in particular to a method and a device for predicting photovoltaic power generation power.
Background
Photovoltaic power generation is a novel clean energy, and by converting solar energy into electric energy, dependence of human beings on fossil energy is effectively reduced, and meanwhile, pollution emission caused by combustion of the fossil energy and the like is also reduced, so that a safe and reliable clean energy is provided. However, due to the data transmission problem and the stability problem of the photovoltaic monitoring points, the data quality cannot be guaranteed, so that the real-time power generation power condition of the medium-voltage photovoltaic cannot be mastered in real time, and the management and the safety control of the power grid are not facilitated.
At present, the photovoltaic real-time prediction method mainly comprises a time sequence method, a linear regression method, an LSTM algorithm and the like. For the time series method, although the model is simple, the overall prediction ability is not high. The simple linear regression method has small calculation amount, but the prediction precision needs to be improved. The LSTM algorithm, the most deep learning algorithm used for photovoltaic power generation prediction, is an improved version of RNN, and has the problems of long training time consumption, large required training data amount, large calculation overhead, high hardware requirement and the like although the prediction precision is high, so that the LSTM algorithm is subject to problems.
Therefore, in order to improve the accuracy and efficiency of predicting the photovoltaic power generation power and solve the technical problems of low accuracy and low efficiency of predicting the photovoltaic power generation power at present, a method for predicting the photovoltaic power generation power is urgently needed to be constructed.
Disclosure of Invention
The invention provides a method and a device for predicting photovoltaic power generation power, which solve the technical problems of low accuracy and low efficiency of predicting the photovoltaic power generation power at present.
In a first aspect, the present invention provides a method for predicting photovoltaic power generation power, including:
acquiring real-time photovoltaic data and weather forecast information of an area to which power supply is subordinate; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
calculating historical similar generating power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity;
the photovoltaic power generation power at the moment and the historical similar power generation power are combined and calculated to obtain the predicted daily power generation amount;
and calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
Optionally, obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs, including:
calculating to obtain the average irradiance in hours according to the real-time irradiance of the area to which the power supply station belongs;
summarizing the hourly average irradiance of the area to which the power supply is subordinate to obtain a daily irradiance integral of the area to which the power supply is subordinate;
and dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral.
Optionally, selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate region into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate region, where the method includes:
modeling is carried out on the basis of the weather type information by combining the hourly average irradiance and the historical installed capacity every day to obtain photovoltaic power generation power prediction models of various weather types;
selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information according to the weather forecast information;
and inputting the daily installed capacity and the real-time irradiance of the first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area at the moment.
Optionally, based on the weather type information, modeling is performed in combination with the hourly average irradiance and the historical installed capacity for each day, so as to obtain photovoltaic power generation power prediction models of multiple different weather types, including:
obtaining each characteristic model to be fitted;
adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and training based on the regularized polynomial fitting algorithm model by combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the different weather type information.
Optionally, calculating a historical similar generated power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity includes:
calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the power supply subordinate region, the historical installed capacity and the daily installed capacity;
and selecting a plurality of pieces of historical real-time irradiance data which are closest to the real-time irradiance of the area to which the power supply belongs from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data.
In a second aspect, the present invention provides a device for predicting photovoltaic power generation, including:
the acquisition module is used for acquiring real-time photovoltaic data and weather forecast information of an area to which the power supply station belongs; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
the weather module is used for obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
the calculation module is used for selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed on the basis of the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
the history module is used for calculating to obtain historical similar generating power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity;
the prediction module is used for calculating the photovoltaic power generation power at the moment and the historical similar power generation power in a combined mode to obtain the predicted daily power generation amount;
and the precision module is used for calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
Optionally, the weather module comprises:
the irradiation submodule is used for calculating the average irradiance in hours according to the real-time irradiance of the area to which the power supply belongs;
the integration sub-module is used for summarizing the average hourly irradiance of the area to which the power supply station belongs to obtain a daily irradiance integral of the area to which the power supply station belongs;
and the weather sub-module is used for dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral.
Optionally, the calculation module comprises:
the modeling submodule is used for modeling by combining the hourly average irradiance and the historical installed capacity of each day based on the weather type information to obtain photovoltaic power generation power prediction models of various weather types;
the selecting submodule is used for selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information according to the weather forecast information;
and the input submodule is used for inputting the daily installed capacity and the real-time irradiance of the first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area.
Optionally, the modeling submodule includes:
the fitting unit is used for acquiring various feature models to be fitted;
the adding unit is used for adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and the training unit is used for training based on the regularized polynomial fitting algorithm model and combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the various weather type information.
Optionally, the history module comprises:
the history submodule is used for calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the area to which the power supply station belongs, the historical installed capacity and the daily installed capacity;
and the similarity submodule is used for selecting a plurality of pieces of historical real-time irradiance data which are closest to the real-time irradiance of the area to which the power supply belongs from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data.
According to the technical scheme, the invention has the following advantages: the invention provides a method for predicting photovoltaic power generation power, which comprises the steps of obtaining real-time photovoltaic data and weather forecast information of a power supply subordinate region, wherein the real-time photovoltaic data comprises real-time irradiance of the power supply subordinate region, daily installed capacity and historical installed capacity of a medium-voltage side of the power supply subordinate region, obtaining daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the power supply subordinate region, selecting a photovoltaic power generation power prediction model which is corresponding to the weather forecast information and is constructed on the basis of the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply subordinate region into the selected photovoltaic power generation power prediction model, and calculating the photovoltaic power generation power at the medium-voltage side of the power supply subordinate region, based on the real-time irradiance, the historical installed capacity and the daily installed capacity of the power supply station subordinate area, historical similar generating power is obtained through calculation, the photovoltaic power generation power at the moment and the historical similar generating power are combined and calculated to obtain predicted daily generated energy, the percentage of the predicted daily generated energy to the real daily generated energy is calculated to obtain photovoltaic power prediction accuracy, the technical problems of low accuracy and low efficiency of the photovoltaic power prediction existing at present are solved through the photovoltaic power prediction method, and the photovoltaic power prediction is efficient and accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating a first embodiment of a method for predicting photovoltaic power generation according to the present invention;
FIG. 2 is a flowchart illustrating steps of a second embodiment of a method for predicting photovoltaic power generation according to the present invention;
fig. 3 is a block diagram of a photovoltaic power generation power prediction apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for predicting photovoltaic power generation power, which are used for solving the technical problems of low accuracy and low efficiency of predicting the photovoltaic power generation power at present.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a first embodiment, referring to fig. 1, fig. 1 is a flowchart of a first embodiment of a method for predicting photovoltaic power generation according to the present invention, including:
step S101, acquiring real-time photovoltaic data and weather forecast information of an area to which power supply is subordinate; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
it should be noted that irradiance is irradiance, which is a radiant flux per unit area of an irradiated surface. The unit is kW/m2。
The installed capacity is installed capacity of a power plant, refers to the sum of rated power of all generator sets installed in the power plant, is one of main indexes representing the construction scale and the power production capacity of the power plant, and is in kW.
The daily installed capacity is the installed capacity of the power plant on the same day, and refers to the sum of the rated power of all the generator sets installed on the power plant on the same day.
The historical installed capacity is the installed capacity of the power plant recorded in the history every day, and refers to the sum of all the rated powers of the generator sets installed in the past every day recorded by the power plant.
Step S102, obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
step S103, selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
step S104, calculating to obtain historical similar generating power based on the real-time irradiance of the power supply subordinate region, the historical installed capacity and the daily installed capacity;
step S105, the photovoltaic power generation at the moment and the historical similar power generation power are combined and calculated to obtain the predicted daily power generation amount;
and step S106, calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
The method for predicting the photovoltaic power generation power provided by the embodiment of the invention obtains real-time photovoltaic data and weather forecast information of an area to which power is supplied, wherein the real-time photovoltaic data comprises real-time irradiance of the area to which the power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied, obtains daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power is supplied, selects a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputs the daily installed capacity and the real-time irradiance of a first preset period in the area to which the power is supplied to the selected photovoltaic power generation power prediction model, and calculates the photovoltaic power generation power at the medium-voltage side of the area to which the power is supplied, based on the real-time irradiance, the historical installed capacity and the daily installed capacity of the power supply station subordinate area, historical similar generating power is obtained through calculation, the photovoltaic power generation power at the moment and the historical similar generating power are combined and calculated to obtain predicted daily generated energy, the percentage of the predicted daily generated energy to the real daily generated energy is calculated to obtain photovoltaic power prediction accuracy, the technical problems of low accuracy and low efficiency of the photovoltaic power prediction existing at present are solved through the photovoltaic power prediction method, and the photovoltaic power prediction is efficient and accurate.
In a second embodiment, referring to fig. 2, fig. 2 is a flowchart illustrating a method for predicting photovoltaic power generation according to the present invention, including:
step S201, acquiring real-time photovoltaic data and weather forecast information of an area where a power supply station is subordinate; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
step S202, calculating to obtain the average irradiance in hours according to the real-time irradiance of the area to which the power supply belongs;
in the embodiment of the invention, the hour average irradiance is calculated according to the real-time irradiance of the area to which the power supply belongs.
In particular implementations, the number of irradiance levels of each power supplyAccordingly, reference is made to the real-time irradiance of its corresponding slave region. For example: and a power supply station id 1000110012, wherein the corresponding area irradiance is an A area. I.e., irradiance data for power supply id 1000110012, is taken from the irradiance of the a-region. Therefore, the power supply station id 1000110012, 12/month/26/8 in 2020: 15-9: irradiance at the time of 00 is 87kW/m respectively2，74kW/m2，111kW/m2，133kW/m2Averaging to obtain the hour average irradiance of 101.25kW/m in the period2。
In addition, the medium-voltage-side small-power generation amount of the area to which the power supply is subordinate can also be calculated from the acquired data. On the medium-voltage side of the power supply station, the minimum time interval for the user electricity measuring point is 1 hour and 15 minutes. And according to the summary direction of the measuring points- > users- > power supply stations, from bottom to top, summarizing the small power generation amount of the medium-voltage side of the area which is subordinate to the power supply stations. For example: first, under the medium-voltage user id 306000193760024, all the measuring points id include 26969850669, 26969850670 and 26969850671, and the electricity quantity difference values of the hour meter of the 3 measuring points are summarized in units of hours to obtain the electricity generation quantity of the user per hour. Then, in the power supply station id 1000110012, all the medium-voltage-side user ids contain 306000193760024, and the medium-voltage-side small power generation amount of the power supply station can be obtained by summarizing the small power generation amounts thereof.
The hourly power generation can be converted into the hourly power generation. And as no electricity is generated at night, only 6-18 days of data are used for training the model. By the method, the extreme relation between irradiance and photovoltaic power generation amount in early morning and evening can be prevented from influencing training, and the prediction accuracy and robustness of the model obtained by training are improved. On the basis of the field meter, photovoltaic power generation power data do not exist, and only the meter value of the generated energy is available. Therefore, the calculation formula of the photovoltaic power generation (photovoltaic power generation) is as follows:
the difference value of the generated energy of the meter is the difference value of one time period of the generated energy of the meter, and the time interval is one hour.
Since the unit of the power generation amount is kW · h, here the photovoltaic hour power generation power is numerically equal to the photovoltaic hour power generation amount.
Step S203, summarizing the average hourly irradiance of the area to which the power supply station belongs to obtain a daily irradiance integral of the area to which the power supply station belongs;
in an embodiment of the invention, the daily irradiance integral of the area to which the power supply is dependent is calculated.
In a specific implementation, the hourly irradiance of the area to which the power supply station belongs is summarized in units of days to obtain a daily irradiance integral of the area to which the power supply station belongs. For example: the daily irradiance integral of the power supply station id 1000110012 in 12-month and 26-day 2020 is 2579kW/m2。
Step S204, dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral;
in the embodiment of the invention, the weather conditions are divided according to the daily irradiance integral to obtain the weather type information corresponding to the daily irradiance integral.
In a specific implementation, the sun irradiance is divided into sunny, cloudy and rainy days according to the integral of the daily irradiance. For example: setting the daily irradiance integral threshold value of different weather to be lower than 2000kW/m by referring to local historical weather and historical daily irradiance integral2In rainy days, 2000kW/m2~4000kW/m2Is cloudy and higher than 4000kW/m2It is a sunny day.
Step S205, modeling is carried out based on the weather type information by combining the hourly average irradiance and the historical installed capacity every day, and photovoltaic power generation power prediction models of various weather types are obtained;
in an optional embodiment, based on the weather type information, modeling is performed in combination with the hourly average irradiance and the historical installed capacity for each day, and a photovoltaic power generation power prediction model of a plurality of different weather types is obtained, including:
obtaining each characteristic model to be fitted;
adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and training based on the regularized polynomial fitting algorithm model by combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the different weather type information.
In the embodiment of the invention, each feature model to be fitted is obtained by using a polynomialFeatures method of a sklern library, a polynomial fitting target function regularization term is added to each feature model to be fitted by using a RidgeCV method of the sklern library to obtain a regularized polynomial fitting algorithm model, and the regularized polynomial fitting algorithm model is based on and is trained by combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the different weather type information.
In a specific implementation, a Python-based third party library sklern's sklern preprocessing. polymomial features method is used to generate each feature value to be fitted. The parameters are set as follows: degree =1, interaction _ only = False, include _ bias = False. Wherein the highest fitting order degree is 1; because there is no term that multiplies each other, interaction _ only is False; when fitting, no bias term 1 is introduced (but the output polynomial contains a constant term), so include _ bias is False.
And adding an objective function regularization term of polynomial fitting by using a skleern. linear _ model. RidgeCV method of a third-party library skleern based on Python. The parameter setting alpha = numpy, logspace (-3, 2, 50) is used for generating an equal ratio number array (total 50 numbers) of 10 < -3 > -102, and the larger the value of alpha is, the larger the constraint force of the regularization term is. By adding the regularization term of the objective function, the overfitting condition is effectively reduced, and the accuracy and robustness of photovoltaic power generation power prediction are remarkably improved.
Respectively training a polynomial fitting algorithm model with regularization according to different power supply stations and different weather types, thereby obtaining photovoltaic power generation power prediction models of 3 weather types of each power supply station (the training time of used historical data is 4 months, and the models obtained by each power supply station and different weather types are different). And (3) model training input: hourly average irradiance, daily installed capacity. And (3) outputting model training: the method can be used for solving the problem that the minimum time interval of some user measuring points is small and cannot be accurate to the moment, and simultaneously can be used for preventing the extreme influence of individual photovoltaic power generation power with slight deviation, so that the prediction accuracy and robustness of a model can be improved.
Step S206, selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information according to the weather forecast information;
in the embodiment of the invention, the photovoltaic power generation power prediction model of the corresponding weather type is selected according to the weather forecast information.
In the concrete implementation, according to the current weather forecast, as the current weather type, a correspondingly trained model is selected. For example: the weather forecast of the prefecture city of 2021, 1, 6 days is cloudy. An algorithmic model of photovoltaic power generation power prediction in cloudy conditions needs to be used.
Step S207, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
in the embodiment of the invention, the daily installed capacity of the medium-voltage side of the power supply subordinate region and the real-time irradiance of the first preset period in the power supply subordinate region are input into the photovoltaic power generation power prediction model, so that the photovoltaic power generation power at the medium-voltage side of the power supply subordinate region is obtained.
In a specific implementation, on the medium voltage side of different power supplies, time-of-day irradiance (15 minute intervals instead of 1 hour intervals), daily installed capacity are input for predicting medium voltage side photovoltaic time-of-day generated power (15 minute intervals instead of 1 hour intervals). For example: the power supply station id 1000110012 has the time irradiance of 206kW/m2 in 1, 6 and 6 days of 2021 at 9:45, and the solar installed capacity of the power supply station is 2985.3 kW. And predicting the current photovoltaic power generation power to 454.14kW by using the photovoltaic power generation power prediction model trained on the medium-voltage side of the power supply station.
And S208, calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the power supply subordinate region, the historical installed capacity and the daily installed capacity.
In the embodiment of the invention, historical real-time irradiance data of a second preset period is calculated and obtained based on the real-time irradiance of the area to which the power supply station belongs, the historical installed capacity and the daily installed capacity.
In a specific implementation, historical real-time irradiance conditions are intelligently estimated with historical installed capacity. And (4) aligning the historical daily installed capacities of nearly 3 months according to the daily installed capacities, and then mapping the average generated power of the historical hours according to the daily installed capacities in proportion. The specific method is that the historical daily installed capacity of nearly 3 months is completely modified into the current installed capacity, and then the average generated power per day in historical hours is correspondingly modified according to the ratio of the change range of the historical daily installed capacity. For example: the average hourly power generation rate of the power supply station id 1000110012 is 1113kW and the daily installed capacity is 2190kW at 26 days 10 and 10 months 10 in 2020. After being aligned with the installed capacity today at 2985.3kW, the historical generated power after the scaling is 1517.2 kW.
Step S209, selecting a plurality of pieces of historical real-time irradiance data which are most similar to the real-time irradiance of the power supply subordinate region from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data;
in the embodiment of the invention, a plurality of pieces of historical real-time irradiance data which are most similar to the real-time irradiance of the power supply subordinate region are selected from the historical real-time irradiance data, and historical similar generating power is calculated according to the average value of the plurality of pieces of historical real-time irradiance data.
In a particular implementation, according to the presentAnd (3) irradiance at the current moment of day, searching the most similar 3 historical irradiances (irradiance at the current moment in the historical data) from the historical real-time irradiance data of the last 3 months after mapping according to a threshold value, and averaging the irradiances. Screening data of a current hour time node from historical data, searching previous 3 pieces of historical data with the closest irradiance, and averaging hour average power generation power values of the 3 pieces of historical data. Note that the threshold needs to be set here, and the absolute value of the difference between the irradiance of the history and the irradiance at the present moment must be less than 50kW/m2. For example: the current time is 2021, 6 months and 9 days at 45: 45, and the irradiance at the moment is 206kW/m2. Of the irradiance data of the current time in the past 3 months, the most similar is 202.75kW/m at 10, 7, and 10 of 10 months and 7 days in 20202194.75kW/m at 9, 14, 10 in 20202And 192.75kW/m at 11, 19, 10 of 20202. As can be seen, the absolute values of the difference values between the irradiance of the 3 historical time nodes and the irradiance at the present moment are less than 50kW/m2Therefore, all of the 3 data points were selected. The hour average power generation power of the 3 historical nodes is respectively 482.6kW, 385.8kW and 502.6kW through proportional mapping according to the alignment of the daily installed capacity of 2985.3kW today, and the average power generation power is 457 kW.
Step S210, the photovoltaic power generation at the moment and the historical similar power generation power are combined and calculated to obtain the predicted daily power generation amount;
in the embodiment of the invention, the predicted value of the combined model, namely the photovoltaic power generation power at the moment and the historical similar power generation power are calculated to obtain the predicted daily power generation amount;
in the specific implementation, the model predicted value and the historical similar generating power are weighted and averaged according to the proportion of 0.618 (1-0.618). For example: the current time is 1 month, 6 days, 9:45 in 2021, the photovoltaic power generation power at the moment predicted by directly using the model is 439.20kW, and the searched historical reference irradiance is 457kW, according to the formula:
and calculating to obtain the current final predicted value of 446.0 kW.
And S211, calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
In the embodiment of the invention, the prediction accuracy of the photovoltaic power generation power is verified by comparing the predicted daily power generation amount with the real daily power generation amount.
In the specific implementation, the predicted daily power generation amount is compared with the real daily power generation amount, and the average absolute error is calculated to obtain the prediction accuracy of the medium-voltage side photovoltaic output of the area where the power supply station is subordinate. For example: the power supply station id 1000110012 obtains predicted daily power generation amount of 7664.23 kW.h and real daily power generation amount of 8145.8 kW.h in a summary manner according to the photovoltaic power generation amount predicted on the same day (15-minute intervals instead of 1-hour intervals) on 1, 6 and 1 year of 2021. Therefore, the accuracy of predicting the medium-voltage photovoltaic output of the power supply station is 94.09% in the same day.
The method for predicting the photovoltaic power generation power provided by the embodiment of the invention obtains real-time photovoltaic data and weather forecast information of an area to which power is supplied, wherein the real-time photovoltaic data comprises real-time irradiance of the area to which the power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied, obtains daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power is supplied, selects a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputs the daily installed capacity and the real-time irradiance of a first preset period in the area to which the power is supplied to the selected photovoltaic power generation power prediction model, and calculates the photovoltaic power generation power at the medium-voltage side of the area to which the power is supplied, based on the real-time irradiance, the historical installed capacity and the daily installed capacity of the power supply station subordinate area, historical similar generating power is obtained through calculation, the photovoltaic power generation power at the moment and the historical similar generating power are combined and calculated to obtain predicted daily generated energy, the percentage of the predicted daily generated energy to the real daily generated energy is calculated to obtain photovoltaic power prediction accuracy, the technical problems of low accuracy and low efficiency of the photovoltaic power prediction existing at present are solved through the photovoltaic power prediction method, and the photovoltaic power prediction is efficient and accurate.
Referring to fig. 3, fig. 3 is a block diagram illustrating a structure of a photovoltaic power generation power prediction apparatus according to an embodiment of the present invention, including:
the acquisition module 301 is used for acquiring real-time photovoltaic data and weather forecast information of an area to which the power supply station belongs; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
a weather module 302, configured to obtain a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
the calculation module 303 is configured to select a photovoltaic power generation power prediction model, which is of a weather type corresponding to the weather forecast information and is constructed based on the weather type information, input the daily installed capacity and the real-time irradiance of a first preset period in the power supply station-dependent area into the selected photovoltaic power generation power prediction model, and calculate to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station-dependent area;
a history module 304, configured to calculate historical similar generated power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity, and the daily installed capacity;
the prediction module 305 is configured to calculate the photovoltaic power generation at the moment and the historical similar power generation power in a combined manner to obtain a predicted daily power generation amount;
and the precision module 306 is used for calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
In an alternative embodiment, the weather module 302 includes:
the irradiation submodule is used for calculating the average irradiance in hours according to the real-time irradiance of the area to which the power supply belongs;
the integration sub-module is used for summarizing the average hourly irradiance of the area to which the power supply station belongs to obtain a daily irradiance integral of the area to which the power supply station belongs;
and the weather sub-module is used for dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral.
In an alternative embodiment, the calculation module 303 includes:
the modeling submodule is used for modeling by combining the hourly average irradiance and the historical installed capacity of each day based on the weather type information to obtain photovoltaic power generation power prediction models of various weather types;
the selecting submodule is used for selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information according to the weather forecast information;
and the input submodule is used for inputting the daily installed capacity and the real-time irradiance of the first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area.
In an alternative embodiment, the modeling submodule includes:
the fitting unit is used for acquiring various feature models to be fitted;
the adding unit is used for adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and the training unit is used for training based on the regularized polynomial fitting algorithm model and combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the various weather type information.
In an alternative embodiment, the history module 304 includes:
the history submodule is used for calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the area to which the power supply station belongs, the historical installed capacity and the daily installed capacity;
and the similarity submodule is used for selecting a plurality of pieces of historical real-time irradiance data which are closest to the real-time irradiance of the area to which the power supply belongs from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the method and apparatus disclosed in the present invention can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a readable storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for predicting photovoltaic power generation power is characterized by comprising the following steps:
acquiring real-time photovoltaic data and weather forecast information of an area to which power supply is subordinate; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed based on the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
calculating historical similar generating power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity;
the photovoltaic power generation power at the moment and the historical similar power generation power are combined and calculated to obtain the predicted daily power generation amount;
and calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
2. The method for predicting photovoltaic power generation according to claim 1, wherein obtaining the daily irradiance integral and the weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs comprises:
calculating to obtain the average irradiance in hours according to the real-time irradiance of the area to which the power supply station belongs;
summarizing the hourly average irradiance of the area to which the power supply is subordinate to obtain a daily irradiance integral of the area to which the power supply is subordinate;
and dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral.
3. The method for predicting photovoltaic power generation power according to claim 2, wherein a photovoltaic power generation power prediction model, which is constructed based on the weather type information and corresponds to a weather type corresponding to the weather forecast information, is selected, the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area are input into the selected photovoltaic power generation power prediction model, and the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area is calculated, and the method comprises the following steps:
modeling is carried out on the basis of the weather type information by combining the hourly average irradiance and the historical installed capacity every day to obtain photovoltaic power generation power prediction models of various weather types;
selecting a photovoltaic power generation power prediction model of a weather type corresponding to weather forecast information according to the weather forecast information;
and inputting the daily installed capacity and the real-time irradiance of the first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area at the moment.
4. The method for predicting photovoltaic power generation according to claim 3, wherein modeling is performed based on the weather type information and in combination with the hourly average irradiance and the historical installed capacity of each day, so as to obtain photovoltaic power generation power prediction models of a plurality of different weather types, and the method comprises:
obtaining each characteristic model to be fitted;
adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and training based on the regularized polynomial fitting algorithm model by combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the different weather type information.
5. The method for predicting photovoltaic generating power according to any one of claims 1 to 4, wherein the step of calculating historical similar generating power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity comprises:
calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the power supply subordinate region, the historical installed capacity and the daily installed capacity;
and selecting a plurality of pieces of historical real-time irradiance data which are closest to the real-time irradiance of the area to which the power supply belongs from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data.
6. A photovoltaic power generation power prediction apparatus, comprising:
the acquisition module is used for acquiring real-time photovoltaic data and weather forecast information of an area to which the power supply station belongs; the real-time photovoltaic data comprises real-time irradiance of an area to which power is supplied, daily installed capacity and historical installed capacity of a medium-voltage side of the area to which the power is supplied;
the weather module is used for obtaining a daily irradiance integral and weather type information corresponding to the daily irradiance integral according to the real-time irradiance of the area to which the power supply belongs;
the calculation module is used for selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information and constructed on the basis of the weather type information, inputting the daily installed capacity and the real-time irradiance of a first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model, and calculating to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area;
the history module is used for calculating to obtain historical similar generating power based on the real-time irradiance of the area to which the power supply belongs, the historical installed capacity and the daily installed capacity;
the prediction module is used for calculating the photovoltaic power generation power at the moment and the historical similar power generation power in a combined mode to obtain the predicted daily power generation amount;
and the precision module is used for calculating the percentage of the predicted daily generated energy to the real daily generated energy to obtain the photovoltaic power generation power prediction precision.
7. The photovoltaic power generation prediction device of claim 6, wherein the weather module comprises:
the irradiation submodule is used for calculating the average irradiance in hours according to the real-time irradiance of the area to which the power supply belongs;
the integration sub-module is used for summarizing the average hourly irradiance of the area to which the power supply station belongs to obtain a daily irradiance integral of the area to which the power supply station belongs;
and the weather sub-module is used for dividing weather conditions based on the daily irradiance integral to obtain weather type information corresponding to the daily irradiance integral.
8. The photovoltaic power generation prediction device of claim 7, wherein the calculation module comprises:
the modeling submodule is used for modeling by combining the hourly average irradiance and the historical installed capacity of each day based on the weather type information to obtain photovoltaic power generation power prediction models of various weather types;
the selecting submodule is used for selecting a photovoltaic power generation power prediction model of a weather type corresponding to the weather forecast information according to the weather forecast information;
and the input submodule is used for inputting the daily installed capacity and the real-time irradiance of the first preset period in the power supply station subordinate area into the selected photovoltaic power generation power prediction model to obtain the photovoltaic power generation power at the medium-voltage side of the power supply station subordinate area.
9. The photovoltaic power generation prediction apparatus of claim 8, wherein the modeling submodule includes:
the fitting unit is used for acquiring various feature models to be fitted;
the adding unit is used for adding a target function regularization term of polynomial fitting to each characteristic model to be fitted to obtain a regularized polynomial fitting algorithm model;
and the training unit is used for training based on the regularized polynomial fitting algorithm model and combining the weather type information, the hourly average irradiance and the historical installed capacity every day to obtain the photovoltaic power generation power prediction models of the various weather type information.
10. The photovoltaic power generation prediction device of any one of claims 6-9, wherein the history module comprises:
the history submodule is used for calculating to obtain historical real-time irradiance data of a second preset period based on the real-time irradiance of the area to which the power supply station belongs, the historical installed capacity and the daily installed capacity;
and the similarity submodule is used for selecting a plurality of pieces of historical real-time irradiance data which are closest to the real-time irradiance of the area to which the power supply belongs from the historical real-time irradiance data, and calculating to obtain historical similar generating power according to the average value of the plurality of pieces of historical real-time irradiance data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237428.4A CN113689057A (en) | 2021-10-25 | 2021-10-25 | Photovoltaic power generation power prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111237428.4A CN113689057A (en) | 2021-10-25 | 2021-10-25 | Photovoltaic power generation power prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113689057A true CN113689057A (en) | 2021-11-23 |
Family
ID=78587775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111237428.4A Pending CN113689057A (en) | 2021-10-25 | 2021-10-25 | Photovoltaic power generation power prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689057A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115529002A (en) * | 2022-11-28 | 2022-12-27 | 天津海融科技有限公司 | Photovoltaic power generation power prediction method under various weather conditions |
| CN116365508A (en) * | 2023-03-09 | 2023-06-30 | 北京东润环能科技股份有限公司 | Photovoltaic power station generating capacity prediction method and system based on climate mode |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学（保定） | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
| CN106022528A (en) * | 2016-05-26 | 2016-10-12 | 上海电力学院 | Short-term power prediction method of photovoltaic power plant based on density peak hierarchical clustering |
| CN112508246A (en) * | 2020-11-26 | 2021-03-16 | 国电南瑞科技股份有限公司 | Photovoltaic power generation power prediction method based on similar days |
-
2021
- 2021-10-25 CN CN202111237428.4A patent/CN113689057A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学（保定） | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
| CN106022528A (en) * | 2016-05-26 | 2016-10-12 | 上海电力学院 | Short-term power prediction method of photovoltaic power plant based on density peak hierarchical clustering |
| CN112508246A (en) * | 2020-11-26 | 2021-03-16 | 国电南瑞科技股份有限公司 | Photovoltaic power generation power prediction method based on similar days |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115529002A (en) * | 2022-11-28 | 2022-12-27 | 天津海融科技有限公司 | Photovoltaic power generation power prediction method under various weather conditions |
| CN115529002B (en) * | 2022-11-28 | 2023-04-07 | 天津海融科技有限公司 | Photovoltaic power generation power prediction method under various weather conditions |
| CN116365508A (en) * | 2023-03-09 | 2023-06-30 | 北京东润环能科技股份有限公司 | Photovoltaic power station generating capacity prediction method and system based on climate mode |
| CN116365508B (en) * | 2023-03-09 | 2023-12-12 | 北京东润环能科技股份有限公司 | Photovoltaic power station generating capacity prediction method and system based on climate mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khatib et al. | A review on sizing methodologies of photovoltaic array and storage battery in a standalone photovoltaic system | |
| Saez-de-Ibarra et al. | Co-optimization of storage system sizing and control strategy for intelligent photovoltaic power plants market integration | |
| Yona et al. | Determination method of insolation prediction with fuzzy and applying neural network for long-term ahead PV power output correction | |
| Ross et al. | Microgrid economic dispatch with energy storage systems | |
| Behm et al. | How to model European electricity load profiles using artificial neural networks | |
| Nogueira et al. | Sizing and simulation of a photovoltaic-wind energy system using batteries, applied for a small rural property located in the south of Brazil | |
| Junior et al. | On the use of maximum likelihood and input data similarity to obtain prediction intervals for forecasts of photovoltaic power generation | |
| Bashir et al. | Optimal sizing of hybrid wind/photovoltaic/battery considering the uncertainty of wind and photovoltaic power using Monte Carlo | |
| Nazari et al. | A two-stage stochastic model for energy storage planning in a microgrid incorporating bilateral contracts and demand response program | |
| CN113689057A (en) | Photovoltaic power generation power prediction method and device | |
| Jethmalani et al. | Auxiliary hybrid PSO-BPNN-based transmission system loss estimation in generation scheduling | |
| Duignan et al. | Capacity value of solar power | |
| KR101635450B1 (en) | PV (Photo-Voltaic) generation forecasting system for the city energy management system based on weather information | |
| Gheouany et al. | Experimental validation of multi-stage optimal energy management for a smart microgrid system under forecasting uncertainties | |
| Ananth et al. | A review of different optimisation techniques for solving single and multi-objective optimisation problem in power system and mostly unit commitment problem | |
| Tahir et al. | Optimal ESS size calculation for ramp rate control of grid-connected microgrid based on the selection of accurate representative days | |
| Memmel et al. | Forecast of renewable curtailment in distribution grids considering uncertainties | |
| CN111478374B (en) | Dynamic evaluation method for probability distribution and prediction of wind-solar output characteristics | |
| Ding et al. | A dynamic period partition method for time-of-use pricing with high-penetration renewable energy | |
| Radovanović et al. | Deep Learning-based Equivalent Modelling of Hybrid RES Plant for Efficient, Repetitive Power System Transient Stability Studies | |
| Nobis et al. | Modeling forecasting errors of fluctuating renewables and electrical loads | |
| CN113725896B (en) | Power grid new energy access method based on uncertainty risk calculation | |
| Batsala et al. | Forecasting day-ahead of power generation from photovoltaic stations and use weather apps.„ | |
| Wei et al. | Ultra-short-term/short-term wind power continuous prediction based on fuzzy clustering analysis | |
| Sarkar | Minding the P's and Q's: Real and reactive power assessment of hybrid energy conversion systems with wind and solar resources |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |
|
| RJ01 | Rejection of invention patent application after publication |