CN112326684A - Photovoltaic module dust accumulation detection method, device, equipment and storage medium - Google Patents
Photovoltaic module dust accumulation detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112326684A CN112326684A CN202011131007.9A CN202011131007A CN112326684A CN 112326684 A CN112326684 A CN 112326684A CN 202011131007 A CN202011131007 A CN 202011131007A CN 112326684 A CN112326684 A CN 112326684A
- Authority
- CN
- China
- Prior art keywords
- time period
- current time
- dust deposition
- data
- preset
- 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
- 239000000428 dust Substances 0.000 title claims abstract description 387
- 238000009825 accumulation Methods 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 230000008021 deposition Effects 0.000 claims abstract description 322
- 238000004364 calculation method Methods 0.000 claims abstract description 105
- 238000012795 verification Methods 0.000 claims abstract description 68
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 67
- 238000000034 method Methods 0.000 claims abstract description 60
- 238000012937 correction Methods 0.000 claims description 15
- 238000004140 cleaning Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000000692 Student's t-test Methods 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012353 t test Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
- G01N2021/945—Liquid or solid deposits of macroscopic size on surfaces, e.g. drops, films, or clustered contaminants
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method, a device, equipment and a storage medium for detecting dust deposition of a photovoltaic module, wherein the method for detecting the dust deposition of the photovoltaic module comprises the following steps: acquiring a dust accumulation calculation parameter of the current time period based on the data density of the current time period; determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period; verifying the dust deposition rate of the current time period based on a preset verification algorithm to obtain a verification result; determining data density of a next time period based on the verification result; and taking the next time period as a new current time period, and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period. The invention can switch the data density of the dust accumulation calculation parameter in the current time period based on the dust accumulation calculation result in the historical time period, and can realize the control of data density access while ensuring the dust accumulation detection precision, thereby meeting the requirements of different application scenes on the access data density.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method, a device, equipment and a storage medium for detecting dust deposition of a photovoltaic module.
Background
The photovoltaic field generally determines the dust accumulation condition of a component by monitoring the power value of the component in a power station, for example, by calculating the actual generated power of the component, comparing the actual generated power with the theoretical value of the component under standard conditions, and determining the dust accumulation condition of the component by the difference ratio. In the prior art, one data density is often used in a fixed manner, and in an actual application scenario, an initially appropriate data density may become inappropriate along with a change in environment, which may reduce the accuracy of a dust accumulation detection result.
Disclosure of Invention
The invention solves the problems that the fixed data density in the prior art cannot adapt to the changing environment and the accuracy of the dust accumulation detection result cannot be ensured.
In order to solve the above problems, the present invention provides a method for detecting dust deposition on a photovoltaic module, comprising:
acquiring a dust accumulation calculation parameter of the current time period based on the data density of the current time period;
determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period;
verifying the dust deposition rate of the current time period based on a preset verification algorithm to obtain a verification result;
determining data density of a next time period based on the verification result;
and taking the next time period as a new current time period, and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period.
Optionally, the determining the data density of the next time period based on the verification result includes:
and when the dust deposition rate of the current time period is not verified, taking a first data density as the data density of the next time period, wherein the first data density is greater than the data density of the current time period.
Optionally, the determining the data density of the next time period based on the verification result includes:
and when the dust deposition rate of the current time period passes the verification, taking a second data density as the data density of the next time period, wherein the second data density is less than or equal to the data density of the current time period.
Optionally, the verifying the dust deposition rate of the current time period based on a preset verification algorithm, and after obtaining a verification result, further includes:
and when the dust deposition rate of the current time period does not pass the verification, correcting the dust deposition rate of the current time period based on a preset correction algorithm to obtain the corrected dust deposition rate of the current time period.
Optionally, the preset correction algorithm is one or a combination of a moving average method, a weighted average method, a hanning window convolution noise reduction method, and an exponential moving average method.
Optionally, when the dust deposition rate of the current time period fails to be verified, the method, after correcting the dust deposition rate of the current time period based on a preset correction algorithm to obtain the corrected dust deposition rate of the current time period, further includes:
verifying the corrected dust deposition rate of the current time period based on the preset verification algorithm;
and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
Optionally, the verifying the dust deposition rate of the current time period based on a preset verification algorithm, and after obtaining a verification result, further includes:
and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
Optionally, the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm includes:
acquiring preset data of each time period within a preset historical period, wherein the preset data is at least one of data contained in the dust accumulation calculation parameters;
comparing the preset data of the current time period with the preset data of each time period within the preset historical period respectively to obtain a comparison result;
determining a preset number of time periods closest to the current time period based on the comparison result;
and determining the final dust deposition rate of the current time period based on the dust deposition rate of the closest preset number of time periods.
Optionally, the preset data is irradiation data, and the comparing the preset data of the current time period with the preset data of each time period within the preset historical time limit respectively to obtain a comparison result includes:
respectively calculating the distance between the irradiation data of the current time period and the irradiation data of each time period in the preset historical period based on a preset formula, wherein the distance is the comparison result, and the preset formula is as follows:
wherein dist (X, Y) is the distance of irradiation data in X and Y time periods, and XkAnd ykThe radiation values at the kth time in X and Y time periods respectively, wherein k is more than or equal to 0.
Optionally, after obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period, the method further includes:
judging whether the data volume of the dust accumulation calculation parameter of the current time period is larger than a preset value or not;
when the data volume of the dust deposition calculation parameter of the current time period is larger than a preset value, the step of determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period is executed;
and when the data volume of the dust accumulation calculation parameter of the current time period is smaller than or equal to the preset value, taking a third data density as the data density of the next time period, and determining the final dust accumulation rate of the current time period based on a preset historical data padding algorithm, wherein the third data density is greater than the data density of the current time period.
Optionally, the preset verification algorithm comprises a t-test algorithm.
Optionally, the determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period comprises:
and executing data cleaning operation based on the dust deposition calculation parameters of the current time period to obtain cleaned dust deposition calculation parameters, wherein the data cleaned by executing the data cleaning operation comprises at least one of the following data: repeating data, power abnormal data, data in a power limiting state and temperature abnormal data;
and determining the dust deposition rate of the current time period based on the cleaned dust deposition calculation parameters.
Optionally, after the step of taking the next time period as a new current time period and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period, the method further includes:
acquiring the final dust deposition rate of all time periods in a preset time length;
and calculating the dust deposition rate of the preset duration based on the final dust deposition rate of all the time periods.
Optionally, the dust deposition calculation parameters include irradiation data, ambient temperature data, and total dc power at the dc side of the inverter, and determining the dust deposition rate of the current time period based on the dust deposition calculation parameters of the current time period includes:
calculating the normalized power value of each moment in the current time period, determining the maximum normalized power value in the current time period, and calculating the average value of the normalized power values in the current time period;
and calculating the dust deposition rate of the current time period based on the maximum normalized power value and the average value.
The invention also provides a photovoltaic module dust accumulation detection device, which comprises:
an acquisition unit for acquiring a dust accumulation calculation parameter of a current time period based on a data density of the current time period;
a calculation unit for determining a dust deposition rate of the current time period based on a dust deposition calculation parameter of the current time period;
the checking unit is used for checking the dust deposition rate of the current time period based on a preset checking algorithm to obtain a checking result;
a processing unit for determining a data density of a next time period based on the verification result; and taking the next time period as a new current time period, and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period.
The invention further provides a photovoltaic module dust accumulation detection device, which comprises a computer readable storage medium and a processor, wherein the computer readable storage medium is used for storing a computer program, and the computer program is read by the processor and runs to realize the photovoltaic module dust accumulation detection method.
The invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is read and executed by a processor, the method for detecting the dust deposition on the photovoltaic module is implemented.
According to the invention, the data density of the next time period is determined based on the verification result of the dust deposition rate of the current time period, and the data density access control in the dust deposition rate calculation process is realized on the premise of ensuring the dust detection precision, so that the requirements of dust deposition detection of different application environments on the data density are met, the adaptability of the dust deposition detection function is improved, and higher detection precision is always kept.
Drawings
FIG. 1 is a schematic view of an embodiment of a method for detecting dust deposition on a photovoltaic module according to the present invention;
FIG. 2 is a schematic view of another embodiment of the method for detecting dust deposition on a photovoltaic module according to the present invention;
FIG. 3 is a schematic view of another embodiment of the method for detecting dust on a photovoltaic module according to the present invention;
FIG. 4 is a schematic view of an embodiment of a device for detecting dust on a photovoltaic module according to the present invention;
fig. 5 is a schematic view of an embodiment of a photovoltaic module dust accumulation detection apparatus according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
The invention provides a method for detecting dust deposition of a photovoltaic module.
Referring to fig. 1, in an embodiment of the method for detecting dust deposition on a photovoltaic module according to the present invention, the method includes:
step S10, acquiring dust deposition calculation parameters of the current time period based on the data density of the current time period;
a certain time duration (e.g., one day, one week, one month) may be divided into a plurality of time periods, for example, one day is divided into 24 time periods, and the time duration of each time period is 1 hour, or a certain time is used as a starting point, and a preset interval time duration is used as a time period duration, and the time periods are acquired one by one, for example, a zero time of the first day of one week is used as a starting point, and a time period is taken every 1 hour until a zero time of the last day of the week.
The current time period refers to the time period in which the dust deposition rate is currently calculated, and after the data of the current time period are collected, dust deposition calculation parameters are obtained from the collected data and are used for calculating the dust deposition rate of the current time period. The data density refers to the amount of data contained in a unit time, the data density of the current time period refers to the data density of the dust deposition calculation parameter of the current time period, for example, the data density of 5 minutes means that the acquisition time interval of two adjacent data is 5 minutes, and the data density of 30 seconds means that the acquisition time interval of two adjacent data is 30 seconds.
The dust deposition calculation parameters refer to parameters for calculating the dust deposition rate and comprise one or more of irradiation data, environment temperature data and total direct current power of the direct current side of the inverter. In one embodiment, irradiation data, ambient temperature, and total dc power at the dc side of the inverter collected at a certain time are obtained as a set of dust deposition calculation parameters.
For convenience of description, the data included in the dust deposition calculation parameter is referred to as first data, for example, if the dust deposition calculation parameter includes irradiation data, an ambient temperature, and a total dc power on the dc side of the inverter, the irradiation data, the ambient temperature, and the total dc power on the dc side of the inverter are referred to as first data. In an alternative embodiment, all the first data collected in the current time period are used as the dust deposition calculation parameter, and the data density of the dust deposition calculation parameter can be controlled by controlling the data collection frequency of the first data, for example, the data density of the dust deposition calculation parameter is in the order of 5 minutes, and the data collection frequency of the first data is 1/5 minutes, that is, 5 minutes of data collection. In another alternative embodiment, if a part of data is acquired from the first data acquired in the current time period as the dust-accumulation calculation parameter, and the data acquisition frequency of the first data is greater than the data density of the dust-accumulation calculation parameter, for example, the data acquisition frequency of the first data is 1 time/1 minute, and the data density of the dust-accumulation calculation parameter is on the order of 5 minutes, then data with a time interval of 5 minutes are sequentially acquired from the first data, for example, the data at the initial time (time is 0), the data at the 5 th time, the data at the 10 th time, the data at the 15 th time, and the like are taken from the front to the back in chronological order.
Step S30, determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period;
in one embodiment, the dust deposition calculation parameter includes total dc power on the dc side of the inverter, and step S30 includes: the method comprises the steps of obtaining the total direct current power with the most backward acquisition time in the current time period, calculating the difference value of the total direct current power with the most backward acquisition time and preset power, and taking the ratio of the difference value to the preset power as the dust deposition rate of the current time period, wherein the preset power is the power of the assembly in a clean state.
In another embodiment, the dust deposition calculation parameters include irradiation data, ambient temperature data, and total dc power on the dc side of the inverter, as shown in fig. 2, and step S30 includes:
step S301, calculating the normalized power value of each moment in the current time period, and determining the maximum normalized power value in the current time period;
calculating the normalized power value of each moment in the current time period based on a preset first formula, wherein the first formula is as follows:
wherein, TTRC＝25℃，GTRC＝1000w/m2，GmeasFor the current actual irradiation, TCIs the current component temperature, Pcorr_STCTo normalize the power, PmeasTo measure power, δ is the power temperature coefficient of the component.
Step S302, calculating the average value of the normalized power values of the current time period based on the normalized power values of all the moments in the current time period;
the step of determining the maximum normalized power value in the current time period in step S301 and step S302 may be executed simultaneously or sequentially, and the order of the two steps is not limited.
Step S303, calculating the dust deposition rate of the current time period based on the maximum normalized power value and the average value.
The dust deposition rate of the current time period may be calculated based on a preset second formula:
among them, dustiIs the dust deposition rate of the i-th period, PcorrSTC,maxIs the maximum normalized power value, P, in the i-th time periodcorrSTC,avgIs the average value of normalized power over the ith time period, optionally, i e [0,24]. Wherein the maximum normalized power is approximately the normalized generated power when the component is in a clean state.
The dust deposition rate of the current time period is calculated based on the average value and the maximum value of the normalized power values of the current time period by calculating the normalized power values of all the moments in the current time period, so that the dust deposition rate is accurately determined based on the assembly power, the assembly temperature and the irradiation data of the current time period, and subsequent verification and calculation are facilitated.
Step S40, verifying the dust deposition rate of the current time period based on a preset verification algorithm to obtain a verification result;
optionally, the preset verification algorithm includes a t-verification algorithm, a confidence interval of the overall mean value is constructed, whether the dust deposition rate of the current time period falls into the confidence interval is judged, if yes, the dust deposition rate of the current time period is judged to pass the verification, and if not, the dust deposition rate of the current time period is judged not to pass the verification.
Step S50, determining the data density of the next time period based on the verification result;
if the dust deposition rate of the current time period passes the verification, the data density of the current time period can ensure sufficient detection precision; if the dust deposition rate of the current time period does not pass the verification, it indicates that the data density of the current time period is not large enough, and higher detection precision cannot be ensured.
Optionally, step S50 includes:
step S501, when the dust deposition rate of the current time period does not pass the verification, taking a first data density as the data density of the next time period, where the first data density is greater than the data density of the current time period.
That is, when the detection accuracy of the current period is insufficient, the dust deposition detection accuracy of the next period is improved by increasing the data density of the next period.
In one embodiment, a plurality of data density levels are preset, such as: 30 seconds, 1 minute, 1.5 minutes, 2 minutes, 2.5 minutes, 3 minutes, 3.5 minutes, 4 minutes, 4.5 minutes, 5 minutes. The data density of the dust deposition calculation parameter in the next time period may be increased by one or more levels, and taking the above level example as an example, if the data density in the current time period is 4 minutes level, and if the dust deposition rate in the current time period fails to be verified, two data density levels are increased, and the first data density is 3 minutes level. By setting the data density level, the data density is convenient to adjust.
Optionally, step S50 includes:
step S502, when the dust deposition rate of the current time period passes the verification, taking a second data density as the data density of the next time period, wherein the second data density is less than or equal to the data density of the current time period.
When the dust deposition rate of the current time period passes the inspection, the data density of the current time period can ensure enough detection precision, at the moment, the data density of the current time period can be used as the data density of the next time period to maintain higher detection precision, and the data density of the next time period can be reduced to reduce the storage burden and the calculation burden of equipment.
And step S60, taking the next time period as a new current time period, and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period.
And taking the next time period as a new current time period, and continuously calculating the dust deposition rate of the current time period.
The data density of the next time period is determined through the verification result based on the dust deposition rate of the current time period, and then on the premise of ensuring the dust detection precision, the data density access is controlled in the dust deposition rate calculation process, so that the requirements of dust deposition detection of different application environments on the data density are met, the adaptability of the dust deposition detection function is improved, and higher detection precision is always kept.
Optionally, step S40 is followed by:
when the dust deposition rate of the current time period is not verified, executing step S70: and correcting the dust deposition rate of the current time period based on a preset correction algorithm to obtain the corrected dust deposition rate of the current time period.
Correcting the dust deposition rate of the current time period based on a preset correction algorithm, specifically: and predicting the dust deposition rate of the current time period based on the recently calculated dust deposition rates of the time periods. And after the dust deposition rate of the current time period is corrected, the correction flag bit is modified from 0 to 1. The preset correction algorithm can be selected from one or a combination of a moving average method, a weighted average method, a Hanning window convolution noise reduction method and an exponential sliding average method, so that random fluctuation in prediction can be effectively eliminated, and a more accurate prediction result can be obtained.
In one embodiment, the preset correction algorithm is a moving average method, and the dust deposition rate in the current time period is corrected based on a preset third formula, where the third formula is:
among them, dustdeal,iCorrecting the post-treatment dust deposition rate for the ith time period, dusti-tThe dust accumulation rate in the i-t period is t 1,2.
The weighted average method, the hanning window convolution noise reduction method, the exponential moving average method, and the like are all commonly used data correction algorithms, and are not described herein.
When the dust deposition rate calculated based on the dust deposition calculation parameters of the current time period does not pass the verification, a preset correction algorithm is used for correcting, and the finally calculated dust deposition rate is guaranteed to have higher precision.
Optionally, the corrected dust deposition rate of the current time period is used as the final dust deposition rate of the current time period,
optionally, step S70 is followed by:
step S80, verifying the corrected dust deposition rate of the current time period based on the preset verification algorithm;
and step S90, when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
And when the corrected dust deposition rate of the current time period passes the verification, taking the corrected dust deposition rate of the current time period as the final dust deposition rate of the current time period.
Optionally, the preset historical data padding algorithm includes taking an average value of a preset number of time periods that are most recent in time as a final dust deposition rate of the current time period.
Optionally, the preset historical data padding algorithm includes taking the dust deposition rate of the time period closest to the irradiation value of the current time period as the final dust deposition rate of the current time period. Optionally, the preset historical data padding algorithm includes taking an average value of the dust deposition rates of a plurality of time periods closest to the irradiation value of the current time period as a final dust deposition rate of the current time period.
In one embodiment, the preset historical data padding algorithm comprises taking the average value of the dust deposition rates of the 3 time segments closest to the irradiation value of the current time segment as the final dust deposition rate of the current time segment, that is,
among them, dustjFor the dust deposition rate in the time period to be filled (i.e. in the current time period), dustnear1、dustnear2、dustnear3Respectively is the dust deposition rate corresponding to the time section closest to the irradiation value of the time section to be filled.
Wherein, the closest time period is the first 3 time periods with the shortest Euclidean distance, and the specific calculation formula is as follows:
where dist (X, Y) is the distance between two time periods on different dates, XkAnd ykThe radiation values at the kth time in X and Y time periods respectively, wherein k is more than or equal to 0.
And when the dust deposition rate of the current time period still fails to pass the verification after being corrected, obtaining the final dust deposition rate of the current time period through a historical data filling algorithm to ensure that the detection result of the current time period does not deviate too much, and obtaining a relatively accurate result when calculating the long-time dust deposition rate based on the current time period.
Optionally, step S40 is followed by: and S100, when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
When the dust deposition rate of the current time period is not verified, the final dust deposition rate of the current time period can be calculated by directly using a preset historical data filling algorithm. Optionally, the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm includes: and taking the average value of the time periods with the latest preset number as the final dust deposition rate of the current time period. Optionally, the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm includes: and taking the dust deposition rate of the time section closest to the irradiation value of the current time section as the final dust deposition rate of the current time section. Optionally, the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm includes: and taking the average value of the dust deposition rates of a plurality of time periods closest to the irradiation value of the current time period as the final dust deposition rate of the current time period.
Optionally, the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm includes:
step S1001, acquiring preset data of each time period in a preset historical period, wherein the preset data is at least one of data contained in the dust accumulation calculation parameters;
the preset historical time limit refers to a time limit calculated before, such as the past month, the past 15 days, and the like, and a specific value of the preset historical time limit can be preset.
For the preset data, when the dust deposition calculation parameter includes irradiation data, an ambient temperature, and a total dc power at the dc side of the inverter, the preset data is at least one of the three data, for example, the preset data is irradiation data.
Step S1002, comparing the preset data of the current time period with the preset data of each time period within the preset historical period respectively to obtain a comparison result;
when the preset data is one datum, directly comparing the datum in the current time period with the datum in each time period within the preset historical period; when the preset data comprises a plurality of data, comparing the plurality of data of the current time period with corresponding data of each time period in a preset historical term, for example, if the preset data comprises irradiation data and ambient temperature, comparing the irradiation data of the current time period with the irradiation data of each time period in the preset historical term, and comparing the ambient temperature of the current time period with the ambient temperature of each time period in the preset historical term.
Optionally, the preset data is irradiation data, and the step S1002 includes:
respectively calculating the distance between the irradiation data of the current time period and the irradiation data of each time period in the preset historical period based on a preset formula, wherein the preset formula is as follows:
where dist (X, Y) is the distance of the irradiation data for two time periods, XkAnd ykThe radiation values at the kth time in X and Y time periods respectively, wherein k is more than or equal to 0.
The smaller the distance between the irradiation data of the two time periods is, the more similar the irradiation conditions of the two time periods are, the more the dust deposition data of one time period can be filled in the dust deposition data of the other time period, whereas, the larger the distance between the irradiation data of the two time periods is, the more dissimilar the irradiation conditions of the two time periods is, the lower the accuracy is caused by filling in the dust deposition data of one time period in the dust deposition data of the other time period.
The irradiation data are based on the formula, so that the similarity of the irradiation data of the two time periods can be accurately calculated, the time periods with the highest preset number of similarities with the current time period can be further determined, and the dust deposition rate of the current time period can be determined conveniently and accurately based on the time periods with the preset number.
Step S1003, determining a preset number of time periods closest to the current time period based on the comparison result;
step S1004, determining a final dust deposition rate of the current time period based on the dust deposition rate of the closest preset number of time periods.
Optionally, the average value of the dust deposition rates of the closest preset number of time periods may be used as the final dust deposition rate of the current time period; or based on the time interval between the closest preset number of time periods and the current time period, distributing weight to the closest preset number of time periods, and calculating a weighted average value based on the dust deposition rate and the weight of the closest preset number of time periods to be used as the final dust deposition rate of the current time period.
Optionally, after step S10, the method further includes:
step S20, judging whether the data volume of the dust accumulation calculation parameter of the current time period is larger than a preset value;
and after the dust accumulation calculation parameters of the current time period are obtained, judging whether the data volume meets the requirements or not. The preset value may be obtained based on the duration of the current time period (in hours) and the data density. In one embodiment, the preset value is 60 × S/data density of the current time period, where S may be selected from 60% to 80%, where the data amount refers to the number of data bars. For example, if S is 80%, the duration of the current time period is 1 hour, the data density is 5 minutes, the preset value is 1 × 60 × 80%/5 is 9.6, and the data amount is greater than 9.6, then step S30 may be directly executed.
When the data amount of the dust deposition calculation parameter of the current time period is greater than the preset value, the dust deposition rate may be calculated based on the dust deposition calculation parameter of the current time period, that is, the step S30 is executed;
when the data volume of the dust deposition calculation parameter in the current time period is less than or equal to the preset value, executing step S120: and taking a third data density as the data density of the next time period, and determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm, wherein the third data density is greater than the data density of the current time period.
And the data volume of the dust deposition calculation parameter in the current time period is smaller than or equal to a preset value, which indicates that the data volume is too small to be used for calculating the dust deposition rate, and at the moment, the historical dust deposition data is directly used for filling, wherein the related explanation of the preset historical data filling algorithm is as described above, and the explanation is not repeated here.
The data volume of the dust accumulation calculation parameter in the current time period is judged, and when the data volume meets a certain amount of requirements, the dust accumulation calculation parameter is used for calculating the dust accumulation rate in the current time period so as to ensure certain dust accumulation detection precision.
Optionally, after the step of taking the next time period as a new current time period and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period, the method further includes:
step S130, acquiring the final dust deposition rate of all time periods in a preset time length;
the preset time duration can be a day, a week, a month, etc., and can comprise a plurality of time periods, and can be set manually. For example, the preset time is one day, the time of each time period is 1 hour, and the starting point is 0 time, so that the preset time includes 24 time periods with the time of 1 hour.
And step S40, calculating the dust deposition rate of the preset time length based on the final dust deposition rate of all the time segments.
Calculating the dust deposition rate of the preset time duration according to the dust deposition rates of all time periods within the preset time duration, and optionally calculating the dust deposition rate of the preset time duration based on the following formula:
among them, dustdeal,iAnd the dust deposition rate is the final dust deposition rate in the ith time period, and the dust deposition rate is the preset time length.
The dust deposition rate of the preset time duration is calculated based on the final dust deposition rate of all the time durations in the preset time duration, namely the dust deposition rate of the preset time duration which is a long time is calculated and is decomposed into a plurality of time durations to calculate the dust deposition rate, the data of the corresponding time duration are corrected by using a statistical method once the data are calculated in each time duration and the data do not pass the verification, and the accuracy is improved.
Optionally, the preset verification algorithm includes a t-test algorithm, and step S40 includes:
step S401, obtaining a check sample mean value and a check sample standard deviation, and determining a dust accumulation rate confidence interval based on the check sample mean value and the check sample standard deviation;
and determining a dust accumulation rate confidence interval based on the mean value and the standard deviation of the check sample by setting the mean value and the standard deviation of the check sample with high accuracy. In one embodiment, the test device calculates a dust deposition rate at each time in the current time period, calculates a dust deposition rate mean and a standard deviation in the current time period based on the dust deposition rate at each time, and uses the dust deposition rate mean and the standard deviation in the current time period calculated by the test device as the check sample mean and the check sample standard deviation in step S401.
The dust deposition rate confidence interval can be expressed by the following formula:
wherein,
in order to verify the mean value of the samples,
is t distribution of bilateral values alpha of the degree of freedom n-1, S is standard deviation of the check sample, alpha can be selected to be 0.05, and n is total number of the check sample. The dust rate confidence interval is the overall mean confidence interval.
Step S402, judging whether the dust deposition rate of the current time period falls into the dust deposition rate confidence interval;
step S403, if yes, the dust deposition rate of the current time period passes the verification;
if the dust deposition rate of the current time period falls into the dust deposition rate confidence interval, it is indicated that the dust deposition rate of the current time period has no significant difference, the confidence level of the dust deposition rate of the current time period is higher, and it is indicated that the dust deposition rate of the current time period passes the verification.
And step S404, if not, the dust deposition rate of the current time period is not verified.
If the dust deposition rate of the current time period does not fall into the dust deposition rate confidence interval, it is indicated that the dust deposition rate of the current time period has a significant difference, the confidence level of the dust deposition rate of the current time period is low, and the dust deposition rate of the current time period does not pass the verification.
And verifying the dust deposition rate of the current time period through a t-verification algorithm, determining the confidence level of the dust deposition rate of the current time period, and determining the final dust deposition rate of the current time period in other modes when the confidence level is lower so as to improve the accuracy of the finally calculated dust deposition rate.
Optionally, the determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period comprises:
and executing data cleaning operation based on the dust deposition calculation parameters of the current time period to obtain cleaned dust deposition calculation parameters, wherein the data cleaned by executing the data cleaning operation comprises at least one of the following data: repeating data, power abnormal data, data in a power limiting state and temperature abnormal data;
and determining the dust deposition rate of the current time period based on the cleaned dust deposition calculation parameters.
The duplicate data refers to duplicate data caused by retransmission of the device and the like.
Optionally, the dust deposition calculation parameters include total dc power at the dc side of the inverter, and power anomaly data refers to data of which the power value exceeds a power value mean value ± 3 times of a standard deviation range according to irradiation fitting, that is:
wherein,
for the power fitted from the irradiation, μ is the mean of the power fitted from the irradiation, σ is the standard deviation of the power fitted from the irradiation, i.e. the deletion power value exceeds [ μ -3 σ, μ +3 σ [ ]]Data of (2). Wherein, the fitting of the power and the irradiation adopts a linear fitting mode.
Optionally, the dust deposition calculation parameter includes total dc power on the dc side of the inverter, and for data in the limited power state, specifically, for a constructed power curve, if there are a plurality of states in which time appears to be approximate straight lines, the time of the approximate straight lines is considered to be in the limited power state, and data at the time of the approximate straight lines is deleted, that is, data in the limited power state is deleted.
Optionally, the dust deposition calculation parameter includes component temperature data, temperature abnormal data is determined according to a partial correlation coefficient of temperature and power in each time period, and the temperature abnormal data is deleted, wherein when the partial correlation coefficient of temperature and power is a positive value, the temperature abnormal data is considered to exist at the corresponding time, and the data in the time when the temperature abnormal data exists is deleted.
Fig. 3 shows an embodiment of a method for detecting dust deposition on a photovoltaic module according to the present invention, which includes: accessing the dust deposition calculation parameter in the current time period, performing data cleaning on the dust deposition calculation parameter, judging whether the data volume after the data cleaning is larger than a preset value (a), if the data volume after the data cleaning is larger than the preset value, calculating the dust deposition rate in the current time period, carrying out t check on the dust deposition rate of the current time period, judging whether the dust deposition rate of the current time period has significant difference or not, if yes, the dust rate in the current time period is not checked, whether the correction flag bit is 0 is judged, if so, the dust rate in the current time period is not corrected, at the moment, correcting the dust deposition rate of the current time period, setting the correction flag position to be 1, then performing t-check on the corrected dust deposition rate of the current time period, if not 0, indicating that the dust deposition rate of the current time period is corrected, and at the moment, filling and determining the dust deposition rate of the current time period by using historical data; and if the data volume after data cleaning is smaller than or equal to a preset value, filling historical data to determine the dust deposition rate of the current time period, and meanwhile, judging whether the data density of the current time period is the highest data density, if not, increasing the data density of the next time period, and if so, filling the historical data to determine the dust deposition rate of the next time period. And recording the dust deposition rate of each time period, and calculating the daily dust deposition rate based on the dust deposition rate of each time period.
The invention further provides a device for detecting the dust deposition of the photovoltaic module. As shown in fig. 4, in an embodiment of the photovoltaic module dust deposition detection apparatus, the photovoltaic module dust deposition detection apparatus includes:
an acquisition unit for acquiring a dust accumulation calculation parameter of a current time period based on a data density of the current time period;
a calculation unit for determining a dust deposition rate of the current time period based on a dust deposition calculation parameter of the current time period;
the checking unit is used for checking the dust deposition rate of the current time period based on a preset checking algorithm to obtain a checking result;
and the processing unit is used for determining the data density of the next time period based on the verification result, taking the next time period as a new current time period, and returning to execute the step of acquiring the dust deposition calculation parameter of the current time period based on the data density of the current time period.
Optionally, the processing unit is further configured to, when the dust deposition rate of the current time period fails to be verified, take a first data density as the data density of the next time period, where the first data density is greater than the data density of the current time period.
Optionally, the processing unit is further configured to, when the dust deposition rate of the current time period passes the verification, use a second data density as the data density of the next time period, where the second data density is less than or equal to the data density of the current time period.
Optionally, the processing unit is further configured to, after the dust deposition rate of the current time period is verified based on a preset verification algorithm and a verification result is obtained, perform: and when the dust deposition rate of the current time period does not pass the verification, correcting the dust deposition rate of the current time period based on a preset correction algorithm to obtain the corrected dust deposition rate of the current time period.
Optionally, the preset correction algorithm is one or a combination of a moving average method, a weighted average method, a hanning window convolution noise reduction method, and an exponential moving average method.
Optionally, the processing unit is further configured to verify the corrected dust deposition rate of the current time period based on the preset verification algorithm; and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
Optionally, the processing unit is further configured to, after the dust deposition rate of the current time period is verified based on a preset verification algorithm and a verification result is obtained, perform: and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
Optionally, the processing unit is further configured to obtain preset data of each time period within a preset historical time limit, where the preset data is at least one of data included in the dust deposition calculation parameter; comparing the preset data of the current time period with the preset data of each time period within the preset historical period respectively to obtain a comparison result; determining a preset number of time periods closest to the current time period based on the comparison result; and determining the final dust deposition rate of the current time period based on the dust deposition rate of the closest preset number of time periods.
Optionally, the preset data is irradiation data, and the processing unit is further configured to:
respectively calculating the distance between the irradiation data of the current time period and the irradiation data of each time period in the preset historical period based on a preset formula, wherein the preset formula is as follows:
where dist (X, Y) is the distance of the irradiation data for two time periods, XkAnd ykThe radiation values at the kth time in X and Y time periods respectively, wherein k is more than or equal to 0.
Optionally, the processing unit is further configured to determine whether a data amount of the dust accumulation calculation parameter in the current time period is greater than a preset value; when the data volume of the dust deposition calculation parameter of the current time period is larger than a preset value, the step of determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period is executed by a calculation unit; and the processing unit is further used for taking a third data density as the data density of the next time period and determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm when the data volume of the dust deposition calculation parameter of the current time period is less than or equal to the preset value, wherein the third data density is greater than the data density of the current time period.
Optionally, the preset verification algorithm comprises a t-test algorithm.
Optionally, the photovoltaic module dust collecting detection device further includes: a data cleaning unit, configured to perform a data cleaning operation based on the dust deposition calculation parameter of the current time period, to obtain a cleaned dust deposition calculation parameter, where data cleaned by performing the data cleaning operation includes at least one of: repeating data, power abnormal data, data in a power limiting state and temperature abnormal data; and determining the dust deposition rate of the current time period based on the cleaned dust deposition calculation parameters by a calculation unit.
Optionally, the calculating unit is further configured to obtain a final dust deposition rate of all time periods within a preset time duration; and calculating the dust deposition rate of the preset duration based on the final dust deposition rate of all the time periods.
Optionally, the dust accumulation calculation parameters include irradiation data, ambient temperature data, and total dc power at the dc side of the inverter, and the calculation unit is further configured to calculate normalized power values at various times in the current time period, determine a maximum normalized power value in the current time period, and calculate an average value of the normalized power values in the current time period; and calculating the dust deposition rate of the current time period based on the maximum normalized power value and the average value.
Compared with the prior art, the photovoltaic module dust accumulation detection device has the beneficial effects consistent with the photovoltaic module dust accumulation detection method, and is not repeated herein.
The invention further provides a photovoltaic module dust accumulation detection device. Referring to fig. 5, in an embodiment of the photovoltaic module dust deposition detection apparatus of the present invention, the photovoltaic module dust deposition detection apparatus includes: a computer-readable storage medium and a processor storing a computer program, which when read and executed by the processor, implements the method for detecting the dust deposition on the photovoltaic module as described in any one of the above.
Compared with the prior art, the photovoltaic module dust accumulation detection equipment has the beneficial effects consistent with the photovoltaic module dust accumulation detection method, and is not repeated herein.
The invention also provides a computer readable storage medium. In an embodiment, the computer-readable storage medium stores a computer program, which when read and executed by a processor, implements the method for detecting the dust deposition on the photovoltaic module as described in any one of the above. Compared with the prior art, the beneficial effects of the computer-readable storage medium are consistent with the method for detecting the dust deposition of the photovoltaic module, and are not repeated herein.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (17)
1. A method for detecting dust deposition of a photovoltaic module is characterized by comprising the following steps:
acquiring a dust accumulation calculation parameter of the current time period based on the data density of the current time period;
determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period;
verifying the dust deposition rate of the current time period based on a preset verification algorithm to obtain a verification result;
determining data density of a next time period based on the verification result;
and taking the next time period as a new current time period, and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period.
2. The method according to claim 1, wherein the determining the data density for the next time period based on the verification result comprises:
and when the dust deposition rate of the current time period is not verified, taking a first data density as the data density of the next time period, wherein the first data density is greater than the data density of the current time period.
3. The method for detecting the dust on the photovoltaic module according to claim 1 or 2, wherein the determining the data density of the next time period based on the verification result comprises:
and when the dust deposition rate of the current time period passes the verification, taking a second data density as the data density of the next time period, wherein the second data density is less than or equal to the data density of the current time period.
4. The method for detecting the dust deposition on the photovoltaic module according to claim 1 or 2, wherein the verifying the dust deposition rate of the current time period based on a preset verifying algorithm further comprises:
and when the dust deposition rate of the current time period does not pass the verification, correcting the dust deposition rate of the current time period based on a preset correction algorithm to obtain the corrected dust deposition rate of the current time period.
5. The method for detecting the dust on the photovoltaic module according to claim 4, wherein the predetermined modification algorithm is one or a combination of a moving average method, a weighted average method, a Hanning window convolution noise reduction method and an exponential moving average method.
6. The method for detecting dust deposition on a photovoltaic module according to claim 5, wherein when the dust deposition rate in the current time period fails to be verified, the method for detecting dust deposition in the current time period is modified based on a preset modification algorithm, and after obtaining the modified dust deposition rate in the current time period, the method further comprises:
verifying the corrected dust deposition rate of the current time period based on the preset verification algorithm;
and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
7. The method for detecting the dust deposition on the photovoltaic module according to claim 1 or 2, wherein the verifying the dust deposition rate of the current time period based on a preset verifying algorithm further comprises:
and when the corrected dust deposition rate of the current time period does not pass the verification, determining the final dust deposition rate of the current time period based on a preset historical data filling algorithm.
8. The method according to claim 7, wherein the determining the final dust deposition rate of the current time period based on a preset historical data padding algorithm comprises:
acquiring preset data of each time period within a preset historical period, wherein the preset data is at least one of data contained in the dust accumulation calculation parameters;
comparing the preset data of the current time period with the preset data of each time period within the preset historical period respectively to obtain a comparison result;
determining a preset number of time periods closest to the current time period based on the comparison result;
and determining the final dust deposition rate of the current time period based on the dust deposition rate of the closest preset number of time periods.
9. The method for detecting the dust deposition on the photovoltaic module according to claim 8, wherein the preset data is irradiation data, and the comparing the preset data of the current time period with the preset data of each time period within the preset historical period respectively to obtain the comparison result comprises:
respectively calculating the distance between the irradiation data of the current time period and the irradiation data of each time period in the preset historical period based on a preset formula, wherein the distance is the comparison result, and the preset formula is as follows:
wherein dist (X, Y) is the distance of irradiation data in X and Y time periods, and XkAnd ykThe radiation values at the kth time in X and Y time periods respectively, wherein k is more than or equal to 0.
10. The method for detecting the dust deposition on the photovoltaic module according to claim 1 or 2, wherein after the obtaining of the dust deposition calculation parameter of the current time period based on the data density of the current time period, the method further comprises:
judging whether the data volume of the dust accumulation calculation parameter of the current time period is larger than a preset value or not;
when the data volume of the dust deposition calculation parameter of the current time period is larger than a preset value, the step of determining the dust deposition rate of the current time period based on the dust deposition calculation parameter of the current time period is executed;
and when the data volume of the dust accumulation calculation parameter of the current time period is smaller than or equal to the preset value, taking a third data density as the data density of the next time period, and determining the final dust accumulation rate of the current time period based on a preset historical data padding algorithm, wherein the third data density is greater than the data density of the current time period.
11. The method for detecting the dust accumulation of the photovoltaic module according to claim 1 or 2, wherein the preset verification algorithm comprises a t-test algorithm.
12. The method according to claim 1 or 2, wherein the determining the dust deposition rate for the current time period based on the dust deposition calculation parameter for the current time period comprises:
and executing data cleaning operation based on the dust deposition calculation parameters of the current time period to obtain cleaned dust deposition calculation parameters, wherein the data cleaned by executing the data cleaning operation comprises at least one of the following data: repeating data, power abnormal data, data in a power limiting state and temperature abnormal data;
and determining the dust deposition rate of the current time period based on the cleaned dust deposition calculation parameters.
13. The method for detecting the dust deposition on the photovoltaic module according to claim 1 or 2, wherein the step of taking the next time period as a new current time period and returning to the step of obtaining the dust deposition calculation parameter of the current time period based on the data density of the current time period further comprises:
acquiring the final dust deposition rate of all time periods in a preset time length;
and calculating the dust deposition rate of the preset duration based on the final dust deposition rate of all the time periods.
14. The method for detecting the dust deposition of the photovoltaic module according to claim 1 or 2, wherein the dust deposition calculation parameters comprise irradiation data, ambient temperature data and total DC power on the DC side of the inverter, and the determining the dust deposition rate of the current time period based on the dust deposition calculation parameters of the current time period comprises:
calculating the normalized power value of each moment in the current time period, determining the maximum normalized power value in the current time period, and calculating the average value of the normalized power values in the current time period;
and calculating the dust deposition rate of the current time period based on the maximum normalized power value and the average value.
15. The utility model provides a photovoltaic module laying dust detection device which characterized in that includes:
an acquisition unit for acquiring a dust accumulation calculation parameter of a current time period based on a data density of the current time period;
a calculation unit for determining a dust deposition rate of the current time period based on a dust deposition calculation parameter of the current time period;
the checking unit is used for checking the dust deposition rate of the current time period based on a preset checking algorithm to obtain a checking result;
and the processing unit is used for determining the data density of the next time period based on the verification result, taking the next time period as a new current time period, and returning to execute the step of acquiring the dust deposition calculation parameter of the current time period based on the data density of the current time period.
16. A photovoltaic module dust deposition detection apparatus comprising a computer readable storage medium storing a computer program and a processor, the computer program being read and executed by the processor to implement the photovoltaic module dust deposition detection method according to any one of claims 1 to 14.
17. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when read and executed by a processor, implements the photovoltaic module dust detection method according to any one of claims 1 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011131007.9A CN112326684B (en) | 2020-10-21 | 2020-10-21 | Photovoltaic module dust accumulation detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011131007.9A CN112326684B (en) | 2020-10-21 | 2020-10-21 | Photovoltaic module dust accumulation detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112326684A true CN112326684A (en) | 2021-02-05 |
| CN112326684B CN112326684B (en) | 2022-05-24 |
Family
ID=74310776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011131007.9A Active CN112326684B (en) | 2020-10-21 | 2020-10-21 | Photovoltaic module dust accumulation detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112326684B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393046A (en) * | 2021-06-23 | 2021-09-14 | 阳光电源股份有限公司 | Photovoltaic power prediction method and application device thereof |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6447991A (en) * | 1987-08-18 | 1989-02-22 | Fujitsu Ltd | Snow cover measuring method |
| US4987913A (en) * | 1988-06-25 | 1991-01-29 | Kabushiki Kaisha Toshiba | Apparatus and method for controlling operation of storm sewage pump |
| JPH052084A (en) * | 1991-01-24 | 1993-01-08 | Takuwa:Kk | Automatic snowfall depth measurement method |
| JPH07260945A (en) * | 1994-03-23 | 1995-10-13 | Nkk Corp | Estimation method and control method for dust concentration |
| WO2013158847A1 (en) * | 2012-04-19 | 2013-10-24 | Atonometrics, Inc. | System for field measurement and calibration of photovoltatic reference devices |
| CN103631919A (en) * | 2013-12-02 | 2014-03-12 | 北京奇虎科技有限公司 | Capturing method and capturing device for timeliness seed page |
| CN104166171A (en) * | 2014-08-25 | 2014-11-26 | 清华大学 | Method and system for predicating thundercloud cover area based on lightning locating system |
| US20150280644A1 (en) * | 2012-11-21 | 2015-10-01 | Atonometrics, Inc. | Soiling measurement system for photovoltaic arrays |
| CN106096767A (en) * | 2016-06-07 | 2016-11-09 | 中国科学院自动化研究所 | A kind of link travel time prediction method based on LSTM |
| CN106407050A (en) * | 2016-10-20 | 2017-02-15 | 厦门科华恒盛股份有限公司 | Data storage method |
| CN106454437A (en) * | 2015-08-12 | 2017-02-22 | ***通信集团设计院有限公司 | Streaming media service rate prediction method and device |
| CN107679672A (en) * | 2017-10-20 | 2018-02-09 | 中冶华天南京电气工程技术有限公司 | A kind of photovoltaic plant occasion of rinsing aid decision-making method based on the prediction of laying dust power generation loss |
| CN108079701A (en) * | 2016-11-21 | 2018-05-29 | 苏州三星电子有限公司 | A kind of detection method and system of filter screen dust accumulation degree |
| CN108572648A (en) * | 2018-04-24 | 2018-09-25 | 中南大学 | A kind of automatic driving vehicle power supply multi-source fusion prediction technique and system |
| CN110059446A (en) * | 2019-05-17 | 2019-07-26 | 河海大学常州校区 | A method of prediction photovoltaic module dust stratification degree |
| CN110173809A (en) * | 2019-05-21 | 2019-08-27 | 广东美的制冷设备有限公司 | Dust accumulation detection method, device and the storage medium of air-conditioner outdoor unit |
-
2020
- 2020-10-21 CN CN202011131007.9A patent/CN112326684B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6447991A (en) * | 1987-08-18 | 1989-02-22 | Fujitsu Ltd | Snow cover measuring method |
| US4987913A (en) * | 1988-06-25 | 1991-01-29 | Kabushiki Kaisha Toshiba | Apparatus and method for controlling operation of storm sewage pump |
| JPH052084A (en) * | 1991-01-24 | 1993-01-08 | Takuwa:Kk | Automatic snowfall depth measurement method |
| JPH07260945A (en) * | 1994-03-23 | 1995-10-13 | Nkk Corp | Estimation method and control method for dust concentration |
| WO2013158847A1 (en) * | 2012-04-19 | 2013-10-24 | Atonometrics, Inc. | System for field measurement and calibration of photovoltatic reference devices |
| US20150280644A1 (en) * | 2012-11-21 | 2015-10-01 | Atonometrics, Inc. | Soiling measurement system for photovoltaic arrays |
| CN103631919A (en) * | 2013-12-02 | 2014-03-12 | 北京奇虎科技有限公司 | Capturing method and capturing device for timeliness seed page |
| CN104166171A (en) * | 2014-08-25 | 2014-11-26 | 清华大学 | Method and system for predicating thundercloud cover area based on lightning locating system |
| CN106454437A (en) * | 2015-08-12 | 2017-02-22 | ***通信集团设计院有限公司 | Streaming media service rate prediction method and device |
| CN106096767A (en) * | 2016-06-07 | 2016-11-09 | 中国科学院自动化研究所 | A kind of link travel time prediction method based on LSTM |
| CN106407050A (en) * | 2016-10-20 | 2017-02-15 | 厦门科华恒盛股份有限公司 | Data storage method |
| CN108079701A (en) * | 2016-11-21 | 2018-05-29 | 苏州三星电子有限公司 | A kind of detection method and system of filter screen dust accumulation degree |
| CN107679672A (en) * | 2017-10-20 | 2018-02-09 | 中冶华天南京电气工程技术有限公司 | A kind of photovoltaic plant occasion of rinsing aid decision-making method based on the prediction of laying dust power generation loss |
| CN108572648A (en) * | 2018-04-24 | 2018-09-25 | 中南大学 | A kind of automatic driving vehicle power supply multi-source fusion prediction technique and system |
| CN110059446A (en) * | 2019-05-17 | 2019-07-26 | 河海大学常州校区 | A method of prediction photovoltaic module dust stratification degree |
| CN110173809A (en) * | 2019-05-21 | 2019-08-27 | 广东美的制冷设备有限公司 | Dust accumulation detection method, device and the storage medium of air-conditioner outdoor unit |
Non-Patent Citations (2)
| Title |
|---|
| AHMED AMINE HACHICHA ET AL.: "Impact of dust on the perfor mance of solar photovoltaic (PV) systems under United Arab Emirates weathe r conditions", 《RENEWABLE ENERGY》 * |
| 翁捷等: "基于大数据分析的光伏组件灰尘预警***设计", 《科学技术创新》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393046A (en) * | 2021-06-23 | 2021-09-14 | 阳光电源股份有限公司 | Photovoltaic power prediction method and application device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112326684B (en) | 2022-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435725B (en) | Power grid host dynamic threshold setting method based on FARIMA-LSTM prediction | |
| US20090024356A1 (en) | Determination of root cause(s) of symptoms using stochastic gradient descent | |
| CN112326684B (en) | Photovoltaic module dust accumulation detection method, device, equipment and storage medium | |
| WO2018137324A1 (en) | System upgrade assessment method based on system parameter correlation coefficients | |
| CN106483401B (en) | A kind of failure zero moment judgment method and device based on recorder data | |
| CN111458661A (en) | Power distribution network line variation relation diagnosis method, device and system | |
| CN115587673B (en) | Voltage transformer error state prediction method and system | |
| CN111931354A (en) | Transformer top layer oil temperature prediction method based on gray-autoregressive differential moving average model | |
| CN111752481B (en) | Memory monitoring and service life prediction method and system based on SPD | |
| CN117931094B (en) | Block chain-based reliable storage method for ambient air monitoring data | |
| CN109065176B (en) | Blood glucose prediction method, device, terminal and storage medium | |
| CN111658006B (en) | Method and device for predicting female physiological cycle | |
| US20090182534A1 (en) | Accurate measurement and monitoring of computer systems | |
| CN114280485A (en) | SOC estimation and consistency evaluation method and device, and computer equipment | |
| CN116743180B (en) | Intelligent storage method for energy storage power supply data | |
| CN117034177A (en) | Intelligent monitoring method for abnormal data of power load | |
| CN113777497B (en) | Online SOC and SOH joint estimation method and device for degraded battery, storage medium and electronic equipment | |
| CN113311220B (en) | Voltage sag diagnosis method, system, medium and electronic equipment | |
| CN106788816A (en) | A kind of channel status detection method and device | |
| CN112488461B (en) | Method for estimating total fission times in emergency of metal uranium critical accident | |
| CN112710979B (en) | Intelligent electric energy meter operation monitoring management system and method based on deep learning | |
| CN111751732B (en) | Electric quantity calculation method based on self-adaptive Gaussian convolution integral method | |
| CN117390379B (en) | On-line signal measuring device and confidence measuring device for signal characteristics | |
| CN113009347A (en) | Method and device for setting power of battery at end of life stage and related product | |
| CN117250520B (en) | Safety analysis and evaluation method and system for large-scale battery energy storage power station |
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 |