CN114895380A - Solar radiation prediction method, device, equipment and medium - Google Patents
Solar radiation prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN114895380A CN114895380A CN202210430524.9A CN202210430524A CN114895380A CN 114895380 A CN114895380 A CN 114895380A CN 202210430524 A CN202210430524 A CN 202210430524A CN 114895380 A CN114895380 A CN 114895380A
- Authority
- CN
- China
- Prior art keywords
- target
- time period
- radiation
- cloud layer
- layer distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005855 radiation Effects 0.000 title claims abstract description 265
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000009826 distribution Methods 0.000 claims abstract description 143
- 230000008859 change Effects 0.000 claims abstract description 83
- 238000010248 power generation Methods 0.000 claims description 23
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 5
- 230000007787 long-term memory Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Environmental & Geological Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a solar radiation prediction method, a device, equipment and a medium, which comprises the following steps: acquiring a cloud layer distribution image observed by a satellite in a target historical time period and surface monitored solar radiation data in the target historical time period; extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data; determining target association characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics; and predicting the ground radiation amount corresponding to the future time period of the target according to the target correlation characteristics. According to the method and the device, the radiation quantity is predicted through the cloud layer distribution characteristics and the radiation change characteristics which are matched in the time sequence, the relevance between the cloud layer distribution and the radiation change can be more accurately determined, the radiation quantity in a future time period is more accurately predicted, the phenomenon of prediction lag in the related technology is avoided, and the prediction error is greatly reduced.
Description
Technical Field
The invention relates to the technical field of solar radiation prediction, in particular to a solar radiation prediction method, device, equipment and medium.
Background
Photovoltaic power generation is a technology of directly converting light energy into electric energy by using the photovoltaic effect of a semiconductor interface. Because the energy of the photovoltaic power generation is derived from renewable solar energy, the photovoltaic power generation has no possibility of exhaustion, and the power generation mode does not generate noise or pollution, is environment-friendly and is a sustainable power generation mode.
The photovoltaic power generation capacity intermittent fluctuation caused by solar radiation change can influence the balance of a power grid, and accurate prediction of the solar radiation change is very critical to guarantee the stable operation of the power grid. In the related art, the radiation prediction mode is only carried out through data observed on the ground, solar radiation fluctuation caused by cloud layer change is difficult to reflect, so that the prediction error under the cloud condition is large, and the problem of time sequence delay exists.
Disclosure of Invention
The embodiment of the application provides a solar radiation prediction method, a device, equipment and a medium, solves the technical problems of low accuracy and time sequence lag existing in the existing technology for predicting the radiation quantity based on ground data, and achieves the technical effects of accurately analyzing cloud layer changes, dynamically matching the cloud layer changes with ground radiation fluctuation and greatly improving the reliability of solar radiation prediction.
In a first aspect, the present application provides a method for predicting solar radiation, the method comprising:
acquiring a cloud layer distribution image observed by a satellite in a target historical time period and surface monitored solar radiation data in the target historical time period;
extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
determining target association characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics;
and predicting the ground radiation amount corresponding to the future time period of the target according to the target correlation characteristics.
Further, extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data, including:
extracting cloud layer distribution characteristics from the cloud layer distribution image through a first convolution network, and extracting radiation change characteristics from solar radiation data through a second convolution network;
and according to the time sequence of the target historical time period, the cloud layer distribution characteristics and the radiation change characteristics are in one-to-one correspondence.
Further, determining target association characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics, and the method comprises the following steps:
inputting corresponding cloud layer distribution characteristics and radiation change characteristics into a long-term and short-term memory network according to the time sequence of the target historical time period, and outputting historical association characteristics and preliminary prediction characteristics of cloud layer distribution and radiation change;
and fusing the historical association features and the preliminary prediction features to obtain target association features of cloud layer distribution and radiation change.
Further, according to the target association characteristics, predicting the ground radiation amount corresponding to the target future time period includes:
and inputting the target correlation characteristics into a full-connection network, and predicting the ground radiation amount corresponding to the target future time period.
Further, according to the target association characteristics, predicting the ground radiation amount corresponding to the target future time period, including:
when the target future time period is adjacent to the target historical time period and the duration of the target future time period is less than or equal to the duration of a single preset unit, predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics corresponding to the target historical time period;
when the time length of the target future time period is greater than or equal to M preset unit time lengths, predicting the ground radiation amount corresponding to the (i + 1) th preset unit time length in the target future time period according to the target correlation characteristics corresponding to the target historical time period, the ground radiation amount predicted by the ith preset unit time length in the target future time period and the ground radiation amount predicted by all the preset unit time lengths before the ith preset unit time length, wherein M is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to M-1.
Further, after predicting the amount of ground radiation corresponding to the target future time period, the method further comprises:
determining a corresponding solar zenith angle and solar altitude angle in a target future time period, and an azimuth angle and an inclination angle of a target photovoltaic system;
determining theoretical effective radiant quantity received by a target photovoltaic system in a target future time period according to the ground radiant quantity, the solar zenith angle, the solar altitude angle, the azimuth angle and the inclination angle predicted and obtained in the target future time period;
and determining the theoretical power generation amount of the target photovoltaic system in the target future time period according to the environmental factors around the target photovoltaic system in the target future time period, the system parameters of the target photovoltaic system and the theoretical effective radiation amount.
In a second aspect, the present application provides a solar radiation prediction apparatus comprising:
the system comprises an original data acquisition module, a satellite observation module and a target data acquisition module, wherein the original data acquisition module is used for acquiring cloud layer distribution images observed by a satellite in a target historical time period and surface monitored solar radiation data in the target historical time period;
the original characteristic analysis module is used for extracting cloud layer distribution characteristics from the cloud layer distribution image and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
the correlation characteristic determining module is used for determining target correlation characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics;
and the radiation prediction module is used for predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics.
Further, the raw feature analysis module includes:
the characteristic extraction submodule is used for extracting cloud layer distribution characteristics from the cloud layer distribution image through a first convolution network and extracting radiation change characteristics from solar radiation data through a second convolution network;
and the characteristic sequence corresponding module is used for corresponding the cloud layer distribution characteristics and the radiation change characteristics one by one according to the time sequence of the target historical time period.
In a third aspect, the present application provides an electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute to implement a solar radiation prediction method as provided in the first aspect.
In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having instructions which, when executed by a processor of an electronic device, enable the electronic device to perform a method of solar radiation prediction as provided in the first aspect.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the cloud layer distribution observed by the satellite in the target historical time period is obtained firstly, the cloud layer distribution characteristics are determined, and compared with ground observation, the cloud layer distribution observed by the satellite is more accurate, so that the accuracy of subsequent ground radiation prediction is improved; then, acquiring surface monitored solar radiation data in a target historical time period, and determining radiation change characteristics; and finally, according to the matched cloud layer distribution characteristics and solar radiation characteristics, the relevance between cloud layer distribution and radiation change can be determined to obtain target relevance characteristics, and then the ground radiation amount corresponding to the target future time period is predicted through the target relevance characteristics. Therefore, the cloud layer distribution characteristics can be analyzed more accurately through the cloud layer images acquired by the satellites, and the accuracy and reliability of the radiation prediction are improved; according to the method and the device, the radiation amount is predicted through the cloud layer distribution characteristics and the radiation change characteristics which are matched in time series, the relevance between cloud layer distribution and radiation change can be more accurately determined, the radiation amount in a future time period can be more accurately predicted, the phenomenon of prediction lag in the related technology is avoided, and the prediction error is greatly reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a solar radiation prediction method provided in the present application;
FIG. 2 is a flow chart illustrating operation of the predictive model provided herein;
fig. 3 is a flowchart for calculating theoretical power generation provided by the present application;
fig. 4 is a schematic structural diagram of a solar radiation prediction apparatus provided in the present application;
fig. 5 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
The embodiment of the application provides a solar radiation prediction method, and solves the technical problem that the accuracy of a radiation prediction mode through ground observation data is low in the prior art.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
a method of solar radiation prediction, the method comprising: acquiring a cloud layer distribution image observed by a satellite in a target historical time period and surface monitored solar radiation data in the target historical time period; extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data; determining target association characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics; and predicting the ground radiation amount corresponding to the future time period of the target according to the target correlation characteristics.
In the embodiment, the cloud layer distribution observed by the satellite in the target historical time period is firstly obtained, and the cloud layer distribution characteristics are determined, so that compared with the ground observation, the cloud layer distribution observed by the satellite is more accurate, and the accuracy of the subsequent ground radiation prediction is improved; then, acquiring surface monitored solar radiation data in a target historical time period, and determining radiation change characteristics; and finally, according to the matched cloud layer distribution characteristics and the matched solar radiation characteristics, the relevance between the cloud layer distribution and the radiation change can be determined to obtain target relevance characteristics, and the ground radiation amount corresponding to the target future time period is predicted through the target relevance characteristics. Therefore, the cloud layer characteristics can be more accurately acquired through the cloud layer images acquired by the satellite, and the accuracy and reliability of the radiation quantity prediction are improved; according to the method and the device, the radiation quantity is predicted through the cloud layer distribution characteristics and the radiation change characteristics which are matched in the time sequence, the relevance between the cloud layer distribution and the radiation change can be more accurately determined, the radiation quantity in a future time period is more accurately predicted, the phenomenon of prediction lag in the related technology is avoided, and the prediction error is greatly reduced.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
First, it is stated that the term "and/or" appearing herein is merely one type of associative relationship that describes an associated object, meaning that three types of relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.
In the related art, the historical radiation amount of the ground and the cloud layer change monitored on the ground are mainly analyzed in a staged manner. For example, historical radiation dose and cloud layer changes of 12:00-13:00 of the day are analyzed, radiation change trends of the time period of 12:00-13:00 are determined, and the fact that the cloud layer of the time period is thin, the cloud is few and the radiation dose is high is assumed. The related technology mainly refers to the cloud layer characteristics and the radiation amount in the time period of 12:00-13:00, and then predicts that the cloud layer characteristics and the radiation amount in the time period of 13:00-14:00 are the same as those in the time period of 12:00-13: 00. However, in practice, the cloud layer has actually increased in thickness after a period of 13:00 to 14:00, resulting in a significant reduction in the radiation dose. Therefore, there is a phenomenon of prediction lag in the related art, resulting in a significantly large prediction error.
In order to solve the above problem, the present embodiment provides a solar radiation prediction method as shown in fig. 1, which includes steps S11-S14.
Step S11, acquiring cloud layer distribution images observed by the satellite in a target historical time period and surface monitored solar radiation data in the target historical time period;
step S12, extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
step S13, determining target association characteristics between cloud layer distribution and radiation change in a target historical time period according to the cloud layer distribution characteristics and the radiation change characteristics;
and step S14, predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics.
With respect to step S11, images of the cloud cover distribution observed by the satellite over a target historical period of time are acquired, as well as data of the solar radiation monitored above over the target historical period of time.
The target historical time period may be determined according to a target future time period for which radiation dose prediction is required. There may be no time interval between the target historical time period and the target future time period, or there may be a time interval of a certain length. It should be noted, however, that the shorter the time interval between the target historical time period and the target future time period (or the closer to 0), the more accurate the subsequent predicted radiation dose will be. For example, if the current time is 13:00 at 1 month and 1 day of 2020, and the target future time period for which radiation dose prediction is required is 13:00-14:00 at 1 month and 1 day of 2020, the target historical time period may be 10:00-13:00 at 1 month and 1 day of 2020.
The satellite can capture the distribution and the change of the cloud layer more clearly from the upper part of the cloud layer to form a cloud layer distribution image. According to the cloud layer distribution image observed by the satellite in the target historical time period, the information such as the thickness, the area, the moving direction and the like of the cloud layer can be determined.
The ground radiation monitoring station can collect the solar radiation data on the ground. The solar radiation data collected in the target historical time period can reflect the change trend of the radiation in the target historical time period.
The acquired cloud layer distribution image and the acquired solar radiation data in the target historical time period need to be mutually corresponding according to the time sequence of the target historical time period. In actual operation, the target history time period may be divided into a plurality of sub-time periods, and the time lengths of the plurality of sub-time periods may be the same or different. For example, the target historical time period is 12:00-13:00 on 1 month and 1 day of 2020, the time duration is 1 hour, 1 hour is averagely divided into 3600 parts, each part corresponds to 1 second, and the corresponding time of each part of sub-time period is sequentially recorded as t1, t2 and t3 … … t3600 (namely t1 represents 12:00:00-12:00:01 on 1 month and 1 day of 2020). the cloud distribution image and the solar radiation data corresponding to the t1 sub-period are matched with each other. Similarly, the cloud layer distribution image and the solar radiation data corresponding to the time periods t2 and t3 … … t3600 are also matched with each other.
Regarding step S12, cloud layer distribution characteristics are extracted from the cloud layer distribution image, and radiation change characteristics corresponding to the cloud layer distribution characteristics are extracted from the solar radiation data.
Specifically, cloud layer distribution features can be extracted from a cloud layer distribution image through a first convolution network (e.g., a three-dimensional convolution network), and radiation change features can be extracted from solar radiation data through a second convolution network (e.g., a one-dimensional convolution network); and according to the time sequence of the target historical time period, the cloud layer distribution characteristics and the radiation change characteristics are in one-to-one correspondence. The first convolution network and the second convolution network can be obtained by performing supervised learning on previously recorded cloud layer distribution images and corresponding solar radiation data.
Continuing with the above example, the cloud distribution image and the solar radiation data corresponding to the t1 sub-period are matched, and then the cloud distribution characteristics obtained from the cloud distribution image corresponding to the t1 sub-period and the radiation variation characteristics obtained from the solar radiation data corresponding to the t1 sub-period are also matched. Similarly, the cloud layer distribution characteristics and the radiation change characteristics corresponding to the time periods t2 and t3 … … t3600 are also matched with each other.
With respect to step S13, a target association characteristic between the cloud profile and the radiation variation over the target historical time period is determined based on the cloud profile characteristic and the radiation variation characteristic.
And inputting the corresponding cloud layer distribution characteristics and radiation change characteristics into the long-short term memory network according to the time sequence of the target historical time period, analyzing the cloud layer distribution characteristics and the radiation change characteristics by the long-short term memory network, and outputting historical association characteristics and preliminary prediction characteristics of cloud layer distribution and radiation change. And fusing the historical association features and the preliminary prediction features to obtain target association features of cloud layer distribution and radiation change.
The Long Short-Term Memory network (LSTM) is a time-cycle neural network, and is specially designed for solving the Long-Term dependence problem of the general cycle neural network. The long-term and short-term memory network can be obtained by performing supervised learning on cloud layer distribution characteristics corresponding to previously recorded cloud layer distribution images and radiation change characteristics corresponding to solar radiation data.
Regarding step S14, the amount of ground radiation corresponding to the target future time period is predicted according to the target-related feature.
And inputting the target correlation characteristics into a full-connection network, and predicting the ground radiation amount corresponding to the target future time period. The fully connected network can be obtained by performing supervised learning on data recorded in the past.
Specifically, the target future time period may be determined according to actual demand, and according to the relationship between the target future time period and the target historical time period, there may be the following two cases:
[ situation one ]
And when the target future time period is adjacent to the target historical time period and the duration of the target future time period is less than or equal to the duration of a single preset unit, predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics corresponding to the target historical time period.
For example, the current time is 13:00 at 1 month and 1 day of 2020, the target future time period for which radiation dose prediction is required is 13:00 to 14:00 at 1 month and 1 day of 2020, the preset unit time length is 1 hour, and the target historical time period is 10:00 to 13:00 at 1 month and 1 day of 2020. The target future time period 13:00-14:00 is adjacent to the target historical time period 10:00-13:00 and only has one preset unit time length, and at the moment, the ground radiation amount corresponding to the target future time period 13:00-14:00 can be predicted according to the target correlation characteristics corresponding to the target historical time period 10:00-13: 00.
[ case two ]
When the time length of the target future time period is greater than or equal to M preset unit time lengths, predicting the ground radiation amount corresponding to the (i + 1) th preset unit time length in the target future time period according to the target correlation characteristics corresponding to the target historical time period, the ground radiation amount predicted by the ith preset unit time length in the target future time period and the ground radiation amount predicted by all the preset unit time lengths before the ith preset unit time length, wherein M is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to M-1.
For example, the current time is 13:00 at 1 month and 1 day of 2020, the target future time period for which radiation dose prediction is required is 13:00 to 17:00 at 1 month and 1 day of 2020, the preset unit time length is 1 hour, and the target historical time period is 10:00 to 13:00 at 1 month and 1 day of 2020. At this time, the target future time period includes 4 hours, that is, includes 4 preset unit durations, which are respectively denoted as T1(13:00-14:00), T2(14:00-15:00), T3(15:00-16:00), and T4(16:00-17: 00).
The T1 meets the above case one, so the ground radiation amount corresponding to the T1 segment can be predicted according to the case one. When the ground radiation amount corresponding to the T1 is predicted according to the target correlation characteristics, cloud layer distribution of the T1 period can be predicted, and cloud layer distribution characteristics of the T1 period are further determined.
When the radiation amount of the T2 segment is predicted, the target historical time segment 10:00-13:00 and the T1 segment are used as a new target historical time segment together in 1 month and 1 day of 2020, and are marked as a second target historical time segment. And determining the correlation characteristics between the corresponding cloud layer distribution and the radiation change of the second target historical time period, and predicting the ground radiation quantity of the T2 section according to the correlation characteristics. In addition, the cloud layer distribution of the section T2 is also predicted.
In predicting the radiation amount of the T3 segment, similarly to the predicted radiation amount of the T2, the target history time segment 10:00 to 13:00 on 1 month and 1 day of 2020, the T1 segment and the T2 segment are collectively regarded as a new target history time segment, and are regarded as a third target history time segment. And determining the correlation characteristics between the cloud layer distribution and the radiation change corresponding to the third target historical time period, and predicting the ground radiation quantity of the T3 section according to the correlation characteristics. In addition, the cloud layer distribution of the section T3 is also predicted.
In predicting the radiation amount of the T4 segment, similarly to the predicted radiation amount of the T2, the target history time segments 2020, 1 month, 1 day 10:00 to 13:00, T1 segment, T2 segment, and T3 segment are collectively referred to as a new target history time segment, which is a fourth target history time segment. And determining the correlation characteristics between the cloud layer distribution and the radiation change corresponding to the fourth target historical time period, and predicting the ground radiation quantity of the T4 section according to the correlation characteristics. In addition, the cloud layer distribution of the section T4 is also predicted.
It should be particularly noted that the predicted ground radiation amount in the T1 segment is predicted according to the actual data of the target historical time segment, and the actual data of the target historical time segment is actually present, so that only measurement or calculation errors exist, and no prediction error exists, so that the predicted ground radiation amount in the T1 segment is more accurate than the predicted radiation amounts in the T2 segment, the T3 segment and the T4 segment.
The predicted ground radiation amount of the T2 segment is predicted based on the actual data of the target historical time segment and the predicted data of the T1 segment, and due to the fact that prediction errors are introduced into the predicted data of the T1 segment, the predicted ground radiation amount of the T2 segment is larger in error, and accuracy of the predicted ground radiation amount is reduced.
Similarly, the accuracy of the predicted radiation amount decreases in the T1 segment, the T2 segment, the T3 segment and the T4 segment. In actual operation, the length of the target future time period can be determined according to the requirement on accuracy.
In summary, in the embodiment, the cloud layer distribution observed by the satellite in the target historical time period is obtained first, and the cloud layer distribution characteristics are determined, so that compared with the ground observation, the cloud layer distribution observed by the satellite is more accurate, and the accuracy of the subsequent ground radiation prediction is improved; then, acquiring surface monitored solar radiation data in a target historical time period, and determining radiation change characteristics; and finally, according to the matched cloud layer distribution characteristics and the matched solar radiation characteristics, the relevance between the cloud layer distribution and the radiation change can be determined to obtain target relevance characteristics, and the ground radiation amount corresponding to the target future time period is predicted through the target relevance characteristics. Therefore, the cloud layer characteristics can be more accurately acquired through the cloud layer images acquired by the satellite, and the accuracy and reliability of the radiation quantity prediction are improved; according to the method and the device, the radiation quantity is predicted through the cloud layer distribution characteristics and the radiation change characteristics which are matched in the time sequence, the relevance between the cloud layer distribution and the radiation change can be more accurately determined, the radiation quantity in a future time period is more accurately predicted, the phenomenon of prediction lag in the related technology is avoided, and the prediction error is greatly reduced.
After predicting the amount of ground radiation corresponding to the target future time period, the method further includes:
and step S21, determining the corresponding solar zenith angle and solar altitude angle in the target future time period, and the azimuth angle and inclination angle of the target photovoltaic system.
And step S22, determining the theoretical effective radiant quantity received by the target photovoltaic system in the target future time period according to the ground radiant quantity, the solar zenith angle, the solar altitude angle, the azimuth angle and the inclination angle which are obtained by predicting the target future time period.
And step S23, determining theoretical power generation amount of the target photovoltaic system in the target future time period according to the environmental factors around the target photovoltaic system in the target future time period, the system parameters of the target photovoltaic system and the theoretical effective radiation amount.
The zenith angle and the altitude angle can be determined according to a zenith angle formula and an altitude angle formula according to the specific moment of the target future time period. According to the geographical position where the ground radiation amount prediction is required and the specific time of the target future time period, the azimuth angle and the inclination angle of the target photovoltaic system can be calculated by depending on an azimuth angle formula and an inclination angle formula, and the specific calculation mode can refer to the related prior art, which is not described in detail in this embodiment.
And inputting the ground radiation quantity predicted in the target future time period and the solar zenith angle, the solar altitude angle, the solar azimuth angle and the solar inclination angle obtained in the step S21 into a geometric parameter resolver, so as to determine the theoretical effective radiation quantity which can be received by the photovoltaic system in the current state.
The environmental factors include temperature in the air, wind speed, dust, and the like. The system parameters of the photovoltaic system include I-V curves (current-voltage curves), inverter parameters, and the like. The method comprises the steps of firstly predicting environmental factors around a target photovoltaic system in a target future time period, determining corresponding environmental parameters, inputting system parameters, the environmental parameters and theoretical effective radiant quantity of the photovoltaic system into a photovoltaic power generation simulator for simulation calculation, and obtaining corresponding theoretical generated energy.
In summary, the present embodiment determines the theoretical power generation amount corresponding to the target future time period based on the predicted radiation amount, and then may predict the trend of the future power generation amount, so as to provide a planning basis for the power generation plan of the power plant and the distribution plan of the power supply plant, and ensure the rationality of power utilization.
Now, based on fig. 3 and fig. 4, the above scheme provided by the present embodiment is explained as follows:
and taking the time length T as a target historical time period, taking T as a sub-time period, dividing the time length T according to the sub-time period T, and sequentially acquiring cloud layer distribution images and solar radiation data of the satellite for each T sub-time period. Sequentially performing three-dimensional convolution, activation function, two-dimensional maximum pooling and global maximum pooling on the cloud layer distribution image to obtain cloud layer distribution characteristics (namely the spatial characteristics shown in the figure 2); and sequentially performing one-dimensional convolution, activation function and one-dimensional maximum pooling on the solar radiation data to obtain a radiation change characteristic (namely the time characteristic shown in the figure 2). Inputting the cloud layer distribution characteristics and the radiation change characteristics into the LSTM to obtain historical associated characteristics (namely the preorder state shown in figure 2) and preliminary prediction characteristics (namely the prediction state shown in figure 2), and inputting the historical associated characteristics and the preliminary prediction characteristics into the full-connection layer to further obtain the solar radiation of the target future time period of M hours.
The prediction model in fig. 2 is the model shown in fig. 1, the satellite observation map and the radiation data of the ground observation are input into the prediction model, the predicted solar radiation amount can be obtained, and the solar radiation amount is used as the input of a geometric parameter solver, and the geometric parameter solver receives the solar zenith angle, the solar altitude angle, the photovoltaic panel azimuth angle, the photovoltaic panel inclination angle and the predicted solar radiation amount, so that the effective solar radiation received by the panel can be obtained. The photovoltaic power generation simulator receives effective solar radiation, environmental factors and photovoltaic system parameters, and further can obtain photovoltaic output (namely theoretical power generation).
In summary, the present embodiment integrates cloud layer information (the first half of fig. 2) observed by a satellite, and can effectively reflect radiation fluctuation caused by cloud change; in the embodiment, dynamic evolution analysis and simulation are carried out on sequence characteristics observed by the ground and the satellite (the second half part of figure 2), so that the defect of time sequence prediction lag in the related technology is overcome; in the embodiment, the geometric parameters of the photovoltaic system layout are accurately calculated (the middle part of fig. 2), the influence of various environmental factors on the photovoltaic system power generation efficiency and the system loss in the photovoltaic power generation process (the right part of fig. 2) are considered, and the practical and practical power generation process of photovoltaic power generation forecast is ensured.
The application test is carried out by utilizing the solar radiation and meteorological observation data of a ground radiation station-Beijing station, the ground measurement is the hourly observation data of 2007 and 2008, the time sequence is complete, and the quality inspection is carried out; setting the inclination angle of the photovoltaic system layout as an optimal inclination angle (the calculation formula is 2.14+0.764 latitude), setting the orientation of the photovoltaic panel as the south-bound direction, and enabling the system temperature to change along with the ambient temperature (air temperature); and the relative root mean square error of the final photovoltaic power generation amount simulation result is 17%, the absolute error of 50% of prediction results is less than 10Wh, and the absolute error of 90% of prediction results is less than 32 Wh.
Based on the same inventive concept, the present embodiment provides a solar radiation prediction apparatus as shown in fig. 4, the apparatus including:
the original data acquisition module 41 is used for acquiring cloud layer distribution images observed by the satellites in a target historical time period and surface monitored solar radiation data in the target historical time period;
the original characteristic analysis module 42 is used for extracting cloud layer distribution characteristics from the cloud layer distribution image and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
the association characteristic determining module 43 is configured to determine, according to the cloud layer distribution characteristic and the radiation change characteristic, a target association characteristic between cloud layer distribution and radiation change in a target historical time period;
and the radiation prediction module 44 is configured to predict the ground radiation amount corresponding to the target future time period according to the target association characteristic.
Further, the raw feature analysis module 42 includes:
the characteristic extraction submodule is used for extracting cloud layer distribution characteristics from the cloud layer distribution image through a first convolution network and extracting radiation change characteristics from solar radiation data through a second convolution network;
and the characteristic sequence corresponding module is used for corresponding the cloud layer distribution characteristics and the radiation change characteristics one by one according to the time sequence of the target historical time period.
Further, the associated feature determining module 43 includes:
the preliminary characteristic analysis submodule is used for inputting the corresponding cloud layer distribution characteristics and radiation change characteristics into the long-term and short-term memory network according to the time sequence of the target historical time period and outputting historical association characteristics and preliminary prediction characteristics of cloud layer distribution and radiation change;
and the correlation characteristic analysis submodule is used for fusing the historical correlation characteristic and the preliminary prediction characteristic to obtain a target correlation characteristic of cloud layer distribution and radiation change.
Further, the radiation prediction module 44 includes:
and the radiation prediction submodule is used for inputting the target correlation characteristics into the full-connection network and predicting the ground radiation amount corresponding to the target future time period.
Further, the radiation prediction module 44 includes:
the first radiation prediction submodule is used for predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics corresponding to the target historical time period when the target future time period is adjacent to the target historical time period and the duration of the target future time period is less than or equal to the duration of a single preset unit;
and the second radiation prediction submodule is used for predicting the ground radiation amount corresponding to the (i + 1) th preset unit time length in the target future time period according to the target correlation characteristic corresponding to the target historical time period, the ground radiation amount predicted by the ith preset unit time length in the target future time period and the ground radiation amount predicted by all preset unit time lengths before the ith preset unit time length when the time length of the target future time period is greater than or equal to M preset unit time length, wherein M is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to M-1.
Further, the apparatus further comprises:
the angle determination module is used for determining a solar zenith angle and a solar altitude angle corresponding to a target future time period and an azimuth angle and an inclination angle of a target photovoltaic system after predicting the ground radiation amount corresponding to the target future time period;
the theoretical effective radiant quantity determining module is used for determining the theoretical effective radiant quantity received by the target photovoltaic system in the target future time period according to the ground radiant quantity, the solar zenith angle, the solar altitude angle, the azimuth angle and the inclination angle which are obtained by prediction in the target future time period;
and the theoretical power generation amount determining module is used for determining the theoretical power generation amount of the target photovoltaic system in the target future time period according to the environmental factors around the target photovoltaic system in the target future time period, the system parameters of the target photovoltaic system and the theoretical effective radiation amount.
Based on the same inventive concept, the present embodiment provides an electronic device as shown in fig. 5, including:
a processor 51;
a memory 52 for storing instructions executable by the processor 51;
wherein the processor 51 is configured to execute to implement a solar radiation prediction method as provided above.
Based on the same inventive concept, the present embodiment provides a non-transitory computer-readable storage medium, wherein instructions, when executed by the processor 51 of the electronic device, enable the electronic device to perform a method for solar radiation prediction that implements the method provided above.
Since the electronic device described in this embodiment is an electronic device used for implementing the method for processing information in this embodiment, a person skilled in the art can understand the specific implementation manner of the electronic device of this embodiment and various variations thereof based on the method for processing information described in this embodiment, and therefore, how to implement the method in this embodiment by the electronic device is not described in detail here. Electronic devices used by those skilled in the art to implement the method for processing information in the embodiments of the present application are all within the scope of the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of solar radiation prediction, the method comprising:
acquiring a cloud layer distribution image observed by a satellite in a target historical time period and surface monitored solar radiation data in the target historical time period;
extracting cloud layer distribution characteristics from the cloud layer distribution image, and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
according to the cloud layer distribution characteristics and the radiation change characteristics, determining target association characteristics between cloud layer distribution and radiation change in the target historical time period;
and predicting the ground radiation amount corresponding to the future time period of the target according to the target correlation characteristics.
2. The method of claim 1, wherein extracting cloud distribution features from the cloud distribution image and extracting radiation variation features corresponding to the cloud distribution features from the solar radiation data comprises:
extracting the cloud layer distribution characteristics from the cloud layer distribution image through a first convolution network, and extracting the radiation change characteristics from the solar radiation data through a second convolution network;
and according to the time sequence of the target historical time period, the cloud layer distribution characteristics and the radiation change characteristics are in one-to-one correspondence.
3. The method of claim 1, wherein determining the target association signature between cloud distribution and radiation variation over the target historical time period based on the cloud distribution signature and the radiation variation signature comprises:
inputting the corresponding cloud layer distribution characteristics and the radiation change characteristics into a long-term and short-term memory network according to the time sequence of the target historical time period, and outputting historical association characteristics and preliminary prediction characteristics of cloud layer distribution and radiation change;
and fusing the historical associated features and the preliminary prediction features to obtain the target associated features of cloud layer distribution and radiation change.
4. The method of claim 1, wherein predicting the amount of ground radiation corresponding to a target future time period based on the target correlation features comprises:
inputting the target correlation characteristics into a full-connection network, and predicting the ground radiation amount corresponding to the target future time period.
5. The method of claim 1, wherein predicting the amount of ground radiation corresponding to a target future time period based on the target correlation features comprises:
when the target future time period is adjacent to the target historical time period and the duration of the target future time period is less than or equal to the duration of a single preset unit, predicting the ground radiation amount corresponding to the target future time period according to the target association characteristics corresponding to the target historical time period;
when the time length of the target future time period is greater than or equal to M preset unit time lengths, predicting the ground radiation amount corresponding to the (i + 1) th preset unit time length in the target future time period according to the target correlation characteristics corresponding to the target historical time period, the ground radiation amount predicted by the ith preset unit time length in the target future time period and the ground radiation amount predicted by all preset unit time lengths before the ith preset unit time length, wherein M is an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to M-1.
6. The method of claim 1, wherein after predicting the amount of ground radiation corresponding to the target future time period, the method further comprises:
determining a corresponding solar zenith angle and solar altitude angle in the target future time period, and an azimuth angle and an inclination angle of a target photovoltaic system;
determining a theoretical effective radiant quantity received by the target photovoltaic system in the target future time period according to the ground radiant quantity, the solar zenith angle, the solar altitude angle, the azimuth angle and the inclination angle predicted by the target future time period;
and determining the theoretical power generation amount of the target photovoltaic system in the target future time period according to the environmental factors around the target photovoltaic system in the target future time period, the system parameters of the target photovoltaic system and the theoretical effective radiation amount.
7. A solar radiation prediction apparatus, characterized in that the apparatus comprises:
the system comprises an original data acquisition module, a satellite observation module and a satellite monitoring module, wherein the original data acquisition module is used for acquiring cloud layer distribution images observed by a satellite in a target historical time period and surface monitoring solar radiation data in the target historical time period;
the original characteristic analysis module is used for extracting cloud layer distribution characteristics from the cloud layer distribution image and extracting radiation change characteristics corresponding to the cloud layer distribution characteristics from the solar radiation data;
the correlation characteristic determining module is used for determining a target correlation characteristic between cloud layer distribution and radiation change in the target historical time period according to the cloud layer distribution characteristic and the radiation change characteristic;
and the radiation prediction module is used for predicting the ground radiation amount corresponding to the target future time period according to the target correlation characteristics.
8. The apparatus of claim 7, wherein the raw feature analysis module comprises:
the characteristic extraction submodule is used for extracting the cloud layer distribution characteristics from the cloud layer distribution image through a first convolution network and extracting the radiation change characteristics from the solar radiation data through a second convolution network;
and the characteristic sequence corresponding module is used for corresponding the cloud layer distribution characteristics and the radiation change characteristics one by one according to the time sequence of the target historical time period.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute to implement a solar radiation prediction method as claimed in any one of claims 1 to 6.
10. A non-transitory computer readable storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform implementing a solar radiation prediction method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210430524.9A CN114895380A (en) | 2022-04-22 | 2022-04-22 | Solar radiation prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210430524.9A CN114895380A (en) | 2022-04-22 | 2022-04-22 | Solar radiation prediction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114895380A true CN114895380A (en) | 2022-08-12 |
Family
ID=82716540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210430524.9A Pending CN114895380A (en) | 2022-04-22 | 2022-04-22 | Solar radiation prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114895380A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115618714A (en) * | 2022-09-09 | 2023-01-17 | 北京思源知行科技发展有限公司 | Solar radiation probability forecasting method and related equipment |
| CN116612393A (en) * | 2023-05-05 | 2023-08-18 | 北京思源知行科技发展有限公司 | Solar radiation prediction method, system, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600064A (en) * | 2016-12-16 | 2017-04-26 | 东软集团股份有限公司 | Data prediction method and device |
| CN110782024A (en) * | 2019-11-15 | 2020-02-11 | 兰州理工大学 | Photo-thermal electric field solar direct normal radiation prediction method based on convolutional neural network |
| CN111815038A (en) * | 2020-06-24 | 2020-10-23 | 山东大学 | Photovoltaic ultra-short term prediction method and system |
| CN112668469A (en) * | 2020-12-28 | 2021-04-16 | 西安电子科技大学 | Multi-target detection and identification method based on deep learning |
| CN112785067A (en) * | 2021-01-28 | 2021-05-11 | 深信服科技股份有限公司 | Data prediction method and device, equipment and storage medium |
| CN113159466A (en) * | 2021-05-27 | 2021-07-23 | 沃太能源股份有限公司 | Short-time photovoltaic power generation prediction system and method |
| CN113537561A (en) * | 2021-06-09 | 2021-10-22 | 中国电力科学研究院有限公司 | Ultra-short-term solar radiation prediction method and system based on foundation cloud picture |
| CN114185114A (en) * | 2022-02-16 | 2022-03-15 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Correction method and device for rainfall forecast falling area, electronic equipment and medium |
-
2022
- 2022-04-22 CN CN202210430524.9A patent/CN114895380A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600064A (en) * | 2016-12-16 | 2017-04-26 | 东软集团股份有限公司 | Data prediction method and device |
| CN110782024A (en) * | 2019-11-15 | 2020-02-11 | 兰州理工大学 | Photo-thermal electric field solar direct normal radiation prediction method based on convolutional neural network |
| CN111815038A (en) * | 2020-06-24 | 2020-10-23 | 山东大学 | Photovoltaic ultra-short term prediction method and system |
| CN112668469A (en) * | 2020-12-28 | 2021-04-16 | 西安电子科技大学 | Multi-target detection and identification method based on deep learning |
| CN112785067A (en) * | 2021-01-28 | 2021-05-11 | 深信服科技股份有限公司 | Data prediction method and device, equipment and storage medium |
| CN113159466A (en) * | 2021-05-27 | 2021-07-23 | 沃太能源股份有限公司 | Short-time photovoltaic power generation prediction system and method |
| CN113537561A (en) * | 2021-06-09 | 2021-10-22 | 中国电力科学研究院有限公司 | Ultra-short-term solar radiation prediction method and system based on foundation cloud picture |
| CN114185114A (en) * | 2022-02-16 | 2022-03-15 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Correction method and device for rainfall forecast falling area, electronic equipment and medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115618714A (en) * | 2022-09-09 | 2023-01-17 | 北京思源知行科技发展有限公司 | Solar radiation probability forecasting method and related equipment |
| CN116612393A (en) * | 2023-05-05 | 2023-08-18 | 北京思源知行科技发展有限公司 | Solar radiation prediction method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200063710A1 (en) | System and methods for hyper short-term wind power prediction using real-time wind parameter measurements | |
| Carneiro et al. | Review on photovoltaic power and solar resource forecasting: current status and trends | |
| US10956993B2 (en) | Method and device for determining energy system operating scenario | |
| CN114895380A (en) | Solar radiation prediction method, device, equipment and medium | |
| CN108196317B (en) | Meteorological prediction method for micro-grid system | |
| CN110929963A (en) | Wind speed prediction method, wind speed prediction device, and storage medium | |
| KR102283487B1 (en) | A Forecasting System of Photovoltaic Generation Based on Machine-learning Using Realtime Satellite Data and Numerical Modeling Data | |
| Yen et al. | Solar power prediction via support vector machine and random forest | |
| Yang et al. | Sub-minute probabilistic solar forecasting for real-time stochastic simulations | |
| CN107358059A (en) | Short-term photovoltaic energy Forecasting Methodology and device | |
| CN113984198A (en) | Short wave radiation prediction method and system based on convolutional neural network | |
| KR20190131808A (en) | Apparatus and method for estimating the power generation of photovoltaic generator | |
| CN117277304A (en) | Photovoltaic power generation ultra-short-term power prediction method and system considering sunrise and sunset time | |
| TW201740296A (en) | Method and system for predicting power generation capacity of renewable energy using a neural network to accurately calculate the power generation capacity of renewable energy | |
| CN110019167A (en) | Long-term new forms of energy resource data base construction method and system in one kind | |
| CN110705769B (en) | New energy power generation power prediction optimization method and device | |
| CN113962432A (en) | Wind power prediction method and system integrating three-dimensional convolution and light-weight convolution threshold unit | |
| CN115563848A (en) | Distributed photovoltaic total radiation prediction method and system based on deep learning | |
| Cho et al. | Application of Parallel ANN-PSO to Hourly Solar PV Estimation | |
| CN112215383A (en) | Distributed photovoltaic power generation power prediction method and system | |
| KR102642404B1 (en) | Method for prediction power generation using meta-learning, device and system using the same | |
| Jogunuri et al. | Deep Neural Network based Forecasting of Short-Term Solar Photovoltaic Power output | |
| Ku et al. | Self-learning mechanism for prediction of energy consumption and generation | |
| CN116108761B (en) | Regional climate simulation method and system for coupling deep learning and HASM | |
| CN116703007B (en) | Wind power cluster prediction model construction method, power prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220812 |
|
| RJ01 | Rejection of invention patent application after publication |