CN114021838A - Photovoltaic power station dust coverage prediction method - Google Patents
Photovoltaic power station dust coverage prediction method Download PDFInfo
- Publication number
- CN114021838A CN114021838A CN202111353709.6A CN202111353709A CN114021838A CN 114021838 A CN114021838 A CN 114021838A CN 202111353709 A CN202111353709 A CN 202111353709A CN 114021838 A CN114021838 A CN 114021838A
- Authority
- CN
- China
- Prior art keywords
- dust
- power station
- real
- power generation
- dust coverage
- 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
- 239000000428 dust Substances 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000010248 power generation Methods 0.000 claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000007423 decrease Effects 0.000 claims description 4
- 238000011158 quantitative evaluation Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 28
- 238000004140 cleaning Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method for predicting dust coverage of a photovoltaic power station comprises the steps of carrying out quantitative calculation and analysis on the dust coverage of the power station by utilizing operation data existing in a monitoring system of the photovoltaic power station; the method comprises the steps of analyzing and predicting the dust coverage and estimating the loss electric quantity by determining the functional relation between the power generation loss rate and time t caused by the dust coverage of a power station, and simultaneously providing a dust coverage quantitative index to realize quantitative calculation of the dust coverage; the invention can predict the dust coverage of the power station; the dust that power station fortune dimension personnel can know whole power station in real time covers the condition, and then decides when to carry out photovoltaic panel and wash comparatively rationally.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method for predicting dust coverage of a photovoltaic power station.
Background
In recent years, the installed photovoltaic capacity of China is continuously increased, the development of photovoltaic power generation technology is changed day by day, and new technology and new method in the photovoltaic field are continuously emerged. The northern area is the area with the most photovoltaic power stations in China, the northern area has more sand storms and large dust, and the dust covered on the photovoltaic power station component seriously influences the power generation efficiency of the photovoltaic power station component.
At present, a reference standard is needed for a method for predicting dust coverage of a photovoltaic power station, such as regularly cleaning a string, and the like, and the dust coverage condition of the power station is monitored and the dust shielding loss rate is calculated by comparing current data of regularly cleaning a component with current data of an unwashed string. The method needs manual participation, cannot predict the covering condition of the dust, and mainly has the following defects:
1. the power loss caused by dust covering before and after the cleaning time point can only be calculated, and cannot be predicted. Because the irradiance and the current of the photovoltaic string are not in a linear relation, the difference value of the current values before and after the photovoltaic string is cleaned cannot effectively estimate the power generation loss caused by dust coverage.
2. Only the dust covering condition of the cluster can be monitored and the loss electric quantity can be analyzed, and the square matrix loss cannot be estimated. The influence degrees of dust on each group string are different, the average value measured and calculated by partial group strings is used for estimating the power generation loss of the whole photovoltaic power station, and the error ratio is large.
3. When the dust coverage condition is evaluated and analyzed, quantitative indexes are lacked, and the dust coverage condition of each group of strings and square matrixes cannot be intuitively reflected.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method for predicting the dust coverage of a photovoltaic power station, which determines the functional relation between the dust coverage and the loss electric quantity of the photovoltaic power station by using the existing operation data in a monitoring system of the photovoltaic power station, analyzes and predicts the dust coverage and estimates the loss electric quantity, and simultaneously provides a quantitative index of the dust coverage to realize quantitative calculation of the dust coverage.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method for predicting dust coverage of a photovoltaic power station comprises the following steps:
step 1: acquiring real-time current, voltage, generating capacity and irradiance data from a real-time database of an existing operation control system of a photovoltaic power station;
step 2: making a prediction of dust coverage, at a period TjInner, TjReading real-time data I of irradiance per minute in a real-time database at least by daykThen accumulating the real-time data of irradiance per minute to obtain the total daily irradiation Id,
Total daily exposure IdConversion to equivalent daily hours of sunshine HR-dCombining the formula: theoretical daily generated energy QL-dInstalled capacity C of power stationIX equivalent hours of sunshine HR-dX the efficiency of the system, mu,
QL-d=CI(MW)×HR-d(H)×μ
installed capacity C of power stationICapacity C installed by power generation unitI-zReplacing, calculating the daily generated energy Q of each theoryL-d-zAccumulating the theoretical daily generated energy to calculate the period TjInternal theoretical generated energy QC-p-iAnd then according to the power decline empirical coefficient K of the photovoltaic moduleP-s-zCalculating the period TjGenerating capacity Q of inner unit kilowattC-Y-iThe power generation units are configured identically in the same photovoltaic power plant, so that Q is the same in the same photovoltaic power plantC-Y-iThere is only one value:
QC-Y-i=(1-KP-s-z)×QC-p-i
and step 3: in an evaluation period TjInner, TjReading the current, voltage and real-time data per minute in the real-time database at least in units of days, and calculating the actual data per minuteTime power PiFurther calculate the daily generated energy Qzd-n:
Here TiIs and PiFor each minute, and then calculate the period TjHistorical power generation QC-iIf minute-level Q is already in the real-time databaseC-iThen, the following can be directly read for use:
and 4, step 4: in the period TjInternal and external calculation unit kilowatt generating capacity QC-Tj-iInstalled capacity CI-zRepresents:
QC-Tj-i=QC-i/CI-z(kw)
and 5: for unit kilowatt generating capacity QC-Tj-iSorting and determining the maximum value QC-max;
Step 6: calculating the unit kilowatt dust coverage power generation loss rate phiC-Tj-i:
And 7: calculating the power generation loss rate value phi of dust coverage in at least three different periodsC-Tj-i-1、ΦC-Tj-i-2、ΦC-Tj-i-3。
And 8: fitting a function relation f (phi) of the power generation loss rate caused by the ith dust cover and the time t by using a least square methodiAnd t), calculating the ith dust coverage power generation loss rate at any time t according to the functional relation in the step 7, and taking the dust coverage power generation loss rate as a dust coverage quantitative evaluation index.
The invention has the advantages that:
carrying out quantitative calculation and analysis on the dust coverage of the power station; the dust coverage of the power station can be predicted by determining the functional relation between the power generation loss rate caused by the dust coverage of the power station and the time t; the dust that power station fortune dimension personnel can know whole power station in real time covers the condition, and then decides when to carry out photovoltaic panel and wash comparatively rationally.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
Referring to fig. 1, a method for predicting dust coverage of a photovoltaic power station includes the following steps:
step 1: acquiring data from a real-time database of an existing operation control system of a photovoltaic power station, firstly judging whether daily operation data of a photovoltaic string can be acquired or not, wherein the daily operation data of the photovoltaic string comprises real-time current, voltage, generated energy and irradiance data of each string, and if the daily operation data of the photovoltaic string can be acquired, predicting the coverage of string-level dust; otherwise, setting an inverter corresponding to a square matrix, and predicting the coverage of the square matrix dust.
The "string group" is a power generation unit formed by connecting a plurality of photovoltaic panels in series, and taking the photovoltaic power station 1 st of Jing county Longzhou as an example, the rated power of one photovoltaic panel is 260W, 22 photovoltaic panels are connected in series to form one "string group", the installed capacity of one "string group" is approximately 260W × 22 ═ 5720W (5.72KW), and approximately 176 string groups are arranged under one "square matrix".
Step 2: predicting the coverage of group cascade dust in the period TjInner, TjReading real-time data I of irradiance per minute in a real-time database at least by daykThen accumulating the real-time data of irradiance per minute to obtain the total daily irradiation Id,
Total daily exposure IdConversion to daily, etcHours of effective sunshine HR-dCombining the formula: theoretical daily generated energy QL-dInstalled capacity C of power stationIX equivalent hours of sunshine HR-dX the efficiency of the system, mu,
QL-d=CI(MW)×HR-d(H)×μ
installed capacity C of power stationICapacity C of series-packed by groupsI-zReplacing, calculating the theoretical daily generated energy Q of each group stringL-d-zAccumulating the theoretical daily generated energy to calculate the period T of each stringjInternal theoretical generated energy QC-p-iAnd then according to the power decline empirical coefficient K of the photovoltaic moduleP-s-zCalculating the period TjEach internal group of series unit kilowatt power generation capacity QC-Y-iIn the same photovoltaic power plant, the configuration of the strings is the same, so that in the same photovoltaic power plant, QC-Y-iThere is only one value:
QC-Y-i=(1-KP-s-z)×QC-p-i
and step 3: in an evaluation period TjInner, TjReading real-time data of string current and string voltage per minute in the real-time database at least in units of days, and calculating real-time power P of each string per minuteiAnd further calculating the daily power generation quantity Q of each group stringzd-n:
Here TiIs and PiEvery minute correspondingly, and then calculates the period T of each group stringjHistorical power generation QC-iIf minute-level Q is already in the real-time databaseC-iAnd the data can be directly read and used.
And 4, step 4: in the period TjIn the interior, the unit kilowatt generating capacity Q of each group of strings is calculatedC-Tj-iFor assembling the capacity CI-zRepresents:
QC-Tj-i=QC-i/CI-z(kw)
and 5: for each group of series unit kilowatt generating capacity QC-Tj-iSorting and determining the maximum value QC-max。
Step 6: calculating the dust covering power generation loss rate phi of each group of serial units of kilowattsC-Tj-i:
And 7: calculating the power generation loss rate value phi of each group of dust coverage in three different periodsC-Tj-i-1、ΦC-Tj-i-2、ΦC-Tj-i-3。
And 8: fitting a function expression f (phi) of the power generation loss rate caused by the dust coverage of the ith group string and the time t by using a least square methodiAnd t), calculating the dust coverage power generation loss rate of the ith group string at any time t according to the functional relation in the step 7, and calculating and predicting the dust coverage of the group string by taking the 'dust coverage power generation loss rate' as a quantitative evaluation index of the dust coverage.
If the prediction of the dust coverage of the square matrix level is carried out, the period T isjIn the method, the square matrix level related data is used for calculating and predicting the square matrix level dust coverage, and firstly, a power generation area below a photovoltaic power station is generally called as a square matrix. Take Jing Keng county Longzhou photovoltaic power plant 1 phase as an example: the installed capacity of the power station is 30MW, 30 photovoltaic square matrixes are arranged below the power station, and the installed capacity of each square matrix is 1MW (one square matrix comprises two inverters, and each inverter is 500 KW). The data of each square matrix can be directly read from the inverter. If only one inverter exists under one square matrix, the data of the inverter is the data of the square matrix; if two inverters exist under one square matrix, the generated energy and power data of the square matrix are the sum of the data of the two inverters.
The method specifically comprises the following steps:
(1): read period TjHistory of internal real-time database variety party matrixGenerated energy QF-iCalculating the period TjThe kilowatt generating capacity of each square array unit is as follows: qF-T-i。
(2): sequencing kilowatt generating capacity of each square array unit and determining maximum value QF-max。
(3): calculating the period TjThe theoretical generated energy of each square matrix in the system is as follows: qF-P-i。
(4): according to the past accumulated power decline empirical coefficient K of the photovoltaic moduleP-s-zCalculating the kilowatt-response generating capacity Q of each square matrix unitF-Y-iThe square matrix configuration is generally the same in the same photovoltaic power plant, so that in the same photovoltaic power plant, QF-Y-iThere is only one value.
QF-Y-i=(1-KP-s-z)×QF-P-i
(5): calculating the dust covering power generation loss rate phi of each group of serial units of kilowattsF-Tj-i:
(6): calculating the power generation loss rate value phi of each square matrix of dust coverage in three different periodsF-Tj-i-1、ΦF-Tj-i-2、ΦF-Tj-i-3。
(7): fitting a function relation f (phi) of the power generation loss rate caused by the dust coverage of the ith square matrix and the time t by using a least square methodiAnd t), calculating the dust coverage power generation loss rate of the ith square matrix at any time t according to the determined functional relation, and calculating and predicting the dust coverage of the square matrix by taking the 'dust coverage power generation loss rate' as a quantitative evaluation index of the dust coverage.
And (4) conclusion:
the strings and the square matrix belong to two-dimensional power generation units common to photovoltaic power plants. Because some photovoltaic power plants put into operation in the previous years are influenced by the current power plant construction standard and the intelligentization degree of photovoltaic power generation equipment, data of group string current and group string voltage cannot be acquired, so that the group string level dust coverage can not be predicted by using the method, and only the square matrix level dust coverage can be predicted; in recent years, the intelligent degree of installed photovoltaic power generation equipment of photovoltaic power plants in operation is gradually improved, and a plurality of power plants can acquire string current and string voltage data, so that the dust coverage of the photovoltaic power plants can be predicted from two dimensions of strings and matrixes by using the method. Because the data acquisition positions of the cluster and the square matrix are different, and the calculation process of the data is different:
the method comprises the steps that current and voltage data of a minute level are taken for string grouping, then power data of the minute level are obtained through calculation, the power data of the minute level are multiplied by corresponding time and then accumulated, and finally actual generated energy data of the string grouping are obtained;
the generated energy data required by the square matrix is directly read from the inverters, and if a plurality of inverters are arranged below the square matrix, the actual generated energy data of the square matrix can be obtained only by accumulating the generated energy data of the plurality of inverters, so that the prediction results of two dimensions are generally different.
Therefore, the power plant operation maintenance personnel comprehensively consider the prediction results of the two dimensions, select the optimal power plant photovoltaic panel dust cleaning time point, reduce the power plant operation maintenance cost and improve the generated energy to the maximum extent.
Claims (1)
1. A method for predicting dust coverage of a photovoltaic power station is characterized by comprising the following steps:
step 1: acquiring real-time current, voltage, generating capacity and irradiance data from a real-time database of an existing operation control system of a photovoltaic power station;
step 2: making a prediction of dust coverage, at a period TjInner, TjReading real-time data I of irradiance per minute in a real-time database at least by daykThen accumulating the real-time data of irradiance per minute to obtain the total daily irradiation Id,
Total daily exposure IdConversion to equivalent daily hours of sunshine HR-dCombining the formula: theoretical daily generated energy QL-dInstalled capacity C of power stationIX equivalent hours of sunshine HR-dX the efficiency of the system, mu,
QL-d=CI(MW)×HR-d(H)×μ
installed capacity C of power stationICapacity C installed by power generation unitI-zReplacing, calculating the daily generated energy Q of each theoryL-d-zAccumulating the theoretical daily generated energy to calculate the period TjInternal theoretical generated energy QC-p-iAnd then according to the power decline empirical coefficient K of the photovoltaic moduleP-s-zCalculating the period TjGenerating capacity Q of inner unit kilowattC-Y-iThe power generation units are configured identically in the same photovoltaic power plant, so that Q is the same in the same photovoltaic power plantC-Y-iThere is only one value:
QC-Y-i=(1-KP-s-z)×QC-p-i
and step 3: in an evaluation period TjInner, TjReading current, voltage and real-time data per minute in a real-time database at least in units of days, and calculating real-time power per minute PiFurther calculate the daily generated energy Qzd-n:
Here TiIs and PiFor each minute, and then calculate the period TjHistorical power generation QC-iIf minute-level Q is already in the real-time databaseC-iThen, the following can be directly read for use:
and 4, step 4: in the period TjInternal and external calculation unit kilowatt generating capacity QC-Tj-iInstalled capacity CI-zRepresents:
QC-Tj-i=QC-i/CI-z(kw)
and 5: for unit kilowatt generating capacity QC-Tj-iSorting and determining the maximum value QC-max;
Step 6: calculating the unit kilowatt dust coverage power generation loss rate phiC-Tj-i:
And 7: calculating the power generation loss rate value phi of dust coverage in at least three different periodsC-Tj-i-1、ΦC-Tj-i-2、ΦC-Tj-i-3;
And 8: fitting a function relation f (phi) of the power generation loss rate caused by the ith dust cover and the time t by using a least square methodiAnd t), calculating the ith dust coverage power generation loss rate at any time t according to the functional relation in the step 7, and taking the dust coverage power generation loss rate as a dust coverage quantitative evaluation index.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111353709.6A CN114021838A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station dust coverage prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111353709.6A CN114021838A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station dust coverage prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114021838A true CN114021838A (en) | 2022-02-08 |
Family
ID=80064346
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111353709.6A Pending CN114021838A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station dust coverage prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114021838A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114898232A (en) * | 2022-04-29 | 2022-08-12 | 中科云尚(南京)智能技术有限公司 | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis |
-
2021
- 2021-11-16 CN CN202111353709.6A patent/CN114021838A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114898232A (en) * | 2022-04-29 | 2022-08-12 | 中科云尚(南京)智能技术有限公司 | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis |
CN114898232B (en) * | 2022-04-29 | 2023-08-15 | 中科云尚(南京)智能技术有限公司 | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic group string data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
CN109615629B (en) | Convolutional neural network-based photovoltaic panel dust accumulation state image recognition system and analysis, regulation and control method thereof | |
CN112257941B (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
CN110880789B (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
CN108399493A (en) | Dust stratification causes photovoltaic power generation quantity loss forecasting method and photovoltaic module to clean judgment method | |
CN109376951B (en) | Photovoltaic probability prediction method | |
CN115249094B (en) | Building energy efficiency management and optimization method based on big data | |
CN110729764A (en) | Optimal scheduling method for photovoltaic power generation system | |
CN115293372A (en) | Photovoltaic string fault diagnosis method based on multi-dimension and multi-parameter numerical analysis | |
CN114021838A (en) | Photovoltaic power station dust coverage prediction method | |
CN115600722A (en) | Long-term prediction method for electric carbon factor of enterprise | |
CN112288130A (en) | New energy consumption calculation method based on two-stage multi-objective optimization | |
CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence | |
CN117251672A (en) | Regional industry multi-dimensional energy carbon emission calculation method and device based on electric power data | |
CN116485139A (en) | Short-term photovoltaic power generation amount prediction method based on multi-feature fusion | |
CN116914719A (en) | Photovoltaic power station power prediction method based on space-time diagram network | |
CN114188942A (en) | Power grid dispatching method comprising large-scale new energy base | |
CN117494910B (en) | Multi-energy coordination optimization control system and method based on carbon emission reduction | |
CN112288285B (en) | Photovoltaic power station string attenuation rate evaluation method based on generalized extreme value distribution | |
CN115310839A (en) | Photovoltaic power station dust deposition early warning assessment method and system | |
Liang et al. | Short-term Day-to-day Maximum Load Forecasting based on Data Mining and Deep Learning | |
CN118174285A (en) | Photovoltaic output power prediction method based on K-GCN-LSTM model | |
CN117874558A (en) | Photovoltaic array running state identification method based on multiple evaluation indexes | |
CN117663503A (en) | Method and system for intelligently adjusting molten salt heat storage rate | |
CN114066085A (en) | Photovoltaic power station cleaning optimization scheduling 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 |