CN115687933A - Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium - Google Patents
Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115687933A CN115687933A CN202211714459.9A CN202211714459A CN115687933A CN 115687933 A CN115687933 A CN 115687933A CN 202211714459 A CN202211714459 A CN 202211714459A CN 115687933 A CN115687933 A CN 115687933A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- data
- day
- power time
- type
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 489
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000002708 enhancing effect Effects 0.000 claims abstract description 25
- 230000005856 abnormality Effects 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000010248 power generation Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 7
- 239000000428 dust Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000032683 aging Effects 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention provides a method, a device, equipment and a storage medium for enhancing abnormal classified data of a photovoltaic string, and relates to the technical field of photovoltaic power generation, wherein the method comprises the following steps: acquiring single-day power time sequence data of each photovoltaic group string of a target area as original sample data based on historical operating data of the target area of the photovoltaic power station; extracting single-day separable abnormal features corresponding to each abnormal type from original sample data; determining single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on the preset abnormal proportion corresponding to each abnormal type; and performing data enhancement on the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data. The invention can improve the balance of positive and negative samples, thereby improving the quality of sample data.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method, a device, equipment and a storage medium for enhancing abnormal classified data of a photovoltaic string.
Background
With the progress of photovoltaic power generation technology, the development of photovoltaic power generation is severely restricted by the problems of optimization, improvement, operation cost and the like of a photovoltaic power station. In order to prevent more serious accidents caused by faults, the abnormal classification problem of the photovoltaic strings of the photovoltaic power station is monitored in time, and the stable and efficient operation of the photovoltaic power station is facilitated.
At present, in a photovoltaic string anomaly classification monitoring scheme, an anomaly classifier can be trained through photovoltaic string sample data with an anomaly type label, and then the anomaly classifier is used for photovoltaic string anomaly classification.
However, the typical abnormal data amount in the abnormal classification sample data of the photovoltaic string is small, the abnormal sample proportion is insufficient, so that the imbalance of positive and negative samples is caused, and the trouble on the data quality is caused for the training of an abnormal classifier.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for enhancing abnormal classified data of a photovoltaic string, which are used for solving the defects that in the prior art, due to the fact that typical abnormal data amount in abnormal classified sample data of the photovoltaic string is small, abnormal sample proportion is insufficient, positive and negative samples are unbalanced, and trouble in data quality is caused to training of an abnormal classifier, the balance of the positive and negative samples is improved, and the quality of the sample data is improved.
The invention provides a photovoltaic string abnormal classified data enhancement method, which comprises the following steps:
acquiring single-day power time sequence data of each photovoltaic group string of a target area based on historical operating data of the target area of a photovoltaic power station, and taking the single-day power time sequence data as original sample data;
extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data;
determining the single-day power time series data to be enhanced in the original sample data and the abnormal type of each single-day power time series data to be enhanced based on a preset abnormal proportion corresponding to each abnormal type;
and performing data enhancement on the to-be-enhanced single-day power time series data corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain photovoltaic string abnormal classification sample data.
According to the photovoltaic string abnormal classification data enhancement method provided by the invention, the extraction of the single-day separable abnormal features corresponding to each abnormal type from the original sample data comprises the following steps:
and screening abnormal single-day power time series data from the original sample data, and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal feature corresponding to the abnormal type.
According to the method for enhancing the abnormal classified data of the photovoltaic string, provided by the invention, abnormal single-day power time series data are screened out from the original sample data, and the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal characteristic corresponding to the abnormal type are determined, wherein the method comprises the following steps:
screening out abnormal single-day power time series data with a sawtooth-shaped power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as a signal acquisition abnormal type;
and determining the characteristic of the typical fluctuation shape of the signal acquisition abnormity in the power curve of the abnormal single-day power time series data as the single-day separable abnormity characteristic corresponding to the signal acquisition abnormity type.
According to the method for enhancing the abnormal classification data of the photovoltaic string, provided by the invention, the abnormal single-day power time series data are screened out from the original sample data, and the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal characteristic corresponding to the abnormal type are determined, and the method comprises the following steps:
screening abnormal single-day power time series data with abnormal intermediate output stage of the power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as a power limiting abnormal type;
and determining the electricity-limiting abnormal critical value characteristic in the power curve of the abnormal single-day power time series data as the single-day separable abnormal characteristic corresponding to the electricity-limiting abnormal type.
According to the method for enhancing the abnormal classification data of the photovoltaic string, provided by the invention, the abnormal single-day power time series data are screened out from the original sample data, and the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal characteristic corresponding to the abnormal type are determined, and the method comprises the following steps:
screening abnormal single-day power time series data in which the generating power of the first photovoltaic string is lower than the generating power of the second photovoltaic string in the power curve from the original sample data; the first photovoltaic string and the other second photovoltaic strings belong to the same inverter;
determining the abnormal type of the abnormal single-day power time series data as an occlusion abnormal type;
and determining the shielding time interval random range characteristic of the abnormal single-day power time sequence data as the single-day separable abnormal characteristic corresponding to the shielding abnormal type.
According to the method for enhancing the abnormal classified data of the photovoltaic string, the abnormal type of the single-day power time series data to be enhanced and each single-day power time series data to be enhanced in the original sample data is determined based on the preset abnormal proportion corresponding to each abnormal type, and the method comprises the following steps:
aiming at each single-day power time series data in the original sample data, according to the priority sequence of each abnormal type and a preset abnormal proportion corresponding to the abnormal type of the current priority, determining whether the single-day power time series data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types;
if so, determining the single-day power time sequence data as the single-day power time sequence data to be enhanced corresponding to the abnormal type of the current priority;
if not, re-determining whether the single-day power time series data need to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal types of the next priority.
According to the method for enhancing the abnormal classification data of the photovoltaic string, provided by the invention, the method further comprises the following steps:
and if the single-day power time sequence data are determined not to need to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal type with the lowest priority, determining that the single-day power time sequence data do not need to be enhanced.
According to the method for enhancing the abnormal classification data of the photovoltaic string provided by the invention, the data enhancement is performed on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal feature corresponding to each abnormal type to obtain the abnormal classification sample data of the photovoltaic string, and the method comprises the following steps:
generating an enhancement function corresponding to each abnormal type based on the single-day separable abnormal features corresponding to each abnormal type;
and performing data enhancement on the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data based on the enhancement function corresponding to the abnormal type to obtain photovoltaic string abnormal classification sample data.
The invention also provides a photovoltaic string abnormal classified data enhancement device, which comprises:
the acquisition module is used for acquiring single-day power time sequence data of each photovoltaic group string of a target area based on historical operating data of the target area of the photovoltaic power station, and the single-day power time sequence data is used as original sample data;
the extraction module is used for extracting the single-day separable abnormal features corresponding to each abnormal type from the original sample data;
the determining module is used for determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on the preset abnormal proportion corresponding to each abnormal type;
and the enhancement module is used for performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal characteristics corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the photovoltaic string abnormal classification data enhancement method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for enhancing abnormal classification data of a photovoltaic string as described in any one of the above.
According to the method, the device, the equipment and the storage medium for enhancing the abnormal classified data of the photovoltaic strings, firstly, historical operation data of a target area of a photovoltaic power station are utilized to obtain single-day power time series data of each photovoltaic string of the target area, and the single-day power time series data are used as original sample data; because the typical abnormal data amount in the original sample data is small and the abnormal sample proportion is insufficient, sample data enhancement needs to be carried out on normal single-day power time series data in the original sample data; for the abnormal features required by enhancement, extracting the single-day separable abnormal features corresponding to each abnormal type from the original sample data; for normal single-day power time series data to be enhanced, determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in original sample data based on a preset abnormal proportion corresponding to each abnormal type; and finally, based on the single-day separable abnormal features corresponding to each abnormal type, performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data to obtain the photovoltaic string abnormal classification sample data.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for enhancing abnormal classification data of a photovoltaic string according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating data enhancement contrast for signal acquisition anomaly types provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of data enhancement contrast for a power-limited anomaly type provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of data enhancement contrast of an occlusion exception type according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a device for enhancing abnormal classification data of a pv string according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The abnormal classification data enhancement method of the photovoltaic string according to the present invention is described below with reference to fig. 1 to 4.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for enhancing abnormal classification data of a pv string according to an embodiment of the present invention. As shown in fig. 1, the method may include the steps of:
102, extracting single-day separable abnormal features corresponding to each abnormal type from original sample data;
103, determining single-day power time series data to be enhanced in original sample data and the abnormal type of each single-day power time series data to be enhanced based on a preset abnormal proportion corresponding to each abnormal type;
and 104, performing data enhancement on the single-day power time sequence data to be enhanced corresponding to each abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data.
In step 101, a 100MW photovoltaic power station can be divided into 80 to 100 areas in physical structure, each area has one box-type transformer, each box-type transformer has 30 to 50 string-type inverters, and each inverter has 5 to 6 string-type inverters.
The target area of the photovoltaic power station can be all areas of the whole photovoltaic power station, and can also be one area of the photovoltaic power station. That is, the whole photovoltaic power station can be used as a research object, and one area of the photovoltaic power station can also be used as a research object.
Single-day power time series data of photovoltaic string(kW) is a vector with a vector dimension of one day data acquisition points。
The historical operation data of the target area of the photovoltaic power station is utilized to obtain the single-day power time series data of each photovoltaic group string of the target area, and the single-day power time series data are used as original sample data, so that the data obtaining cost can be reduced.
In step 102, since the typical abnormal data amount in the original sample data is small, and the abnormal sample proportion is insufficient, sample data enhancement needs to be performed on the normal single-day power time series data in the original sample data. And for the abnormal features required by enhancement, extracting the single-day separable abnormal features corresponding to each abnormal type from the original sample data.
Exemplary types of anomalies for a string of photovoltaic strings include: blocking anomalies, power limiting anomalies, signal acquisition anomalies, dust anomalies, and aging anomalies. Wherein the occlusion exception may include: vegetation shelter anomaly, wall shelter anomaly, telegraph pole shelter anomaly, and the like. The electricity limiting abnormality refers to: when the power generation capacity of the photovoltaic power station is too high (namely the power generation capacity of the photovoltaic power station is greater than the power grid absorption capacity), the photovoltaic power station reduces output by adjusting the data power limit of the inverter, so that abnormity is caused. The signal acquisition abnormity refers to abnormity caused by acquisition signal loss. The dust anomaly means: because large-scale photovoltaic power plant all installs on Gobi stand or desert generally, the vegetation is less, and the dust that the dust fall is higher leads to shelters from unusually. The aging anomaly refers to: and the photovoltaic module is abnormally aged.
Moreover, the shielding abnormity, the electricity limiting abnormity and the signal acquisition abnormity belong to single-day separable abnormity, namely, the single-day power curve can be distinguished. The dust anomalies and aging anomalies are single-day inseparable anomalies, i.e., indistinguishable from a single-day power curve.
Due to the fact that the shielding abnormity, the power limiting abnormity and the signal acquisition abnormity belong to single-day separable abnormity, the dust abnormity and the aging abnormity belong to single-day inseparable abnormity, single-day separable abnormity characteristics corresponding to the shielding abnormity type, the power limiting abnormity type and the signal acquisition abnormity type are extracted from original sample data.
In step 103, the preset exception proportion corresponding to each exception type is a proportion of a sample size corresponding to each preset exception type to a sample size of the original sample data.
And for the normal single-day power time series data to be enhanced, determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on the preset abnormal proportion corresponding to each abnormal type.
Exemplarily, the single-day power time series data to be enhanced, to which the abnormal features of the shielding abnormal type, the power limiting abnormal type and the signal acquisition abnormal type need to be added, are determined based on preset abnormal proportions respectively corresponding to the shielding abnormal type, the power limiting abnormal type and the signal acquisition abnormal type.
In step 104, adding the single-day separable abnormal feature corresponding to the abnormal type to the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data by using the single-day separable abnormal feature corresponding to each abnormal type, namely performing data enhancement to obtain the photovoltaic string abnormal classification sample data.
Illustratively, a single-day separable abnormal feature corresponding to an occlusion abnormal type is added to single-day power time series data to be enhanced corresponding to the occlusion abnormal type in original sample data. And adding the single-day separable abnormal feature corresponding to the electricity limiting abnormal type to the single-day power time series data to be enhanced corresponding to the electricity limiting abnormal type in the original sample data. And adding the single-day separable abnormal features corresponding to the signal acquisition abnormal types to the single-day power time series data to be enhanced corresponding to the signal acquisition abnormal types in the original sample data.
The abnormal classification data enhancement method for the photovoltaic strings provided by the embodiment comprises the steps of firstly, obtaining single-day power time series data of each photovoltaic string in a target area as original sample data by using historical operation data of the target area of a photovoltaic power station; because the typical abnormal data amount in the original sample data is small and the abnormal sample proportion is insufficient, sample data enhancement needs to be carried out on normal single-day power time series data in the original sample data; for the abnormal features required by enhancement, extracting the single-day separable abnormal features corresponding to each abnormal type from the original sample data; for normal single-day power time series data to be enhanced, determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in original sample data based on a preset abnormal proportion corresponding to each abnormal type; and finally, based on the single-day separable abnormal features corresponding to each abnormal type, performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data to obtain photovoltaic string abnormal classification sample data.
In one embodiment, step 102 may comprise: and screening abnormal single-day power time series data from the original sample data, and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal characteristic corresponding to the abnormal type.
The abnormal single-day power time series data can be single-day power time series data with photovoltaic string abnormality in original sample data.
Specifically, abnormal single-day power time series data are screened out from original sample data, and then each abnormal single-day power time series data are analyzed to obtain abnormal types of the photovoltaic string and single-day separable abnormal features corresponding to the abnormal types.
In this embodiment, the following three specific embodiments may be included:
in a first possible implementation manner, abnormal single-day power time series data, in which the generated power of a first photovoltaic group string is lower than that of a second photovoltaic group string, in a power curve is screened out from original sample data; the first photovoltaic group string and other second photovoltaic group strings belong to the same inverter; determining the abnormal type of the abnormal single-day power time series data as an occlusion abnormal type; and determining the shielding time interval random range characteristic of the abnormal single-day power time sequence data as a single-day separable abnormal characteristic corresponding to the shielding abnormal type.
The characteristics of abnormal shielding are as follows: in the morning or afternoon, the generated power of some photovoltaic strings is slightly reduced relative to other photovoltaic strings under the same inverter.
Specifically, abnormal single-day power time series data, in which the generated power of some photovoltaic group strings (namely, a first photovoltaic group string) in the power curve is lower than that of other photovoltaic group strings (namely, a second photovoltaic group string) under the same inverter, are screened out from the original sample data. And then determining the abnormal type as an abnormal shielding type based on the characteristics of abnormal shielding. And finally, analyzing the abnormal single-day power time sequence data to obtain the shielding time period random range characteristic, and determining the shielding time period random range characteristic as the single-day separable abnormal characteristic corresponding to the shielding abnormal type.
In this embodiment, the single-day separable abnormal feature corresponding to the type of the abnormal occlusion can be extracted from the original sample data based on the characteristic of the abnormal occlusion.
In a second possible implementation mode, abnormal single-day power time series data with abnormal intermediate output stage of the power curve are screened out from original sample data; determining the abnormal type of the abnormal single-day power time series data as a power limiting abnormal type; and determining the electricity-limiting abnormal critical value characteristic in the power curve of the abnormal single-day power time series data as the single-day separable abnormal characteristic corresponding to the electricity-limiting abnormal type.
The characteristics of the electricity limiting abnormity are as follows: this typically occurs during the noon hours of a sunny day, with an abnormal intermediate output phase of the power curve.
Specifically, abnormal single-day power time series data with abnormal middle output stage of the power curve are screened out from the original sample data. And then determining the type of the abnormality as the electricity-limiting abnormality type based on the characteristics of the electricity-limiting abnormality. And finally, analyzing the abnormal single-day power time series data to obtain an electricity-limiting abnormal critical value feature, and determining the electricity-limiting abnormal critical value feature as a single-day separable abnormal feature corresponding to the electricity-limiting abnormal type.
In this embodiment, the single-day separable abnormal feature corresponding to the power-limiting abnormal type can be extracted from the original sample data based on the characteristic of the power-limiting abnormal.
In a third possible implementation manner, abnormal single-day power time series data with a sawtooth-shaped power curve are screened out from original sample data; determining the abnormal type of the abnormal single-day power time series data as a signal acquisition abnormal type; and determining the characteristic of the typical fluctuation shape of the signal acquisition abnormality in the power curve of the abnormal single-day power time series data as the single-day separable abnormality characteristic corresponding to the signal acquisition abnormality type.
The abnormal signal acquisition is characterized in that: the signal acquisition is intermittently lost, and the power curve is jagged.
Specifically, abnormal single-day power time series data with a sawtooth-shaped power curve are screened from original sample data. And then determining the abnormal type as the signal acquisition abnormal type based on the characteristics of the signal acquisition abnormality. And finally, analyzing the abnormal single-day power time series data to obtain the typical fluctuation shape characteristics of the signal acquisition abnormality, and determining the typical fluctuation shape characteristics of the signal acquisition abnormality as the single-day separable abnormality characteristics corresponding to the signal acquisition abnormality type.
In this embodiment, the single-day separable abnormal feature corresponding to the signal acquisition abnormal type may be extracted from the original sample data based on the characteristic of the signal acquisition abnormality.
In one embodiment, step 103 may comprise: aiming at each single-day power time series data in original sample data, according to the priority sequence of each abnormal type and a preset abnormal proportion corresponding to the abnormal type of the current priority, determining whether the single-day power time series data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal type of the current priority; if so, determining the single-day power time sequence data as the single-day power time sequence data to be enhanced corresponding to the abnormal type of the current priority; if not, re-determining whether the single-day power time series data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal type of the next priority according to the preset abnormal proportion corresponding to the abnormal type of the next priority.
Optionally, step 103 may further include: and if the single-day power time sequence data are determined not to need to be enhanced based on the single-day separable abnormal features corresponding to the abnormal type with the lowest priority according to the preset abnormal proportion corresponding to the abnormal type with the lowest priority, determining that the single-day power time sequence data do not need to be enhanced.
Illustratively, the priority order of the exception types is from high to low: signal acquisition exception type, power limit exception type, and occlusion exception type.
If signal acquisition is abnormal in the single-day power time series data, other abnormal conditions cannot be found, so that the type of the signal acquisition abnormal condition is the first priority. If the power limiting abnormality exists in the single-day power time-series data, the shielding abnormality cannot be found, so that the type of the power limiting abnormality is the second priority. When the single-day power time sequence data has no signal acquisition abnormality or power limiting abnormality, the shielding abnormality can be found, so that the type of the shielding abnormality is the third priority.
Aiming at each single-day power time series data in original sample data, firstly, a preset abnormal proportion corresponding to the abnormal type of signal acquisition is adoptedJudging whether the single-day power time series data need to be enhanced based on the single-day separable abnormal features corresponding to the signal acquisition abnormal types; if so, determining the single-day power time series data as single-day power time series data to be enhanced corresponding to the signal acquisition abnormal type; if not, according to the preset abnormal proportion corresponding to the electricity-limiting abnormal typeJudging whether the single-day power time series data need to be enhanced based on the single-day separable abnormal features corresponding to the power limiting abnormal types or not; if yes, determining the single-day power time series data as single-day power time series data to be enhanced corresponding to the electricity-limiting abnormal type; if not, according to a preset abnormal proportion corresponding to the shielding abnormal typeDetermining the power time series of the single dayWhether the data need to be enhanced based on the single-day separable abnormal features corresponding to the shielding abnormal types or not is determined; if so, determining the single-day power time series data as single-day power time series data to be enhanced corresponding to the shielding abnormal type; if not, determining that the single-day power time series data does not need to be enhanced.
In this embodiment, since each exception type has a priority order, the single-day power time series data is sequentially determined according to the priority order of each exception type for each single-day power time series data in the original sample data, whether the single-day power time series data needs to be enhanced can be quickly and accurately determined, if yes, the exception type of the single-day power time series data to be enhanced is determined, and if not, the single-day power time series data does not need to be enhanced.
In an embodiment, step 104 may include the following sub-steps:
step 1041, generating an enhancement function corresponding to each abnormal type based on the single-day separable abnormal features corresponding to each abnormal type;
and 1042, performing data enhancement on the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data based on the enhancement function corresponding to the abnormal type to obtain the photovoltaic string abnormal classification sample data.
Specifically, step 1041 may include the following sub-steps:
step 10411, generating an enhancement function corresponding to the type of the occlusion anomaly based on the random range feature and the random proportion of the occlusion period;
step 10412, generating an enhancement function corresponding to the electricity limiting abnormal type based on the electricity limiting abnormal critical value feature;
and 10413, generating an enhancement function corresponding to the signal acquisition abnormity type based on the typical fluctuation shape characteristics of the signal acquisition abnormity and the random proportion.
In step 10411, an enhancement function corresponding to the occlusion anomaly type may be generated by expression (1):
wherein the content of the first and second substances,representing an enhancement function corresponding to the type of the occlusion abnormity;expressing a random proportion, wherein the random proportion is used for expressing the abnormal degree and obeys normal distribution;representing the characteristic vector of the random range of the vegetation shielding period, the dimension of the vector and the single-day power time sequence data of the photovoltaic string(kW) consistent;and representing single-day power time series data corresponding to the type of the abnormal occlusion to be enhanced.
In step 10412, an enhancement function corresponding to the electricity-limiting anomaly type may be generated by expression (2):
wherein the content of the first and second substances,an enhancement function corresponding to the power limiting abnormity type is represented;indicating a power-limiting abnormal threshold value,and representing single-day power time series data corresponding to the power limiting abnormity type to be enhanced.
In step 10413, an enhancement function corresponding to the signal acquisition anomaly type may be generated through expression (3):
wherein the content of the first and second substances,representing an enhancement function corresponding to the signal acquisition abnormity type;expressing a random proportion, wherein the random proportion is used for expressing the abnormal degree and obeys normal distribution;representing a characteristic vector of a typical fluctuation shape of signal acquisition abnormity;and the single-day power time sequence data corresponding to the signal acquisition abnormity type to be enhanced is represented.
Specifically, step 1042 may include the following sub-steps:
step 10421, based on the enhancement function corresponding to the signal acquisition exception type, performing data enhancement on the single-day power time series data to be enhanced corresponding to the signal acquisition exception type in the original sample data;
step 10422, performing data enhancement on the to-be-enhanced single-day power time series data corresponding to the power limiting abnormal type in the original sample data based on the enhancement function corresponding to the power limiting abnormal type;
and 10423, performing data enhancement on the single-day power time series data to be enhanced, corresponding to the shielding abnormal type in the original sample data, based on the enhancement function corresponding to the shielding abnormal type.
In step 10421, as shown in fig. 2, a power curve of original data (i.e., the single-day power time-series data to be enhanced corresponding to the signal acquisition exception type) in the original sample data is normal, after data enhancement is performed by using an enhancement function corresponding to the signal acquisition exception type, signal acquisition is intermittently absent, and the power curve is jagged. Moreover, for different single-day power time series data to be enhanced, the abnormal degree of signal acquisition abnormality is normally distributed, and the diversification of samples can be realized.
In step 10422, as shown in fig. 3, a power curve of original data (i.e., the single-day power time-series data to be enhanced corresponding to the power-limiting abnormality type) in the original sample data is normal, and after data enhancement is performed by using an enhancement function corresponding to the power-limiting abnormality type, an intermediate output stage of the power curve is abnormal.
In step 10423, as shown in fig. 4, a power curve of original data (i.e., the single-day power time-series data to be enhanced corresponding to the abnormal blocking type) in the original sample data is normal, and after data enhancement is performed by using the enhancement function corresponding to the abnormal blocking type, the generated power of some pv strings is slightly decreased relative to other pv strings under the same inverter in the morning. Moreover, for different single-day power time sequence data to be enhanced, abnormal shielding degree is normally distributed, and diversification of samples can be realized.
In the embodiment, because typical abnormal data amount in the original sample data is less, and the proportion of abnormal samples is insufficient, the normal single-day power time series data in the original sample data can be subjected to data enhancement by adopting an enhancement function according to the characteristics of different abnormal types (such as a signal acquisition abnormal type, a power limiting abnormal type and a shielding abnormal type), so that the balance of positive and negative samples can be improved, and the quality of the sample data is improved.
The abnormal classified data enhancement device for pv strings provided by the present invention is described below, and the abnormal classified data enhancement device for pv strings described below and the abnormal classified data enhancement method for pv strings described above can be referred to each other.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a device for enhancing abnormal classification data of a pv string according to an embodiment of the present invention. As shown in fig. 5, the apparatus may include:
the acquisition module 10 is configured to acquire single-day power time series data of each photovoltaic group string in a target area of a photovoltaic power station based on historical operating data of the target area, and use the single-day power time series data as original sample data;
an extracting module 20, configured to extract, from the original sample data, a single-day separable abnormal feature corresponding to each abnormal type;
the determining module 30 is configured to determine, based on a preset anomaly ratio corresponding to each anomaly type, to-be-enhanced single-day power time series data in the original sample data and an anomaly type of each to-be-enhanced single-day power time series data;
and the enhancing module 40 is configured to perform data enhancement on the to-be-enhanced single-day power time series data corresponding to each exception type in the original sample data based on the single-day separable exception features corresponding to each exception type, so as to obtain photovoltaic string exception classification sample data.
Optionally, the extraction module 20 is specifically configured to: and screening abnormal single-day power time series data from the original sample data, and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal feature corresponding to the abnormal type.
Optionally, the extraction module 20 is specifically configured to:
screening out abnormal single-day power time series data with a sawtooth-shaped power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as a signal acquisition abnormal type;
and determining the characteristic of the typical fluctuation shape of the abnormal signal acquisition in the power curve of the abnormal single-day power time series data as the single-day separable abnormal characteristic corresponding to the abnormal type of the signal acquisition.
Optionally, the extraction module 20 is specifically configured to:
screening abnormal single-day power time series data with abnormal intermediate output stage of the power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as a power limiting abnormal type;
and determining the electricity-limiting abnormal critical value characteristic in the power curve of the abnormal single-day power time series data as the single-day separable abnormal characteristic corresponding to the electricity-limiting abnormal type.
Optionally, the extraction module 20 is specifically configured to:
screening abnormal single-day power time series data in which the generating power of the first photovoltaic group string is lower than that of the second photovoltaic group string in the power curve from the original sample data; the first photovoltaic group string and the other second photovoltaic group strings belong to the same inverter;
determining the abnormal type of the abnormal single-day power time series data as an occlusion abnormal type;
and determining the shielding time interval random range characteristic of the abnormal single-day power time sequence data as the single-day separable abnormal characteristic corresponding to the shielding abnormal type.
Optionally, the determining module 30 is specifically configured to:
according to each single-day power time sequence data in the original sample data, determining whether the single-day power time sequence data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the priority sequence of each abnormal type and the preset abnormal proportion corresponding to the abnormal type of the current priority;
if so, determining the single-day power time sequence data as the single-day power time sequence data to be enhanced corresponding to the abnormal type of the current priority;
if not, re-determining whether the single-day power time series data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal types of the next priority.
Optionally, the determining module 30 is further configured to:
and if the single-day power time sequence data are determined not to need to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal type with the lowest priority, determining that the single-day power time sequence data do not need to be enhanced.
Optionally, the enhancing module 40 is specifically configured to:
generating an enhancement function corresponding to each abnormal type based on the single-day separable abnormal features corresponding to each abnormal type;
and performing data enhancement on the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data based on the enhancement function corresponding to the abnormal type to obtain photovoltaic string abnormal classification sample data.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor) 610, a communication Interface 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 complete communication with each other through the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a photovoltaic string anomaly classification data enhancement method comprising:
acquiring single-day power time series data of each photovoltaic group string in a target area based on historical operation data of the target area of a photovoltaic power station, and taking the single-day power time series data as original sample data;
extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data;
determining the single-day power time series data to be enhanced in the original sample data and the abnormal type of each single-day power time series data to be enhanced based on a preset abnormal proportion corresponding to each abnormal type;
and performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data.
In addition, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the method for enhancing abnormal classification data of photovoltaic strings provided by the above methods, the method includes:
acquiring single-day power time sequence data of each photovoltaic group string of a target area based on historical operating data of the target area of a photovoltaic power station, and taking the single-day power time sequence data as original sample data;
extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data;
determining the single-day power time series data to be enhanced in the original sample data and the abnormal type of each single-day power time series data to be enhanced based on a preset abnormal proportion corresponding to each abnormal type;
and performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the above-mentioned each provided method for enhancing abnormal classification data of a pv string, the method comprising:
acquiring single-day power time sequence data of each photovoltaic group string of a target area based on historical operating data of the target area of a photovoltaic power station, and taking the single-day power time sequence data as original sample data;
extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data;
determining single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on a preset abnormal proportion corresponding to each abnormal type;
and performing data enhancement on the to-be-enhanced single-day power time series data corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain photovoltaic string abnormal classification sample data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (11)
1. A photovoltaic string abnormal classification data enhancement method is characterized by comprising the following steps:
acquiring single-day power time series data of each photovoltaic group string in a target area based on historical operation data of the target area of a photovoltaic power station, and taking the single-day power time series data as original sample data;
extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data;
determining single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on a preset abnormal proportion corresponding to each abnormal type;
and performing data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal features corresponding to each abnormal type to obtain the photovoltaic string abnormal classification sample data.
2. The method according to claim 1, wherein the extracting single-day separable abnormal features corresponding to each abnormal type from the original sample data includes:
and screening abnormal single-day power time series data from the original sample data, and determining an abnormal type of the abnormal single-day power time series data and a single-day separable abnormal characteristic corresponding to the abnormal type.
3. The method for enhancing abnormal classified data of photovoltaic string according to claim 2, wherein the step of screening abnormal single-day power time series data from the original sample data and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal feature corresponding to the abnormal type comprises:
screening out abnormal single-day power time series data with a sawtooth-shaped power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as a signal acquisition abnormal type;
and determining the characteristic of the typical fluctuation shape of the signal acquisition abnormity in the power curve of the abnormal single-day power time series data as the single-day separable abnormity characteristic corresponding to the signal acquisition abnormity type.
4. The method for enhancing abnormal classified data of photovoltaic string according to claim 2, wherein the screening out abnormal single-day power time series data from the original sample data and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal feature corresponding to the abnormal type comprises:
screening abnormal single-day power time series data with abnormal intermediate output stage of the power curve from the original sample data;
determining the abnormal type of the abnormal single-day power time series data as an electricity limiting abnormal type;
and determining the electricity-limiting abnormal critical value characteristic in the power curve of the abnormal single-day power time series data as the single-day separable abnormal characteristic corresponding to the electricity-limiting abnormal type.
5. The method for enhancing abnormal classified data of photovoltaic string according to claim 2, wherein the screening out abnormal single-day power time series data from the original sample data and determining the abnormal type of the abnormal single-day power time series data and the single-day separable abnormal feature corresponding to the abnormal type comprises:
screening abnormal single-day power time series data in which the generating power of the first photovoltaic group string is lower than that of the second photovoltaic group string in the power curve from the original sample data; the first photovoltaic group string and the other second photovoltaic group strings belong to the same inverter;
determining the abnormal type of the abnormal single-day power time series data as an occlusion abnormal type;
and determining the shielding time interval random range characteristic of the abnormal single-day power time sequence data as the single-day separable abnormal characteristic corresponding to the shielding abnormal type.
6. The method for enhancing abnormal classified data of photovoltaic string according to any one of claims 1 to 5, wherein the determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on the preset abnormal proportion corresponding to each abnormal type comprises:
according to each single-day power time sequence data in the original sample data, determining whether the single-day power time sequence data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the priority sequence of each abnormal type and the preset abnormal proportion corresponding to the abnormal type of the current priority;
if so, determining the single-day power time sequence data as the single-day power time sequence data to be enhanced corresponding to the abnormal type of the current priority;
if not, re-determining whether the single-day power time series data needs to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal types of the next priority.
7. The method of enhancing abnormal classification data of photovoltaic string according to claim 6, further comprising:
and if the single-day power time sequence data are determined not to need to be enhanced based on the single-day separable abnormal features corresponding to the abnormal types according to the preset abnormal proportion corresponding to the abnormal type with the lowest priority, determining that the single-day power time sequence data do not need to be enhanced.
8. The method according to any one of claims 1 to 5, wherein the data enhancement of the single-day power time-series data to be enhanced corresponding to the anomaly type in the original sample data based on the single-day separable anomaly feature corresponding to each anomaly type is performed to obtain sample data of the abnormal classification of the photovoltaic string, including:
generating an enhancement function corresponding to each abnormal type based on the single-day separable abnormal features corresponding to each abnormal type;
and performing data enhancement on the single-day power time series data to be enhanced corresponding to the abnormal type in the original sample data based on an enhancement function corresponding to the abnormal type to obtain the photovoltaic string abnormal classification sample data.
9. A photovoltaic string abnormal classification data enhancement device is characterized by comprising:
the acquisition module is used for acquiring single-day power time sequence data of each photovoltaic group string of a target area based on historical operating data of the target area of the photovoltaic power station, and the single-day power time sequence data is used as original sample data;
the extraction module is used for extracting the single-day separable abnormal features corresponding to each abnormal type from the original sample data;
the determining module is used for determining the single-day power time series data to be enhanced and the abnormal type of each single-day power time series data to be enhanced in the original sample data based on the preset abnormal proportion corresponding to each abnormal type;
and the enhancement module is used for carrying out data enhancement on the single-day power time sequence data to be enhanced corresponding to the abnormal type in the original sample data based on the single-day separable abnormal characteristic corresponding to each abnormal type to obtain photovoltaic string abnormal classification sample data.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method for photovoltaic string abnormality classification data enhancement according to any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for enhancing abnormal classification data of a photovoltaic string according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211714459.9A CN115687933A (en) | 2022-12-30 | 2022-12-30 | Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211714459.9A CN115687933A (en) | 2022-12-30 | 2022-12-30 | Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115687933A true CN115687933A (en) | 2023-02-03 |
Family
ID=85057255
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211714459.9A Pending CN115687933A (en) | 2022-12-30 | 2022-12-30 | Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115687933A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109271736A (en) * | 2018-10-12 | 2019-01-25 | 阳光电源股份有限公司 | The fault type judges method and device of photovoltaic module |
CN110544039A (en) * | 2019-09-06 | 2019-12-06 | 阳光电源股份有限公司 | Method and device for identifying shadow occlusion of photovoltaic string |
CN112668661A (en) * | 2020-12-31 | 2021-04-16 | 新奥数能科技有限公司 | Identification method and device for photovoltaic power abnormal data |
CN114416467A (en) * | 2021-12-22 | 2022-04-29 | 新华三大数据技术有限公司 | Anomaly detection method and device |
CN114511063A (en) * | 2021-12-31 | 2022-05-17 | 国网冀北电力有限公司信息通信分公司 | Power data prediction model construction method, device, apparatus, medium, and program |
CN114898232A (en) * | 2022-04-29 | 2022-08-12 | 中科云尚(南京)智能技术有限公司 | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis |
-
2022
- 2022-12-30 CN CN202211714459.9A patent/CN115687933A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109271736A (en) * | 2018-10-12 | 2019-01-25 | 阳光电源股份有限公司 | The fault type judges method and device of photovoltaic module |
CN110544039A (en) * | 2019-09-06 | 2019-12-06 | 阳光电源股份有限公司 | Method and device for identifying shadow occlusion of photovoltaic string |
CN112668661A (en) * | 2020-12-31 | 2021-04-16 | 新奥数能科技有限公司 | Identification method and device for photovoltaic power abnormal data |
CN114416467A (en) * | 2021-12-22 | 2022-04-29 | 新华三大数据技术有限公司 | Anomaly detection method and device |
CN114511063A (en) * | 2021-12-31 | 2022-05-17 | 国网冀北电力有限公司信息通信分公司 | Power data prediction model construction method, device, apparatus, medium, and program |
CN114898232A (en) * | 2022-04-29 | 2022-08-12 | 中科云尚(南京)智能技术有限公司 | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Schäfer et al. | Detection of gravitational-wave signals from binary neutron star mergers using machine learning | |
CN105894177B (en) | Power equipment operation risk analysis and evaluation method based on decision tree algorithm | |
CN103729557B (en) | Static N-X batch processing method based on PSD-BPA | |
CN108364117B (en) | Power grid risk assessment method considering reliability of photovoltaic power station element | |
CN112115999B (en) | Wind turbine generator fault diagnosis method of space-time multi-scale neural network | |
CN109409444B (en) | Multivariate power grid fault type discrimination method based on prior probability | |
CN116933114B (en) | CNN-LSTM-based direct-current micro-grid detection method and device | |
CN112598148A (en) | Fan variable pitch motor temperature fault early warning method based on collaborative expression and LightGBM algorithm | |
CN111177193A (en) | Flink-based log streaming processing method and system | |
CN115759365A (en) | Photovoltaic power generation power prediction method and related equipment | |
CN111404150A (en) | Transient stability assessment method and system suitable for large power grid operation | |
CN115840920A (en) | Photovoltaic group string single-day separable anomaly classification method, device, equipment and storage medium | |
CN115687933A (en) | Photovoltaic string abnormal classification data enhancement method, device, equipment and storage medium | |
CN110865329B (en) | Electric energy metering method and system based on big data self-diagnosis | |
CN111193289B (en) | Photovoltaic power station parallel mismatch adjusting method and device | |
CN110045197B (en) | Distribution network fault early warning method | |
CN114281846B (en) | New energy power generation prediction method based on machine learning | |
CN116452054A (en) | Method and device for managing material spot check of electric power system | |
CN112783775B (en) | Special character input testing method and device | |
CN110687344B (en) | Single-phase voltage sag detection method and device, voltage restorer, equipment and medium | |
CN111209158B (en) | Mining monitoring method and cluster monitoring system for server cluster | |
CN109888338B (en) | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics | |
CN114417918A (en) | Method for extracting wind power plant signal characteristics and denoising optimization data | |
CN112163695A (en) | Copula function-based wind power photovoltaic power generation prediction method, system and medium | |
CN105186494A (en) | Electric network analysis system and method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230203 |
|
RJ01 | Rejection of invention patent application after publication |