CN112446554A - Power prediction model establishing method, power prediction method and device - Google Patents
Power prediction model establishing method, power prediction method and device Download PDFInfo
- Publication number
- CN112446554A CN112446554A CN202011504830.XA CN202011504830A CN112446554A CN 112446554 A CN112446554 A CN 112446554A CN 202011504830 A CN202011504830 A CN 202011504830A CN 112446554 A CN112446554 A CN 112446554A
- Authority
- CN
- China
- Prior art keywords
- historical
- power
- meteorological
- station
- prediction model
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000010248 power generation Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000005855 radiation Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000013179 statistical model Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Environmental & Geological Engineering (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power prediction model establishing method, a power prediction method and a power prediction device, wherein the power prediction model establishing method comprises the following steps: acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station; determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical generated power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical generated power; and establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter. According to the technical scheme, the power prediction model is established for predicting the generated power of the calibration area, and the method is simple, convenient, practical, efficient and wide in application range.
Description
Technical Field
The invention relates to the technical field of distributed photovoltaic power stations, in particular to a power prediction model establishing method, a power prediction method and a power prediction device.
Background
The distributed photovoltaic power station refers to photovoltaic systems distributed on various roofs or greenhouses and the like and below megawatt level, and has the characteristics of small occupied area, dispersed distribution, spontaneous self-use, surplus internet surfing and the like. With the trend of diversification of development modes of the photovoltaic industry, distributed photovoltaic power stations are more and more, and the influence of grid connection of a large number of distributed photovoltaic power stations on a low-voltage power distribution network is larger and larger, wherein the prediction of the power generation power of the distributed photovoltaic power stations has important significance on planning and operation control of a power grid.
When the generated power of the distributed photovoltaic power station is predicted, the overall prediction is generally performed on all the distributed photovoltaic power stations in a certain area. At present, the following method is often adopted for power prediction:
dividing the whole area into a plurality of sub-areas, determining a reference power station in all distributed photovoltaic power stations in each sub-area, predicting the power of the reference power station by establishing a photovoltaic power prediction model, predicting the generated power of the sub-area by combining with the weight coefficient of the reference base station in the sub-area, and adding the prediction results of all the sub-areas to obtain the predicted power of the whole area.
According to the method, when the sub-regions are divided, the sub-regions are usually divided according to the distance of geographic positions or administrative regions, the photovoltaic power stations in the sub-regions are required to have similarity as much as possible, and a reference power station which is high in spatial correlation and can represent the power generation characteristics of the sub-regions can be found. However, the installation modes of the distributed photovoltaic power stations are very different, it is difficult to ensure that the distributed photovoltaic power stations in each sub-area have power generation similarity, it is also difficult to find a reference power station which can represent the power generation characteristics of the whole sub-area, and it is difficult to calculate the predicted power of the whole area.
Disclosure of Invention
The invention solves the technical problem that the generated power of a certain area is difficult to calculate in the prior art.
In order to solve the above problems, the present invention provides a power prediction model establishing method, a power prediction method and a power prediction device.
In a first aspect, the invention provides a method for establishing a power prediction model of a distributed photovoltaic power station, comprising the following steps:
acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station;
determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical generated power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical generated power;
and establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
Optionally, said determining a reference weather station from said historical weather data and said historical generated power comprises:
respectively calculating correlation parameters corresponding to the meteorological stations according to the historical meteorological data of the meteorological stations, the historical power generation power of the distributed photovoltaic power stations and the regional historical total power;
sequentially carrying out normalization processing and weighted summation on the correlation parameters to obtain irradiance scores of the meteorological stations;
determining the weather station with the highest irradiance score as the reference weather station.
Optionally, the historical meteorological data includes historical irradiance, the correlation parameter includes a first average correlation, a first proportion and a second proportion, and the calculating the correlation parameter corresponding to each meteorological station according to the historical meteorological data of each meteorological station, the historical power generation power of each distributed photovoltaic power station and the regional historical total power includes:
respectively determining time periods to which the historical irradiance, the historical generated power and the historical total power of the region belong;
for each weather station, calculating a first correlation between the historical irradiance of the weather station in each time period and the historical total power of the region in the corresponding time period respectively, and a second correlation between the historical irradiance of the weather station in each time period and the historical generating power of each distributed photovoltaic power station respectively;
determining a first average correlation between the historical irradiance of the weather station and the historical total power of the region according to all the first correlations corresponding to the weather station in each time period;
comparing the first correlation under each time interval with a first preset threshold respectively, and determining a first proportion of the time interval of which the first correlation exceeds the first preset threshold in all the time intervals;
determining a second average correlation between the historical irradiance of the weather station and the historical generated power according to all the second correlations corresponding to the weather station in each time period, comparing the second average correlation corresponding to each weather station with a second preset threshold value, and determining a second proportion of the weather stations of which the second average correlation exceeds the second preset threshold value in all the weather stations.
Optionally, the sequentially performing normalization processing and weighted summation on the correlation parameters to obtain irradiance scores of the weather stations includes:
and respectively carrying out normalization processing on the first average correlation, the first proportion and the second proportion corresponding to each weather station by adopting a min-max algorithm to obtain the normalized first average correlation, the normalized first proportion and the normalized second proportion.
Performing min-max normalization processing on the correlation parameter by adopting a first formula, wherein the first formula comprises:
x'＝(min-x)/(min-max)，
wherein x' is a normalized correlation parameter, min is a minimum value of the correlation parameters corresponding to each weather station, x is the correlation parameter, and includes a first average correlation, a first proportion and a second proportion, and max is a maximum value of the correlation parameters corresponding to each weather station.
And performing weighted summation on the normalized first average correlation, the normalized first proportion and the normalized second proportion to determine the irradiance score of each weather station.
The normalized correlation parameters are subjected to weighted summation by adopting a second formula to obtain the irradiance score of each weather station, the normalized correlation parameters comprise a normalized first average correlation, a normalized first proportion and a normalized second proportion, and the second formula comprises:
wherein score is the irradiance score, Corr(i)For the normalized first average correlation, M, corresponding to the ith weather station(i)Corresponding to the normalized first ratio, N, for the ith weather station(i)And the normalized second proportion is corresponding to the ith meteorological station.
Optionally, the building a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter comprises:
comparing the correlation parameter corresponding to the reference weather station with a third preset threshold value;
and when the correlation parameter corresponding to the reference weather station is greater than or equal to the third preset threshold value, establishing a power prediction model by taking the historical weather data acquired by the reference weather station as an input variable and combining the historical total power of the region.
Optionally, the historical meteorological data comprises historical irradiance, and the building a power prediction model from the historical meteorological data and the historical generated power comprises:
when the correlation parameter is smaller than the third preset threshold, dividing the calibration area into a plurality of sub-areas;
acquiring meteorological satellite historical data of each subregion, and calculating earth surface data of each subregion according to inversion of the meteorological satellite data, wherein the earth surface data comprises earth surface irradiance;
establishing an earth surface irradiance error correction model according to the meteorological satellite historical data of the sub-area where the reference meteorological station is located;
correcting the surface irradiance of each sub-area according to the surface irradiance error correction model to obtain corrected surface irradiance;
respectively calculating historical summary power of each subarea according to the historical power generation power of all the distributed photovoltaic power stations in each subarea;
and respectively establishing a power prediction model of each sub-area according to the corrected surface irradiance and the historical summary power.
Optionally, the meteorological satellite historical data includes surface short wave radiation, and the building of the surface irradiance error correction model according to the meteorological satellite historical data of the sub-area where the reference meteorological station is located includes:
calculating the deviation between the historical irradiance collected by the reference weather station and the surface short-wave radiation of the sub-area where the reference weather station is located;
and fitting by adopting a machine learning regression algorithm according to the deviation and the meteorological satellite historical data of the sub-area where the reference meteorological station is located to obtain the earth surface irradiance error correction model.
Optionally, the respectively establishing a power prediction model of each sub-region according to the corrected surface irradiance and the historical summarized power includes:
for each sub-area, calculating a first correlation of the historical aggregate power and the corrected surface irradiance at each time period;
comparing the first correlation of each time period with a fourth preset threshold, and taking the historical summary power corresponding to the first correlation which is greater than or equal to the fourth preset threshold and the corrected ground surface irradiance as modeling data;
and establishing a power prediction model of each sub-region according to the modeling data.
In a second aspect, the present invention provides a method for predicting power of a distributed photovoltaic power station, including:
acquiring weather forecast data of a calibration area;
inputting the weather forecast data into a power prediction model of the calibration area, and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
the power prediction model is established by adopting the establishment method of the power prediction model of the distributed photovoltaic power station.
In a third aspect, the present invention provides a device for establishing a power prediction model of a distributed photovoltaic power station, including:
the acquisition module is used for acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station;
the processing module is used for determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical power generation power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical power generation powers;
and the establishing module is used for establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
In a fourth aspect, the present invention provides a distributed photovoltaic power station power prediction apparatus, including:
the acquisition module is used for acquiring weather forecast data of the calibration area;
the prediction module is used for inputting the weather forecast data into a power prediction model of the calibration area and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
the power prediction model is established by adopting the establishment method of the power prediction model of the distributed photovoltaic power station.
In a fifth aspect, the present invention provides an electronic device comprising a processor and a memory;
the memory for storing a computer program;
the processor, when executing the computer program, is configured to implement the method for establishing a power prediction model of a distributed photovoltaic power plant as described above or the method for predicting power of a distributed photovoltaic power plant as described above.
In a sixth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a distributed photovoltaic power plant power prediction model building method as described above or a distributed photovoltaic power plant power prediction method as described above.
The power prediction model establishing method, the power prediction method and the device have the advantages that: the method comprises the steps of obtaining historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data collected by at least one meteorological station, determining the meteorological station in a reference calibration area according to the historical meteorological data and the historical power generation power, and being simpler and more efficient compared with the method for determining a reference power station of each sub-area. Determining a correlation parameter between historical meteorological data of a reference meteorological station and the regional historical total power of a calibration region, constructing a relation between the meteorological data and the generated power of the calibration region, and establishing a power prediction model based on the correlation parameter. The power prediction model is adopted to predict the generated power of the calibration area, and the generated power of the calibration area can be obtained only by inputting the weather forecast data of the calibration area into the power prediction model, so that the method is simple and convenient. In the technical scheme of the invention, the power prediction model is established for predicting the power generation power of the calibration area, the spatial correlation between the distributed photovoltaic power stations is not depended on, the reference power station is not required to be searched, and the method is simple, convenient, practical, efficient and wide in application range.
Drawings
Fig. 1 is a schematic flow chart of a method for establishing a power prediction model of a distributed photovoltaic power station according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for establishing a power prediction model of a distributed photovoltaic power plant according to another embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for predicting power of a distributed photovoltaic power station according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a distributed photovoltaic power station power prediction model building device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a distributed photovoltaic power prediction apparatus with a power station according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
In the prior art, a photovoltaic power prediction model comprises a physical model and a statistical model, wherein the physical model is established based on operating parameters and field equipment parameters of hardware facilities of each power station, and the statistical model is established based on historical meteorological data and historical power generation data, but the number of distributed photovoltaic power stations in a prediction area is large, the distribution is wide, the installation mode is complex and various, so that the specific operating parameters of the equipment of the distributed photovoltaic power stations are difficult to obtain, and the power prediction of the physical model for the distributed photovoltaic power stations is difficult and the prediction error is large. In the prior art, a statistical model is generally adopted in the power prediction of a distributed photovoltaic area. When a statistical model is adopted to predict the power of a distributed photovoltaic power station, two conditions need to be considered: firstly, when sub-regions are divided, photovoltaic power stations in the sub-regions are required to have similarity as much as possible, and a reference power station which has high spatial correlation and can represent the power generation characteristics of the sub-regions can be found; and secondly, at least one set of meteorological acquisition devices are needed for establishing a power prediction model of the reference power station in each divided sub-region. However, the distributed photovoltaic power stations in the area are not uniformly distributed, at least one weather acquisition device is not necessarily arranged in each sub-area, only one weather acquisition device is possibly arranged in one area, or one weather acquisition device is shared in several adjacent areas, and it is difficult to ensure that each sub-area can use historical weather data and historical power data to establish a power prediction model of a reference power station, which may affect the regional power prediction effect of the distributed photovoltaic power stations.
As shown in fig. 1 and fig. 2, a method for establishing a power prediction model of a distributed photovoltaic power station according to an embodiment of the present invention includes:
step S110, obtaining historical generating power of each distributed photovoltaic power station in the calibration area and historical meteorological data collected by at least one meteorological station.
Optionally, historical meteorological data collected by at least one meteorological station in the calibration area or in an adjacent area can be obtained, and the historical meteorological data comprises irradiance G(i,t)Ambient temperature T(i,t)Humidity R(i,t)Wind speed W(i,t)And the like, wherein i represents the ith weather station, i belongs to N, N is a set formed by all the weather stations, and t represents the historical time corresponding to the historical weather data.
Obtaining historical generating power P of each distributed photovoltaic power station in a calibration area(j,t)J belongs to M, wherein j represents the jth distributed photovoltaic power station, M is a set formed by all the distributed photovoltaic power stations, t represents the time corresponding to the historical generating power, and the historical generating power P of all the distributed photovoltaic power stations at the same time in the region(j,t)Adding to obtain the regional historical total power P of the calibration region(t)。
In the optional embodiment, when the power prediction model is established, the power prediction model can be established only by arranging at least one meteorological station in the whole area or the adjacent area without depending on each distributed photovoltaic power station or each sub-area, so that the basic condition of predicting the area power is reduced, and the application range can be greatly improved.
Step S120, determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical generated power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical generated power.
Optionally, said determining a reference weather station from said historical weather data and said historical generated power comprises:
step S121, respectively calculating correlation parameters corresponding to the meteorological stations according to the historical meteorological data of the meteorological stations, the historical power generation power of the distributed photovoltaic power stations and the regional historical total power;
optionally, the historical meteorological data includes historical irradiance, the correlation parameter includes a first average correlation, a first proportion and a second proportion, and the calculating the correlation parameter corresponding to each meteorological station according to the historical meteorological data of each meteorological station, the historical power generation power of each distributed photovoltaic power station and the regional historical total power includes:
and respectively determining the time periods to which the historical irradiance, the historical generating power and the historical total power of the region belong.
Specifically, each time period may be one day in length, and the historical irradiance, the historical generated power, and the total regional historical power for each day may be determined from the corresponding historical time t.
For each weather station, calculating a first correlation between the historical irradiance of the weather station in each time period and the historical total power of the region in the corresponding time period respectively, and a second correlation between the historical irradiance of the weather station in each time period and the historical generating power of each distributed photovoltaic power station respectively;
determining a first average correlation between the historical irradiance of the weather station and the historical total power of the region according to all the first correlations corresponding to the weather station in each time period;
comparing the first correlation under each time interval with a first preset threshold respectively, and determining a first proportion of the time interval of which the first correlation exceeds the first preset threshold in all the time intervals;
determining a second average correlation between the historical irradiance of the weather station and the historical generated power according to all the second correlations corresponding to the weather station in each time period, comparing the second average correlation corresponding to each weather station with a second preset threshold value, and determining a second proportion of the weather stations of which the second average correlation exceeds the second preset threshold value in all the weather stations.
Specifically, the first preset threshold and the second preset threshold may both be 0.8, and the calculation of the correlation between the two parameters is performed in the prior art, which is not described herein again, and the correlation may be a pearson correlation parameter, a spearman correlation parameter, a kender correlation parameter, and the like.
Step S122, carrying out normalization processing and weighted summation on the correlation parameters in sequence to obtain irradiance scores of the weather stations;
optionally, the sequentially performing normalization processing and weighted summation on the correlation parameters to obtain irradiance scores of the weather stations includes:
and respectively carrying out normalization processing on the first average correlation, the first proportion and the second proportion corresponding to each weather station by adopting a min-max algorithm to obtain the normalized first average correlation, the normalized first proportion and the normalized second proportion.
Performing min-max normalization processing on the correlation parameter by adopting a first formula, wherein the first formula comprises:
x'＝(min-x)/(min-max)，
wherein x' is a normalized correlation parameter, min is a minimum value of the correlation parameters corresponding to each weather station, x is the correlation parameter, specifically, a first average correlation, a first proportion and a second proportion, respectively, and max is a maximum value of the correlation parameters corresponding to each weather station, for example: when the first average correlation is normalized, min is the minimum value of the first average correlations corresponding to each weather station, and max is the maximum value of the first average correlations corresponding to each weather station.
And performing weighted summation on the normalized first average correlation, the normalized first proportion and the normalized second proportion to determine the irradiance score of each weather station.
The normalized correlation parameters are subjected to weighted summation by adopting a second formula to obtain the irradiance score of each weather station, the normalized correlation parameters comprise a normalized first average correlation, a normalized first proportion and a normalized second proportion, and the second formula comprises:
wherein score is the irradiance score, Corr(i)For the normalized first average correlation, M, corresponding to the ith weather station(i)Corresponding to the normalized first ratio, N, for the ith weather station(i)And the normalized second proportion is corresponding to the ith meteorological station.
And S123, determining the weather station with the highest irradiance score as the reference weather station.
In this optional embodiment, after the normalization processing is performed on the parameters, the obtained normalized parameters are all between 0 and 1, the optimal value is 1, and the worst value is 0. The method for evaluating the meteorological station is provided, and when a power prediction model is established for predicting the power generation power of a calibration area, data collected by the meteorological station in the calibration area or adjacent areas can be reasonably selected and utilized.
And step S130, establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
Optionally, the building a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter comprises:
judging whether the correlation parameters meet power prediction model establishment conditions or not, namely comparing the correlation parameters corresponding to the reference meteorological station with a third preset threshold value;
and when the correlation parameter corresponding to the reference weather station is greater than or equal to the third preset threshold value, establishing a power prediction model by taking the historical weather data acquired by the reference weather station as an input variable and combining the historical total power of the region.
Specifically, a prediction model to be trained can be established in advance, the prediction model can be a statistical model or a neural network model, and the like, historical meteorological data is used as an input variable, the total regional historical power is used as a test variable to train the prediction model to be trained, and a power prediction model is obtained.
In this optional embodiment, the determination may be performed only according to the first average correlation and the first ratio corresponding to the reference weather station, a threshold corresponding to the first average correlation in the third preset threshold may be set to 0.8, and a threshold corresponding to the first ratio may be set to 60%, where when the first average correlation is greater than or equal to 0.8 and the first ratio is greater than or equal to 60%, it indicates that weather conditions of different sub-areas of the calibration area are relatively consistent at the same time, and a power prediction model may be established directly by using historical weather data acquired by the reference weather station and historical total power historical data of the area.
For historical meteorological data and regional historical total power of a reference meteorological station with high correlation, a power prediction model can be directly established according to the historical meteorological data and the regional historical total power of the reference meteorological station.
Optionally, the historical meteorological data comprises historical irradiance, and the building a power prediction model from the historical meteorological data and the historical generated power comprises:
when the correlation parameter is smaller than the third preset threshold, dividing the calibration area into a plurality of sub-areas.
Specifically, when the first average correlation corresponding to the reference weather station is smaller than 0.8 and the first ratio is smaller than 60%, it indicates that the weather condition difference of different sub-areas of the calibration area at the same time is large, and each sub-area is divided by taking the minimum spatial resolution range of the weather satellite or the weather forecast as a reference.
Acquiring meteorological satellite historical data of each subregion, and calculating earth surface data of each subregion according to inversion of the meteorological satellite data, wherein the earth surface data comprises earth surface irradiance.
Specifically, meteorological satellite historical data of each sub-area can be acquired through a network sharing channel and the like, and the meteorological satellite historical data comprises surface short wave radiation (DSSR)(0,t)Surface temperature T, humidity R, Cloud parameters Cloud (Cloud type, coverage, Cloud optical thickness, etc.), atmospheric parameters Aod (atmospheric optical thickness), etc.
And establishing an earth surface irradiance error correction model according to the meteorological satellite historical data of the sub-area where the reference meteorological station is located.
Optionally, the meteorological satellite historical data includes surface short wave radiation, and the building of the surface irradiance error correction model according to the meteorological satellite historical data of the sub-area where the reference meteorological station is located includes:
and calculating the deviation between the historical irradiance collected by the reference weather station and the surface short-wave radiation of the sub-area where the reference weather station is located.
Specifically, historical irradiance G of a reference weather station at the same moment is calculated(0,t)Earth surface short wave radiation DSSR inverted with meteorological satellite(0,t)Deviation G 'between'(t)Deviation G'(t)＝G(0,t)-DSSR(0,t)Wherein 0 represents the sub-area where the reference weather station is located, and t represents the historical time corresponding to the data.
And fitting by adopting a machine learning regression algorithm according to the deviation and the meteorological satellite historical data of the sub-area where the reference meteorological station is located to obtain the earth surface irradiance error correction model.
Specifically, the deviation between the ground surface short wave radiation inverted by the meteorological satellite historical data and the actual ground surface irradiance is related to the meteorological state, so the deviation of the ground surface irradiance inverted by the meteorological satellite data is fitted by using the ground surface temperature T, the humidity R, the Cloud parameter Cloud and the atmospheric parameter Aod of the meteorological satellite historical data, and fitting training can be carried out by adopting a machine learning regression algorithm to obtain the deviation G'(t)Corrected model G of’(t)＝f(T，R，Cloud，Aod)。
And correcting the surface irradiance of each sub-area according to the surface irradiance error correction model to obtain the corrected surface irradiance.
Specifically, the surface irradiance of each sub-area is corrected by combining the deviation model to obtain the corrected surface irradiance G(n,t)＝G’(t)+DSSR(n,t)Where n represents any sub-region within the nominal region.
And respectively calculating historical summary power of each sub-area according to the historical power generation power of all the distributed photovoltaic power stations in each sub-area.
Specifically, for any sub-area, the historical generated power of each distributed photovoltaic power station in the sub-area is added to obtain the historical aggregated power of the sub-area.
And respectively establishing a power prediction model of each sub-area according to the corrected surface irradiance and the historical summary power.
Optionally, the respectively establishing a power prediction model of each sub-region according to the corrected surface irradiance and the historical summarized power includes:
for each sub-area, calculating a first correlation of the historical aggregate power and the corrected surface irradiance at each time period;
and comparing the first correlation with a fourth preset threshold value in each time period, and taking the historical summary power corresponding to the first correlation which is greater than or equal to the fourth preset threshold value and the corrected surface irradiance as modeling data.
Specifically, the fourth preset threshold may be set to 0.8.
And establishing a power prediction model of each sub-region according to the modeling data.
Specifically, a power prediction model is established by taking the corrected surface irradiance in the modeling data as an input variable and the historical summary power as a test variable. For historical meteorological data and regional historical total power of a reference meteorological station with low correlation, a surface irradiance deviation correction model of each subregion is established through meteorological satellite historical data, the surface irradiance of each subregion can be corrected, a power prediction model of the corresponding subregion is established according to the surface irradiance and historical summary power, and the generating power of the subregion can be predicted under the condition that the subregion has no meteorological station.
In the embodiment, historical power generation power of each distributed photovoltaic power station in the calibration area and historical meteorological data collected by at least one meteorological station are obtained, the meteorological station in the reference calibration area is determined according to the historical meteorological data and the historical power generation power, and compared with the reference power station for determining each sub-area, the method is simpler and more efficient. Determining a correlation parameter between historical meteorological data of a reference meteorological station and the regional historical total power of a calibration region, constructing a relation between the meteorological data and the generated power of the calibration region, and establishing a power prediction model based on the correlation parameter. The power prediction model is adopted to predict the generated power of the calibration area, and the generated power of the calibration area can be obtained only by inputting the weather forecast data of the calibration area into the power prediction model, so that the method is simple and convenient. In the technical scheme of the invention, the power prediction model is established for predicting the power generation power of the calibration area, the spatial correlation between the distributed photovoltaic power stations is not depended on, the reference power station is not required to be searched, and the method is simple, convenient, practical, efficient and wide in application range.
As shown in fig. 3, a method for predicting power of a distributed photovoltaic power station according to an embodiment of the present invention includes:
step S210, acquiring weather forecast data of a calibration area;
step S220, inputting the weather forecast data into a power prediction model of the calibration area, and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
the power prediction model is established by adopting the establishment method of the power prediction model of the distributed photovoltaic power station.
In this embodiment, for the calibration area, when the correlation parameter corresponding to the reference weather station is greater than or equal to the third preset threshold value, and a power prediction model is established according to the historical weather data and the total historical power of the area acquired by the reference weather station, the weather forecast data of the reference weather station in the calibration area can be directly input into the power prediction model, and the predicted generated power of the calibration area can be obtained.
When the correlation parameter corresponding to the reference weather station is smaller than the third preset threshold value and the power prediction model of each sub-region is established after the sub-regions are divided, acquiring the weather forecast data of each sub-region respectively, inputting the power prediction model of each sub-region respectively to obtain the predicted generated power of each sub-region, and adding the generated powers of all the sub-regions to obtain the predicted generated power of the calibration region.
As shown in fig. 4, a distributed photovoltaic power plant power prediction model establishing apparatus provided in an embodiment of the present invention includes:
the acquisition module is used for acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station;
the processing module is used for determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical power generation power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical power generation powers;
and the establishing module is used for establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
As shown in fig. 5, a distributed photovoltaic power plant power prediction apparatus provided in an embodiment of the present invention includes:
the acquisition module is used for acquiring weather forecast data of the calibration area;
the prediction module is used for inputting the weather forecast data into a power prediction model of the calibration area and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
the power prediction model is established by adopting the establishment method of the power prediction model of the distributed photovoltaic power station.
The electronic equipment provided by the embodiment of the invention comprises a processor and a memory; the memory for storing a computer program; the processor, when executing the computer program, is configured to implement the method for establishing a power prediction model of a distributed photovoltaic power plant as described above or the method for predicting power of a distributed photovoltaic power plant as described above. The electronic device can be a computer, a server and the like.
An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the method for establishing a power prediction model of a distributed photovoltaic power plant or the method for predicting power of a distributed photovoltaic power plant.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like. In this application, 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 of the present invention. 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.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (13)
1. A method for establishing a power prediction model of a distributed photovoltaic power station is characterized by comprising the following steps:
acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station;
determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical generated power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical generated power;
and establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
2. The distributed photovoltaic power plant power prediction model building method of claim 1, wherein the determining a reference meteorological station from the historical meteorological data and the historical generated power comprises:
respectively calculating correlation parameters corresponding to the meteorological stations according to the historical meteorological data of the meteorological stations, the historical power generation power of the distributed photovoltaic power stations and the regional historical total power;
sequentially carrying out normalization processing and weighted summation on the correlation parameters to obtain irradiance scores of the meteorological stations;
determining the weather station with the highest irradiance score as the reference weather station.
3. The distributed photovoltaic power plant power prediction model building method of claim 2, wherein the historical meteorological data comprises historical irradiance, the correlation parameters comprise a first average correlation, a first proportion and a second proportion, and the calculating the correlation parameter corresponding to each of the meteorological stations from the historical meteorological data of each of the meteorological stations, the historical generated power of each of the distributed photovoltaic power plant and the regional historical total power comprises:
respectively determining time periods to which the historical irradiance, the historical generated power and the historical total power of the region belong;
for each weather station, calculating a first correlation between the historical irradiance of the weather station in each time period and the historical total power of the region in the corresponding time period respectively, and a second correlation between the historical irradiance of the weather station in each time period and the historical generating power of each distributed photovoltaic power station respectively;
determining a first average correlation between the historical irradiance of the weather station and the historical total power of the region according to all the first correlations corresponding to the weather station in each time period;
comparing the first correlation under each time interval with a first preset threshold respectively, and determining a first proportion of the time interval of which the first correlation exceeds the first preset threshold in all the time intervals;
determining a second average correlation between the historical irradiance of the weather station and the historical generated power according to all the second correlations corresponding to the weather station in each time period, comparing the second average correlation corresponding to each weather station with a second preset threshold value, and determining a second proportion of the weather stations of which the second average correlation exceeds the second preset threshold value in all the weather stations.
4. The method for building the power prediction model of the distributed photovoltaic power plant of claim 3, wherein the step of sequentially performing normalization processing and weighted summation on the correlation parameters to obtain irradiance scores of the meteorological stations comprises the steps of:
respectively carrying out normalization processing on the first average correlation, the first proportion and the second proportion corresponding to each weather station by adopting a min-max algorithm to obtain a normalized first average correlation, a normalized first proportion and a normalized second proportion;
and performing weighted summation on the normalized first average correlation, the normalized first proportion and the normalized second proportion to determine the irradiance score of each weather station.
5. The distributed photovoltaic power plant power prediction model creation method of any of claims 1 to 4, wherein the creating a power prediction model from the historical meteorological data and the historical generated power based on the correlation parameter comprises:
comparing the correlation parameter corresponding to the reference weather station with a third preset threshold value;
and when the correlation parameter corresponding to the reference weather station is greater than or equal to the third preset threshold value, establishing a power prediction model by taking the historical weather data acquired by the reference weather station as an input variable and combining the historical total power of the region.
6. The distributed photovoltaic power plant power prediction model creation method of claim 5, wherein the historical meteorological data comprises historical irradiance, and wherein creating a power prediction model from historical meteorological data and the historical generated power comprises:
when the correlation parameter is smaller than the third preset threshold, dividing the calibration area into a plurality of sub-areas;
acquiring meteorological satellite historical data of each subregion, and calculating earth surface data of each subregion according to inversion of the meteorological satellite data, wherein the earth surface data comprises earth surface irradiance;
establishing an earth surface irradiance error correction model according to the meteorological satellite historical data of the sub-area where the reference meteorological station is located;
correcting the surface irradiance of each sub-area according to the surface irradiance error correction model to obtain corrected surface irradiance;
respectively calculating historical summary power of each subarea according to the historical power generation power of all the distributed photovoltaic power stations in each subarea;
and respectively establishing a power prediction model of each sub-area according to the corrected surface irradiance and the historical summary power.
7. The method of claim 6 wherein the meteorological satellite historical data includes surface shortwave radiation, and wherein the modeling of surface irradiance error corrections based on the meteorological satellite historical data for sub-areas in which the reference meteorological station is located comprises:
calculating the deviation between the historical irradiance collected by the reference weather station and the surface short-wave radiation of the sub-area where the reference weather station is located;
and fitting by adopting a machine learning regression algorithm according to the deviation and the meteorological satellite historical data of the sub-area where the reference meteorological station is located to obtain the earth surface irradiance error correction model.
8. The method for building the power prediction model of the distributed photovoltaic power plant of claim 6 wherein the building the power prediction model of each sub-area according to the modified surface irradiance and the historical aggregate power comprises:
for each sub-area, calculating a first correlation of the historical aggregate power and the corrected surface irradiance at each time period;
comparing the first correlation of each time period with a fourth preset threshold, and taking the historical summary power corresponding to the first correlation which is greater than or equal to the fourth preset threshold and the corrected ground surface irradiance as modeling data;
and establishing a power prediction model of each sub-region according to the modeling data.
9. A power prediction method for a distributed photovoltaic power station is characterized by comprising the following steps:
acquiring weather forecast data of a calibration area;
inputting the weather forecast data into a power prediction model of the calibration area, and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
wherein the power prediction model is built using the distributed photovoltaic power plant power prediction model building method of any one of claims 1 to 8.
10. The utility model provides a distributed photovoltaic power plant power prediction model building device which characterized in that includes:
the acquisition module is used for acquiring historical power generation power of each distributed photovoltaic power station in a calibration area and historical meteorological data acquired by at least one meteorological station;
the processing module is used for determining a reference meteorological station in all the meteorological stations according to the historical meteorological data and the historical power generation power, and determining a correlation parameter between the historical meteorological data corresponding to the reference meteorological station and the regional historical total power, wherein the regional historical total power is the sum of all the historical power generation powers;
and the establishing module is used for establishing a power prediction model according to the historical meteorological data and the historical generated power based on the correlation parameter.
11. A distributed photovoltaic power plant power prediction device, comprising:
the acquisition module is used for acquiring weather forecast data of the calibration area;
the prediction module is used for inputting the weather forecast data into a power prediction model of the calibration area and outputting the predicted power of the distributed photovoltaic power station in the calibration area;
wherein the power prediction model is built using the distributed photovoltaic power plant power prediction model building method of any one of claims 1 to 8.
12. An electronic device comprising a processor and a memory;
the memory for storing a computer program;
the processor, when executing the computer program, is configured to implement the method of establishing a distributed photovoltaic power plant power prediction model according to any one of claims 1 to 8 or the method of predicting a distributed photovoltaic power plant power according to claim 9.
13. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the distributed photovoltaic power plant power prediction model building method according to any one of claims 1 to 8 or the distributed photovoltaic power plant power prediction method according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504830.XA CN112446554B (en) | 2020-12-18 | 2020-12-18 | Power prediction model establishment method, power prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504830.XA CN112446554B (en) | 2020-12-18 | 2020-12-18 | Power prediction model establishment method, power prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446554A true CN112446554A (en) | 2021-03-05 |
| CN112446554B CN112446554B (en) | 2024-05-14 |
Family
ID=74740397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011504830.XA Active CN112446554B (en) | 2020-12-18 | 2020-12-18 | Power prediction model establishment method, power prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446554B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113991638A (en) * | 2021-08-31 | 2022-01-28 | 华能(福建)能源开发有限公司 | Prediction method for generated power of new energy station in different places |
| CN117150891A (en) * | 2023-08-15 | 2023-12-01 | 幂光新材料科技（上海）有限公司 | Intelligent prediction method and system for LED lamp bead power based on data driving |
| CN117639662A (en) * | 2023-12-07 | 2024-03-01 | 电暴猿(上海)科技有限公司 | Intelligent monitoring-based photovoltaic power station power prediction method and system |
Citations (10)
| 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 |
| US20140207437A1 (en) * | 2011-07-25 | 2014-07-24 | Clean Power Research, L.L.C. | Computer-Implemented System And Method For Inferring Operational Specifications Of A Fleet Of Photovoltaic Power Generation Systems |
| CN108053048A (en) * | 2017-11-06 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system |
| CN109636076A (en) * | 2019-02-14 | 2019-04-16 | 国能日新科技股份有限公司 | A kind of distributed photovoltaic power prediction main station system |
| CN109919353A (en) * | 2019-01-11 | 2019-06-21 | 杭州电子科技大学 | A kind of distributed photovoltaic prediction technique of the ARIMA model based on spatial coherence |
| CN110008982A (en) * | 2019-01-11 | 2019-07-12 | 国网浙江省电力有限公司 | A kind of weather monitoring point selection method based on photovoltaic power generation power output cluster |
| US20200004908A1 (en) * | 2012-10-17 | 2020-01-02 | Clean Power Research, L.L.C. | System for tuning a photovoltaic power generation plant forecast with the aid of a digital computer |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111626473A (en) * | 2020-04-17 | 2020-09-04 | 国网上海市电力公司 | Two-stage photovoltaic power prediction method considering error correction |
| CN111832800A (en) * | 2020-05-28 | 2020-10-27 | 中国电力科学研究院有限公司 | Photovoltaic power station power prediction method and device |
-
2020
- 2020-12-18 CN CN202011504830.XA patent/CN112446554B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140207437A1 (en) * | 2011-07-25 | 2014-07-24 | Clean Power Research, L.L.C. | Computer-Implemented System And Method For Inferring Operational Specifications Of A Fleet Of Photovoltaic Power Generation Systems |
| US20200004908A1 (en) * | 2012-10-17 | 2020-01-02 | Clean Power Research, L.L.C. | System for tuning a photovoltaic power generation plant forecast with the aid of a digital computer |
| 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 |
| CN108053048A (en) * | 2017-11-06 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system |
| CN109919353A (en) * | 2019-01-11 | 2019-06-21 | 杭州电子科技大学 | A kind of distributed photovoltaic prediction technique of the ARIMA model based on spatial coherence |
| CN110008982A (en) * | 2019-01-11 | 2019-07-12 | 国网浙江省电力有限公司 | A kind of weather monitoring point selection method based on photovoltaic power generation power output cluster |
| CN109636076A (en) * | 2019-02-14 | 2019-04-16 | 国能日新科技股份有限公司 | A kind of distributed photovoltaic power prediction main station system |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111626473A (en) * | 2020-04-17 | 2020-09-04 | 国网上海市电力公司 | Two-stage photovoltaic power prediction method considering error correction |
| CN111832800A (en) * | 2020-05-28 | 2020-10-27 | 中国电力科学研究院有限公司 | Photovoltaic power station power prediction method and device |
Non-Patent Citations (2)
| Title |
|---|
| 宋人杰;刘福盛;马冬梅;王林;: "基于相似日和WNN的光伏发电功率超短期预测模型", 电测与仪表, no. 07 * |
| 甄皓;: "有限信息下基于深度学习模型的小型分布式光伏电站功率预测", 上海节能, no. 04 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113991638A (en) * | 2021-08-31 | 2022-01-28 | 华能(福建)能源开发有限公司 | Prediction method for generated power of new energy station in different places |
| CN117150891A (en) * | 2023-08-15 | 2023-12-01 | 幂光新材料科技（上海）有限公司 | Intelligent prediction method and system for LED lamp bead power based on data driving |
| CN117150891B (en) * | 2023-08-15 | 2024-04-26 | 幂光新材料科技（上海）有限公司 | Intelligent prediction method and system for LED lamp bead power based on data driving |
| CN117639662A (en) * | 2023-12-07 | 2024-03-01 | 电暴猿(上海)科技有限公司 | Intelligent monitoring-based photovoltaic power station power prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446554B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446554A (en) | Power prediction model establishing method, power prediction method and device | |
| Carpinone et al. | Markov chain modeling for very-short-term wind power forecasting | |
| Rodríguez et al. | Very short-term wind power density forecasting through artificial neural networks for microgrid control | |
| Wang et al. | Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models | |
| CN110705772B (en) | Regional power grid wind power generation power prediction optimization method and device | |
| CN113935512A (en) | Wind power prediction method and device, computer equipment and storage medium | |
| CN110737876A (en) | Regional power grid photovoltaic power prediction optimization method and device | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| CN110705768B (en) | Wind power generation power prediction optimization method and device for wind power plant | |
| CN103440428A (en) | Method for determining self-adaption dynamic weight of combined prediction model for wind electricity power | |
| CN111753461A (en) | Tidal water level correction method, target residual water level acquisition method, device and equipment | |
| CN114065634A (en) | Data-driven power quality monitoring and stationing optimization method and device | |
| Hatamian et al. | Location-aware green energy availability forecasting for multiple time frames in smart buildings: The case of Estonia | |
| Croonenbroeck et al. | Censored spatial wind power prediction with random effects | |
| Madaus et al. | Hyper-local, efficient extreme heat projection and analysis using machine learning to augment a hybrid dynamical-statistical downscaling technique | |
| Alessandrini et al. | Characterization of forecast errors and benchmarking of renewable energy forecasts | |
| CN114492923A (en) | Long-time scale power prediction method | |
| JP7342369B2 (en) | Prediction system, prediction method | |
| CN102096624B (en) | Method for predicting running state of cluster and cluster platform management device | |
| Jang et al. | Spatiotemporal post-calibration in a numerical weather prediction model for quantifying building energy consumption | |
| CN109861222B (en) | Provincial power grid load partition prediction method and system | |
| JP2020123199A (en) | Forecast system and forecast method | |
| Schuster et al. | Design of a Data Driven Reactive Power Forecasting for an Active Cross-Voltage Level Reactive Power Management | |
| Keyantuo et al. | A vector auto-regression based forecast of wind speeds in airborne wind energy systems | |
| Inácio et al. | Ambient Temperature Estimation Using WSN Links and Gaussian Process Regression |
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 | ||
| GR01 | Patent grant |