CN112085350A - Method for evaluating photovoltaic array state in large photovoltaic power station - Google Patents

Method for evaluating photovoltaic array state in large photovoltaic power station Download PDF

Info

Publication number
CN112085350A
CN112085350A CN202010844355.4A CN202010844355A CN112085350A CN 112085350 A CN112085350 A CN 112085350A CN 202010844355 A CN202010844355 A CN 202010844355A CN 112085350 A CN112085350 A CN 112085350A
Authority
CN
China
Prior art keywords
photovoltaic array
output power
data
array
power data
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
Application number
CN202010844355.4A
Other languages
Chinese (zh)
Other versions
CN112085350B (en
Inventor
李庚达
胡文森
梁凌
段震清
朱润泽
朱红路
史淯城
孙建民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guodian New Energy Technology Research Institute Co ltd
Original Assignee
Guodian New Energy Technology Research Institute Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guodian New Energy Technology Research Institute Co ltd filed Critical Guodian New Energy Technology Research Institute Co ltd
Priority to CN202010844355.4A priority Critical patent/CN112085350B/en
Publication of CN112085350A publication Critical patent/CN112085350A/en
Application granted granted Critical
Publication of CN112085350B publication Critical patent/CN112085350B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • G06N3/045—Combinations of 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Biomedical Technology (AREA)
  • Educational Administration (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Photovoltaic Devices (AREA)

Abstract

The invention belongs to the technical field of photovoltaic power generation, and particularly discloses a method for evaluating the state of a photovoltaic array in a large photovoltaic power station. The method comprises the following steps: collecting historical power data of a photovoltaic array in a power station, and predicting theoretical output power data of a target photovoltaic array by using an ELM prediction network; and extracting characteristic indexes according to theoretical output power data and actual output power data of the target photovoltaic array, realizing automatic clustering of the photovoltaic array based on the characteristic indexes, and evaluating the running state of the formed array cluster. The assessment method can be applied to arrays without meteorological information, avoids the requirement on high-precision meteorological data, and can also be applied to large photovoltaic power stations with poor detection conditions.

Description

Method for evaluating photovoltaic array state in large photovoltaic power station
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method for evaluating the state of a photovoltaic array in a large photovoltaic power station.
Background
The photovoltaic power generation is a utilization mode of directly converting light energy into electric energy by means of a solar cell panel, has the advantages of simple structure, small occupied area, simplicity in maintenance, cleanness, environmental protection, safety, reliability, wide application and the like, and has a great significance in the field of solar energy application. The photovoltaic power generation is a random unsteady process under the influence of geographic sound speed such as the installation position and angle of a photovoltaic array, irradiation intensity, temperature and other meteorological factors.
As a core element of a photovoltaic power generation system, a photovoltaic array usually works in a complex outdoor environment and is easily interfered by various environmental factors, so that faults such as open circuit, short circuit, hard shadow, hot spot and the like are caused, the power generation efficiency of a power station may be affected by the faults of the photovoltaic array, and even a fire may happen in a severe case.
In the prior art, because a theoretical generation model of a photovoltaic array is difficult to establish in a large photovoltaic power station, performance evaluation cannot be performed on the photovoltaic array lacking meteorological information.
Disclosure of Invention
The invention aims to provide an evaluation method of a photovoltaic array state in a large photovoltaic power station, and aims to solve the problem that performance evaluation cannot be performed on a photovoltaic array lacking meteorological information.
In order to achieve the purpose, the scheme of the invention is as follows:
a method for evaluating the state of a photovoltaic array in a large photovoltaic power station comprises the following steps:
collecting historical power data of a photovoltaic array in a power station, and predicting theoretical output power data of a target photovoltaic array by using an ELM prediction network;
and extracting characteristic indexes according to theoretical output power data and actual output power data of the target photovoltaic array, realizing automatic clustering of the photovoltaic array based on the characteristic indexes, and evaluating the running state of the formed array cluster.
Preferably, the acquiring historical power data of the photovoltaic array in the power station comprises:
and acquiring the output power of the target photovoltaic array and the peripheral arrays thereof in a historical period, and establishing a historical output power sequence based on the sampling time sequence.
Preferably, after the acquiring historical power data of the photovoltaic array in the power station, the method further comprises: and cleaning and normalizing the historical power data.
Preferably, the cleaning and normalizing the historical power data includes:
cleaning the historical power data, wherein the cleaning comprises the steps of removing data which do not accord with actual conditions and removing incomplete data generated by errors of a data acquisition system;
the cleaned data were normalized to the [0,1] interval.
Preferably, the predicting theoretical output power data of the target photovoltaic array by using the ELM prediction network comprises the following steps:
in the training stage, the output power of a target photovoltaic array and peripheral arrays thereof in a historical period is used as input, the output power of the target photovoltaic array is used as output, a training sample set is established, and ELM neural network training is carried out;
and in the prediction stage, inputting actual output power data of the peripheral photovoltaic array in the corresponding prediction time period into an ELM prediction network for power prediction, and performing inverse normalization processing on an output result to obtain the theoretical output power of the target photovoltaic array based on the time sequence.
Preferably, the principle according to a photovoltaic array
The method for extracting the characteristic indexes of the theoretical output power and the actual output power comprises the following steps:
calculating a first performance evaluation index based on the deviation degree according to actual output power data and theoretical output power data of the target photovoltaic array;
and calculating a second performance evaluation index based on the similarity according to the actual output power data and the theoretical output power data of the target photovoltaic array.
Preferably, the calculating a first performance evaluation index based on the deviation degree according to the actual output power data and the theoretical output power data of the target photovoltaic array includes:
calculating the deviation (X) between the actual output power and the theoretical output power of the target photovoltaic array according to the Euclidean distance formula (1)Tar,XRef) And using the first performance evaluation index as a first performance evaluation index;
Figure BDA0002642540170000031
wherein, XTarIs the actual output power of the target photovoltaic array based on the time series;
XRefis the theoretical output power of the target photovoltaic array based on time series.
Preferably, the calculating a second performance evaluation index based on similarity according to the actual output power data and the theoretical output power data of the target photovoltaic array includes:
calculating a correlation coefficient r between the actual output power and the theoretical output power of the target photovoltaic array according to a Pearson correlation coefficient formula (2), and taking the correlation coefficient r as a second performance evaluation index;
Figure BDA0002642540170000032
wherein the content of the first and second substances,
Figure BDA0002642540170000033
is XTarIs determined by the average value of (a) of (b),
Figure BDA0002642540170000034
is XRefAverage value of (a).
Preferably, the implementing the automatic clustering of the photovoltaic array based on the characteristic index includes:
and taking the first performance evaluation index and the second performance evaluation index of the photovoltaic arrays as input characteristics, automatically clustering each photovoltaic array by using a K-means algorithm, and dividing the plurality of photovoltaic arrays into K array clusters.
Preferably, the operating state of the photovoltaic array as the center of the cluster is characterized as the operating state of the whole array cluster;
the evaluation of the operation state of the array cluster comprises the following steps:
a first performance assessment indicator of the photovoltaic array as a cluster center is negatively correlated with an operating level of the array cluster;
the second performance evaluation index of the photovoltaic array at the center of the cluster is positively correlated with the operation level of the array cluster
By the technical scheme, the evaluation method of the photovoltaic array state is provided on the basis of not considering relevant meteorological information, the theoretical power output of the photovoltaic array is predicted by using historical operating data, and the performance comparison and evaluation of the photovoltaic array are realized by automatically clustering the photovoltaic array under different conditions. The assessment method can be applied to arrays without meteorological information, avoids the requirement on high-precision meteorological data, and can also be applied to large photovoltaic power stations with poor detection conditions.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a method for assessing the condition of a photovoltaic array;
fig. 2 is a schematic diagram of the evaluation result of the state of the photovoltaic array.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The invention provides a method for evaluating the state of a photovoltaic array in a large photovoltaic power station, which comprises the following steps of:
s1, collecting historical power data of a photovoltaic array in a power station, and predicting theoretical output power data of a target photovoltaic array by using an ELM prediction network;
and S2, extracting characteristic indexes according to the theoretical output power and the actual output power of the target photovoltaic array, realizing automatic clustering of the photovoltaic array based on the characteristic indexes, and evaluating the running state of the formed array cluster.
In step S1, the acquiring historical power data of the photovoltaic array in the power station includes: and acquiring the output power of the target photovoltaic array and the peripheral arrays thereof in a historical period, and establishing a historical output power sequence based on the sampling time sequence.
Further, after collecting the historical power data of the photovoltaic array in the power station, the method further comprises the following steps: and cleaning and normalizing the historical power data.
Specifically, the method for cleaning and normalizing the historical power data comprises the following steps:
cleaning historical power data, including eliminating data which do not conform to actual conditions and incomplete data generated by errors of a data acquisition system;
the cleaned data were normalized to the [0,1] interval.
An extreme Learning machine (elm) is a machine Learning system based on a single hidden layer feedforward neural network, and comprises an input layer, a hidden layer and an output layer, wherein an output function of the hidden layer has the following definitions:
Figure BDA0002642540170000051
where x is the input data, ωiAs input weights, βiFor output weights, g is a feature mapping or excitation function, which functions to map the input data from its native space to the ELM feature space, biAre feature mapping parameters, also referred to as node parameters in the ELM study. Input weight ωiCharacteristic mapping parameter biIs set by past experience to output a weight betaiAnd obtaining the theoretical output power data of the photovoltaic array in the prediction time period by initial calculation training and calculating.
In the invention, the predicting theoretical output power data of the target photovoltaic array by using the ELM prediction network comprises the following steps:
in the training stage, the output power of a target photovoltaic array and peripheral arrays thereof in a historical period is used as input, the output power of the target photovoltaic array is used as output, a training sample set is established, and ELM neural network training is carried out;
and in the prediction stage, inputting actual output power data of the peripheral photovoltaic array in the corresponding prediction time period into an ELM prediction network for power prediction, and performing inverse normalization processing on an output result to obtain the theoretical output power of the target photovoltaic array based on the time sequence.
The extracting of the characteristic index according to the theoretical output power and the actual output power of the photovoltaic array in step S2 includes:
calculating a first performance evaluation index based on the deviation degree according to actual output power data and theoretical output power data of the target photovoltaic array;
and calculating a second performance evaluation index based on the similarity according to the actual output power data and the theoretical output power data of the target photovoltaic array.
According to a specific embodiment, the calculating a first performance evaluation index based on the deviation degree according to the actual output power data and the theoretical output power data of the target photovoltaic array includes:
calculating the deviation (X) between the actual output power and the theoretical output power of the target photovoltaic array according to the Euclidean distance formula (1)Tar,XRef) And using the first performance evaluation index as a first performance evaluation index;
Figure BDA0002642540170000061
wherein, XTarIs the actual output power of the target photovoltaic array based on the time series;
XRefis the theoretical output power of the target photovoltaic array based on time series.
The Euclidean distance is used for recording the linear distance between two vectors, and is a more visual and common similarity calculation method, and the smaller the Euclidean distance is, the smaller the deviation of the vectors is, and the greater the similarity is; the larger the euclidean distance, the larger the deviation of the vector, and the smaller the similarity.
According to a specific embodiment, the calculating a second performance evaluation index based on similarity according to the actual output power data and the theoretical output power data of the target photovoltaic array includes:
calculating a correlation coefficient r between the actual output power and the theoretical output power of the target photovoltaic array according to a Pearson correlation coefficient formula (2), and taking the correlation coefficient r as a second performance evaluation index;
Figure BDA0002642540170000071
wherein the content of the first and second substances,
Figure BDA0002642540170000072
is XTarIs determined by the average value of (a) of (b),
Figure BDA0002642540170000073
is XRefAverage value of (a).
The Pearson correlation coefficient r is used for reflecting the linear correlation degree of the two vectors, and the larger the absolute value of r is, the stronger the correlation is.
In the present invention, the implementing of automatic clustering of photovoltaic arrays based on characteristic indexes in step S2 includes: and taking the first performance evaluation index and the second performance evaluation index of the photovoltaic array as input, automatically clustering the photovoltaic array by using a K-means algorithm, and dividing the plurality of photovoltaic arrays into K array clusters.
In practical application, the K-means algorithm is used for dividing a data set D into K clusters, so that the distances between data points in the clusters are as small as possible, and the distances between the clusters are as large as possible, and the basic principle and the algorithm steps are as follows:
1. inputting a data set D and a cluster number K, wherein K data points randomly selected from the data set D are used as an initial cluster center;
2. respectively calculating the distance from each data point to the center of K initial clusters, generally taking Euclidean distance or cosine distance, distributing each data point to the closest cluster, thereby dividing the data set D into K clusters, namely { S }1,S2,S3,...Sk}；
3. Updating the cluster center according to the data points in the cluster, namely defining the mean value of the coordinates of each data point in the cluster as a new cluster center;
4. and repeating the step 2-3 until the algorithm is converged.
The common convergence conditions include iteration times, minimum square error, cluster center point change rate and the like, and the convergence is stopped when the preset convergence conditions are reached.
In the scheme of the invention, a first performance evaluation index and a second performance evaluation index of the target photovoltaic array, namely the deviation (X) of the actual output power and the theoretical output power of the target photovoltaic arrayTar,XRef) And inputting the formed data set and a data set formed by a correlation coefficient r of actual output power and theoretical output power into a classifier, wherein the classifier divides the photovoltaic arrays under different fault conditions into K array clusters by using a K-means algorithm, and each array cluster has a cluster center.
It should be noted that the operation state of the photovoltaic array as the center of the cluster is characterized as the operation state of the whole array cluster in the present invention.
The evaluating the operation state of the array cluster specifically comprises:
a first performance assessment indicator of the photovoltaic array as a cluster center is negatively correlated with an operating level of the array cluster;
the second performance assessment indicator for the photovoltaic array as the center of the cluster is positively correlated with the operating level of the array cluster.
Practice proves that different faults of the photovoltaic array have different influences on the output power of the photovoltaic array, and the specific expression is as follows:
under open circuit fault conditions, the second performance evaluation index of the photovoltaic array is 0, while the first performance evaluation index is increased;
under a short circuit fault condition, the second performance evaluation index of the photovoltaic array decreases, while the first performance evaluation index increases;
under shadow fault conditions, the second performance assessment indicator of the photovoltaic array decreases but is not 0, while the first performance assessment indicator increases;
under aging fault conditions, the second performance evaluation index of the photovoltaic array is unchanged, while the first performance evaluation index is increased.
The scheme of the invention provides an evaluation method of the state of the photovoltaic array without considering relevant meteorological information, the theoretical power output of the photovoltaic array is calculated by utilizing historical operating data of the photovoltaic array and an ELM network, and the performance comparison and evaluation of the photovoltaic array are realized by utilizing a k-means algorithm to automatically cluster the photovoltaic array under different conditions. The evaluation method identifies the abnormal state of the array by using the related array information, is easy to implement, can be applied to the state evaluation problem of the large photovoltaic power station when no reference irradiation data or irradiation data is abnormal, avoids the requirement on high-precision meteorological data, and can also be applied to the large photovoltaic power station with poor detection conditions.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. A method for evaluating the state of a photovoltaic array in a large photovoltaic power station is characterized by comprising the following steps:
collecting historical power data of a photovoltaic array in a power station, and predicting theoretical output power data of a target photovoltaic array by using an ELM prediction network;
and extracting characteristic indexes according to theoretical output power data and actual output power data of the target photovoltaic array, realizing automatic clustering of the photovoltaic array based on the characteristic indexes, and evaluating the running state of the formed array cluster.
2. The method of claim 1, wherein collecting historical power data for a photovoltaic array in the power plant comprises:
and acquiring the output power of the target photovoltaic array and the peripheral arrays thereof in a historical period, and establishing a historical output power sequence based on the sampling time sequence.
3. The method of claim 1, further comprising, after said collecting historical power data for photovoltaic arrays in the power plant: and cleaning and normalizing the historical power data.
4. The method of claim 3, wherein the cleansing and normalizing the historical power data comprises:
cleaning the historical power data, wherein the cleaning comprises the steps of removing data which do not accord with actual conditions and removing incomplete data generated by errors of a data acquisition system;
the cleaned data were normalized to the [0,1] interval.
5. The method of claim 1, wherein predicting theoretical output power data for the target photovoltaic array using the ELM prediction network comprises:
in the training stage, the output power of a target photovoltaic array and peripheral arrays thereof in a historical period is used as input, the output power of the target photovoltaic array is used as output, a training sample set is established, and ELM neural network training is carried out;
and in the prediction stage, inputting actual output power data of the peripheral photovoltaic array in the corresponding prediction time period into an ELM prediction network for power prediction, and performing inverse normalization processing on an output result to obtain the theoretical output power of the target photovoltaic array based on the time sequence.
6. The method of claim 1, wherein extracting the characteristic indicator from theoretical output power and actual output power of the photovoltaic array comprises:
calculating a first performance evaluation index based on the deviation degree according to actual output power data and theoretical output power data of the target photovoltaic array;
and calculating a second performance evaluation index based on the similarity according to the actual output power data and the theoretical output power data of the target photovoltaic array.
7. The method of claim 6, wherein calculating a first deviation-based performance assessment indicator based on actual output power data and theoretical output power data of the target photovoltaic array comprises:
calculating the deviation (X) between the actual output power and the theoretical output power of the target photovoltaic array according to the Euclidean distance formula (1)Tar,XRef) And using the first performance evaluation index as a first performance evaluation index;
Figure FDA0002642540160000021
wherein, XTarIs the actual output power of the target photovoltaic array based on the time series;
XRefis the theoretical output power of the target photovoltaic array based on time series.
8. The method of claim 6, wherein calculating a second similarity-based performance assessment indicator based on actual output power data and theoretical output power data of the target photovoltaic array comprises:
calculating a correlation coefficient r between the actual output power and the theoretical output power of the target photovoltaic array according to a Pearson correlation coefficient formula (2), and taking the correlation coefficient r as a second performance evaluation index;
Figure FDA0002642540160000031
wherein the content of the first and second substances,
Figure FDA0002642540160000032
is XTarIs determined by the average value of (a) of (b),
Figure FDA0002642540160000033
is XRefAverage value of (a).
9. The method of claim 6, wherein the implementing photovoltaic array automatic clustering based on the characteristic index comprises:
and taking the first performance evaluation index and the second performance evaluation index of the photovoltaic arrays as input characteristics, automatically clustering each photovoltaic array by using a K-means algorithm, and dividing the plurality of photovoltaic arrays into K array clusters.
10. The method of claim 9, wherein the operating state of the photovoltaic array as the center of the cluster is characterized as the operating state of the entire array cluster;
the evaluation of the operation state of the array cluster comprises the following steps:
a first performance assessment indicator of the photovoltaic array as a cluster center is negatively correlated with an operating level of the array cluster;
the second performance assessment indicator of the photovoltaic array at the center of the cluster is positively correlated with the operating level of the array cluster.
CN202010844355.4A 2020-08-20 2020-08-20 Evaluation method for photovoltaic array state in large photovoltaic power station Active CN112085350B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010844355.4A CN112085350B (en) 2020-08-20 2020-08-20 Evaluation method for photovoltaic array state in large photovoltaic power station

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010844355.4A CN112085350B (en) 2020-08-20 2020-08-20 Evaluation method for photovoltaic array state in large photovoltaic power station

Publications (2)

Publication Number Publication Date
CN112085350A true CN112085350A (en) 2020-12-15
CN112085350B CN112085350B (en) 2024-05-28

Family

ID=73728485

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010844355.4A Active CN112085350B (en) 2020-08-20 2020-08-20 Evaluation method for photovoltaic array state in large photovoltaic power station

Country Status (1)

Country Link
CN (1) CN112085350B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966400A (en) * 2021-04-23 2021-06-15 重庆大学 Centrifugal fan trend prediction method based on multi-source information fusion
CN116596194A (en) * 2023-06-27 2023-08-15 中国大唐集团技术经济研究院有限责任公司 Photovoltaic array running state dividing method, system and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109711609A (en) * 2018-12-15 2019-05-03 福州大学 Photovoltaic plant output power predicting method based on wavelet transformation and extreme learning machine
CN110059862A (en) * 2019-03-25 2019-07-26 国网浙江省电力有限公司电力科学研究院 A kind of photovoltaic interval prediction method and system based on from coding and extreme learning machine
CN111275295A (en) * 2020-03-23 2020-06-12 华北电力大学 Distributed photovoltaic fault diagnosis method based on inverse distance weight interpolation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109711609A (en) * 2018-12-15 2019-05-03 福州大学 Photovoltaic plant output power predicting method based on wavelet transformation and extreme learning machine
CN110059862A (en) * 2019-03-25 2019-07-26 国网浙江省电力有限公司电力科学研究院 A kind of photovoltaic interval prediction method and system based on from coding and extreme learning machine
CN111275295A (en) * 2020-03-23 2020-06-12 华北电力大学 Distributed photovoltaic fault diagnosis method based on inverse distance weight interpolation

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112966400A (en) * 2021-04-23 2021-06-15 重庆大学 Centrifugal fan trend prediction method based on multi-source information fusion
CN116596194A (en) * 2023-06-27 2023-08-15 中国大唐集团技术经济研究院有限责任公司 Photovoltaic array running state dividing method, system and device
CN116596194B (en) * 2023-06-27 2024-01-23 中国大唐集团技术经济研究院有限责任公司 Photovoltaic array running state dividing method, system and device

Also Published As

Publication number Publication date
CN112085350B (en) 2024-05-28

Similar Documents

Publication Publication Date Title
CN109873610B (en) Photovoltaic array fault diagnosis method based on IV characteristic and depth residual error network
CN110070226B (en) Photovoltaic power prediction method and system based on convolutional neural network and meta-learning
CN109842373B (en) Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics
CN110533331B (en) Fault early warning method and system based on transmission line data mining
CN114792156B (en) Photovoltaic output power prediction method and system based on curve characteristic index clustering
CN110503153B (en) Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine
CN111695736B (en) Photovoltaic power generation short-term power prediction method based on multi-model fusion
CN112085350B (en) Evaluation method for photovoltaic array state in large photovoltaic power station
CN113988477A (en) Photovoltaic power short-term prediction method and device based on machine learning and storage medium
CN114006369A (en) Regional wind and light station power joint prediction method and device, electronic equipment and storage medium
CN115036922B (en) Distributed photovoltaic power generation electric quantity prediction method and system
CN115271253A (en) Water-wind power generation power prediction model construction method and device and storage medium
CN112149905A (en) Photovoltaic power station short-term power prediction method based on wavelet transformation and wavelet neural network
CN110674864A (en) Wind power abnormal data identification method with synchronous phasor measurement device
Chen et al. Research on wind power prediction method based on convolutional neural network and genetic algorithm
CN115879602A (en) Ultra-short-term photovoltaic output prediction method based on transient weather
CN116467648A (en) Early monitoring method for nonlinear platform power failure based on Internet of things table
CN113991711A (en) Capacity configuration method for energy storage system of photovoltaic power station
CN112132344A (en) Short-term wind power prediction method based on similar day and FRS-SVM
CN117200181A (en) Photovoltaic power generation amount prediction method based on DBSCAN-EM-GMM and Web technology
KR20210115911A (en) Apparatus for predicting photovoltaic ouput and method thereof
CN110796292A (en) Photovoltaic power short-term prediction method considering haze influence
CN117764547A (en) Photovoltaic string fault diagnosis method and system
CN114282637A (en) Method suitable for predicting power generation capacity of photovoltaic power station
CN113780643A (en) Photovoltaic power station short-term output prediction method based on case reasoning

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