CN111489028A - Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition - Google Patents
Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition Download PDFInfo
- Publication number
- CN111489028A CN111489028A CN202010272463.9A CN202010272463A CN111489028A CN 111489028 A CN111489028 A CN 111489028A CN 202010272463 A CN202010272463 A CN 202010272463A CN 111489028 A CN111489028 A CN 111489028A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic power
- thundercloud
- cloud
- time
- irradiance
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A photovoltaic power prediction method under a lightning condition based on thundercloud track tracking is characterized in that the time when thundercloud arrives and leaves the sky above a photovoltaic power station is predicted based on the thundercloud track tracking technology, and the relation between the size of a cloud body and the wind intensity is judged by combining momentum theorem, so that the duration time of the thundercloud above the photovoltaic power station is known; and then, using the BP neural network to predict irradiance by taking temperature and humidity as input according to meteorological factors and irradiance historical information, and finally obtaining a predicted value of photovoltaic power through a photovoltaic power conversion formula. The invention simplifies the nonlinear relation between weather factors and irradiance through a photovoltaic power conversion formula, solves the problem of photovoltaic power prediction effectiveness under extreme climate conditions such as thunder and lightning through a cloud track tracking technology, improves prediction precision, provides a reliable predicted value for a power dispatching department, facilitates the dispatching department to carry out power grid tide optimization and dispatching in advance under the influence of extreme climate conditions such as thunder and lightning, and improves the safety and stability of a power system.
Description
Technical Field
The invention belongs to the technical field of photovoltaic power prediction, and particularly relates to a thundercloud trajectory tracking prediction and BP neural network-based photovoltaic power prediction method under a lightning climate condition.
Background
With global warming, fossil energy on earth is reduced day by day, new energy is certainly the trend of future power generation, and the installed capacity of photovoltaic power generation is gradually improved in recent years. The fluctuation and instability are caused by meteorological conditions, wherein cloud layer changes above a photovoltaic power station are the main reasons for causing photovoltaic output changes, particularly under the condition of thunder and lightning climate, the phenomenon of photovoltaic severe fluctuation can occur due to obvious changes of thickness of thunderclouds and other surrounding clouds, and the fluctuation is characterized by large amplitude change fall, short time difference before and after change, large impact on a power grid can be brought, small-proportion photovoltaic investment can influence the quality of electric energy, large-proportion photovoltaic investment can influence the safe and stable operation of a power system, so that a timely and accurate thundercloud tracking technology is used for photovoltaic prediction under the condition of thunder and lightning, and the timeliness and the accuracy of the photovoltaic prediction are greatly improved.
At present, in the aspect of photovoltaic power prediction, direct prediction and indirect prediction are divided. In the aspect of direct prediction, the photovoltaic power is directly predicted by using the existing power, irradiance and meteorological information, and the method combines a large amount of historical information and summarizes statistical rules by a machine learning method to finally obtain a more accurate photovoltaic power predicted value.
In the prior art, a typical direct prediction scheme is photovoltaic power prediction based on an inverse error propagation neural network according to target photovoltaic power station meteorological and photovoltaic power historical information. The method comprises the following specific steps: 1. screening historical data, and selecting meteorological data related to photovoltaic power; 2. training a neural network: the method comprises the steps of taking meteorological data as input of a neural network, taking photovoltaic power data as output of the neural network, and correcting weights of an input layer and a hidden layer, the hidden layer and an output layer of the neural network and thresholds of nerve sources of all layers according to reverse error propagation to obtain a trained neural network; 3. photovoltaic power prediction: and (3) taking the meteorological information of the predicted time period as the input of the trained neural network, and obtaining the output result which is the photovoltaic power of the predicted time period.
The prior art direct photovoltaic power prediction scheme has the following disadvantages:
(1) because meteorological information only has direct physical connection with irradiance, and photovoltaic power and irradiance are connected through a photoelectric conversion model, namely, there is no direct physical connection between the meteorological information and the photovoltaic power, the prediction method adopts a simple statistical method, the physical meaning of a prediction result cannot be explained, and the complexity of a nonlinear function established in statistical prediction is increased.
(2) Under the condition of thunder weather, the appearance and disappearance of thunderclouds above a photovoltaic power station are main reasons causing severe fluctuation of photovoltaic, the existing method cannot effectively distinguish two phenomena that the thunderclouds appear above the photovoltaic power station and do not appear above the photovoltaic power station, the prediction result cannot reflect the characteristics of short-time irradiance or steep rise and steep fall of photovoltaic power under the condition of thunder weather, and the prediction is often invalid under the condition of thunder.
(3) The existing method generally uses all meteorological information as input of prediction in a unified way, a large amount of data occupies a large amount of memory of a computer, and a large amount of time is consumed when the historical data is used for machine learning.
Aiming at the defects, the irradiance is predicted through meteorological factors, the irradiance prediction is carried out according to the temperature and the humidity, the irradiance is suitable for the meteorological factors to be directly related, so that the irradiance prediction method has certain physical significance, compared with the method of directly establishing the nonlinear relation between the meteorological factors and the photovoltaic power, the predicted nonlinear relation is simplified, and the machine can obtain a more accurate nonlinear relation by needing less historical data in the learning process. Based on a thundercloud track tracking technology, two phenomena of thundercloud appearing above a photovoltaic power station and thundercloud not appearing above the photovoltaic power station are effectively distinguished, the time when the thundercloud arrives at and leaves the space above the photovoltaic power station is predicted, the duration time of the thundercloud above the photovoltaic power station is further known, the amplitude value of irradiance is predicted by combining meteorological and irradiance historical data when the thundercloud arrives at the space above the photovoltaic power station, the change degree of steep rise and decline of the irradiance under a meteorological condition of thunder and the duration time after the irradiance falls are effectively predicted, and the effectiveness and the accuracy of the irradiance under a climatic condition of an extreme end of thunder are improved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention discloses a photovoltaic power prediction method under a lightning condition based on thundercloud trajectory tracking.
The technical problems of the invention are mainly solved by the following technical scheme:
a photovoltaic power prediction method under a lightning condition based on thundercloud trajectory tracking is characterized by comprising the following steps:
step 1, determining the latitude and longitude of a target photovoltaic power station, and collecting thundercloud track prediction data and irradiance prediction data from a historical database;
the thundercloud track prediction data refers to the time and longitude and latitude of cloud-ground flash in a set range around a target photovoltaic power station; the irradiance prediction data refers to values of temperature, humidity and irradiance during cloud-to-ground flashing in a set range around a target photovoltaic power station;
step 2, preprocessing the thundercloud track prediction data and the irradiance prediction data collected in the step 1;
step 3, taking the temperature and humidity in the irradiance prediction data preprocessed in the step 2 during the cloud flash generation period as the input of a neural network, and taking the irradiance data as the output of the neural network to train a BP neural network;
step 4, predicting the moment when the thundercloud arrives and leaves the sky of the target photovoltaic power station and the duration time of the thundercloud in the target photovoltaic power station based on the current actually measured wind speed and the thundercloud track prediction data preprocessed in the step 2;
and 5, predicting the irradiance amplitude of the thundercloud above the target photovoltaic power station and the photovoltaic power amplitude of the target photovoltaic power station.
The present invention further includes the following preferred embodiments.
In step 1, the set range around the target photovoltaic power station is a range with a radius of 3000km-9000km with the target photovoltaic power station as a center.
In a preferred embodiment of the present application, the set range around the target photovoltaic power station is a range with a radius of 5600km with the target photovoltaic power station as a center.
Taking the time of cloud-to-ground flashing at the position farthest from the center of the photovoltaic power station in a set range as the initial time of data acquisition;
the cloud-ground flash positioning spatial resolution is 0.0001 degree longitude and 0.0001 degree latitude respectively, and the time resolution is 0.1 × 10-6And second.
Obtaining the values of temperature, humidity and irradiance during each cloud-to-ground flash in a set range and a set time period around the target photovoltaic power plant by: inquiring the date recorded by the cloud flashing within the set range and the set time of the target photovoltaic power station in the historical record, observing the irradiance change curve of the photovoltaic power station corresponding to the date, intercepting the irradiance change curve which is firstly steeply reduced so that the irradiance is equal to or lower than the set irradiance threshold value and is continuously set for a set time period, then steeply raised, and recording the values of the temperature, the humidity and the irradiance under the continuous time period.
Wherein, the steep drop and the steep rise refer to irradiance per square meter being greater than or equal to an irradiance change threshold in a set time. The steep drop and rise refer to irradiance change being more than or equal to 400W/m within 30min2/h。
The irradiance threshold is set to mean that the average value of irradiance clear index is less than 0.28.
The duration setting time period means that the duration is more than 90 min.
In step 2, the processing of the thundercloud trajectory prediction data includes:
calculating the time difference and the latitude and longitude difference of cloud-ground flashes at adjacent moments, and recording the first time difference as t according to the time sequence1The corresponding longitude difference is denoted as Sψ1And the corresponding latitude difference is recorded as Sφ1Similarly, the nth time difference is denoted as tnTo, forThe difference in longitude is denoted as SψnAnd the corresponding latitude difference is recorded as Sφn。
In step 2, the processing of irradiance prediction data comprises:
the temperature and the humidity during the cloud-ground flash generation are used as the input of a BP neural network, the irradiance data is used as the output of the BP neural network, and a data set is formed by corresponding two-to-one mapping relation;
in step 4, predicting the time when the thundercloud arrives and leaves the sky of the target photovoltaic power station and the duration of the thundercloud at the target photovoltaic power station comprises the following steps:
step 4.1, thundercloud track prediction is carried out, preprocessed thundercloud track prediction data, namely the time difference and the longitude and latitude difference of cloud-ground lightning at adjacent moments are sequentially subjected to a kinematic fitting expression of the thundercloud moving track in the longitude direction and the latitude direction, the middle moment in the cloud-ground lightning duration in the cloud-ground lightning event is calculated and recorded as tIntermediate time;
Substituting the thundercloud track prediction data preprocessed in the step 2, namely the time difference and the latitude and longitude difference of cloud-ground lightning at adjacent moments into a kinematic fitting expression of the thundercloud moving track in the longitude direction and the latitude direction in sequence;
t1,t2,…,tn;Sψ1,Sψ2,…,Sψn;Sφ1,Sφ2,…,Sφnsubstituting into fitting expressions in longitude and latitude directions, and respectively fitting initial velocities v in the longitude and latitude directions by using a linear fitting method0And an acceleration a; finally, obtaining a fitting expression:
the fitted expression in the longitudinal direction is:
the fitted expression in the latitudinal direction is:
tnthe time difference between the nth cloud-to-ground flash of the same thundercloud and the next adjacent cloud-to-ground flash of the same thundercloud, SψnIs cloud layer tnDistance moved in the longitudinal direction within a time period, vψ0Is the initial velocity of the cloud layer moving in the longitudinal direction, aψAcceleration of movement of the cloud layer in the longitudinal direction; sφ1Is cloud layer tnThe distance moved in the latitudinal direction over the time period,is the initial velocity of the movement of the cloud layer in the latitudinal direction, aφAcceleration of movement of the cloud layer in the latitudinal direction;
respectively subtracting the longitude and latitude of the central position of the photovoltaic power station and the recorded longitude and latitude of the last cloud-ground flash generation, and respectively substituting the difference values into S in the expressionψnAnd SφnIn (1), find tnT in two fitting expressionsnThe calculation results respectively represent the coincidence time of the thundercloud longitude center and the photovoltaic power station longitude center and the coincidence time of the thundercloud latitude center and the photovoltaic power station latitude center, and t in the two fitting expressions is solvednThe average value of the calculation results is regarded as the middle moment of the irradiance value in the minimum duration time of the amplitude under the influence of the thundercloud, and is recorded as tIntermediate time。
Step 4.2, predicting duration t of thundercloud above the photovoltaic power stationDuration of time;
Calculating the time constant tau of each cloud-ground lightning event of the target photovoltaic power station in the historical database according to the following formula:
wherein v is a vertical cloud layer wind speed measured value in the historical database; v. of0The initial velocity of the cloud layer is vψ0Andby step 4.1 fittingCalculating to obtain; a is the acceleration of the cloud layer, and isψAnd aφThe synthetic vector is obtained by fitting calculation in the step 4.1; v. ofCloudThe cloud layer moving speed is calculated according to the cloud layer acceleration a and each cloud-to-ground flash occurrence and ending time obtained from a historical database;
and obtaining a statistical ratio p by averaging according to the following formula according to the historical data information:
wherein w is variable representation of the number of cloud-ground lightning events in the historical database, m is the total number of cloud-ground lightning events in the historical database, and is determined by querying the historical database, and tauwCalculating a time constant of the w-th cloud-to-ground flash event in the historical database; t is tDuration wThe duration of the w-th cloud-to-ground flash event is obtained through historical database query; p is a statistical ratio;
according to the current actually measured wind speed v and v in the fitting result0And a, calculating to obtain a time constant tau of the forecast cloud-ground lightning event, eliminating a negative value, and obtaining duration t of the forecast thundercloud above the photovoltaic power station according to a statistical ratio pDuration of time:
tDuration of time=p×τ。
And 4.3, calculating and predicting the time when the thundercloud arrives and leaves the space above the photovoltaic power station.
T obtained in step 4.2Duration of timeT obtained by combining step 4.1Intermediate timeRespectively obtaining the predicted time t when the thundercloud arrives and leaves the sky of the photovoltaic power stationsAnd te:
Wherein:
in step 5, forecasting the time when the thundercloud reaches and leaves the sky of the target photovoltaic power station, which is obtained by forecasting in step 4, and forecasting the irradiance of the thundercloud when the thundercloud passes through the target photovoltaic power station by taking forecast data of the temperature and the humidity at the corresponding time as the input of the BP neural network forecasting model trained in step 3; then, calculating a photovoltaic power predicted value under the lightning condition according to the predicted value of the irradiance;
converting the irradiance predicted value into a photovoltaic power predicted value according to the following formula:
Ps=ηPVSE[1-0.005(T+0.03E+25)]
wherein: psFor photovoltaic power generation power prediction value ηPVConverting the efficiency of the photovoltaic cell; s is the area of the photovoltaic cell panel; e is an irradiance predicted value; t is the air temperature.
The invention has the following beneficial technical effects:
the photovoltaic power prediction method based on thundercloud tracking is provided according to irradiance characteristics under the thunder condition, the problem of effectiveness of photovoltaic power prediction under the thunder extreme climate condition is solved, the prediction precision of the photovoltaic power under the thunder extreme climate condition is improved, reliable prediction values are provided for power dispatching departments, the power grid tide transfer and dispatching can be conveniently carried out in advance by the dispatching departments under the influence of the thunder extreme climate condition, the influence of the thunder weather on the power grid is reduced, and the safety and the stability of a power system are improved.
Drawings
Fig. 1 is a schematic flow chart of a photovoltaic power prediction method based on thundercloud trajectory tracking under a lightning condition according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and examples of the specification.
As shown in the attached figure 1, the invention discloses a photovoltaic power prediction method under a lightning condition based on thundercloud trajectory tracking. In the present invention, first, a hypothesis condition and a fitting expression are determined:
determining the hypothetical conditions: (1) the researched object is thundercloud flying from a distant place, and cannot be suddenly generated above a photovoltaic power station. (2) Approximately considering the longitude and latitude of the cloud-ground flash point as the position of the rain-accumulating cloud center; (3) the wind thrust and the cloud speed meet the momentum theorem; (4) and considering that the moving track of the cloud layer is uniformly accelerated linear motion with the initial speed not being 0 in the warp direction and the weft direction respectively, and fitting multiple groups of data to obtain corresponding results.
Determining a fitting expression: the kinematic fitting expressions of the moving track of the cloud layer in the warp direction and the weft direction are as follows:
the meridian direction fitting expression is:
the weft direction fitting expression is as follows:
wherein, tnTime difference S between adjacent moments when cloud-to-ground flash occurs on the same cloud layerψnIs cloud layer tnDistance moved in the longitudinal direction within a time period, vψ0Is the initial velocity of the cloud layer moving in the longitudinal direction, aψAcceleration of movement of the cloud layer in the longitudinal direction; sφ1Is cloud layer tnThe distance moved in the latitudinal direction over the time period,is the initial velocity of the movement of the cloud layer in the latitudinal direction, aφIs the acceleration of the movement of the cloud in the latitudinal direction.
As shown in fig. 1, the present invention specifically comprises the following steps:
step 1, determining the longitude and latitude of a target photovoltaic power station, and acquiring thundercloud track prediction data in a set range and a set time period around the photovoltaic power station from a historical database according to the longitude and latitude of the target photovoltaic power station; inquiring the date recorded by cloud-to-ground flashing in a set range and a set time period around the target photovoltaic power station in a historical database, and acquiring irradiance prediction data of the target photovoltaic power station;
screening thundercloud track prediction data, namely recording the cloud-ground flash generation time and longitude and latitude in a certain range around a photovoltaic power station on the premise of knowing the accurate longitude and latitude range of a target photovoltaic power station, wherein the cloud-ground flash positioning spatial resolution is 0.0001 degree longitude and 0.0001 degree latitude respectively, and the time resolution is 0.1 × 10-6And second.
The set range around the target photovoltaic power station is a range with the target photovoltaic power station as the center and the radius of 3000km-9000 km. In the preferred embodiment of the application, a range with the radius of 5600km is selected as a set range around the target photovoltaic power station for prediction.
Screening for irradiance prediction history data: inquiring the date recorded by cloud field flashing within a certain range around the photovoltaic power station in the historical record, observing the irradiance change curve of the photovoltaic power station corresponding to the date, and intercepting the curve with steep drop firstly and then lasting for a period of time at a position with a very low amplitude, wherein the average value of the irradiance clear index of the period of time is less than 0.28, and then recording the values of temperature, humidity and irradiance of the period of time.
Wherein, the steep drop and the steep rise refer to irradiance per square meter being greater than an irradiance change threshold within a set time. In the preferred embodiment of the application, the steep drop and rise refer to irradiance change of more than or equal to 400W/m within 30min2H is used as the reference value. The irradiance threshold is set to mean that the average value of irradiance clear index is less than 0.28. The duration setting time period means that the duration is more than 90 min.
The calculation formula of the irradiance clear index is as follows:
true solar time ═ Beijing time- (120-local longitude)/15 + E
Wherein: k is a radical ofexIs a clear index; i is the actual irradiance; i isexThe irradiance in clear sky which is not influenced by cloud layer and atmosphere is calculated; isc is the solar constant, which is about 1367; i isONThe intensity of solar radiation of an atmospheric layer circumscribed plane; thetaZIs the solar zenith angle; solar declination angle; phi is the local geographical latitude; omega is the solar time angle; n is the accumulated day; s and F respectively represent the hours and minutes of the real sun; and E is the time difference generated by the movement and the rotation speed change of the earth around the sun, and the time difference unit is min.
And 2, preprocessing the thundercloud track prediction data and the irradiance prediction data acquired in the step 1.
Step 2.1, processing the thundercloud trajectory prediction data: according to the thundercloud track prediction screening data, calculating to obtain the time difference and the latitude and longitude difference of the cloud-ground lightning at the adjacent moments, and according to the time sequence, recording the first time difference as t1The corresponding longitude difference is denoted as Sψ1And the corresponding latitude difference is recorded as Sφ1Similarly, the nth time difference is denoted as tnThe corresponding longitude difference is denoted as SψnAnd the corresponding latitude difference is recorded as Sφn。
Step 2.2, processing irradiance prediction data: and taking the same time as a basis, taking the temperature and the humidity at the lightning occurrence time as the input of the neural network, taking the irradiance data as the output of the neural network, and correspondingly forming a data set by using a two-to-one mapping relation.
Step 3, training the BP neural network: and (3) taking the temperature and the humidity of the lightning occurrence moment in the historical data as the input of the neural network, and taking the irradiance data as the output of the neural network to train the BP neural network.
Step 4, predicting the time when the thundercloud arrives and leaves the sky of the target photovoltaic power station and the duration time of the thundercloud in the target photovoltaic power station;
in the technical solution of the present application, the method for predicting a thundercloud trajectory may adopt a time series method and an artificial intelligence method in the prior art, and may also adopt the preferred embodiments introduced below in the present application.
The following thundercloud trajectory prediction method is preferred in the present application, and is not intended to limit the spirit of the present invention, but to better illustrate the technical solution of the present invention. All existing thundercloud trajectory prediction methods in the prior art can be applied to the method and can obtain beneficial technical effects.
Step 4.1, thundercloud trajectory prediction:
will t1,t2,…,tn;Sψ1,Sψ2,…,Sψn;Sφ1,Sφ2,…,SφnSubstituting into the fitting expressions of the longitude and latitude directions in the step 1.2, and respectively fitting the initial velocities v in the longitude and latitude directions by using a linear fitting method0And an acceleration a. Finally, obtaining a fitting expression:
the fitted expression in the longitudinal direction is:
the fitted expression in the latitudinal direction is:
respectively subtracting the longitude and latitude of the central position of the photovoltaic power station and the recorded longitude and latitude of the last cloud-ground flash generation, and respectively substituting the difference values into S in the expressionψnAnd SφnIn (1), find tnEach equation has two results, the result that the median of each equation is negative is respectively discarded, the two results that the median is positive are finally reserved, the two results that the median is positive respectively represent the time when the thundercloud longitude center and the photovoltaic power station longitude center coincide and the time when the thundercloud latitude center and the photovoltaic power station latitude center coincide, the average value is calculated to be the middle moment of the irradiance numerical value in the minimum continuous time period under the influence of the thundercloud, and the average value is recorded as tIntermediate time。
Step 4.2, forecasting the duration of the thundercloud above the photovoltaic power station:
Ft=mwind power(v-v0)
mWind power=ρWind powerQS
Q=v*1=v
Obtaining:
F=ρwind powerv(v-v0)S
Because:
a refers to the total acceleration of thundercloud, is aψAnd aφVector sum of
mCloud=ρCloudV∝hr2
V is the volume of thundercloud
S∝hr
Obtaining:
satisfies the following conditions:
vcloudRefers to the moving speed of cloud layer, tau is a set parameter, has no practical physical meaning, and tDuration of timeIn direct proportion, wherein:
τ∝tduration of time
Wherein: s is the contact area of wind and the cloud layer; q is the flow of wind; v is a vertical cloud layer wind speed measured value in a certain direction; v. of0The initial velocity of the cloud in the same direction as the wind speed is vψ0Andthe synthetic vector is obtained by fitting calculation in the step 4.1; f is thrust; m isWind powerIs the air mass; rhoWind powerFor the air density, the value of m is 1.293 g/LCloudIs the mass of the cloud; h is the height of the cloud; r is the generalized radius of the cloud top view;
according to historical data information, the data can be obtained by statistical analysis and mean calculation:
wherein, w is variable representation of the number of the historical data, m is the specific number of the historical data, and the specific value of m is determined according to the number of the inquired historical data; p is the statistical ratio
According to the measured wind speed v and v in the fitting result0And a, calculating to obtain tau, eliminating a negative value, and obtaining the duration t of the thundercloud above the photovoltaic power station according to a statistical result pDuration of time:
tDuration of time=p×τ
Step 4.3, the moment when the thundercloud arrives and leaves the space above the photovoltaic power station:
t obtained in step 4.2Duration of timeT obtained by combining step 4.1Intermediate timeRespectively obtaining the time t when the thundercloud arrives and leaves the space above the photovoltaic power stationsAnd te。
Wherein:
step 5, predicting the irradiance amplitude of the thundercloud above the target photovoltaic power station and the photovoltaic power amplitude of the target photovoltaic power station:
predicting the moments when the thundercloud arrives and leaves the sky above the target photovoltaic power station, which are obtained by predicting in the step 4, and taking forecast data of the temperature and the humidity at the corresponding moments as the input of the BP neural network prediction model trained in the step 3 to predict the irradiance of the thundercloud during the period when the thundercloud passes through the target photovoltaic power station; then, calculating a photovoltaic power predicted value under the lightning condition according to the predicted value of the irradiance;
converting the irradiance predicted value into a photovoltaic power predicted value according to the following formula:
Ps=ηPVSE[1-0.005(T+0.03E+25)]
wherein: psFor photovoltaic power generation power prediction value ηPVConverting the efficiency of the photovoltaic cell; s is the area of the photovoltaic cell panel; e is an irradiance predicted value; t is the air temperature.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (13)
1. A photovoltaic power prediction method under a lightning condition based on thundercloud trajectory tracking is characterized by comprising the following steps:
step 1, determining the latitude and longitude of a target photovoltaic power station, and collecting thundercloud track prediction data and irradiance prediction data from a historical database;
the thundercloud track prediction data refers to the time and longitude and latitude of cloud-ground flash in a set range around a target photovoltaic power station; the irradiance prediction data refers to values of temperature, humidity and irradiance during cloud-to-ground flashing in a set range around a target photovoltaic power station;
step 2, preprocessing the thundercloud track prediction data and the irradiance prediction data collected in the step 1;
step 3, taking the temperature and humidity in the irradiance prediction data preprocessed in the step 2 during the cloud flash generation period as the input of a neural network, and taking the irradiance data as the output of the neural network to train a BP neural network;
step 4, predicting the moment when the thundercloud arrives and leaves the sky of the target photovoltaic power station and the duration time of the thundercloud in the target photovoltaic power station based on the current actually measured wind speed and the thundercloud track prediction data preprocessed in the step 2;
and 5, predicting the irradiance amplitude of the thundercloud above the target photovoltaic power station and the photovoltaic power amplitude of the target photovoltaic power station.
2. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1, characterized in that:
in step 1, the set range around the target photovoltaic power station is a range with a radius of 3000km-9000km with the target photovoltaic power station as a center.
3. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 2, characterized in that:
the set range around the target photovoltaic power station is a range with the target photovoltaic power station as the center and the radius of 5600 km.
4. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1 or 2, characterized in that:
taking the time of cloud-to-ground flashing at the position farthest from the center of the photovoltaic power station in a set range as the initial time of data acquisition;
the cloud-ground flash positioning spatial resolution is 0.0001 degree longitude and 0.0001 degree latitude, and the time resolution is 0.1 × 10-6And second.
5. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1 or 2, characterized in that:
obtaining values of temperature, humidity and irradiance during each cloud-to-ground flash within a set range around a target photovoltaic power plant by: inquiring the date recorded by the cloud flashing within the set range and the set time of the target photovoltaic power station in the historical record, observing the irradiance change curve of the photovoltaic power station corresponding to the date, intercepting the irradiance change curve which is firstly steeply reduced so that the irradiance is equal to or lower than the set irradiance threshold value and is continuously set for a period of time, then steeply raised, and recording the values of temperature, humidity and irradiance under the continuous period of time;
wherein, the steep drop and the steep rise refer to that the change of irradiance is larger than or equal to an irradiance change threshold value in a set time.
6. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 5, wherein:
the steep drop and rise refer to irradiance change being more than or equal to 400W/m within 30min2。
Setting an irradiance threshold value means that the average value of irradiance clear index is less than 0.28;
the duration setting time period means that the duration is more than 90 min.
7. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1 or 6, characterized in that:
in step 2, the processing of the thundercloud trajectory prediction data includes:
calculating the time difference and the latitude and longitude difference of cloud-ground flashes at adjacent moments, and recording the first time difference as t according to the time sequence1The corresponding longitude difference is denoted as Sψ1And the corresponding latitude difference is recorded as Sφ1Similarly, the nth time difference is denoted as tnThe corresponding longitude difference is denoted as SψnAnd the corresponding latitude difference is recorded as Sφn。
8. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 7, wherein:
in step 2, the processing of irradiance prediction data comprises:
and (3) taking the temperature and the humidity during the cloud-to-ground flash generation as the input of the BP neural network, taking the irradiance data as the output of the BP neural network, and corresponding the irradiance data to form a data set according to a two-to-one mapping relation.
9. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1 or 8, characterized in that:
in step 4, predicting the time when the thundercloud arrives and leaves the sky of the target photovoltaic power station and the duration of the thundercloud at the target photovoltaic power station comprises the following steps:
step 4.1, thundercloud track prediction is carried out, preprocessed thundercloud track prediction data, namely the time difference and the longitude and latitude difference of cloud-ground lightning at adjacent moments are sequentially subjected to a kinematic fitting expression of the thundercloud moving track in the longitude direction and the latitude direction, the middle moment in the cloud-ground lightning duration in the cloud-ground lightning event is calculated and recorded as tIntermediate time;
Step 4.2, predicting duration t of thundercloud above the photovoltaic power stationDuration of time;
And 4.3, calculating and predicting the time when the thundercloud arrives and leaves the space above the photovoltaic power station.
10. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 9, wherein:
in step 4.1, the thundercloud trajectory prediction data preprocessed in step 2, namely the time difference and the latitude and longitude difference of cloud-ground flashes at adjacent moments are substituted into a kinematic fitting expression of the thundercloud movement trajectory in the warp direction and the weft direction in sequence;
t1,t2,…,tn;Sψ1,Sψ2,…,Sψn;Sφ1,Sφ2,…,Sφnsubstituting into fitting expressions in longitude and latitude directions, and respectively fitting initial velocities v in the longitude and latitude directions by using a linear fitting method0And an acceleration a; finally, obtaining a fitting expression:
the fitted expression in the longitudinal direction is:
the fitted expression in the latitudinal direction is:
tnthe time difference between the nth cloud-to-ground flash of the same thundercloud and the next adjacent cloud-to-ground flash of the same thundercloud, SψnIs cloud layer tnDistance moved in the longitudinal direction within a time period, vψ0Is the initial velocity of the cloud layer moving in the longitudinal direction, aψAcceleration of movement of the cloud layer in the longitudinal direction; sφ1Is cloud layer tnThe distance moved in the latitudinal direction over the time period,is the initial velocity of the movement of the cloud layer in the latitudinal direction, aφAcceleration of movement of the cloud layer in the latitudinal direction; v. of0The initial velocity of the cloud layer is vψ0Andthe resultant vector of (a); a is the acceleration of the cloud layer, and isψAnd aφThe resultant vector of (a);
respectively subtracting the longitude and latitude of the central position of the target photovoltaic power station from the recorded longitude and latitude of the last cloud-ground flash generation, and respectively substituting the difference into S in the expressionψnAnd SφnIn (1), find tnT in two fitting expressionsnThe calculation results respectively represent the coincidence time of the thundercloud longitude center and the photovoltaic power station longitude center and the coincidence time of the thundercloud latitude center and the photovoltaic power station latitude center, and t in the two fitting expressions is solvednThe average value of the calculation results is regarded as the middle moment of the irradiance value in the minimum duration time of the amplitude under the influence of the thundercloud, and is recorded as tIntermediate time。
11. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 10, wherein:
in step 4.2, the duration of the thundercloud over the photovoltaic power station is predicted, which comprises the following steps:
calculating the time constant tau of each cloud-ground lightning event of the target photovoltaic power station in the historical database according to the following formula:
wherein v is a vertical cloud layer wind speed measured value in the historical database; v. of0The initial velocity of the cloud layer is vψ0Andthe synthetic vector is obtained by fitting calculation in the step 4.1; a is the acceleration of the cloud layer, and isψAnd aφThe synthetic vector is obtained by fitting calculation in the step 4.1; v. ofCloudThe cloud layer moving speed is calculated according to the cloud layer acceleration a and each cloud-to-ground flash occurrence and ending time obtained from a historical database;
and obtaining a statistical ratio p by averaging according to the following formula according to the historical data information:
wherein w is variable representation of the number of cloud-ground lightning events in the historical database, m is the total number of cloud-ground lightning events in the historical database, and is determined by querying the historical database, and tauwCalculating a time constant of the w-th cloud-to-ground flash event in the historical database; t is tDuration wThe duration of the w-th cloud-to-ground flash event is obtained through historical database query; p is a statistical ratio;
according to the current actually measured wind speed v and v in the fitting result0And a, calculating to obtain a time constant tau of the forecast cloud-ground lightning event, eliminating a negative value, and obtaining duration t of the forecast thundercloud above the photovoltaic power station according to a statistical ratio pDuration of time:
tDuration of time=p×τ。
12. The thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 11, wherein:
step 4.3, calculating the moment when the thundercloud arrives and leaves the sky above the photovoltaic power station, wherein the moment comprises the following contents:
t obtained in step 4.2Duration of timeT obtained by combining step 4.1Intermediate timeRespectively obtaining the predicted time t when the thundercloud arrives and leaves the sky of the photovoltaic power stationsAnd te:
Wherein:
13. the thundercloud trajectory tracking-based photovoltaic power prediction method under lightning conditions according to claim 1 or 12, wherein:
in step 5, forecasting the time when the thundercloud reaches and leaves the sky of the target photovoltaic power station, which is obtained by forecasting in step 4, and forecasting the irradiance of the thundercloud when the thundercloud passes through the target photovoltaic power station by taking forecast data of the temperature and the humidity at the corresponding time as the input of the BP neural network forecasting model trained in step 3; then, calculating a photovoltaic power predicted value under the lightning condition according to the predicted value of the irradiance;
converting the irradiance predicted value into a photovoltaic power predicted value according to the following formula:
Ps=ηPVSE[1-0.005(T+0.03E+25)]
wherein: psFor photovoltaic power generation power prediction value ηPVConverting the efficiency of the photovoltaic cell; s is the area of the photovoltaic cell panel; e is an irradiance predicted value; t is the air temperature.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010272463.9A CN111489028B (en) | 2020-04-09 | 2020-04-09 | Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition |
PCT/CN2021/086048 WO2021204226A1 (en) | 2020-04-09 | 2021-04-09 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010272463.9A CN111489028B (en) | 2020-04-09 | 2020-04-09 | Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111489028A true CN111489028A (en) | 2020-08-04 |
CN111489028B CN111489028B (en) | 2021-06-08 |
Family
ID=71812691
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010272463.9A Active CN111489028B (en) | 2020-04-09 | 2020-04-09 | Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111489028B (en) |
WO (1) | WO2021204226A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021204226A1 (en) * | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
CN114676893A (en) * | 2022-03-11 | 2022-06-28 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN115173408A (en) * | 2022-07-27 | 2022-10-11 | 国网湖南省电力有限公司 | Distributed photovoltaic power station aggregation prediction method based on Pearson correlation coefficient |
CN115811044A (en) * | 2022-11-18 | 2023-03-17 | 国网河北省电力有限公司营销服务中心 | Photovoltaic power abrupt change prediction method |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113837121B (en) * | 2021-09-28 | 2024-03-01 | 中国科学技术大学先进技术研究院 | Epidemic prevention robot visual and visual sense cooperative sensing method and system based on brain-like |
CN114418093B (en) * | 2022-01-19 | 2023-08-25 | 北京百度网讯科技有限公司 | Method and device for training path characterization model and outputting information |
CN114462723B (en) * | 2022-04-12 | 2022-07-29 | 南方电网数字电网研究院有限公司 | Cloud layer migration minute-level photovoltaic power prediction method based on high-altitude wind resource influence |
CN114880958B (en) * | 2022-07-12 | 2022-10-11 | 南京气象科技创新研究院 | Visibility forecasting method based on multi-meteorological-factor intelligent deep learning |
CN116307269B (en) * | 2023-05-16 | 2023-10-31 | 华能山东泰丰新能源有限公司 | Photovoltaic power generation power prediction method and device based on artificial intelligence |
CN116865263B (en) * | 2023-08-30 | 2024-01-09 | 天津市普迅电力信息技术有限公司 | Distributed photovoltaic power prediction method based on space grid |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103218673A (en) * | 2013-03-27 | 2013-07-24 | 河海大学 | Method for predicating short-period output power of photovoltaic power generation based on BP (Back Propagation) neural network |
CN103886616A (en) * | 2014-02-25 | 2014-06-25 | 国家电网公司 | Method for short-term prediction of photovoltaic power generation power based on whole-sky imaging data |
CN103971169A (en) * | 2014-04-14 | 2014-08-06 | 国家电网公司 | Photovoltaic super-short-term generated power forecasting method based on cloud cover simulation |
US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
CN109829572A (en) * | 2019-01-14 | 2019-05-31 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power generation power prediction method under thunder and lightning weather |
CN110443405A (en) * | 2019-06-28 | 2019-11-12 | 国网山东省电力公司济宁市任城区供电公司 | A kind of built photovoltaic power station power generation amount forecasting system and method |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10599747B1 (en) * | 2011-07-25 | 2020-03-24 | Clean Power Research, L.L.C. | System and method for forecasting photovoltaic power generation system degradation |
KR20160003373A (en) * | 2014-07-01 | 2016-01-11 | 경북대학교 산학협력단 | Photovoltaic power generation measurement system by latitude and longitude |
CN105182089B (en) * | 2015-07-24 | 2019-03-26 | 中国石油化工股份有限公司 | A kind of thundercloud trajectory predictions method of self-correction |
CN105303254B (en) * | 2015-10-26 | 2019-05-31 | 国网浙江省电力公司电力科学研究院 | A kind of pair of photovoltaic plant receives the method and device that radiation is predicted |
CN105913150A (en) * | 2016-04-12 | 2016-08-31 | 河海大学常州校区 | BP neural network photovoltaic power station generating capacity prediction method based on genetic algorithm |
US11545830B2 (en) * | 2017-01-18 | 2023-01-03 | Board Of Regents, The University Of Texas System | Systems and methods of hierarchical forecasting of solar photovoltaic energy production |
CN109615131A (en) * | 2018-12-07 | 2019-04-12 | 国能日新科技股份有限公司 | Photovoltaic power prediction technique and device |
CN111489028B (en) * | 2020-04-09 | 2021-06-08 | 国网江苏省电力有限公司苏州供电分公司 | Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition |
-
2020
- 2020-04-09 CN CN202010272463.9A patent/CN111489028B/en active Active
-
2021
- 2021-04-09 WO PCT/CN2021/086048 patent/WO2021204226A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103218673A (en) * | 2013-03-27 | 2013-07-24 | 河海大学 | Method for predicating short-period output power of photovoltaic power generation based on BP (Back Propagation) neural network |
CN103886616A (en) * | 2014-02-25 | 2014-06-25 | 国家电网公司 | Method for short-term prediction of photovoltaic power generation power based on whole-sky imaging data |
CN103971169A (en) * | 2014-04-14 | 2014-08-06 | 国家电网公司 | Photovoltaic super-short-term generated power forecasting method based on cloud cover simulation |
US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
CN109829572A (en) * | 2019-01-14 | 2019-05-31 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power generation power prediction method under thunder and lightning weather |
CN110443405A (en) * | 2019-06-28 | 2019-11-12 | 国网山东省电力公司济宁市任城区供电公司 | A kind of built photovoltaic power station power generation amount forecasting system and method |
Non-Patent Citations (2)
Title |
---|
朱想等: ""组合数值天气预报与地基云图的光伏超短期功率预测模型"", 《电力系统自动化》 * |
陈志宝等: ""地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型"", 《中国电机工程学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021204226A1 (en) * | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
CN114676893A (en) * | 2022-03-11 | 2022-06-28 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN114676893B (en) * | 2022-03-11 | 2024-02-02 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN115173408A (en) * | 2022-07-27 | 2022-10-11 | 国网湖南省电力有限公司 | Distributed photovoltaic power station aggregation prediction method based on Pearson correlation coefficient |
CN115173408B (en) * | 2022-07-27 | 2024-05-07 | 国网湖南省电力有限公司 | Distributed photovoltaic power station aggregation prediction method based on Pearson correlation coefficient |
CN115811044A (en) * | 2022-11-18 | 2023-03-17 | 国网河北省电力有限公司营销服务中心 | Photovoltaic power abrupt change prediction method |
Also Published As
Publication number | Publication date |
---|---|
CN111489028B (en) | 2021-06-08 |
WO2021204226A1 (en) | 2021-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111489028B (en) | Thundercloud trajectory tracking-based photovoltaic power prediction method under lightning condition | |
CN105046374B (en) | A kind of power interval prediction technique based on core extreme learning machine model | |
CN108388956B (en) | Photovoltaic power prediction method considering radiation attenuation | |
Liu et al. | An improved photovoltaic power forecasting model with the assistance of aerosol index data | |
WO2020215405A1 (en) | Photovoltaic power station power prediction method and system based on grid-tie inverter operating data | |
Chai et al. | PV power prediction based on LSTM with adaptive hyperparameter adjustment | |
CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
CN102566597A (en) | Photovoltaic generation intelligent adaptive tracking control method and control system thereof | |
CN109034464A (en) | A kind of method that short-term photovoltaic generating system power prediction and result are checked | |
Chung | Estimating solar insolation and power generation of photovoltaic systems using previous day weather data | |
Hiester et al. | Meteorological aspects of siting large wind turbines | |
CN112819189A (en) | Wind power output prediction method based on historical predicted value | |
CN109599899B (en) | Setting method for new energy operation simulation boundary conditions | |
Pawar et al. | Solar PV power forecasting using modified SVR with Gauss-Newton method | |
Marzouq et al. | ANN-based modelling and prediction of daily global solar irradiation using commonly measured meteorological parameters | |
Sahoo et al. | Energy forecasting for grid connected MW range solar PV system | |
CN109829572B (en) | Photovoltaic power generation power prediction method under thunder and lightning weather | |
CN112288129A (en) | Ultra-short-term photovoltaic power prediction model based on transfer learning and foundation cloud chart | |
Azad et al. | Effect of wind shear coefficient on wind velocity at coastal sites of Bangladesh | |
Poitras et al. | Wind speed prediction for a target station using neural networks and particle swarm optimization | |
CN109961190A (en) | A kind of photovoltaic plant power forecasting method a few days ago based on study day degree of fitting cluster | |
CN105956685B (en) | A kind of photovoltaic power factor table prediction technique | |
Aji et al. | Highly accurate daily solar radiation forecasting using SW-SVR for hybrid power plant in Indonesia | |
Sommerfeld | Optimal performance of airborne wind energy systems subject to realistic wind profiles | |
Shi et al. | Short-term photovoltaic power forecast based on long short-term memory network |
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 | ||
GR01 | Patent grant |