CN115660132A - Photovoltaic power generation power prediction method and system - Google Patents
Photovoltaic power generation power prediction method and system Download PDFInfo
- Publication number
- CN115660132A CN115660132A CN202210938497.6A CN202210938497A CN115660132A CN 115660132 A CN115660132 A CN 115660132A CN 202210938497 A CN202210938497 A CN 202210938497A CN 115660132 A CN115660132 A CN 115660132A
- Authority
- CN
- China
- Prior art keywords
- power
- predicted
- photovoltaic
- power generation
- prediction
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 130
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000012407 engineering method Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000013499 data model Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000002310 reflectometry Methods 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 101000604223 Homo sapiens Nocturnin Proteins 0.000 description 1
- 102100038815 Nocturnin Human genes 0.000 description 1
- 229910021419 crystalline silicon Inorganic materials 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000002210 silicon-based material Substances 0.000 description 1
Images
Classifications
-
- 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
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a photovoltaic power generation power prediction method and a system, which belong to the technical field of electric power systems and comprise the following steps: generating a first predicted generated power of the photovoltaic module corresponding to the predicted time period according to the meteorological parameters, the equipment parameters of the photovoltaic module and the basic information of the power station; matching photovoltaic power generation parameters of the photovoltaic module based on a preset clustering model to obtain second predicted power generation power corresponding to the predicted time period; and comparing the first predicted generated power with the second predicted generated power, and determining the final photovoltaic power generation predicted power according to the comparison result. Has the beneficial effects that: and adding a parallel preset clustering model as a data model, performing similarity matching of Euclidean distances by using a K-means algorithm to obtain second predicted power generation power at an average similar time period, determining final photovoltaic power generation predicted power according to comparison results of two times of prediction, improving prediction precision and improving robustness of the prediction method.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a photovoltaic power generation power prediction method and system.
Background
The photovoltaic power generation has strong periodic variability, the output power of the photovoltaic power generation is influenced by various meteorological factors, and parameters such as solar radiation intensity, atmospheric temperature, relative humidity, wind speed, wind direction and air pressure influence the photovoltaic power generation to different degrees. The prediction algorithm for photovoltaic power generation is mainly used for predicting the direct-current power generation power of a photovoltaic power station and providing a reference for the power generation performance of all the assets of the photovoltaic power station.
Currently, the common practice in the industry falls into two broad categories: a prediction method based on deep learning and a prediction method based on a physical model. The prediction method based on deep learning uses historical photovoltaic power generation power data, and obtains prediction of future power generation power by learning mode rules in the historical data; the prediction method based on the physical model uses meteorological data and obtains the prediction of future generation power based on the photoelectric conversion principle of a photovoltaic module. The method completely depends on the accuracy and precision of prediction, and due to the characteristic of high randomness of photovoltaic power generation, when the difference between the predicted data and the real data is large, the robustness of the whole prediction is poor, and the fault-tolerant capability is low.
Disclosure of Invention
In order to solve the technical problems, the invention provides a photovoltaic power generation power prediction method and a photovoltaic power generation power prediction system.
The technical problem solved by the invention can be realized by adopting the following technical scheme:
a photovoltaic power generation power prediction method comprises the following steps:
generating a first predicted power generation power corresponding to the predicted time period according to the meteorological parameters, the equipment parameters of the photovoltaic module and the basic information of the power station;
clustering photovoltaic power generation parameters in a photovoltaic power generation database through a K-means algorithm based on a preset clustering model to obtain second predicted power generation power corresponding to the predicted time period;
and comparing the first predicted generated power with the second predicted generated power, and determining the predicted photovoltaic power generation power according to the comparison result.
Preferably, the preset clustering model generation method includes:
step A1, acquiring a data set comprising a plurality of samples to be trained, and randomly initializing a preset number of the samples to be trained as clustering centers, wherein each clustering center corresponds to a category;
step A2, calculating the Euclidean distance from the rest samples to be trained to each clustering center, and matching each sample to be trained to the category corresponding to the minimum Euclidean distance;
step A3, calculating the mass center of each category, and taking the calculated mass center as the updated clustering center;
and step A4, repeating the steps A2-A3 until the samples to be trained in each category do not change any more.
Preferably, before the clustering processing is performed on the photovoltaic power generation parameters, a feature engineering processing procedure is further included, and the feature engineering processing procedure includes:
combining the photovoltaic power generation parameters in the photovoltaic power generation database with meteorological parameters in a meteorological database based on a characteristic engineering method to obtain statistical data;
extracting characteristic data from the statistical data, and taking the extracted characteristic data as the data set comprising a plurality of samples to be trained, wherein the characteristic data comprises time characteristic information and meteorological characteristic information.
Preferably, in the step A2, the euclidean distance calculating method includes:
wherein s _ i represents the ithThe sample to be trained; c _ j represents the jth cluster center; s _ i m Representing the mth attribute of the ith sample to be trained; c _ j m An mth attribute representing a jth of the cluster centers; d (s _ i, c _ j) represents the Euclidean distance from the ith sample to be trained to the jth cluster center.
Preferably, in the step A3, the update formula of the centroid is as follows:
wherein, R _ i represents the ith category; s represents the sample to be trained corresponding to the ith category; c _ i new Representing the cluster center after the ith update.
Preferably, the clustering processing method for the photovoltaic power generation parameters includes:
acquiring meteorological parameters corresponding to the prediction time period, and performing the characteristic engineering processing process on the meteorological parameters to obtain characteristic data serving as meteorological prediction data;
calculating Euclidean distance from the meteorological prediction data to each clustering center;
taking the category corresponding to the minimum Euclidean distance as an attribution class obtained by matching the meteorological prediction data, wherein each attribution class comprises a plurality of feature data;
inputting the time characteristic information of the characteristic data into the photovoltaic power generation database to obtain photovoltaic instantaneous power generation power corresponding to the time characteristic information;
and calculating the average value of the photovoltaic instantaneous generating power to obtain the second predicted generating power.
Preferably, the second predicted generated power calculation method includes:
wherein R represents the attribution class; p _ pv _ s _ i represents the photovoltaic instantaneous generated power corresponding to the temporal characteristic information of the ith piece of the characteristic data; pc represents the second predicted generated power.
Preferably, the method for determining the photovoltaic power generation predicted power comprises the following steps:
calculating an absolute difference between the first predicted generated power and the second predicted generated power;
judging whether the absolute difference value is smaller than a preset threshold value:
if so, outputting the first predicted power generation power as the photovoltaic power generation predicted power;
and if not, outputting the first predicted power generation power, the second predicted power generation power and the average value as the photovoltaic power generation predicted power.
Preferably, the first predicted generated power generation method includes:
P dc ＝η pv ×I t ×S×K 1 ÷1000；
wherein, P dc For the first predicted generated power; eta pv The photoelectric conversion efficiency of the photovoltaic module; i is t The total irradiance of the inclined plane of the photovoltaic component; s is the area of the photovoltaic module; k is 1 And the direct current line loss coefficient of the photovoltaic module.
The invention also provides a photovoltaic power generation power prediction system, which is used for implementing the photovoltaic power generation power prediction method and comprises the following steps:
the generating power prediction module is used for generating first predicted generating power corresponding to a predicted time period according to the meteorological parameters, the equipment parameters of the photovoltaic assembly and the basic information of the power station;
the preset clustering model is used for clustering the photovoltaic power generation parameters in the photovoltaic power generation database through a K-means algorithm to obtain second predicted power generation power corresponding to the predicted time period;
and the comparison output module is respectively connected with the generated power prediction module and the preset clustering model and is used for comparing the first predicted generated power with the second predicted generated power and determining the predicted photovoltaic power according to the comparison result.
The technical scheme of the invention has the advantages or beneficial effects that:
according to the method, on the basis that the first predicted generated power is obtained by a traditional photovoltaic power generation power prediction method based on a physical model, a parallel preset clustering model is added to serve as a data model, similar matching of Euclidean distances is carried out by using a K-means algorithm, the second predicted generated power in an average similar time period is obtained, the final photovoltaic power generation predicted power is determined according to the comparison result of two times of prediction, the problem that the prediction precision is reduced due to the fact that the difference between the first predicted generated power obtained by prediction based on the physical model and the real situation is too large is solved, and the robustness of the prediction method is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting photovoltaic power generation power according to a preferred embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for generating a preset clustering model according to a preferred embodiment of the present invention;
FIG. 3 is a flow chart illustrating a feature engineering process according to a preferred embodiment of the present invention;
FIG. 4 is a schematic flow chart of a clustering method for photovoltaic power generation parameters according to a preferred embodiment of the present invention;
FIG. 5 is a flow chart illustrating a method for determining a predicted photovoltaic power generation power according to a preferred embodiment of the present invention;
FIG. 6 is a block diagram of a photovoltaic power generation power prediction system according to a preferred embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
In a preferred embodiment of the present invention, based on the above problems in the prior art, a method for predicting photovoltaic power generation power is provided, which belongs to the technical field of power systems, and as shown in fig. 1, the method includes:
s1, generating first predicted generating power corresponding to a predicted time period according to meteorological parameters, equipment parameters of a photovoltaic assembly and basic information of a power station;
specifically, the meteorological parameters may be obtained from the meteorological database 1, and include, but are not limited to, air temperature, horizontal plane direct irradiance, horizontal plane scattered irradiance, horizontal plane total irradiance, and the like corresponding to a certain time stamp.
The device parameters of the photovoltaic module can be obtained from the device database 2, and include, but are not limited to, the photoelectric conversion efficiency under the standard test condition of the photovoltaic module, the temperature coefficient of the photovoltaic module, the rated operating temperature of the photovoltaic cell, the annual attenuation rate of the photovoltaic cell, and the like.
The basic information of the power station can be obtained from the power station database 3, and the basic information of the power station includes, but is not limited to, the area of the photovoltaic module, the direct current line loss coefficient, the mismatch loss coefficient, the dust shielding loss coefficient, the number of years of the photovoltaic module in use, the ratio of the inclined plane to the direct radiation irradiance of the horizontal plane, the panel inclination angle of the photovoltaic module, the ground reflectivity and the like.
Providing a physical model, wherein the physical model is connected with the meteorological database 1, the equipment database 2 and the power station database 3, and a first predicted generated power is obtained by predicting according to the parameters based on a traditional photovoltaic generated power prediction method, and the generation method of the first predicted generated power comprises the following steps:
P dc ＝η pv ×I t ×S×K 1 ÷1000；
wherein, P dc A first predicted generated power; eta pv The photoelectric conversion efficiency of the photovoltaic module; i is t The total irradiance of the inclined plane of the photovoltaic component is measured in kilowatt per square meter (kW/m) 2 ) (ii) a S is the area of the photovoltaic module and has a unit of square meter (m) 2 )；K 1 The direct current line loss coefficient of the photovoltaic module is dimensionless, and the default value can be 0.95.
Further, the method for generating the photoelectric conversion efficiency of the photovoltaic module includes:
η pv ＝η s ×(1-α(T c -25))×K 2 ×K 3 ×K 4 ；
wherein eta is pv The photoelectric conversion efficiency of the photovoltaic module; eta s For photovoltaic modules under standard test conditions (1 kW/m of incident light irradiance) 2 Temperature 25 ℃ and atmospheric mass 1.5); alpha is the temperature coefficient of the photovoltaic module, is related to the solar cell material and has the unit of DEG C -1 For crystalline silicon material, the value range is 0.003 DEG C -1 ～0.005℃ -1 ；T c The plate temperature of the photovoltaic module in a prediction time period is measured in units of; k is 2 The aging loss coefficient of the photovoltaic module is dimensionless and is decreased gradually according to a certain proportion every year; k 3 The mismatch loss coefficient of the photovoltaic module is dimensionless, and the value range is 0.95-0.98; k is 4 The dust shielding loss coefficient of the photovoltaic module is dimensionless, and the value range is 0.9-0.95.
Further, the method for generating the plate temperature comprises the following steps:
wherein, T c The plate temperature is adopted; t is a The local air temperature corresponding to the predicted time period is obtained according to meteorological data and is measured in units of ℃; i is t The total irradiance of the bevel is measured in kilowatts per square meter (kW/m) 2 )；T NOCT The rated working temperature of the photovoltaic module is shown in the unit of ℃.
Further, the method for generating the aging loss coefficient includes:
K 2 ＝(1-Y) i ；
wherein, K 2 Is the aging loss coefficient; y is the annual decay rate of the photovoltaic module, and the default value can be 0.8%; and iota is the number of years that the photovoltaic module is put into use.
Further, the method for generating the total irradiance of the inclined plane comprises the following steps:
wherein, I t The total irradiance of the inclined plane is measured in kilowatt per square meter (kW/m) 2 )；R b The ratio of the direct radiation irradiance of the inclined plane to the horizontal plane is dimensionless, and the ratio is obtained by comprehensively calculating a declination angle, a geographical latitude, a photovoltaic array inclination angle, a photovoltaic array azimuth angle and a time angle, wherein the calculation process can be obtained by adopting the prior art and is not repeated herein; i is b Direct irradiance on the horizontal plane; i is d Is the horizontal plane scattered irradiance in kilowatts per square meter (kW/m) 2 ) (ii) a I is the total horizontal irradiance in kilowatts per square meter (kW/m) 2 ) (ii) a Beta is the panel inclination angle of the photovoltaic module; ρ is the ground reflectivity, and its value can vary according to the ground material, and when the ground reflectivity has a default value, it can be taken as follows:
TABLE 1 shows the reflectivity of the ground for different ground conditions
S2, clustering photovoltaic power generation parameters in a photovoltaic power generation database through a K-means (K-means) algorithm based on a preset clustering model 6 to obtain second predicted power generation power corresponding to a predicted time period;
as a preferred embodiment, before the clustering process is performed on the photovoltaic power generation parameters, a feature engineering process is further included, as shown in fig. 3, the feature engineering process includes:
combining the photovoltaic power generation parameters in the photovoltaic power generation database 4 with the meteorological parameters in the meteorological database based on a characteristic engineering method to obtain statistical data;
and extracting characteristic data from the statistical data, wherein the extracted characteristic data is used as a data set comprising a plurality of samples to be trained, and the characteristic data comprises time characteristic information and meteorological characteristic information.
Specifically, the feature engineering is to extract features suitable for subsequent model input from the raw data. In this embodiment, before the clustering process, a characteristic engineering is performed on the photovoltaic power generation parameters in the photovoltaic power generation database 4, so as to prepare data for the generation of the preset clustering model 6.
In the actual implementation process, the photovoltaic power generation parameters are historical power generation data of the photovoltaic module, and include photovoltaic instantaneous power generation power at a certain moment corresponding to a certain day of a certain month in a certain year. In a preferred embodiment, the storage format of the photovoltaic power generation parameters in the photovoltaic power generation database 4 may be { "timeframe": timestamp, "P _ pv": p _ pv } has two attributes, where timestamp represents a timestamp, which may be a certain time of a certain day of a certain month of a certain year, and the prediction time period exists in a timestamp format; and P _ pv represents the photovoltaic instantaneous generated power corresponding to the time stamp.
Combining (merge) the photovoltaic power generation database and the meteorological database according to the timestamp to obtain the photovoltaic instantaneous power generation power and the meteorological parameters at a certain moment corresponding to a certain day of a certain month of a certain year, wherein the extracted characteristic data comprises time characteristic information and meteorological characteristic information, and the time characteristic information comprises but is not limited to: hour, month, month, etc a season; preferably, the time characteristic information is extracted in a manner of: converting the timestamp attribute into a standard readable datatime format; then extracting two attributes of hour and month from the datetime format; and finally, constructing a seasonal season based on the month attribute. Weather (meteorology)The characteristic information includes but is not limited to: air temperature T a (ii) a Direct horizontal irradiance I b (ii) a Horizontal plane scattered irradiance I d (ii) a Total irradiance I in horizontal plane.
Feature engineered data set S fixed The individual parameters (i.e. characterizing the samples to be trained as follows) are stored in the following format: { "hour": hour, "month": month, "season": season, "T a ”：T a ，”I b ”：I b ，”I d ”：I d And an "I": i, having 7 attributes.
As a preferred embodiment, as shown in fig. 2, the method for generating the preset clustering model 6 includes:
step A1, acquiring a data set S comprising a plurality of samples to be trained fixed Randomly initializing a preset number of samples to be trained as clustering centers, wherein each clustering center corresponds to one class;
step A2, calculating the Euclidean distance from the rest samples to be trained to each clustering center, and matching each sample to be trained to the category corresponding to the minimum Euclidean distance;
step A3, calculating the mass center of each category, and taking the calculated mass center as an updated clustering center;
and step A4, repeating the steps A2-A3 until the samples to be trained in each category do not change any more.
Specifically, in this embodiment, a preset clustering model 6 based on matching of similar sequences of euclidean distances is generated by using a data set subjected to feature engineering, and the specific generation method is as follows: (1) Randomly initializing k samples to be trained in the data set as clustering centers: setting a random number seed at {0,length (S) fixed ) K random numbers are generated in the range of { a1, a2, a3 \8230ak }, and are used as indexes in the data set S fixed The samples to be trained corresponding to the k random number indexes are found out and used as initial clustering centers, and the k samples to be trained are marked as { s1, s2, s3 \8230k; sk }. Let each category be R, there are k categories: { R1, R2 \8230, rk }, category(s) ∈ { R1, R2 \8230, rk }, k polyThe class center is marked as { c1, c2, c3 \8230; ck }. At this time, the k samples to be trained are corresponding clustering centers, i.e., c1= s1, c2= s2, and ck = sk.
(2) And calculating Euclidean distances from the other samples to be trained of the k initial clustering centers to the k initial clustering centers, and classifying the Euclidean distances into the category corresponding to the clustering center with the minimum Euclidean distance.
(3) And respectively calculating the centroid of each category after the sample to be trained is redistributed, and updating the clustering center according to the calculated centroid.
(4) Repeating (2) and (3) until the internal elements of each category are not changed any more.
As a preferred embodiment, in the step A2, the method for calculating the euclidean distance includes:
wherein s _ i represents the ith sample to be trained; c _ j represents the jth cluster center; s _ i m Representing the mth attribute of the ith sample to be trained; c _ j m An mth attribute representing a jth cluster center; d (s _ i, c _ j) represents the Euclidean distance from the ith sample to be trained to the jth cluster center.
As a preferred embodiment, in step A3, the update formula of the centroid is as follows:
wherein, R _ i represents the ith category; s represents a sample to be trained corresponding to the ith category; c _ i new Representing the ith updated cluster center.
As a preferred embodiment, the second predicted generated power generation method includes: acquiring meteorological parameters of a time period to be predicted, performing similar matching of Euclidean distances by using a K mean value algorithm to obtain an attribution class to which the meteorological parameters belong, and performing mean value processing on instantaneous photovoltaic power generation power of the attribution class to obtain second predicted power generation power;
the second predicted generated power calculation method includes:
wherein R represents an attribution class; p _ pv _ s _ i represents the photovoltaic instantaneous generated power of the temporal characteristic information corresponding to the ith characteristic data; pc denotes the second predicted generated power.
As a preferred embodiment, as shown in fig. 4, the method for clustering photovoltaic power generation parameters includes:
acquiring meteorological parameters corresponding to the prediction time period, and performing a characteristic engineering processing process on the meteorological parameters to obtain characteristic data serving as meteorological prediction data;
calculating the Euclidean distance from the meteorological prediction data to each clustering center;
taking the category corresponding to the minimum Euclidean distance as an attribution category obtained by weather prediction data matching, wherein each attribution category comprises a plurality of characteristic data;
inputting the time characteristic information of the plurality of characteristic data into a photovoltaic power generation database to obtain photovoltaic instantaneous power generation power corresponding to the time characteristic information;
and calculating the average value of the photovoltaic instantaneous generating power to obtain a second predicted generating power.
Specifically, in this embodiment, the time period to be predicted is the future time of the photovoltaic power generation power to be predicted in the photovoltaic power prediction method, and is denoted as tp; firstly, converting a time period tp to be predicted into a standard readable datatime format, thereby extracting time characteristic information; then, the meteorological data are queried and matched based on the time period tp to be predicted to obtain meteorological prediction data corresponding to the time period tp to be predicted, and the meteorological prediction data are marked as sp: { "hour": hour, "month": month, "season": season, "T a ”：T a ，”I b ”：I b ，”I d ”：I d ，”I”：I}；
Inputting meteorological prediction data sp into a preset clustering model 6, and performing similarity matching of Euclidean distances to obtain an attribution type R to which the meteorological parameters belong;
acquiring time characteristic information of all objects in the attribution class, matching the time characteristic information from a photovoltaic power generation database to obtain photovoltaic instantaneous power generation power based on all the time characteristic information, and calculating the mean value of all the photovoltaic instantaneous power generation power obtained through matching to be used as second predicted power generation power.
In the above scheme, the K-means algorithm is used to find the attribution class of the time period to be predicted first, then only the power of the samples in this attribution class is homogenized, only the sample points with the most similar small range (i.e. a single attribution class) are considered, and the essence of the method is that the weights of other sample points with a larger difference from the time period to be predicted are all forcibly set to 0, so as to eliminate the problem of excessive smoothing of the overall weighting method.
And S3, comparing the first predicted generated power with the second predicted generated power, and determining the predicted photovoltaic power generation power according to the comparison result.
As a preferred embodiment, as shown in fig. 5, the method for determining the photovoltaic power generation predicted power includes:
calculating an absolute difference between the first predicted generated power and the second predicted generated power;
judging whether the absolute difference is smaller than a preset threshold value, wherein the preset threshold value is used for representing an acceptable deviation range of the first predicted generating power:
if so, outputting the first predicted power generation power as the predicted power of photovoltaic power generation;
and if not, outputting the first predicted power generation power, the second predicted power generation power and the average value as the photovoltaic power generation predicted power.
The invention also provides a photovoltaic power generation power prediction system, which is used for implementing the photovoltaic power generation power prediction method, as shown in fig. 6, and comprises the following steps:
the generating power prediction module 5 is used for generating first predicted generating power corresponding to the prediction time period according to the meteorological parameters, the equipment parameters of the photovoltaic module and the basic information of the power station;
the preset clustering model 6 is used for clustering the photovoltaic power generation parameters in the photovoltaic power generation database through a K-means algorithm to obtain second predicted power generation power corresponding to the predicted time period;
and the comparison output module 7 is respectively connected with the generated power prediction module 5 and the preset clustering model 6 and is used for comparing the first predicted generated power with the second predicted generated power and determining the photovoltaic power generation predicted power according to the comparison result.
Specifically, aiming at the problems that the predicted power generation power predicted by the traditional photovoltaic power generation power prediction method based on the physical model is easy to have larger difference with the real situation, so that the power generation performance is lower and the efficiency is low, the embodiment of the invention adds a parallel preset clustering model 6 as a data model on the basis of the physical model, the data model uses a K-means algorithm to carry out similar matching of Euclidean distance, so as to obtain the second predicted power generation power in an average similar time period, then the second predicted power generation power is compared with the first predicted power generation power output by the physical model, if the difference between the two predicted power generation powers is larger, the average value of the two predicted power generation powers is taken as the photovoltaic power generation predicted power output, otherwise, the first predicted power generation power is directly output as the photovoltaic power generation predicted power, the final photovoltaic power generation predicted power is determined according to the comparison results of the two predictions, the prediction precision is improved, and the prediction robustness is further improved.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A photovoltaic power generation power prediction method is characterized by comprising the following steps:
generating first predicted generating power corresponding to the predicted time period according to the meteorological parameters, the equipment parameters of the photovoltaic module and the basic information of the power station;
clustering photovoltaic power generation parameters in a photovoltaic power generation database through a K-means algorithm based on a preset clustering model to obtain second predicted power generation power corresponding to the predicted time period;
and comparing the first predicted generated power with the second predicted generated power, and determining the predicted photovoltaic power generation power according to the comparison result.
2. The photovoltaic power generation power prediction method according to claim 1, wherein the preset clustering model generation method includes:
step A1, acquiring a data set comprising a plurality of samples to be trained, and randomly initializing a preset number of the samples to be trained as clustering centers, wherein each clustering center corresponds to a category;
step A2, calculating the Euclidean distance from the rest samples to be trained to each clustering center, and matching each sample to be trained to the category corresponding to the minimum Euclidean distance;
step A3, calculating the centroid of each category, and taking the calculated centroid as the updated clustering center;
and step A4, repeating the steps A2-A3 until the samples to be trained in each category do not change any more.
3. The photovoltaic power generation power prediction method according to claim 2, wherein before the clustering process is performed on the photovoltaic power generation parameters, a feature engineering process is further included, and the feature engineering process includes:
combining the photovoltaic power generation parameters in the photovoltaic power generation database with meteorological parameters in a meteorological database based on a characteristic engineering method to obtain statistical data;
extracting characteristic data from the statistical data, and taking the extracted characteristic data as the data set comprising a plurality of samples to be trained, wherein the characteristic data comprises time characteristic information and meteorological characteristic information.
4. The photovoltaic power generation power prediction method according to claim 2, wherein in the step A2, the calculation method of the euclidean distance includes:
wherein s _ i represents the ith sample to be trained; c _ j represents the jth cluster center; s _ i m Representing the mth attribute of the ith sample to be trained; c _ j m An mth attribute representing a jth of the cluster centers; d (s _ i, c _ j) represents the Euclidean distance from the ith sample to be trained to the jth cluster center.
5. The photovoltaic power generation power prediction method according to claim 2, wherein in the step A3, the update formula of the centroid is as follows:
wherein, R _ i represents the ith category; s represents the sample to be trained corresponding to the ith category; c _ i new Representing the cluster center after the ith update.
6. The photovoltaic power generation power prediction method according to claim 3, wherein the photovoltaic power generation parameter clustering method includes:
acquiring meteorological parameters corresponding to the prediction time period, and performing the characteristic engineering processing process on the meteorological parameters to obtain characteristic data serving as meteorological prediction data;
calculating Euclidean distance from the meteorological prediction data to each clustering center;
taking the category corresponding to the minimum Euclidean distance as an attribution class obtained by matching the meteorological prediction data, wherein each attribution class comprises a plurality of characteristic data;
inputting the time characteristic information of the characteristic data into the photovoltaic power generation database to obtain photovoltaic instantaneous power generation power corresponding to the time characteristic information;
and calculating the average value of the photovoltaic instantaneous generating power to obtain the second predicted generating power.
7. The photovoltaic generated power prediction method according to claim 6, characterized in that the calculation method of the second predicted generated power includes:
wherein R represents the attribution class; p _ pv _ s _ i represents the photovoltaic instantaneous generated power corresponding to the temporal characteristic information of the ith characteristic data; pc represents the second predicted generated power.
8. The photovoltaic power generation power prediction method according to claim 1, wherein the determination method of the photovoltaic power generation predicted power includes:
calculating an absolute difference between the first predicted generated power and the second predicted generated power;
judging whether the absolute difference value is smaller than a preset threshold value:
if so, outputting the first predicted power generation power as the predicted photovoltaic power generation power;
and if not, outputting the first predicted power generation power, the second predicted power generation power and the average value as the photovoltaic power generation predicted power.
9. The photovoltaic generated power prediction method according to claim 1, characterized in that the generation method of the first predicted generated power includes:
P dc ＝η pv ×I t ×S×K 1 ÷1000；
wherein, P dc For the first predicted generated power; eta pv The photoelectric conversion efficiency of the photovoltaic module is obtained; i is t The total irradiance of the inclined plane of the photovoltaic component; s is the area of the photovoltaic module; k is 1 And the direct current line loss coefficient of the photovoltaic module.
10. A photovoltaic power generation power prediction system for implementing the photovoltaic power generation power prediction method according to any one of claims 1 to 9, comprising:
the generating power prediction module is used for generating first predicted generating power corresponding to a predicted time period according to the meteorological parameters, the equipment parameters of the photovoltaic assembly and the basic information of the power station;
the preset clustering model is used for clustering the photovoltaic power generation parameters in the photovoltaic power generation database through a K-means algorithm to obtain second predicted power generation power corresponding to the predicted time period;
and the comparison output module is respectively connected with the generated power prediction module and the preset clustering model and is used for comparing the first predicted generated power with the second predicted generated power and determining the predicted photovoltaic power according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210938497.6A CN115660132B (en) | 2022-08-05 | 2022-08-05 | Photovoltaic power generation power prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210938497.6A CN115660132B (en) | 2022-08-05 | 2022-08-05 | Photovoltaic power generation power prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115660132A true CN115660132A (en) | 2023-01-31 |
| CN115660132B CN115660132B (en) | 2024-01-30 |
Family
ID=85024222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210938497.6A Active CN115660132B (en) | 2022-08-05 | 2022-08-05 | Photovoltaic power generation power prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660132B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522156A (en) * | 2023-10-17 | 2024-02-06 | 江苏尚诚能源科技有限公司 | Distributed photovoltaic prediction evaluation method and system based on big data analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286838A1 (en) * | 2016-03-29 | 2017-10-05 | International Business Machines Corporation | Predicting solar power generation using semi-supervised learning |
| CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
| CN109086928A (en) * | 2018-07-27 | 2018-12-25 | 福州大学 | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model |
| CN111091139A (en) * | 2019-11-18 | 2020-05-01 | 特变电工西安电气科技有限公司 | Photovoltaic prediction method, device and equipment for similar day clustering and readable storage medium |
| CN111695601A (en) * | 2020-05-15 | 2020-09-22 | 特变电工西安电气科技有限公司 | Photovoltaic power prediction method, device, equipment and readable storage medium |
| CN112561139A (en) * | 2020-12-03 | 2021-03-26 | 安徽大学 | Short-term photovoltaic power generation power prediction method and system |
| CN114421530A (en) * | 2022-02-17 | 2022-04-29 | 科大智能科技股份有限公司 | Scheduling method and device of photovoltaic energy storage system |
-
2022
- 2022-08-05 CN CN202210938497.6A patent/CN115660132B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286838A1 (en) * | 2016-03-29 | 2017-10-05 | International Business Machines Corporation | Predicting solar power generation using semi-supervised learning |
| CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
| CN109086928A (en) * | 2018-07-27 | 2018-12-25 | 福州大学 | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model |
| CN111091139A (en) * | 2019-11-18 | 2020-05-01 | 特变电工西安电气科技有限公司 | Photovoltaic prediction method, device and equipment for similar day clustering and readable storage medium |
| CN111695601A (en) * | 2020-05-15 | 2020-09-22 | 特变电工西安电气科技有限公司 | Photovoltaic power prediction method, device, equipment and readable storage medium |
| CN112561139A (en) * | 2020-12-03 | 2021-03-26 | 安徽大学 | Short-term photovoltaic power generation power prediction method and system |
| CN114421530A (en) * | 2022-02-17 | 2022-04-29 | 科大智能科技股份有限公司 | Scheduling method and device of photovoltaic energy storage system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522156A (en) * | 2023-10-17 | 2024-02-06 | 江苏尚诚能源科技有限公司 | Distributed photovoltaic prediction evaluation method and system based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660132B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257941B (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| Lai et al. | Daily clearness index profiles cluster analysis for photovoltaic system | |
| US20230136352A1 (en) | Method and system for predicting a day-ahead wind power of wind farms | |
| CN107194495B (en) | Photovoltaic power longitudinal prediction method based on historical data mining | |
| Lu et al. | A hybrid approach for day-ahead forecast of PV power generation | |
| CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN107403015B (en) | Short-term optical power prediction method based on time series similarity | |
| CN110766134A (en) | Photovoltaic power station short-term power prediction method based on cyclic neural network | |
| CN112070311A (en) | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting | |
| CN115829105A (en) | Photovoltaic power prediction method based on historical data feature search | |
| CN115204444A (en) | Photovoltaic power prediction method based on improved cluster analysis and fusion integration algorithm | |
| CN113837426A (en) | Weather-typing-based photovoltaic power prediction method | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| CN115660132B (en) | Photovoltaic power generation power prediction method and system | |
| CN116702937A (en) | Photovoltaic output day-ahead prediction method based on K-means mean value clustering and BP neural network optimization | |
| CN110795841B (en) | Mathematical modeling method for uncertainty of intermittent energy output | |
| CN110852492A (en) | Photovoltaic power ultra-short-term prediction method for finding similarity based on Mahalanobis distance | |
| Xu et al. | One-day ahead forecast of PV output based on deep belief network and weather classification | |
| CN112116127B (en) | Photovoltaic power prediction method based on association of meteorological process and power fluctuation | |
| CN114897229A (en) | Ultra-short-term prediction method for irradiance of photovoltaic power station based on AP clustering and Markov chain | |
| CN113112085A (en) | New energy station power generation load prediction method based on BP neural network | |
| CN112580899A (en) | Medium-and-long-term wind power generation prediction method and system fused with machine learning model | |
| TWI810750B (en) | Solar power forecasting method |
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 |