CN111027816B - Photovoltaic power generation efficiency calculation method based on data envelope analysis - Google Patents
Photovoltaic power generation efficiency calculation method based on data envelope analysis Download PDFInfo
- Publication number
- CN111027816B CN111027816B CN201911148048.6A CN201911148048A CN111027816B CN 111027816 B CN111027816 B CN 111027816B CN 201911148048 A CN201911148048 A CN 201911148048A CN 111027816 B CN111027816 B CN 111027816B
- Authority
- CN
- China
- Prior art keywords
- data
- power generation
- power station
- photovoltaic power
- historical
- 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.)
- Expired - Fee Related
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 50
- 238000004458 analytical method Methods 0.000 title claims abstract description 17
- 238000004364 calculation method Methods 0.000 title claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims description 22
- 230000004913 activation Effects 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000032683 aging Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000005477 standard model Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a photovoltaic power generation efficiency calculation method based on data envelope analysis, which comprises the steps of firstly obtaining historical solar irradiation data and historical meteorological data of an area where a photovoltaic power station is located and photovoltaic power station power generation power at a corresponding moment, judging the relative efficiency of each data by using a data envelope analysis method, screening out data with the relative efficiency of 20% in front, and taking the data as a training sample of a neural network model for training; and finally, acquiring solar irradiation data, meteorological data and the power generation power of the photovoltaic power station at the corresponding moment in real time, inputting the solar irradiation data, the meteorological data and the power generation power of the photovoltaic power station into the neural network model, outputting the standard power generation power of the power station, and comparing the actually-measured power generation power with the standard power generation power to obtain the real-time power generation efficiency of the power station. According to the method, the input and output model of the photovoltaic power station under the ideal working condition is built, a reference standard is provided for calculating the power generation efficiency of the photovoltaic power station, and the reference standard is used as an important basis for judging the operation working condition of the photovoltaic power station on line, so that the operation and maintenance cost of the power station is effectively reduced, and the maintenance efficiency of the power station is improved.
Description
Technical Field
The invention relates to the field of solar power generation, in particular to a photovoltaic power generation efficiency calculation method based on data envelope analysis.
Background
Through the development of photovoltaic power generation in the last decade, great breakthroughs are made in links such as photovoltaic cell efficiency improvement, MPPT algorithm research, inversion algorithm research and grid-connected mode; the power station furthest alleviates the defects of large fluctuation and instability of solar power generation and weakens the impact of photovoltaic power generation on grid connection by developing various topological structures, mutually combining with storage batteries and matching with an energy management system and other methods.
Nevertheless, the operation and maintenance of photovoltaic power plants has been a difficult point within the industry. The mode that some power stations adopted periodic inspection overhauls the main equipment of photovoltaic power station regularly, often consumes time and consumes labour, and efficiency is comparatively low. The ideal mode is to calculate the generating efficiency of the power station in real time, and when the generating efficiency is obviously reduced, the main equipment of the power station is overhauled, so that the utilization rate of personnel and time is improved.
However, the output power of the photovoltaic power station is influenced by a plurality of factors such as meteorological factors and equipment working conditions, and the numerical value fluctuation is large. Even if meteorological factors and output power are measured, whether the power generation efficiency is in a proper interval at the moment can not be judged due to the lack of the comparison index.
Therefore, the patent provides a method for calculating the generating efficiency of the photovoltaic power station. According to the method, an input and output model of the power station under an ideal working condition is extracted based on historical power generation data of the power station and is used as a standard model for measuring power generation efficiency. During the working period of the power station, the meteorological conditions and the output power of the power station are measured in real time, and the real-time power generation efficiency of the power station is calculated by combining the standard model, so that the working condition of the power station is measured, and the operation and maintenance efficiency of the power station is improved.
Disclosure of Invention
The invention aims to provide a novel photovoltaic power generation efficiency calculation method aiming at the defects of the prior art, and the power generation efficiency calculated by the method can better reflect the working condition of a power station, so that the operation and maintenance efficiency of the power station is improved.
The purpose of the invention is realized by the following technical scheme: a photovoltaic power generation efficiency calculation method based on data envelope analysis mainly comprises the following steps:
1) and acquiring historical solar irradiation data S and historical meteorological data of the area where the photovoltaic power station is located and the power generation power P of the photovoltaic power station at the corresponding moment. The required historical meteorological data includes temperature T, humidity H and wind speed W.
2) Normalizing the data; performing maximum and minimum normalization processing on the historical irradiation data S, the historical meteorological data and the photovoltaic power station power generation data P at the corresponding moment which are collected in the step 1);
3) judging the relative efficiency of each data by using a data envelope analysis method for the data after normalization processing; assuming that n groups of historical data exist at present, each group of historical data takes 4 characteristics such as solar irradiation data S, temperature T, humidity H, wind speed W and the like as input, and takes the power P of the photovoltaic power station at the corresponding moment as output. The weight coefficient of four input characteristics of solar irradiation data S, temperature T, humidity H and wind speed W is v ═ v [ [ v [ ] 1 ，v 2 ，v 3 ，v 4 ]. For the jth group of historical data, its relative efficiency η j Can be solved by the following linear programming equation, where X i ，Y i Representing the input and output of the ith sample.
4) Screening a training sample; according to the relative efficiency of each sample calculated in the step 3), arranging the samples from large to small according to the relative efficiency, and screening out data with the relative efficiency being 20% of the previous relative efficiency to be used as a training sample of the BP neural network model;
5) training a BP neural network by using the screened sample data; the BP neural network consists of an input layer, a hidden layer and an output layer; each layer has a corresponding activation function. The training process of the BP neural network mainly comprises two parts of input forward propagation and error backward propagation.
The BP neural network comprises five layers, wherein the first layer is an input layer and comprises four neurons, and 4-dimensional input characteristics such as solar irradiance S, temperature T, humidity H, wind speed W and the like are corresponded; the second, third and fourth layers are hidden layers, each of which comprises eight neurons; the fifth layer is an output layer and comprises a neuron, and the neuron corresponds to the generated power P of the photovoltaic power station. The activation function used is the Relu function, described below:
and inputting the training sample into the BP neural network model to obtain the trained BP neural network model.
6) For the solar irradiation data, the meteorological data and the generated power of the photovoltaic power station at the corresponding moment which are acquired in real time, firstly, the solar irradiation data and the meteorological data are input into a trained BP neural network model, and the standard generated power P of the power station is output i . Then the actually measured generating power P is measured o With standard power generation function P i And comparing to obtain the real-time generating efficiency eta of the power station:
further, only the whole point data of 5:00-19:00 per day need to be collected in the step 1).
Furthermore, each physical quantity to be collected in the step 1) is mainly detected by corresponding field devices such as a temperature sensor, an irradiation sensor, a humidity sensor, an air speed sensor and a power meter, and is transmitted to a PC (personal computer) end through a field bus to be monitored and stored in a database.
Further, the maximum and minimum normalization processing formula in step 2) is as follows:
where x is the original characteristic value of the data, x norm Is a normalized characteristic value, x min For the minimum of the features to be normalized, x max Is the maximum of the features to be normalized.
Further, the forward propagation of the BP neural network in the step 5) can be described by the following formula:
wherein,
is the input of the ith neuron of the l layer,
is the output of the neuron, f is the activation function of the layer,
is the weight between the jth neuron of the l-1 layer and the ith neuron of the l layer,
is the bias of the ith neuron of the l-th layer.
The corresponding back propagation formula can be described by:
wherein E represents the total error of the model, E (i) represents the error brought by the ith sample,
represents the total error pair
A gradient of (a);
representing the total error pair
Of the gradient of (c).
The invention has the beneficial effects that: according to the photovoltaic power generation efficiency calculation method based on data envelope analysis, an input and output model of a photovoltaic power station under an ideal working condition is built through collected historical data, and the model provides a reference standard for calculating the power generation efficiency of the photovoltaic power station. Through real-time measurement photovoltaic power plant's actual power and real-time calculation photovoltaic power plant's ideal power, can obtain photovoltaic power plant's real-time generating efficiency, as the important basis of online judgement photovoltaic power plant operating condition to effectively reduce the fortune maintenance cost of power plant, improve the maintenance efficiency of power plant.
Drawings
FIG. 1 is a flow chart of a photovoltaic power plant efficiency real-time assessment method;
FIG. 2 is a block diagram of a data acquisition system.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the attached drawings and the detailed implementation modes.
As shown in fig. 1, the method for calculating photovoltaic power generation efficiency based on data envelope analysis provided by the present invention includes the following steps:
1) and acquiring solar irradiation data S and meteorological data of the whole point of 5:00-19:00 per day of the area where the power station is located and corresponding photovoltaic power station power generation power P. Wherein, the meteorological data to be collected comprises temperature T, humidity H and wind speed W.
As shown in FIG. 2, the temperature of the back plate of the photovoltaic module is measured by selecting PT100 platinum thermal resistance, irradiance data is collected by an EKOMS-602 irradiance meter, humidity is measured by a 485 type humidity sensor, wind speed is measured by a high-precision digital anemometer, and output power is collected by a power meter. The various field instruments adopt RS485 communication interfaces, data are transmitted to the PLC through a field bus, and the PLC transmits collected data to the upper computer through Ethernet connection.
The collected sample data is shown in table 1.
TABLE 1 sample data collected
| Time | Irradiance (W/m ^2) | Temperature (. degree.C.) | Humidity (%) | Wind speed (m/s) | Generating power (KW) |
| 7_1_9:00 | 134 | 25.3 | 54 | 3.8 | 12.59 |
| 7_1_10:00 | 365 | 27.7 | 51 | 2.9 | 30.1 |
| 7_1_11:00 | 626 | 28.5 | 48 | 3.1 | 46.8 |
| ... | ... | ... | ... | ... | ... |
2) Normalizing the data; adopting maximum and minimum normalization processing on the historical irradiation data S, the historical meteorological data and the photovoltaic power station power generation data P at the corresponding moment collected in the step 1), wherein the formula is as follows:
where x is the original characteristic value of the data, x norm Is a normalized characteristic value, x min For the minimum of the features to be normalized, x max Is the maximum of the features to be normalized.
3) And calculating the relative efficiency of each data by using a data envelope analysis method for the data after normalization processing, and storing the relative efficiency into a database. The data envelope analysis method is a numerical analysis method based on linear programming and used for carrying out relative effectiveness evaluation on similar units which have comparability and comprise multinomial input and multinomial output; assuming that n groups of historical data are in total at present, each group of historical data takes 4 characteristics such as solar radiation data S, temperature T, humidity H, wind speed W and the like as input, and takes the photovoltaic power station power P at the corresponding moment as output.Defining the weight coefficient of four input characteristics of solar irradiation data S, temperature T, humidity H and wind speed W as v ═ v [ [ v [ ] 1 ，v 2 ，v 3 ，v 4 ]. For the jth group of historical data, its relative efficiency η j Can be solved by the following linear programming equation, where X i ，Y i Representing the input and output of the ith sample.
The sample data after calculating the relative efficiency is shown in table 2 (the features of each dimension in the table are normalized).
TABLE 2 sample data after calculating relative efficiency
| Time | Irradiance of | Temperature of | Humidity | Wind speed | Generated power | Relative efficiency |
| 7_1_9:00 | 0.134 | 0.632 | 0.540 | 0.190 | 0.209 | 0.76 |
| 7_1_10:00 | 0.365 | 0.693 | 0.510 | 0.145 | 0.501 | 0.89 |
| 7_1_11:00 | 0.626 | 0.713 | 0.480 | 0.155 | 0.780 | 0.83 |
| ... | ... | ... | ... | ... | ... |
4) Screening a training sample; according to the relative efficiency of each sample calculated in the step 3), arranging the samples from large to small according to the relative efficiency, screening out data with the efficiency being 20% higher than the relative efficiency, and comparing the data with the data which is directly adopted for training as a training sample of the BP neural network model, wherein the screened data enables the network model to be closer to an input/output model of the photovoltaic power station under the ideal working condition.
5) And training the BP neural network by using the screened sample data. The BP neural network consists of an input layer, a hidden layer and an output layer; each layer has a corresponding activation function. The training process of the BP neural network mainly comprises two parts of input forward propagation and error backward propagation.
The forward propagation of the BP neural network can be described by:
wherein,
is the input of the ith neuron of the l layer,
is the output of the neuron, f is the activation function of the layer,
is the weight between the jth neuron of the l-1 layer and the ith neuron of the l layer,
is the bias of the ith neuron of the l-th layer.
The corresponding back propagation formula can be described by:
wherein E represents the total error of the model, E (i) represents the error brought by the ith sample,
represents the total error pair
A gradient of (a);
represents the total error pair
Of the gradient of (a).
The neural network comprises five layers, wherein the first layer is an input layer and comprises four neurons, and the input layer corresponds to 4-dimensional input characteristics such as solar irradiance S, temperature T, humidity H, wind speed W and the like; the second, third and fourth layers are hidden layers, each of which comprises eight neurons; the fifth layer is an output layer and comprises a neuron, and the neuron corresponds to the generated power of the photovoltaic power station. The activation function used is the Relu function, described below:
compared with other activation functions, Relu has the advantage of constant gradient, and is convenient for rapid convergence of the model in the training process.
And inputting the training sample into the BP neural network model to obtain the trained BP neural network model.
6) For the solar irradiation data, the meteorological data and the generated power of the photovoltaic power station at the corresponding moment which are acquired in real time, firstly, the solar irradiation data and the meteorological data are input into a trained BP neural network model, and the standard generated power P of the power station is output i . Then the measured hair is sentElectric power P o With standard power generation function P i And comparing to obtain the real-time generating efficiency eta of the power station:
according to the calculated real-time power generation efficiency, the equipment running condition of the photovoltaic power station can be judged, if the calculated real-time power generation efficiency is too low, the working condition of main equipment of the photovoltaic power station is indicated to be in a problem, faults such as short circuit of a photovoltaic panel, short circuit or damage of a combiner box can exist, and power station personnel are required to be organized immediately for troubleshooting.
Three groups of data of the power station under normal working conditions, shadow shielding and component aging states are selected, the power generation efficiency is calculated respectively, and the obtained results are shown in table 3. The power generation efficiency of the power station calculated by the model under the normal working condition is high, the power generation efficiency of the power station calculated by the model under the shadow shielding and component aging states is low, the power generation efficiency accords with the reality, and the power generation efficiency calculated by the model can well reflect the equipment running condition of the photovoltaic power station, as shown in table 3.
TABLE 3 Power Generation efficiency under different operating conditions
| Working conditions | Irradiance of | Temperature of | Humidity | Wind speed | Generated power | Relative efficiency |
| Is normal | 0.792 | 0.778 | 0.420 | 0.330 | 0.810 | 0.88 |
| Shadow masking | 0.933 | 0.896 | 0.680 | 0.185 | 0.766 | 0.67 |
| Component aging | 0.745 | 0.690 | 0.450 | 0.252 | 0.629 | 0.69 |
| ... | ... | ... | ... | ... | ... |
The above-described embodiments are intended to illustrate rather than to limit the invention, and any modifications and variations of the present invention are within the spirit of the invention and the scope of the appended claims.
Claims (4)
1. A photovoltaic power generation efficiency calculation method based on data envelope analysis is characterized by mainly comprising the following steps:
1) acquiring historical solar irradiation data S, historical meteorological data and photovoltaic power station power generation data P at corresponding moments of the area where the photovoltaic power station is located, wherein the historical meteorological data comprise temperature T, humidity H and wind speed W;
2) normalizing the data, specifically: performing maximum and minimum normalization processing on the historical solar irradiation data S, the historical meteorological data and the photovoltaic power station power generation data P at the corresponding moment which are obtained in the step 1);
3) for the data after normalization processing, the relative efficiency of each data is judged by using a data envelope analysis method, which specifically comprises the following steps: assuming that n groups of historical data are available at present, each group of historical data takes the characteristics of historical solar irradiation data S, temperature T, humidity H and wind speed W4 as input, takes the generated power data P of the photovoltaic power station at the corresponding moment as output, and the weight coefficient of 4 input characteristics of the historical solar irradiation data S, the temperature T, the humidity H and the wind speed W is v ═ v 1 ,v 2 ,v 3 ,v 4 ]For the jth group of historical data, its relative efficiency eta j Solving by the following linear programming equation:
wherein X i ，Y i Represents the input and output of the ith sample;
4) screening training samples, specifically: arranging the n groups of historical data from large to small according to the relative efficiency of the n groups of historical data calculated in the step 3), and screening out data with the relative efficiency of the top 20% to serve as a training sample of the BP neural network model;
5) training a BP neural network model by using the screened sample data, which specifically comprises the following steps: the BP neural network model consists of an input layer, a hidden layer and an output layer, each layer is provided with a corresponding activation function, and the training process of the BP neural network model comprises two parts of input forward propagation and error backward propagation;
the BP neural network model has five layers, the first layer is an input layer and comprises four neurons, and historical solar irradiation data S, temperature T, humidity H and wind speed W4 dimensional input characteristics are corresponded; the second, third and fourth layers are hidden layers, each of which comprises eight neurons; the fifth layer is an output layer and comprises a neuron, and the neuron corresponds to the photovoltaic power station generated power data P at the moment; the activation function used is the Relu function, described below:
inputting the training sample of the BP neural network model into the BP neural network model to obtain a trained BP neural network model;
6) for the solar irradiation data, the meteorological data and the photovoltaic power station power generation power data at the corresponding moment which are obtained in real time, firstly, the solar irradiation data and the meteorological data which are obtained in real time are input into a trained BP neural network model, and the standard power generation power P of the power station is output i Then the actually measured generated power P is measured o And the standard generated power P i And comparing to obtain the real-time generating efficiency eta of the power station:
2. the method for calculating photovoltaic power generation efficiency based on data envelope analysis according to claim 1, wherein the obtaining of the historical solar irradiation data S, the historical meteorological data and the photovoltaic power station power generation data P at the corresponding time in the area of the photovoltaic power station in step 1) is to obtain 5:00-19: an hour data of 00.
3. The method for calculating photovoltaic power generation efficiency based on data envelope analysis according to claim 1, wherein the temperature T in the historical meteorological data obtained in step 1) is detected by a temperature sensor, the obtained humidity H is detected by a humidity sensor, the obtained wind speed W is detected by a wind speed sensor, the obtained historical solar radiation data S is detected by a radiation sensor, the obtained photovoltaic power station power generation data P is detected by a power meter, and the detected data is transmitted to a PC terminal through a field bus to be monitored and stored in a database.
4. The photovoltaic power generation efficiency calculation method based on the data envelope analysis according to claim 1, wherein the maximum and minimum normalization processing formula in the step 2) is as follows:
where x is the original characteristic value of the data, x norm Is a normalized characteristic value, x min For the minimum of the features to be normalized, x max Is the maximum of the features to be normalized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911148048.6A CN111027816B (en) | 2019-11-21 | 2019-11-21 | Photovoltaic power generation efficiency calculation method based on data envelope analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911148048.6A CN111027816B (en) | 2019-11-21 | 2019-11-21 | Photovoltaic power generation efficiency calculation method based on data envelope analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111027816A CN111027816A (en) | 2020-04-17 |
| CN111027816B true CN111027816B (en) | 2022-07-26 |
Family
ID=70206104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911148048.6A Expired - Fee Related CN111027816B (en) | 2019-11-21 | 2019-11-21 | Photovoltaic power generation efficiency calculation method based on data envelope analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027816B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780683A (en) * | 2021-10-15 | 2021-12-10 | 电子科技大学成都学院 | Rural energy optimization scheduling method based on BP neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218673A (en) * | 2013-03-27 | 2013-07-24 | 河海大学 | Method for predicating short-period output power of photovoltaic power generation based on BP (Back Propagation) neural network |
| CN103925155A (en) * | 2014-04-09 | 2014-07-16 | 中国水利水电科学研究院 | Self-adaptive detection method for abnormal wind turbine output power |
| JP2018007312A (en) * | 2016-06-27 | 2018-01-11 | 藤崎電機株式会社 | Generated power prediction apparatus, server, computer program, and generated power prediction method |
-
2019
- 2019-11-21 CN CN201911148048.6A patent/CN111027816B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218673A (en) * | 2013-03-27 | 2013-07-24 | 河海大学 | Method for predicating short-period output power of photovoltaic power generation based on BP (Back Propagation) neural network |
| CN103925155A (en) * | 2014-04-09 | 2014-07-16 | 中国水利水电科学研究院 | Self-adaptive detection method for abnormal wind turbine output power |
| JP2018007312A (en) * | 2016-06-27 | 2018-01-11 | 藤崎電機株式会社 | Generated power prediction apparatus, server, computer program, and generated power prediction method |
Non-Patent Citations (3)
| Title |
|---|
| 光伏电站PR效率研究;孙丽兵 等;《上海电力》;20150228;第28卷(第1期);第9-11页 * |
| 基于日类型及融合理论的BP网络光伏功率预测;冉成科 等;《中南大学学报(自然科学版)》;20180926;第49卷(第9期);第2232-2239页 * |
| 基于样本评价的广义数据包络分析方法;马占新 等;《数学的实践与认识》;20111108;第41卷(第21期);第155-171页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111027816A (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934423B (en) | Photovoltaic power station power prediction method and system based on grid-connected inverter operation data | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN109086928B (en) | Photovoltaic power station real-time power prediction method based on SAGA-FCM-LSSVM model | |
| CN114004139B (en) | Photovoltaic power generation power prediction method | |
| CN102562469B (en) | Short-term wind driven generator output power predicting method based on correction algorithm | |
| Yang et al. | Day-ahead forecasting of photovoltaic output power with similar cloud space fusion based on incomplete historical data mining | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN111475909B (en) | Wind turbine generator output correlation mapping modeling method based on long-term and short-term memory network | |
| CN110334870B (en) | Photovoltaic power station short-term power prediction method based on gated cyclic unit network | |
| CN113657662B (en) | Downscaling wind power prediction method based on data fusion | |
| CN105787594A (en) | Irradiation prediction method based on multivariate time series and regression analysis | |
| CN116167531A (en) | Photovoltaic power generation prediction method based on digital twin | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| CN104574221B (en) | A kind of photovoltaic plant running status discrimination method based on loss electricity characteristic parameter | |
| CN115829145A (en) | Photovoltaic power generation capacity prediction system and method | |
| CN116611702A (en) | Integrated learning photovoltaic power generation prediction method for building integrated energy management | |
| CN111027816B (en) | Photovoltaic power generation efficiency calculation method based on data envelope analysis | |
| CN117060407B (en) | Wind power cluster power prediction method and system based on similar day division | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| CN110555566B (en) | B-spline quantile regression-based photoelectric probability density prediction method | |
| CN117236720A (en) | Photovoltaic power station generated power prediction method utilizing multi-meteorological factor characteristics | |
| Jun-Ma et al. | Photovoltaic power generation prediction based on MEA-BP neural network | |
| CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
| CN110059972A (en) | Day solar radiation stock assessment method based on functional deepness belief network |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220726 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |