CN111814829A - Power generation abnormity identification method and system for photovoltaic power station - Google Patents
Power generation abnormity identification method and system for photovoltaic power station Download PDFInfo
- Publication number
- CN111814829A CN111814829A CN202010515789.XA CN202010515789A CN111814829A CN 111814829 A CN111814829 A CN 111814829A CN 202010515789 A CN202010515789 A CN 202010515789A CN 111814829 A CN111814829 A CN 111814829A
- Authority
- CN
- China
- Prior art keywords
- power generation
- generation unit
- sample
- data
- photovoltaic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 222
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 238000009434 installation Methods 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a method and a system for identifying power generation abnormity of a photovoltaic power station in the technical field of photovoltaic power generation, and aims to solve the technical problems that in the prior art, manual detection and judgment of the working state of a power generation unit are long in time consumption, low in efficiency and easy to miss detection and misjudgment. The method comprises the following steps: extracting a sample data set based on pre-acquired historical operating data of the power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal; and classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data, and extracting power generation units with abnormal power generation in the photovoltaic power station.
Description
Technical Field
The invention relates to a method and a system for identifying power generation abnormity of a photovoltaic power station, and belongs to the technical field of photovoltaic power generation.
Background
In order to effectively use solar energy resources, a solar power generation system in which solar photovoltaic panels are arranged has been widely used in social production and life. The design life of a solar power generation system is as long as 25 years, so that the operation and maintenance of equipment are extremely important, and a special industry for operating and maintaining a photovoltaic power station is gradually developed at present. The large-scale photovoltaic power station comprises a large number of photovoltaic power generation units consisting of inverters and components. When people operate and maintain the photovoltaic power station, the equipment with poor power generation performance needs to be quickly found from a large number of photovoltaic power generation units, so that the operation and maintenance work effect of the photovoltaic power station is improved. At present, the conventional method is that an operator on duty judges a fault by analyzing an output curve of a photovoltaic power generation unit, and the manual detection mode is long in time consumption, low in efficiency and easy to miss detection and misjudgment. Therefore, a method for automatically identifying the power generation abnormity of the photovoltaic power station is urgently needed to timely and accurately find the power generation units with poor power generation.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method and a system for identifying power generation abnormity of a photovoltaic power station, so as to solve the technical problems that the time consumption is long, the efficiency is low, and the missing detection and the erroneous judgment are easy to occur when the working state of a power generation unit is manually detected and judged in the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a power generation abnormity identification method for a photovoltaic power station comprises the following steps:
extracting a sample data set based on pre-acquired historical operating data of the power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal;
and classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data, and extracting power generation units with abnormal power generation in the photovoltaic power station.
Further, the method for acquiring the historical operation data of the power generation unit comprises the following steps:
acquiring operation data of the power generation unit according to a preset acquisition period, wherein the operation data comprises the generated energy of the power generation unit and the equipment state;
historical operating data of the power generation unit is generated based on the operating data of not less than two continuous collection periods.
Further, after collecting the operation data of the power generation unit, the method further comprises the following steps: writing the collected operation data into a pre-established operation database, wherein the operation database comprises an accumulative power generation array and an equipment state array, and the recording structure is as follows:
E＝{t,E1,E2,…EN}，
S＝{t,S1,S2,…SN}；
in the formula, E is an accumulated power generation amount array, S is an equipment state array, t is a collection time, N is the number of power generation units in the photovoltaic power station, E1 is a daily accumulated power generation amount corresponding to the power generation unit with the number 1#, E2 is a daily accumulated power generation amount corresponding to the power generation unit with the number 2#, EN is a daily accumulated power generation amount corresponding to the power generation unit with the number N #, S1 is an equipment state corresponding to the power generation unit with the number 1#, S2 is an equipment state corresponding to the power generation unit with the number 2#, and SN is an equipment state corresponding to the power generation unit with the number N #.
Further, the historical equivalent full-power generation hours data has the following record structure:
Ei＝{[Ei(t1)-Ei(t0)]/Pi,[Ei(t2)-Ei(t1)]/Pi,[Ei(t3)-Ei(t2)]/Pi,…[Ei(tm)-Ei(tm-1)]/Pi}，
i＝1,2,…N；
wherein Ei is data of the number i # of the sample data set, i.e., the number t of historical equivalent full-power generation hours when the power generation unit is in a normal state0、t1、t2、t3、…、tm-1、tmFor m +1 measurement instants arranged in sequence, Ei (t)0)、Ei(t1)、Ei(t2)、Ei(t3)、Ei(tm-1)、…、Ei(tm) The power generation unit of number i # corresponds to the daily cumulative amount of power generation at the time of measurement when the plant state is normal, and Pi is the power generation capacity of the power generation unit of number i # [ Ei (t #) ]1)-Ei(t0)]Power generation unit with/Pi as number i #, at t0～t1Equivalent full-power generation hours during period, [ Ei (t)2)-Ei(t1)]Power generation unit with/Pi as number i #, at t1～t2Equivalent full-power generation hours during period, [ Ei (t)3)-Ei(t2)]Power generation unit with/Pi as number i #, at t2～t3Equivalent full-power generation hours during period, [ Ei (t)m)-Ei(tm-1)]Power generation unit with/Pi as number i #, at tm-1～tmEquivalent full power generation hours in the period.
Further, the method for classifying the power generation units in the photovoltaic power station comprises a K-means clustering algorithm.
Further, the method for extracting the abnormal power generation unit in the photovoltaic power station comprises the following steps:
determining K samples from the sample data set based on a preset K value to serve as an initial clustering center;
extracting any sample from the sample data set until all samples in the sample data set are traversed;
calculating the distance between the extracted sample and K initial clustering centers, classifying the extracted sample into the initial clustering center with the minimum distance to obtain K types of samples as K clustering sample sets;
extracting any one clustering sample set from the K clustering sample sets until the K clustering sample sets are traversed, calculating the average value of the samples in the extracted clustering sample sets, and determining the average value as a new clustering center of the extracted clustering sample sets;
randomly extracting one sample from the K clustering sample sets as a target sample until all samples in the K clustering sample sets are traversed, and calculating the distance between the extracted target sample and a new clustering center corresponding to the extracted target sample as a target distance;
and comparing the target distance with a preset threshold value, and extracting the power generation unit corresponding to the sample with the target distance larger than the preset threshold value as the power generation unit with abnormal power generation in the photovoltaic power station.
Further, before arbitrarily extracting one sample from the K cluster sample sets as a target sample, the method further includes:
solving a quadratic root of a difference sum of squares of new clustering centers and initial clustering centers in K clustering sample sets, and comparing the quadratic root with a preset error threshold;
and if at least any quadratic root is not less than the preset error threshold, resetting the K value.
Further, the setting method of the K value comprises the steps of setting based on the combination of at least any one of the component type, the installation mode and the inverter type of the power generation unit;
the assembly types comprise a single-sided assembly and a double-sided assembly, the installation modes comprise double-sided assembly tracking type installation, single-sided assembly tracking type installation and fixed inclination angle installation, and the inverter types comprise a string inverter and a centralized inverter.
In order to achieve the above object, the present invention further provides a power generation abnormality recognition system for a photovoltaic power station, including:
the sample data extraction module: the method comprises the steps of extracting a sample data set based on pre-acquired historical operating data of a power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal;
a sample classification and identification module: and the power generation unit is used for classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data and extracting abnormal power generation units in the photovoltaic power station.
Further, the system also comprises a historical operating data acquisition module, wherein the historical operating data acquisition module comprises:
an operation data acquisition unit: the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring operation data of the power generation unit according to a preset acquisition cycle, and the operation data comprises the generated energy of the power generation unit and the equipment state;
a historical operating data generation unit: the method is used for generating historical operating data of the power generation unit based on operating data of not less than two continuous acquisition periods.
Compared with the prior art, the invention has the following beneficial effects: based on pre-extracted operation data of each power generation unit in the photovoltaic power station, eliminating data of the power generation unit when the equipment state is abnormal or fails, and generating historical operation data when the equipment state is normal; then, the ratio of the generated energy of the power generation unit to the generated capacity is obtained based on the historical operation data, so that the historical equivalent full-power generation hours of the power generation unit are evaluated, and the historical equivalent full-power generation hours data of the power generation unit in the photovoltaic power station when the equipment state is normal are obtained; and then, determining classification according to the component type, the installation mode and the inverter type of the power generation unit, and classifying and identifying historical equivalent full-power generation time data by adopting a K-mean clustering algorithm so as to effectively extract the power generation unit with abnormal power generation in the photovoltaic power station. The method and the system can automatically identify the power generation unit with abnormal equivalent full-power generation hours in the photovoltaic power station, assist operation and maintenance personnel to quickly find faults, and are beneficial to shortening troubleshooting time, improving power generation capacity and reducing labor intensity.
Detailed Description
The invention is further described below. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The specific implementation mode of the invention provides a power generation abnormity identification method for a photovoltaic power station, which comprises the following steps:
the method comprises the following steps of firstly, acquiring operation data of each power generation unit in the photovoltaic power station according to a preset acquisition cycle, wherein the operation data are the generated energy and the equipment state of the power generation unit, writing the acquired operation data into a pre-established operation database, wherein the operation database comprises an accumulated generated energy array and an equipment state array, and the recording structure is as follows:
E＝{t,E1,E2,…EN}，
S＝{t,S1,S2,…SN}；
in the formula, E is an accumulated power generation amount array, S is an equipment state array, t is a collection time, N is the number of power generation units in the photovoltaic power station, E1 is a daily accumulated power generation amount corresponding to the power generation unit with the number 1#, E2 is a daily accumulated power generation amount corresponding to the power generation unit with the number 2#, EN is a daily accumulated power generation amount corresponding to the power generation unit with the number N #, S1 is an equipment state corresponding to the power generation unit with the number 1#, S2 is an equipment state corresponding to the power generation unit with the number 2#, and SN is an equipment state corresponding to the power generation unit with the number N #. Let Si (i ═ 1,2,3 … N), if Si is 1, indicate that the device state at the time corresponding to the power generating cell numbered i # is normal; if Si is 0, the device status is abnormal or failed.
In the photovoltaic power station, an inverter and a photovoltaic module electrically connected with the inverter form a power generation unit. At present, technicians can conveniently acquire the generated energy of each inverter. The acquisition period T of the operation data may be set in advance, and if T is set to 5 minutes, data may be acquired every five minutes 1 time. And in data acquisition, the equipment state and daily accumulated generating capacity of the power generation unit are synchronously acquired. For example:
at t0And at the acquisition moment, acquiring and writing data in the operation database, wherein the records are as follows:
{t0,E1(t0),E2(t0),E3(t0),…EN(t0)}，
{t0,S1(t0),S2(t0),S3(t0),…SN(t0)}；
at t1＝t0At the + T acquisition time, data acquired and written into the operational database are recorded as:
{t1,E1(t1),E2(t1),E3(t1),…EN(t1)}，
{t1,S1(t1),S2(t1),S3(t1),…SN(t1)}，
at tk＝tk-1At the + T acquisition time, data acquired and written into the operational database are recorded as:
{tk,E1(tk),E2(tk),E3(tk),…EN(tk)}，
{tk,S1(tk),S2(tk),S3(tk),…SN(tk)}；
historical operating data for the power generation unit may be generated based on the operating data for a number of consecutive acquisition cycles.
Step two, extracting a sample data set based on the historical operating data of the power generation unit, eliminating the historical operating data of abnormal equipment state or fault in the extraction process, wherein the sample in the sample data set is historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal, and the record structure is as follows:
Ei＝{[Ei(t1)-Ei(t0)]/Pi,[Ei(t2)-Ei(t1)]/Pi,[Ei(t3)-Ei(t2)]/Pi,…[Ei(tm)-Ei(tm-1)]/Pi}，i＝1,2,…N；
wherein Ei isHistorical equivalent full-power generation time data t of the power generation unit with the sample data set number i # when the equipment state is normal0、t1、t2、t3、…、tm-1、tmFor m +1 measurement instants arranged in sequence, Ei (t)0)、Ei(t1)、Ei(t2)、Ei(t3)、Ei(tm-1)、…、Ei(tm) The power generation unit of number i # corresponds to the daily cumulative amount of power generation at the time of measurement when the plant state is normal, and Pi is the power generation capacity of the power generation unit of number i # [ Ei (t #) ]1)-Ei(t0)]Power generation unit with/Pi as number i #, at t0～t1Equivalent full-power generation hours during period, [ Ei (t)2)-Ei(t1)]Power generation unit with/Pi as number i #, at t1～t2Equivalent full-power generation hours during period, [ Ei (t)3)-Ei(t2)]Power generation unit with/Pi as number i #, at t2～t3Equivalent full-power generation hours during period, [ Ei (t)m)-Ei(tm-1)]Power generation unit with/Pi as number i #, at tm-1～tmEquivalent full power generation hours in the period.
And thirdly, classifying all power generation units in the photovoltaic power station by adopting a K-mean clustering algorithm based on the historical equivalent full-power generation time data. Different power generation units have different component types, installation modes and inverter types, so that the corresponding equivalent full-power generation hours are obviously different, and in order to avoid misjudgment, the respective differences need to be classified and identified. Therefore, the initial K value can be set according to the combination of the component type, the installation mode and the inverter type of the power generation unit, after the initial K value is set, the power generation units adopting different component types, installation modes and inverter types are divided into K types according to the K value, and first, K samples meeting the conditions are correspondingly determined from the sample data set and serve as an initial clustering center. For example, a certain photovoltaic power station component has two component types of a single-sided component and a double-sided component, the double-sided component is installed in a tracking mode, the single-sided component is installed in a tracking mode and a fixed inclination angle mode, the double-sided component uses a string inverter, the single-sided component uses a string inverter and a centralized inverter, 5 equipment combinations are provided, namely 5 types of photovoltaic power generation power supplies are provided, and therefore the K value can be preset to be 5. And selecting historical equivalent full-power generation hours data corresponding to the power generation units respectively matched with the 5 equipment combinations from the sample data set as an initial clustering center.
And step four, defining the distance between the sample in the sample data set and the initial clustering center as the quadratic root of the square sum of the corresponding vector component difference values, calculating the distance between each sample in the sample data set and each initial clustering center, classifying the sample into the initial clustering center with the minimum distance to the initial clustering center, and finally dividing the sample in the sample data set into K types of samples, namely K clustering sample sets.
And step five, calculating the average value of all sample data in the ith clustering sample set (i is 1,2, … K) according to the classification result in the step four, and taking the average value as a new clustering center of the clustering sample set.
And sixthly, calculating the quadratic root of the difference sum of squares of the new clustering center and the original initial clustering center in each clustering sample set. If all the error values are smaller than the set error threshold value, the next step is carried out, otherwise, the step III is returned; if the number of times of the certain circulation is exceeded and the error threshold value is not reached, returning to the step three, increasing the classification number, namely increasing the K value, reselecting the sample as the initial clustering center, and then switching to the step four.
Step seven, identifying the power generation units with abnormal power generation in the photovoltaic power station according to the classification result of the step six, and specifically comprising the following steps:
randomly extracting one sample from the K clustering sample sets as a target sample until all samples in the K clustering sample sets are traversed, and calculating the distance between the extracted target sample and a new clustering center corresponding to the extracted target sample as a target distance; and comparing the target distance with a preset threshold, and if the target distance is greater than the preset threshold, determining that the corresponding power generation unit is abnormal and requiring maintenance personnel to maintain. In order to comprehensively detect and identify the power generation units with abnormal power generation, all power generation units corresponding to the samples with the target distances larger than the preset threshold value are extracted and used as the power generation units with abnormal power generation in the photovoltaic power station.
Step eight, when seasonal changes, power generation equipment changes, abnormal accuracy rate reduction identification or other relevant conditions occur, the operation should be returned to the step three, and the photovoltaic power generation units are classified again.
The specific embodiment of the invention provides a power generation abnormity identification system for a photovoltaic power station, and the method is realized based on the system of the invention and comprises the following steps:
the historical operating data acquisition module is used for executing the content in the first step of the method, and specifically comprises the following steps: 1. the operation data acquisition unit is used for acquiring operation data of the power generation unit according to a preset acquisition cycle, wherein the operation data comprises the generated energy of the power generation unit and the equipment state; 2. and the historical operating data generating unit is used for generating historical operating data of the power generating unit based on operating data of not less than two continuous acquisition periods.
The sample data extraction module: the method is used for executing the content in the second step of the method of the invention, namely: extracting a sample data set based on pre-acquired historical operating data of the power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal.
A sample classification and identification module: for carrying out the contents of steps three to seven in the aforementioned inventive method, namely: and classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data, and extracting power generation units with abnormal power generation in the photovoltaic power station.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A power generation abnormity identification method for a photovoltaic power station is characterized by comprising the following steps:
extracting a sample data set based on pre-acquired historical operating data of the power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal;
and classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data, and extracting power generation units with abnormal power generation in the photovoltaic power station.
2. The power generation abnormality recognition method for a photovoltaic power plant according to claim 1, characterized in that the acquisition method of the historical operation data of the power generation cells includes:
acquiring operation data of the power generation unit according to a preset acquisition period, wherein the operation data comprises the generated energy of the power generation unit and the equipment state;
historical operating data of the power generation unit is generated based on the operating data of not less than two continuous collection periods.
3. The method of claim 2 for identifying power generation anomalies for a photovoltaic power plant, further comprising, after collecting operational data for the power generation cells: writing the collected operation data into a pre-established operation database, wherein the operation database comprises an accumulative power generation array and an equipment state array, and the recording structure is as follows:
E＝{t,E1,E2,…EN}，
S＝{t,S1,S2,…SN}；
in the formula, E is an accumulated power generation amount array, S is an equipment state array, t is a collection time, N is the number of power generation units in the photovoltaic power station, E1 is a daily accumulated power generation amount corresponding to the power generation unit with the number 1#, E2 is a daily accumulated power generation amount corresponding to the power generation unit with the number 2#, EN is a daily accumulated power generation amount corresponding to the power generation unit with the number N #, S1 is an equipment state corresponding to the power generation unit with the number 1#, S2 is an equipment state corresponding to the power generation unit with the number 2#, and SN is an equipment state corresponding to the power generation unit with the number N #.
4. The method of claim 1, wherein the historical data of equivalent full power generation hours is recorded as follows:
Ei＝{[Ei(t1)-Ei(t0)]/Pi,[Ei(t2)-Ei(t1)]/Pi,[Ei(t3)-Ei(t2)]/Pi,…[Ei(tm)-Ei(tm-1)]/Pi}，i＝1,2,…N；
wherein Ei is data of the number i # of the sample data set, i.e., the number t of historical equivalent full-power generation hours when the power generation unit is in a normal state0、t1、t2、t3、…、tm-1、tmFor m +1 measurement instants arranged in sequence, Ei (t)0)、Ei(t1)、Ei(t2)、Ei(t3)、Ei(tm-1)、…、Ei(tm) The power generation unit of number i # corresponds to the daily cumulative amount of power generation at the time of measurement when the plant state is normal, and Pi is the power generation capacity of the power generation unit of number i # [ Ei (t #) ]1)-Ei(t0)]Power generation unit with/Pi as number i #, at t0～t1Equivalent full-power generation hours during period, [ Ei (t)2)-Ei(t1)]Power generation unit with/Pi as number i #, at t1～t2Equivalent full-power generation hours during period, [ Ei (t)3)-Ei(t2)]Power generation unit with/Pi as number i #, at t2～t3Equivalent full-power generation hours during period, [ Ei (t)m)-Ei(tm-1)]Power generation unit with/Pi as number i #, at tm-1～tmEquivalent full power generation hours in the period.
5. The method of claim 1 wherein the method of classifying each power generation unit in the photovoltaic plant comprises a K-means clustering algorithm.
6. The power generation abnormality recognition method for a photovoltaic power plant according to claim 5, characterized in that the extraction method of the power generation unit of the photovoltaic power plant having the power generation abnormality includes:
determining K samples from the sample data set based on a preset K value to serve as an initial clustering center;
extracting any sample from the sample data set until all samples in the sample data set are traversed;
calculating the distance between the extracted sample and K initial clustering centers, classifying the extracted sample into the initial clustering center with the minimum distance to obtain K types of samples as K clustering sample sets;
extracting any one clustering sample set from the K clustering sample sets until the K clustering sample sets are traversed, calculating the average value of the samples in the extracted clustering sample sets, and determining the average value as a new clustering center of the extracted clustering sample sets;
randomly extracting one sample from the K clustering sample sets as a target sample until all samples in the K clustering sample sets are traversed, and calculating the distance between the extracted target sample and a new clustering center corresponding to the extracted target sample as a target distance;
and comparing the target distance with a preset threshold value, and extracting the power generation unit corresponding to the sample with the target distance larger than the preset threshold value as the power generation unit with abnormal power generation in the photovoltaic power station.
7. The method of claim 6 for identifying power generation anomalies for a photovoltaic power plant, further comprising, prior to any extraction of one sample from the set of K clustered samples as a target sample:
solving a quadratic root of a difference sum of squares of new clustering centers and initial clustering centers in K clustering sample sets, and comparing the quadratic root with a preset error threshold;
and if at least any quadratic root is not less than the preset error threshold, resetting the K value.
8. The method according to claim 6, wherein the setting of the K value includes setting based on a combination of at least one of a component type of the power generation unit, a mounting method, and a type of inverter;
the assembly types comprise a single-sided assembly and a double-sided assembly, the installation modes comprise double-sided assembly tracking type installation, single-sided assembly tracking type installation and fixed inclination angle installation, and the inverter types comprise a string inverter and a centralized inverter.
9. A power generation abnormality recognition system for a photovoltaic power station, characterized by comprising:
the sample data extraction module: the method comprises the steps of extracting a sample data set based on pre-acquired historical operating data of a power generation unit, wherein samples in the sample data set comprise historical equivalent full-power generation time data of the power generation unit in the photovoltaic power station when the equipment state is normal;
a sample classification and identification module: and the power generation unit is used for classifying all power generation units in the photovoltaic power station based on the historical equivalent full-power generation time data and extracting abnormal power generation units in the photovoltaic power station.
10. The power generation abnormality recognition system for a photovoltaic power plant as recited in claim 8, further comprising a historical operation data acquisition module, said historical operation data acquisition module comprising:
an operation data acquisition unit: the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring operation data of the power generation unit according to a preset acquisition cycle, and the operation data comprises the generated energy of the power generation unit and the equipment state;
a historical operating data generation unit: the method is used for generating historical operating data of the power generation unit based on operating data of not less than two continuous acquisition periods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010515789.XA CN111814829A (en) | 2020-06-09 | 2020-06-09 | Power generation abnormity identification method and system for photovoltaic power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010515789.XA CN111814829A (en) | 2020-06-09 | 2020-06-09 | Power generation abnormity identification method and system for photovoltaic power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814829A true CN111814829A (en) | 2020-10-23 |
Family
ID=72846048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010515789.XA Pending CN111814829A (en) | 2020-06-09 | 2020-06-09 | Power generation abnormity identification method and system for photovoltaic power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814829A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840920A (en) * | 2022-12-30 | 2023-03-24 | 北京志翔科技股份有限公司 | Photovoltaic group string single-day separable anomaly classification method, device, equipment and storage medium |
-
2020
- 2020-06-09 CN CN202010515789.XA patent/CN111814829A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840920A (en) * | 2022-12-30 | 2023-03-24 | 北京志翔科技股份有限公司 | Photovoltaic group string single-day separable anomaly classification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539550B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
| CN107451600B (en) | Online photovoltaic hot spot fault detection method based on isolation mechanism | |
| CN109447107B (en) | On-line detection method for daily energy consumption mode abnormality of air conditioner of office building based on information entropy | |
| CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
| CN109188227A (en) | A kind of double feed wind power generator Condition assessment of insulation method and system | |
| CN112003564B (en) | Distributed photovoltaic system branch power abnormity early warning method based on intelligent terminal | |
| CN105260866A (en) | Locker box-opening fault detection method | |
| CN107359858B (en) | Realize the method that photovoltaic plant health status O&M shows control | |
| CN111814829A (en) | Power generation abnormity identification method and system for photovoltaic power station | |
| Yun et al. | Research on fault diagnosis of photovoltaic array based on random forest algorithm | |
| CN117117862B (en) | Intelligent analysis method and system for running state of solar photovoltaic system | |
| CN117290666A (en) | Photovoltaic abnormal power data cleaning method | |
| CN117318614A (en) | Photovoltaic inverter fault prediction method | |
| Liu et al. | Hierarchical context-aware anomaly diagnosis in large-scale PV systems using SCADA data | |
| CN111880090B (en) | Online fault detection method for million-kilowatt ultra-supercritical unit | |
| CN112782495A (en) | String abnormity identification method for photovoltaic power station | |
| CN109474069B (en) | Distributed power station state monitoring method | |
| CN113922758A (en) | Photovoltaic module fault diagnosis and identification system and method for mine management | |
| CN114154567A (en) | Wind power plant station operation data anomaly identification method based on machine learning | |
| CN114237206A (en) | Wind power variable pitch system fault detection method for complex operation conditions | |
| CN112381130A (en) | Cluster analysis-based power distribution room multivariate data anomaly detection method | |
| Jiao et al. | Photovoltaic Power Abnormal Data Cleaning Based on Variance Change Point and Correlation Analysis | |
| Castellà Rodil et al. | Supervision and fault detection system for photovoltaic installations based on classification algorithms | |
| Attouri et al. | Faults classification in grid-connected photovoltaic systems | |
| CN114070198B (en) | Fault diagnosis method and device for distributed photovoltaic power generation system and electronic equipment |
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 |