CN113676135B - Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement - Google Patents
Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement Download PDFInfo
- Publication number
- CN113676135B CN113676135B CN202111048885.9A CN202111048885A CN113676135B CN 113676135 B CN113676135 B CN 113676135B CN 202111048885 A CN202111048885 A CN 202111048885A CN 113676135 B CN113676135 B CN 113676135B
- Authority
- CN
- China
- Prior art keywords
- power generation
- dust
- photovoltaic
- station
- power station
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 230000003287 optical effect Effects 0.000 title claims abstract description 18
- 238000005259 measurement Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000010248 power generation Methods 0.000 claims abstract description 94
- 239000000428 dust Substances 0.000 claims abstract description 75
- 238000004140 cleaning Methods 0.000 claims abstract description 68
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 230000005855 radiation Effects 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 15
- 239000003344 environmental pollutant Substances 0.000 claims description 19
- 231100000719 pollutant Toxicity 0.000 claims description 19
- 238000012423 maintenance Methods 0.000 claims description 16
- 230000005611 electricity Effects 0.000 claims description 15
- 230000036541 health Effects 0.000 claims description 8
- 230000007547 defect Effects 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 5
- 230000008021 deposition Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract description 3
- 230000002354 daily effect Effects 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000005260 corrosion Methods 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002378 acidificating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention provides a photovoltaic energy efficiency monitoring method based on a neural network and optical pollution measurement, which comprises the following steps of: combining with SR dust monitoring, adopting a neural network model and a full-band optical pollution measurement technology, measuring and calculating the SR value of dust, and combining with the generated energy of a photovoltaic power station to construct model correlation; the method also comprises the following steps of energy efficiency monitoring state sensing: and acquiring power generation and equipment information of the photovoltaic power station, obtaining linear relations of module conversion efficiency, module attenuation rate, power generation and radiation, further obtaining theoretical electric quantity of the photovoltaic power station, obtaining power generation efficiency of the photovoltaic power station by combining the actual power generation quantity of the photovoltaic power station inverter, and carrying out trend analysis on the lost electric quantity by considering electric quantity loss factors. The invention provides data support for the power generation efficiency and digital cleaning of the photovoltaic power station; and more refined analysis is provided for the photovoltaic power station in the power production link, and information support and decision basis are provided for power generation optimization of the photovoltaic power station.
Description
Technical Field
The invention belongs to the field of photovoltaic power generation, and particularly relates to a photovoltaic energy efficiency monitoring method and system based on a neural network and optical pollution measurement.
Background
Along with the rapid growth of the successive construction and installation scale of the photovoltaic power station, a great number of problems gradually appear in the operation of the photovoltaic power station, such as low photoelectric conversion efficiency in photovoltaic power generation, high development and conversion cost, difficult and complicated operation control and maintenance, difficult detection of fault points and difficult metering of efficiency attenuation. For a solar power station operated for a long time, the power generation efficiency is determined by four main parameters of solar irradiance, battery back plate temperature, dust pollutants and power generation capacity. The dust pollutant on the photovoltaic module glass is one of the main problems of rapidly influencing the performance ratio of the photovoltaic power station, so that the power generation efficiency and the Performance Ratio (PR) are reduced, the cleaning cost is increased, the failure rate of the photovoltaic cell is improved due to the dust pollutant containing oxide, the use safety is influenced, and the service life of the solar cell is shortened.
At present, because the technical means are limited, the influence of all factors on the power generation capacity of a photovoltaic power station is difficult to quantify, the power station fault maintenance is usually post maintenance, the maintenance method and the standard are behind and extensive, the efficiency attenuation cannot be evaluated, and the main reasons are as follows:
1) In addition to the generated energy, indexes such as efficiency of the photovoltaic array system, average fault interval time of the photovoltaic array and the like are mostly calculated manually, and when each index is calculated, the influence of human factors on the reliability of data is large;
2) The generated energy of the photovoltaic power station is directly related to solar energy resources, but solar energy has the defects of energy dispersion (low energy density), unstable energy, discontinuous energy and the like, and the factors cause great difficulty in evaluating the performance and faults of the photovoltaic power station, and the operation management level and the operation maintenance technical level of the photovoltaic power station are difficult to objectively and quantitatively evaluate;
3) Because the factors influencing the generated energy are more and difficult to evaluate, the influence of the ash-less coverage thickness on the electric quantity is more difficult to quantify, and in general, the influence of dust on the power generation efficiency of a photovoltaic power station mainly has the following points:
a. the dust has the functions of reflecting, scattering and absorbing solar radiation, so that the transmissivity of the photovoltaic cell panel is reduced, and the generated energy of the component array is influenced; because the dust is unevenly shielded from the photovoltaic module, the radiation quantity is reduced, the irradiation of the radiation quantity is uneven, the mismatch of the photovoltaic module is caused, and the output power of photovoltaic power generation is reduced;
b. dust shielding can reduce the heat dissipation of the surface of the photovoltaic module, so that the photoelectric conversion efficiency of photovoltaic power generation is affected, and the generated energy is reduced;
c. some dust containing oxides falls to the surface of the photovoltaic module, and the addition of the rainfall dew can enable the dust to become acidic or alkaline substances, so that the solar cell panel has a certain corrosion effect, the panel surface can be rough and uneven after long-time corrosion, the accumulation of dust is facilitated, the diffuse reflection of sunlight is increased, and the light transmission is reduced. The failure rate of the photovoltaic cell is improved, the use safety is affected, and the service life of the solar cell is shortened;
d. temperature is also a major factor affecting photovoltaic power generation, and in the same solar radiation situation, the higher the temperature, the less power generation. The dust can directly reduce the light transmittance of the photovoltaic cell panel, reduce the generated energy, influence the heat dissipation due to dust shielding, increase the temperature of the photovoltaic cell panel, and have a certain corrosion effect on the photovoltaic cell panel due to long-term adhesion of the dust;
4) The lack of scientific intelligent operation management system support, the rationality of human decision-making is to be improved.
The problem that the influence of dust covering thickness on electric quantity is difficult to quantify is generally judged according to experience of operation and maintenance personnel, and random factors are large, so that a set of photovoltaic energy efficiency monitoring system is needed to be adopted, and meanwhile, the whole operation performance of the power station is evaluated in real time, so that the method has important significance in improving the operation efficiency and operation management level of the photovoltaic power station.
Disclosure of Invention
The invention provides a photovoltaic energy efficiency monitoring method and system based on a neural network and optical pollution measurement, which provide data support for power generation efficiency and cleaning of a photovoltaic power station. And more refined analysis is provided for the photovoltaic power station in the power production link, and information support and decision basis are provided for power generation optimization of the photovoltaic power station.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
a photovoltaic energy efficiency monitoring method based on a neural network and optical pollution measurement comprises two dimensional points:
s1, intelligent cleaning analysis: establishing a neural network analysis model of the photovoltaic power station, which influences the generated energy due to the pollutant pollution thickness, and carrying out cleaning reminding;
s2, energy efficiency state sensing: and (3) combining the analysis model in the step (S1), carrying out trend analysis on the lost electric quantity from electric quantity state perception caused by attenuation of a power generation unit of the photovoltaic power station and in-field maintenance of the off-site involvement.
Further, the step S1 specifically includes:
s101, counting the average trend of total station dust fall based on the percentage of the dust deposition thickness of the solar cell panel measured by an optical pollutant measurement dust monitor;
s102, combining the result of the S101 and the power generation condition of the photovoltaic power station, and referencing a neural network to obtain a total station SR dust monitoring and power generation amount relation analysis model;
and S103, establishing relation comparison of dust fall, power generation amount and electric settlement, introducing cleaning cost accounting, and carrying out cleaning reminding on the time dimension.
Further, the accounting of the incoming cleaning cost of step S103 includes: according to the settlement of the electricity of the local power grid, converting the generated energy corresponding to 100% of the generated energy in the clean state of the solar photovoltaic power station panel into the settlement cost of the power grid; and when the corresponding power grid settlement cost of the generated energy due to dust loss is more than or equal to the cleaning cost, cleaning reminding is carried out.
Further, the step S2 specifically includes:
s201, collecting power generation and equipment information of a photovoltaic power station, and obtaining linear relations of module conversion efficiency, module attenuation rate, power generation and radiation;
s202, obtaining theoretical electric quantity of the photovoltaic power station, and obtaining the power generation efficiency of the photovoltaic power station by combining the actual power generation quantity of the photovoltaic power station inverter;
s203, carrying out trend analysis on the lost electric quantity according to the deviation between the daily theoretical electric quantity and the actual electric quantity, and electric quantity loss factors under the conditions of maintenance, electricity limiting and defect.
Further, in step S2, a component health model is built for the photovoltaic power station, and steps S201 to S203 are performed according to the component health model.
In another aspect of the present invention, there is also provided a photovoltaic energy efficiency monitoring system based on a neural network and optical pollution measurement, including:
and the intelligent cleaning analysis module: establishing a neural network analysis model of the photovoltaic power station, which influences the generated energy due to the pollutant pollution thickness, and carrying out cleaning reminding;
the energy efficiency state sensing module is used for: and combining an analysis model of the intelligent cleaning analysis module, carrying out trend analysis on the lost electric quantity from electric quantity state perception caused by attenuation of a power generation unit of the photovoltaic power station and on-site accumulated on-site overhaul.
Further, the intelligent cleaning model analysis module includes:
the dust-falling average trend unit is used for counting the total station dust-falling average trend based on the percentage of the dust thickness of the solar cell panel measured by the optical pollutant measuring dust monitor;
the modeling unit is used for combining the dust fall average trend unit and the energy efficiency state sensing module data, and referencing a neural network to obtain a total station SR dust monitoring and generating capacity relation model;
and the cleaning reminding unit refers to a neural network, establishes a relationship comparison model of dust fall, power generation capacity and power balance, introduces cleaning cost accounting, and carries out cleaning reminding in the time dimension.
Furthermore, the cleaning reminding unit introduces cleaning cost accounting comprising: according to the settlement of the electricity of the local power grid, converting the generated energy corresponding to 100% of the generated energy in the clean state of the solar photovoltaic power station panel into the settlement cost of the power grid; and when the corresponding power grid settlement cost of the generated energy due to dust loss is more than or equal to the cleaning cost, cleaning reminding is carried out.
Further, the energy efficiency monitoring state sensing module includes:
the first sensing unit is used for collecting power generation and equipment information of the photovoltaic power station and obtaining linear relations of module conversion efficiency, module attenuation rate, power generation and radiation;
the second sensing unit is used for obtaining the theoretical electric quantity of the photovoltaic power station and obtaining the power generation efficiency of the photovoltaic power station by combining the actual power generation quantity of the photovoltaic power station inverter;
and the third sensing unit is used for carrying out trend analysis on the lost electric quantity according to the deviation between the daily theoretical electric quantity and the actual electric quantity, and electric quantity loss factors under the conditions of maintenance, electricity limiting and defect.
Furthermore, the energy efficiency monitoring state sensing module further comprises a component health degree model module, and the first sensing unit, the second sensing unit and the third sensing unit are connected with the component health degree model module.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention collects and models information of the nominal power and the area of the component of the photovoltaic power station inverter generating capacity, an environment monitor, SR dust monitoring equipment and provides data support for photovoltaic power station generating efficiency and cleaning; and more refined analysis is provided for the photovoltaic power station in the power production link, and information support and decision basis are provided for power generation optimization of the photovoltaic power station.
2. The method can not only improve the operation management level of the photovoltaic power station, but also provide accurate data support for the operation and maintenance of the photovoltaic power station.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention;
fig. 2 is a graph of the amount of power generation of an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
For the purpose of making the objects and features of the present invention more comprehensible, embodiments accompanied with figures are described in detail below. It should be noted that the drawings are in a very simplified form and use non-precise ratios for convenience and clarity in assisting in the description of the embodiments of the invention.
The invention mainly aims to provide data support for the power generation efficiency and digital cleaning of a photovoltaic power station through information acquisition and modeling of the generating capacity of a sigma inverter, an environment monitor, SR dust monitoring equipment, nominal power of components and the area of the photovoltaic power station. And more refined analysis is provided for the photovoltaic power station in the power production link, and information support and decision basis are provided for power generation optimization of the photovoltaic power station.
As shown in FIG. 1, the present invention contemplates from two dimensions, including intelligent cleaning analysis and energy efficiency state sensing.
1. Intelligent cleaning analysis:
the dimension is used for performing osmotic analysis on the influence of pollutants on the power generation capacity of the power station, searching the linear relation of the influence of the thickness of the pollutants on the power generation capacity, introducing a neural network model to judge the linear relation, guiding the power station to carry out cleaning reminding in relative time, and promoting the maximization of the power generation income; the technology is based on the percentage of the thickness of the deposited ash of the solar cell panel measured by an optical pollutant measurement dust monitor, and the corresponding relation of the generated energy of the photovoltaic power station under different pollutant percentages is combined, so that the pollutant coverage reminding power station is carried out for cleaning.
Specifically, by combining with SR dust monitoring and taking high-stability SCADA as a support for platform application and adopting a neural network model and a full-band optical pollution measurement (BOSM) technical principle, the cleanliness is reduced from 100% to 0% all the way by measuring and calculating the SR value of the dust. And the model correlation is built by combining the generated energy, so that investors find balance between the generated energy and the cleaning cost, operation and maintenance personnel of the power station do not need to visually check through experience, and the optimal cleaning scheme can be scientifically and accurately selected, thereby avoiding the loss of the power generation efficiency and the waste of the cleaning cost. The return of the power station and the return on investment of investors are effectively improved.
SR dust monitoring equipment is additionally arranged at each period of the power station, the SR equipment defaults to 100%, after the SR equipment defaults to 100%, the daily electric quantity (the electric quantity of the generated energy of an inverter and/or the electric quantity of an outgoing line measuring meter of a booster station) of the power station is corresponding to the normal production condition of the power station, and the daily electric quantity of the 90MW photovoltaic power station is 36 ten thousand kWh according to the calculation of 4 hours of equivalent utilization per day. Counting every day, and finding out the corresponding relation, such as: after 1 week of addition, dust monitoring was reduced from 100% → 36 kWh for the corresponding to 98% → 35.28 kWh for the dust monitoring.
If the calculation is performed according to the 1 yuan of electricity, 0.72 ten thousand yuan is lost. The cleaning total station is approximately 27 ten thousand yuan according to the calculation of 3000 yuan/MW cleaning cost. At this time, cleaning is not performed at all, and only when the accumulated loss reaches or exceeds 27 ten thousand yuan, cleaning reminding is performed, and comparison of the power generation amount before and after cleaning is performed. And when the SR dust monitoring equipment is cleaned, the SR dust monitoring equipment is synchronously cleaned, and the marking percentages are normalized.
Specific statistical analysis of the cleaning model included:
(1) trend of dust fall at all stations
Counting the average trend of the SR dust monitoring of the pollutant by taking the day as a unit, and carrying out month statistics and quarter statistics; month statistics include: the daily dust percentage trend at 15 minutes resolution over the month inquires about the daily dust percentage columnar trend over the quarter.
(2) Relation curve of dust-settling electric quantity
And counting total station SR dust monitoring and generating capacity data by taking a day as a unit, and carrying out month counting and quarter counting, wherein the counting content comprises the following steps: the percentage of dust and the power generation amount at 15 minutes resolution daily in the current month; inquiring the power generation conditions of the total station and the dust fall trend, wherein the power generation conditions comprise the power generation amount of an inverter and the power loss, and the power loss can be derived from the energy efficiency state sensing dimension of a power station; and introducing a neural network according to the data to obtain a total station SR dust monitoring and generating capacity relation model.
(3) Cleaning reminder
Establishing a comparison of the three relations of dust fall, power generation and electric settlement, and introducing cleaning cost accounting; and carrying out cleaning reminding in the time dimension. The linear relation of the corresponding generated energy under the dust monitoring proportion is considered, meanwhile, the settlement of the local power grid to the electricity is considered, and the settlement cost of the power grid is converted. And carrying out cleaning reminding when the power grid settlement cost compared with the generated energy influenced by dust is more than or equal to the cleaning cost along with the time.
(4) Trend of comparison before and after cleaning
And (5) counting the power generation amount before and after cleaning on the nominal cleaning date. (consider the secondary calibration of SR apparatus)
2. Energy efficiency state perception:
the technology indirectly obtains the conversion efficiency of the assembly through a formula by collecting the power generation and equipment information (including the assembly area, the total solar radiation amount of an inclined plane and the power generation amount of an inverter) of the photovoltaic power station, and the linear relation of the assembly attenuation rate, the power generation and the radiation, so as to obtain the theoretical electric quantity of the photovoltaic power station, combine the actual power generation amount of the inverter of the power station and further obtain the power generation efficiency of the photovoltaic power station. According to the deviation of the daily theory and the actual, and considering maintenance, the power loss factors under the condition of limiting electricity and defects can further carry out trend analysis on the loss power.
The specific analysis comprises the following steps:
(1) average attenuation trend of total station assembly
And checking the total station attenuation trend by taking the day as a unit, and carrying out month statistics and quarter statistics.
(2) Total station power loss statistics
And checking the total station electric quantity loss trend by taking the day as a unit, and carrying out month statistics and quarter statistics. (considering the electricity limiting and the electricity loss during in-station maintenance)
(3) Conversion efficiency of total station assembly
(4) Trend of total station power generation efficiency
PR efficiency statistics are performed in daily units and monthly statistics are performed, quarterly statistics. (actual generated energy, theoretical generated energy, PR trend curve)
(5) Linear curve of total station radiation and generating capacity
And counting total station radiation quantity and generating capacity by taking the day as the point position, and carrying out month statistics and quarter statistics.
The power generation and equipment information (comprising the assembly area, the total solar radiation amount on an inclined plane and the power generation amount of an inverter) of the photovoltaic power station are collected, the assembly conversion efficiency is indirectly obtained through a formula, the linear relation of the assembly attenuation rate, the power generation and the radiation is obtained, the theoretical electric quantity of the photovoltaic power station is further obtained, and the power generation efficiency of the photovoltaic power station is further obtained by combining the actual power generation amount of the inverter of the power station. According to the deviation of the daily theory and the actual, and considering maintenance, the power loss factors under the condition of limiting electricity and defects can further carry out trend analysis on the loss power.
3. Model algorithm description
FIG. 1 is a schematic flow chart of the method of the present invention, and the algorithm involved in the flow chart is described as follows:
the prediction of the theoretical electric quantity of the photovoltaic power station is calculated and determined according to the solar resource condition of the site, and various factors such as the system design of the photovoltaic power station, the arrangement of the photovoltaic square matrix and the environmental conditions are considered.
The theoretical power Ep of the photovoltaic power plant is calculated as follows:
ep=ha×s×k1×k2 formula:
HA is inclined plane solar energy total irradiation (kW.h/m) 2 )；
S is the sum of the areas of the components (m) 2 )
K1-component conversion efficiency;
k2-is the comprehensive efficiency of the system. (generally considered to be 80%)
The integrated efficiency coefficient K2 is a correction coefficient in consideration of various factors, and includes:
1) Energy reduction such as station service electricity and line loss
Ac/dc distribution room and transmission line losses.
2) Inverter reduction
The inverter attenuates losses.
The efficiency of a photovoltaic cell will vary with the temperature at which it operates. As their temperature increases, the power generation efficiency of photovoltaic modules tends to decrease.
Besides the above factors, the influence on the generated energy of the photovoltaic power station also comprises unavailable solar radiation loss, influence reduction of tracking accuracy of the maximum power point, and other uncertain factors such as power grid absorption.
The power loss of the square matrix is calculated by the following calculation formula:
[ input ]). The radiation quantity in the period, the total power generation quantity of the inverter, the system efficiency, the assembly area and the assembly nominal power;
[ output ]: theoretical power, module conversion efficiency, and lost power.
[ computer ] the following:
radiation amount: if the output of the weather station is Mj/m 2 Then it needs to be converted into kwh/m 2 = [ amount of radiation in period ]/3.6)/1kW/m 2 】。
The overall efficiency of the square matrix is calculated in combination with the actual power generation of the inverter:
theoretical power generation amount=ep calculation formula as described above, ep=ha×s×k1×k2.
Actual power generation=sum (current day power generation of the matrix inverter).
PR power generation efficiency= [ 100% (daily actual power generation/daily theoretical power generation) ].
Wherein, the device conversion efficiency=device nominal power/device area is 1000W/m 2 *100％。
Examples:
for a 1MW photovoltaic power station, 250W modules 4000 blocks are used for projects, the module size is 1640 x 992mm, and 10kV voltage level grid connection is adopted.
The device conversion efficiency=1000000 (W)/1.64×0.992 (m) ×4000 (block) ×1000W/m 2 *100％＝15.36％
Loss deviation = theoretical charge-actual charge.
Component attenuation = actual power generation/(total amount of radiation component area x system integrated efficiency)
Final output: sigma daily loss deviation cost > cleaning cost, cleaning reminding. And the generated energy efficiency before and after cleaning are displayed in a graph mode.
As shown in fig. 2, the lost power generation amount (theoretical power generation amount/actual power generation amount):
the cleaning cost is calculated by 1 yuan/kWh of the power-on degree and 3 yuan/kW. Cleaning cost 1 mw=3000 yuan renzu.
5 months 5 days theoretical generating capacity 4543, actual generating capacity 1056 and electric quantity loss 3487kW/h. I.e. 3487 Yuan renminbi > 3000 yuan cleaning cost.
The power loss is 3257kW/h after 5 months and 6 days. I.e. 3257 Yuan renminbi > 3000 yuan of cleaning cost.
And continuously decreases, which indicates that the pollution in the area is serious.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (4)
1. The photovoltaic energy efficiency monitoring method based on the neural network and the optical pollution measurement is characterized by comprising two dimensional points:
s1, intelligent cleaning analysis: establishing a neural network analysis model of the photovoltaic power station, which influences the generated energy due to the pollutant pollution thickness, and carrying out cleaning reminding;
s2, energy efficiency state sensing: combining the analysis model of the step S1, carrying out trend analysis on the lost electric quantity from electric quantity state perception caused by attenuation of a power generation unit of the photovoltaic power station and on-site accumulated on-site overhaul;
the step S1 specifically comprises the following steps:
s101, counting the average trend of total station dust fall based on the percentage of the dust deposition thickness of the solar cell panel measured by an optical pollutant measurement dust monitor;
counting the average trend of the SR dust monitoring of the pollutant by taking the day as a unit, and carrying out month statistics and quarter statistics; month statistics include: inquiring the dust percentage columnar trend of each month and each day in the quarter according to the dust percentage trend of each month and each day in the month with 15 minutes resolution;
s102, combining the result of the S101 and the power generation condition of the photovoltaic power station, and referencing a neural network to obtain a total station SR dust monitoring and power generation amount relation analysis model;
and counting total station SR dust monitoring and generating capacity data by taking a day as a unit, and carrying out month counting and quarter counting, wherein the counting content comprises the following steps: the percentage of dust and the power generation amount at 15 minutes resolution daily in the current month; inquiring the power generation conditions of the total station and the dust fall trend, wherein the power generation conditions comprise the power generation amount of an inverter and the power loss, and the power loss is derived from the energy efficiency state sensing dimension of a power station; introducing a neural network according to the data to obtain a total station SR dust monitoring and generating capacity relation model;
s103, establishing relation comparison of dust fall, power generation capacity and electric settlement, introducing cleaning cost accounting, and carrying out cleaning reminding in a time dimension; comprising the following steps: according to the settlement of the electricity of the local power grid, converting the generated energy corresponding to 100% of the generated energy in the clean state of the solar photovoltaic power station panel into the settlement cost of the power grid; when the corresponding power grid settlement cost of the generated energy due to dust loss is more than or equal to the cleaning cost, cleaning reminding is carried out;
the step S2 specifically comprises the following steps:
s201, collecting power generation and equipment information of a photovoltaic power station, and obtaining linear relations of module conversion efficiency, module attenuation rate, power generation and radiation;
s202, obtaining theoretical electric quantity of the photovoltaic power station, and obtaining the power generation efficiency of the photovoltaic power station by combining the actual power generation quantity of the photovoltaic power station inverter;
s203, carrying out trend analysis on the lost electric quantity according to the deviation between the daily theoretical electric quantity and the actual electric quantity, and electric quantity loss factors under the conditions of maintenance, electricity limiting and defect.
2. The method for monitoring photovoltaic energy efficiency based on neural network and optical pollution measurement according to claim 1, wherein in step S2, the photovoltaic power station establishes a module health model, and performs steps S201 to S203 according to the module health model.
3. A photovoltaic energy efficiency monitoring system based on neural network and optical pollution measurement, comprising:
and the intelligent cleaning analysis module: establishing a neural network analysis model of the photovoltaic power station, which influences the generated energy due to the pollutant pollution thickness, and carrying out cleaning reminding;
the energy efficiency state sensing module is used for: combining an analysis model of the intelligent cleaning analysis module, carrying out trend analysis on the lost electric quantity from electric quantity state perception caused by attenuation of a power generation unit of the photovoltaic power station and on-site accumulated on-site overhaul;
the intelligent cleaning analysis module comprises:
the dust-falling average trend unit is used for counting the total station dust-falling average trend based on the percentage of the dust thickness of the solar cell panel measured by the optical pollutant measuring dust monitor; counting the average trend of the SR dust monitoring of the pollutant by taking the day as a unit, and carrying out month statistics and quarter statistics; month statistics include: inquiring the dust percentage columnar trend of each month and each day in the quarter according to the dust percentage trend of each month and each day in the month with 15 minutes resolution;
the modeling unit is used for combining the dust fall average trend unit and the energy efficiency state sensing module data, and referencing a neural network to obtain a total station SR dust monitoring and generating capacity relation model; and counting total station SR dust monitoring and generating capacity data by taking a day as a unit, and carrying out month counting and quarter counting, wherein the counting content comprises the following steps: the percentage of dust and the power generation amount at 15 minutes resolution daily in the current month; inquiring the power generation conditions of the total station and the dust fall trend, wherein the power generation conditions comprise the power generation amount of an inverter and the power loss, and the power loss is derived from the energy efficiency state sensing dimension of a power station; introducing a neural network according to the data to obtain a total station SR dust monitoring and generating capacity relation model;
the cleaning reminding unit refers to a neural network, establishes a relationship comparison model of dust fall, power generation capacity and power balance, introduces cleaning cost accounting, and carries out cleaning reminding in a time dimension; in the cleaning reminding unit, the step of introducing cleaning cost accounting comprises the following steps: according to the settlement of the electricity of the local power grid, converting the generated energy corresponding to 100% of the generated energy in the clean state of the solar photovoltaic power station panel into the settlement cost of the power grid; when the corresponding power grid settlement cost of the generated energy due to dust loss is more than or equal to the cleaning cost, cleaning reminding is carried out;
the energy efficiency state sensing module comprises:
the first sensing unit is used for collecting power generation and equipment information of the photovoltaic power station and obtaining linear relations of module conversion efficiency, module attenuation rate, power generation and radiation;
the second sensing unit is used for obtaining the theoretical electric quantity of the photovoltaic power station and obtaining the power generation efficiency of the photovoltaic power station by combining the actual power generation quantity of the photovoltaic power station inverter;
and the third sensing unit is used for carrying out trend analysis on the lost electric quantity according to the deviation between the daily theoretical electric quantity and the actual electric quantity, and electric quantity loss factors under the conditions of maintenance, electricity limiting and defect.
4. The photovoltaic energy efficiency monitoring system based on neural network and optical pollution measurement of claim 3, wherein the energy efficiency state sensing module further comprises a component health model module, and the first sensing unit, the second sensing unit and the third sensing unit are connected with the component health model module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111048885.9A CN113676135B (en) | 2021-09-08 | 2021-09-08 | Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111048885.9A CN113676135B (en) | 2021-09-08 | 2021-09-08 | Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113676135A CN113676135A (en) | 2021-11-19 |
| CN113676135B true CN113676135B (en) | 2024-02-20 |
Family
ID=78548765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111048885.9A Active CN113676135B (en) | 2021-09-08 | 2021-09-08 | Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113676135B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114362664B (en) * | 2021-12-29 | 2024-03-22 | 广东南控电力有限公司 | Remote-control photovoltaic module cleaning matrix device |
| CN114781179B (en) * | 2022-05-12 | 2023-03-28 | 广东华矩检测技术有限公司 | Photovoltaic power station generated energy loss verification method based on optical fiber communication information acquisition |
| CN115146403B (en) * | 2022-06-17 | 2024-03-22 | 中国能源建设集团湖南省电力设计院有限公司 | Photovoltaic module with waveform arrangement and calculation method of optimal arrangement angle of photovoltaic module |
| CN117200329B (en) * | 2023-11-06 | 2024-03-22 | 广州菲利斯太阳能科技有限公司 | Off-grid power generation, energy storage and power supply system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105215034A (en) * | 2015-11-16 | 2016-01-06 | 上海许继电气有限公司 | Realize the system and method for photovoltaic plant solar panel intelligence cleaning |
| CN107092994A (en) * | 2017-06-21 | 2017-08-25 | 苏州协鑫新能源运营科技有限公司 | A kind of method for predicting delivery |
| CN107133713A (en) * | 2017-03-13 | 2017-09-05 | 华电电力科学研究院 | A kind of photovoltaic plant intelligently cleans the method for building up of decision system |
| CN107818410A (en) * | 2017-10-23 | 2018-03-20 | 长沙理工大学 | A kind of photovoltaic module dust stratification degree long-distance intelligent diagnostic method |
| CN212693535U (en) * | 2020-08-11 | 2021-03-12 | 东莞绿光新能源科技有限公司 | Photovoltaic power generation dust measuring device based on full-waveband optical pollution measurement technology |
| CN113224756A (en) * | 2021-05-11 | 2021-08-06 | 湖南中大设计院有限公司 | Method applied to photovoltaic building integrated optimal installed capacity measurement and calculation |
-
2021
- 2021-09-08 CN CN202111048885.9A patent/CN113676135B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105215034A (en) * | 2015-11-16 | 2016-01-06 | 上海许继电气有限公司 | Realize the system and method for photovoltaic plant solar panel intelligence cleaning |
| CN107133713A (en) * | 2017-03-13 | 2017-09-05 | 华电电力科学研究院 | A kind of photovoltaic plant intelligently cleans the method for building up of decision system |
| CN107092994A (en) * | 2017-06-21 | 2017-08-25 | 苏州协鑫新能源运营科技有限公司 | A kind of method for predicting delivery |
| CN107818410A (en) * | 2017-10-23 | 2018-03-20 | 长沙理工大学 | A kind of photovoltaic module dust stratification degree long-distance intelligent diagnostic method |
| CN212693535U (en) * | 2020-08-11 | 2021-03-12 | 东莞绿光新能源科技有限公司 | Photovoltaic power generation dust measuring device based on full-waveband optical pollution measurement technology |
| CN113224756A (en) * | 2021-05-11 | 2021-08-06 | 湖南中大设计院有限公司 | Method applied to photovoltaic building integrated optimal installed capacity measurement and calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113676135A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113676135B (en) | Photovoltaic energy efficiency monitoring method and system based on neural network and optical pollution measurement | |
| Peng et al. | Investigation on the development potential of rooftop PV system in Hong Kong and its environmental benefits | |
| Tan et al. | Optimization and evaluation of a dispatch model for an integrated wind-photovoltaic-thermal power system based on dynamic carbon emissions trading | |
| CN107341566A (en) | Photovoltaic system electricity generation power prediction meanss and its method based on meteorologic parameter Yu solar panel running state parameter | |
| Yau et al. | Energy analysis of green office buildings in the tropics—Photovoltaic system | |
| CN115514005B (en) | Economical evaluation method and device for energy storage system configuration of photovoltaic power station | |
| CN107977898B (en) | Generated energy insurance pricing evaluation method of photovoltaic power station | |
| CN105337574A (en) | Robust-regression-based distributed photovoltaic generating electricity-stealing identification method | |
| CN113064937A (en) | Dust cleaning early warning method and system for photovoltaic power station | |
| CN116993388A (en) | Method and system for confirming dynamic carbon emission factor in electric power system | |
| CN113285492B (en) | Analysis method for joint output characteristics of wind-solar combined power generation system of regional power grid | |
| CN116266331A (en) | Electric power energy structure monitoring method and device in power grid company area | |
| CN106548266A (en) | A kind of unit operation mode decision method for considering hydro thermal coordination | |
| Liu et al. | Research on optimum tilt angle of photovoltaic module based on regional clustering of influencing factors of power generation | |
| CN111478374A (en) | Dynamic evaluation method for probability distribution and prediction of wind-solar output characteristics | |
| Bagwari et al. | Solar Energy Technology: Step Towards Bright Future of the World | |
| TWM545838U (en) | Solar power station monitoring system | |
| CN112736899A (en) | Micro-grid planning scheme evaluation index calculation method and device | |
| Spiegel et al. | Distributed grid-connected photovoltaic power system emission offset assessment: statistical test of simulated-and measured-based data | |
| Karki | Reliability and cost evaluation of small isolated power systems containing photovoltaic and wind energy | |
| CN111224429A (en) | Mixed integer linear programming method for optimizing photovoltaic wind energy renewable energy system | |
| Ciocia et al. | An Improved Model for AC Power from Grid Connected Photovoltaic Systems and Comparison with Large-Scale Hourly Measured Data | |
| CN114552582B (en) | Real-time power generation load estimation method and system for photovoltaic power generation users | |
| CN115907981B (en) | Low-carbon joint transaction optimization method for virtual power plant | |
| AURANGZEB et al. | Performance Ratio Analysis Based on Energy Production for Large-Scale Solar Plant |
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 |