CN115081552A - Solar cell data exception handling method and system based on cloud platform - Google Patents

Solar cell data exception handling method and system based on cloud platform Download PDF

Info

Publication number
CN115081552A
CN115081552A CN202210894431.1A CN202210894431A CN115081552A CN 115081552 A CN115081552 A CN 115081552A CN 202210894431 A CN202210894431 A CN 202210894431A CN 115081552 A CN115081552 A CN 115081552A
Authority
CN
China
Prior art keywords
power generation
solar cell
generation data
data
sequence
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210894431.1A
Other languages
Chinese (zh)
Other versions
CN115081552B (en
Inventor
周超
蔡敬国
舒华富
章康平
李斌
王建明
宋登元
朴松源
刘勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yidao New Energy Technology Co ltd
Original Assignee
Das Solar Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Das Solar Co Ltd filed Critical Das Solar Co Ltd
Priority to CN202210894431.1A priority Critical patent/CN115081552B/en
Publication of CN115081552A publication Critical patent/CN115081552A/en
Application granted granted Critical
Publication of CN115081552B publication Critical patent/CN115081552B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2474—Sequence data queries, e.g. querying versioned data
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/34—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering
    • H02J7/35—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering with light sensitive cells
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy

Abstract

The invention provides a solar cell data exception handling method and system based on a cloud platform, and relates to the technical field. In the invention, for each solar cell, continuous power generation data acquisition is carried out on the solar cell to form a corresponding power generation data sequence. And for each solar cell, performing first power generation abnormity analysis according to the corresponding power generation data sequence, and outputting a corresponding first power generation abnormity degree. And for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a corresponding second power generation abnormity degree, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell. Based on the above, the reliability of the exception handling of the solar cell data can be improved.

Description

Solar cell data exception handling method and system based on cloud platform
Technical Field
The invention relates to the technical field of cloud computing, in particular to a solar cell data exception handling method and system based on a cloud platform.
Background
Cloud services are a way of providing data computing and data storage services by network resources, wherein cloud services generally include cloud computing services and cloud storage services. For cloud computing, the computing resources are dynamically extensible, and computing tasks can be processed in a distributed mode through distributed computing nodes. Therefore, the application of the cloud computing technology can improve the computing efficiency to a greater extent. For example, in the application to monitoring of solar power generation, the degree of power generation abnormality can be efficiently analyzed, but in the prior art, the abnormality analysis is generally performed individually for a large number of solar cells, so that there is a problem that the reliability of the abnormality analysis is not good.
Disclosure of Invention
In view of this, the present invention provides a method and a system for exception handling of solar cell data based on a cloud platform, so as to improve the reliability of exception handling of the solar cell data.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a solar cell data exception handling method based on a cloud platform is applied to the data processing cloud platform and comprises the following steps:
for each solar cell, continuously acquiring power generation data of the solar cell to form a power generation data sequence corresponding to the solar cell, wherein the power generation data sequence comprises a plurality of cell power generation data with time precedence relationship, and the number of the solar cells is multiple;
for each solar cell, performing first power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell, and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree indicates the power generation abnormity degree of the solar cell;
and for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormity degree corresponding to the solar cell, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell, wherein the target power generation abnormity degree indicates the power generation abnormity degree of the solar cell.
In some preferred embodiments, in the cloud platform-based solar cell data exception handling method, the step of performing continuous power generation data acquisition on each solar cell to form a power generation data sequence corresponding to the solar cell includes:
for each solar cell, in the current power generation abnormity analysis period, issuing a data acquisition instruction to the data acquisition equipment corresponding to the solar cell at preset intervals, so that the data acquisition equipment acquires data of the solar cell according to the data acquisition instruction;
and for each solar cell, constructing and forming a power generation data sequence corresponding to the solar cell according to power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell.
In some preferred embodiments, in the cloud platform-based solar cell data exception handling method, for each solar cell, the step of constructing a power generation data sequence corresponding to the solar cell according to each piece of cell power generation data collected by the data collection device corresponding to the solar cell includes:
for each solar cell, in the current power generation abnormity analysis period, sequentially receiving power generation data of each cell acquired by data acquisition equipment corresponding to the solar cell, and transmitting the power generation data of each cell to the data processing cloud platform after the data acquisition equipment acquires the power generation data of each cell;
for each solar cell, after receiving power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell, sequencing the received power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell according to the receiving time or the sending time corresponding to the power generation data of each cell to form a power generation data sequence corresponding to the solar cell.
In some preferred embodiments, in the cloud platform-based solar cell data abnormality processing method, for each of the solar cells, the step of performing a first power generation abnormality analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and outputting a first power generation abnormality degree corresponding to the solar cell includes:
for each solar cell, determining the data fluctuation degree of the solar cell according to each cell power generation data included in the power generation data sequence corresponding to the solar cell so as to output the power generation data fluctuation degree corresponding to the solar cell;
for each solar cell, performing first power generation abnormity analysis on the solar cell according to the power generation data fluctuation degree corresponding to the solar cell, and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree is positively correlated with the power generation data fluctuation degree.
In some preferred embodiments, in the cloud platform-based solar cell data exception handling method, for each solar cell, the step of determining a data fluctuation degree of the solar cell according to each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell to output the power generation data fluctuation degree corresponding to the solar cell includes:
for each solar cell, fitting a curve according to power generation data of each cell included in the power generation data sequence corresponding to the solar cell and data characteristic time corresponding to the power generation data of each cell to form a target fitting curve corresponding to the solar cell, wherein the data characteristic time indicates data sending time or data receiving time corresponding to the power generation data of the corresponding cell;
for each solar cell, calculating the fitting deviation of each cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell respectively so as to output the fitting deviation corresponding to each cell power generation data;
for each solar cell, fusing the fitting deviation degree corresponding to each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell, outputting a first data fluctuation degree corresponding to the solar cell, respectively calculating the absolute difference value of every two adjacent pieces of cell power generation data included in the power generation data sequence corresponding to the solar cell, outputting the data absolute difference value between every two adjacent pieces of cell power generation data, then summing the data absolute difference values between every two adjacent pieces of cell power generation data, outputting a data difference value corresponding to the solar cell, and then determining a second data fluctuation degree with positive correlation according to the data difference value;
and for each solar cell, fusing the first data fluctuation degree and the second data fluctuation degree corresponding to the solar cell, and outputting the power generation data fluctuation degree corresponding to the solar cell.
In some preferred embodiments, in the cloud platform-based solar cell data exception handling method, for each solar cell, the step of calculating a deviation degree of fit between each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell to output the deviation degree of fit corresponding to each piece of cell power generation data includes:
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating corresponding fitting data of data characteristic time corresponding to the battery power generation data according to a target fitting curve corresponding to the solar battery so as to output fitting battery power generation data corresponding to the battery power generation data, wherein a two-dimensional coordinate point formed by the fitting battery power generation data and the corresponding data characteristic time is on the corresponding target fitting curve;
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating the absolute difference value of the fitting battery power generation data corresponding to the battery power generation data and the battery power generation data to output the power generation data absolute difference value corresponding to the battery power generation data;
and for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating the ratio of the absolute difference of the power generation data corresponding to the battery power generation data so as to output the fitting deviation degree corresponding to the battery power generation data.
In some preferred embodiments, in the cloud platform-based solar cell data abnormality processing method, for each of the solar cells, the step of performing a second power generation abnormality analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormality degree corresponding to the solar cell, fusing the second power generation abnormality degree and the first power generation abnormality degree corresponding to the solar cell, and outputting a target power generation abnormality degree corresponding to the abnormal solar cell includes:
for every two solar cells, calculating the similarity of the two power generation data sequences corresponding to the two solar cells, and outputting the data sequence similarity between the two solar cells;
for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the data sequence similarity between the solar cell and each other solar cell, and outputting a second power generation abnormity degree corresponding to the solar cell;
and for each solar cell, fusing the first power generation abnormality degree and the second power generation abnormality degree corresponding to the solar cell, and outputting the target power generation abnormality degree corresponding to the solar cell.
In some preferred embodiments, in the cloud platform-based solar cell data exception handling method, for every two solar cells, the step of calculating the similarity between two power generation data sequences corresponding to the two solar cells and outputting the data sequence similarity between the two solar cells includes:
randomly combining first battery power generation data included in a first power generation data sequence according to a target value to form a plurality of first power generation data sets corresponding to the first power generation data sequence, wherein the quantity of the first battery power generation data included in each first power generation data set is equal to the target value, and screening each corresponding second battery power generation data from a second power generation data sequence according to the sequence position of each first battery power generation data included in the first power generation data sequence for each first power generation data set to form a second power generation data set corresponding to the first power generation data set;
for each first power generation data set, determining target characteristic time corresponding to the first power generation data set according to data acquisition time corresponding to each first battery power generation data included in the first power generation data set, sequencing each first power generation data set according to the target characteristic time corresponding to each first power generation data set to form a first set sequence, for each second power generation data set, determining target characteristic time corresponding to the second power generation data set according to data acquisition time corresponding to each second battery power generation data included in the second power generation data set, and sequencing each second power generation data set according to the target characteristic time corresponding to each second power generation data set to form a second set sequence;
for each first power generation data set, respectively calculating an absolute difference value of every two first battery power generation data included in the first power generation data set to output a first absolute difference value set corresponding to the first power generation data set, then constructing and forming a first set internal feature vector corresponding to the first power generation data set according to each first absolute difference value included in the first absolute difference value set, and constructing and forming a corresponding first set internal feature vector sequence according to a first set internal feature vector corresponding to each first power generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of every two pieces of second battery power generation data included in the second power generation data set to output a second absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set internal feature vector corresponding to the second power generation data set according to each second absolute difference value included in the second absolute difference value set, and constructing and forming a corresponding second set internal feature vector sequence according to a second set internal feature vector corresponding to each second power generation data set included in the second set sequence;
for each first electricity generation data set, respectively calculating an absolute difference value of each first battery electricity generation data included in the first electricity generation data set and each first battery electricity generation data included in an adjacent previous first electricity generation data set to output a third absolute difference value set corresponding to the first electricity generation data set, then constructing and forming a first set external feature vector corresponding to the first electricity generation data set according to each third absolute difference value included in the third absolute difference value set, and constructing and forming a corresponding first set external feature vector sequence according to the first set external feature vector corresponding to each first electricity generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of each second battery power generation data included in the second power generation data set and each second battery power generation data included in an adjacent previous second power generation data set to output a fourth absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set external feature vector corresponding to the second power generation data set according to each fourth absolute difference value included in the fourth absolute difference value set, and constructing and forming a corresponding second set external feature vector sequence according to a second set external feature vector corresponding to each second power generation data set included in the second set sequence;
according to the vector similarity between the feature vectors of corresponding sequence positions, calculating the similarity of the first set internal feature vector sequence and the second set internal feature vector sequence, outputting the internal feature similarity, calculating the similarity of the first set external feature vector sequence and the second set external feature vector sequence, outputting the external feature similarity, fusing the internal feature similarity and the external feature similarity, and outputting the data sequence similarity between two solar cells corresponding to the two power generation data sequences.
In some preferred embodiments, in the cloud platform-based solar cell data abnormality processing method, the step of performing, for each of the solar cells, second power generation abnormality analysis on the solar cell according to a data sequence similarity between the solar cell and each of the other solar cells, and outputting a second power generation abnormality degree corresponding to the solar cell includes:
for each solar cell, screening the data sequence similarity between the solar cell and each other solar cell, and outputting at least one target data sequence similarity corresponding to the solar cell, wherein in the data sequence similarity between the solar cell and each other solar cell, if at least one data sequence similarity greater than or equal to a similarity reference value exists, the data sequence similarity is marked as the target data sequence similarity, and if at least one data sequence similarity greater than or equal to the similarity reference value does not exist, the data sequence similarity with the maximum value is marked as the target data sequence similarity;
for each solar cell, marking other solar cells corresponding to each target data sequence similarity in at least one target data sequence similarity corresponding to the solar cell as related solar cells corresponding to the solar cell;
and for each solar cell, fusing the first power generation abnormality degree corresponding to each relevant solar cell according to the data sequence similarity between the solar cell and each corresponding relevant solar cell, and outputting the second power generation abnormality degree corresponding to the solar cell.
The embodiment of the invention also provides a solar cell data exception handling system based on the cloud platform, which is applied to the data processing cloud platform, and the solar cell data exception handling system comprises:
the generating data acquisition module is used for continuously acquiring generating data of each solar cell to form a generating data sequence corresponding to the solar cell, wherein the generating data sequence comprises a plurality of cell generating data with time sequence relation, and the number of the solar cells is multiple;
the power generation abnormity analysis module is used for carrying out first power generation abnormity analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree indicates the power generation abnormity degree of the solar cell;
and the power generation abnormity degree determination module is used for carrying out second power generation abnormity analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormity degree corresponding to the solar cell, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell, wherein the target power generation abnormity degree indicates the power generation abnormity degree of the solar cell.
According to the solar cell data exception handling method and system based on the cloud platform, provided by the embodiment of the invention, for each solar cell, continuous power generation data collection is carried out on the solar cell, and a corresponding power generation data sequence is formed. And for each solar cell, performing first power generation abnormity analysis according to the corresponding power generation data sequence, and outputting a corresponding first power generation abnormity degree. And for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a corresponding second power generation abnormity degree, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell. In the foregoing, not only the abnormality analysis is performed on the solar cell alone to obtain the first power generation abnormality degree, but also the correlated abnormality analysis is performed in combination with the battery power generation data of the other solar cells to obtain the second power generation abnormality degree, so that the target power generation abnormality degree can be determined in combination with the power generation abnormality degrees in both aspects, thereby improving the reliability of the abnormality processing on the solar cell data.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a schematic flowchart illustrating steps included in a cloud platform-based solar cell data exception handling method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of modules included in a cloud platform-based solar cell data exception handling system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the 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 embodiment of the invention provides a data processing cloud platform.
It should be understood that in some embodiments, the data processing cloud platform may include a memory and a processor. In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the cloud platform-based solar cell data exception handling method provided by the embodiment of the present invention.
It should be understood that in some embodiments, the Memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
It should be appreciated that in some embodiments, the data processing cloud platform may be a server with data processing capabilities (which may be a cloud system of multiple servers).
Referring to fig. 1, an embodiment of the present invention further provides a method for processing a data exception of a solar cell based on a cloud platform, which can be applied to the data processing cloud platform. The method steps defined by the flow related to the cloud platform-based solar cell data exception handling method can be realized by the data processing cloud platform. The specific process shown in FIG. 1 will be described in detail below.
Step S110, for each solar cell, performing continuous power generation data acquisition on the solar cell to form a power generation data sequence corresponding to the solar cell.
In the embodiment of the invention, the data processing cloud platform may perform continuous power generation data acquisition on each solar cell to form a power generation data sequence corresponding to the solar cell. The power generation data sequence comprises a plurality of battery power generation data (such as output current) with time sequence relations, and the number of the solar batteries is multiple.
Step S120, for each solar cell, according to the power generation data sequence corresponding to the solar cell, performing a first power generation abnormality analysis on the solar cell, and outputting a first power generation abnormality degree corresponding to the solar cell.
In the embodiment of the present invention, for each solar cell, the data processing cloud platform may perform a first power generation abnormality analysis on the solar cell according to the power generation data sequence corresponding to the solar cell, and output a first power generation abnormality degree corresponding to the solar cell. The first power generation abnormality degree indicates a degree of abnormality in power generation of the solar cell.
Step S130, for each of the solar cells, according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, performing a second power generation abnormality analysis on the solar cell, outputting a second power generation abnormality degree corresponding to the solar cell, and then fusing the second power generation abnormality degree and the first power generation abnormality degree corresponding to the solar cell, and outputting a target power generation abnormality degree corresponding to the solar cell.
In the embodiment of the present invention, for each solar cell, the data processing cloud platform may perform a second power generation abnormality analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, output a second power generation abnormality degree corresponding to the solar cell, merge the second power generation abnormality degree with the first power generation abnormality degree corresponding to the solar cell, and output a target power generation abnormality degree corresponding to the solar cell. The target power generation abnormality degree indicates a degree of power generation abnormality of the solar cell.
In the above, not only the abnormality analysis is performed on the solar cell alone to obtain the first power generation abnormality degree, but also the correlated abnormality analysis is performed in combination with the battery power generation data of the other solar cells to obtain the second power generation abnormality degree, so that the target power generation abnormality degree can be determined in combination with the power generation abnormality degrees in both aspects, thereby improving the reliability of the abnormality processing on the solar cell data.
It should be understood that, in some embodiments, step S110 in the above description may specifically include the following details:
for each solar cell, in a current power generation abnormity analysis period (that is, each power generation abnormity analysis period performs power generation abnormity analysis in sequence, the period length can be configured according to the scene and the requirement of practical application, such as one week and the like), a data acquisition instruction is issued to the data acquisition equipment corresponding to the solar cell at a preset time interval (the preset time interval can also be configured according to the scene and the requirement of practical application), so that the data acquisition equipment performs data acquisition on the solar cell according to the data acquisition instruction;
and for each solar cell, constructing and forming a power generation data sequence corresponding to the solar cell according to power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell.
It should be understood that, in some embodiments, for each of the solar cells described in the above description, the step of constructing the power generation data sequence corresponding to the solar cell according to each piece of cell power generation data collected by the data collection device corresponding to the solar cell may specifically include the following detailed steps:
for each solar cell, in the current power generation abnormity analysis period, sequentially receiving power generation data of each cell acquired by data acquisition equipment corresponding to the solar cell, and transmitting the power generation data of each cell to the data processing cloud platform after the data acquisition equipment acquires the power generation data of each cell;
for each solar cell, after receiving power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell, sequencing the received power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell according to the receiving time or the sending time corresponding to the power generation data of each cell to form a power generation data sequence corresponding to the solar cell.
It should be understood that, in some embodiments, step S120 in the above description may specifically include the following details:
for each solar cell, determining the data fluctuation degree of the solar cell according to each cell power generation data included in the power generation data sequence corresponding to the solar cell so as to output the power generation data fluctuation degree corresponding to the solar cell;
for each solar cell, performing first power generation abnormity analysis on the solar cell according to the power generation data fluctuation degree corresponding to the solar cell, and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree is positively correlated with the power generation data fluctuation degree.
It should be understood that, in some embodiments, for each of the solar cells described in the foregoing description, the step of determining the data fluctuation degree of the solar cell according to each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell to output the power generation data fluctuation degree corresponding to the solar cell may specifically include the following detailed steps:
for each solar cell, fitting a curve according to power generation data of each cell included in the power generation data sequence corresponding to the solar cell and data characteristic time corresponding to the power generation data of each cell to form a target fitting curve corresponding to the solar cell, wherein the data characteristic time indicates data sending time or data receiving time corresponding to the power generation data of the corresponding cell;
for each solar cell, calculating the fitting deviation degree of each cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell respectively so as to output the fitting deviation degree corresponding to each cell power generation data;
for each solar cell, fusing the fitting deviation degree corresponding to each piece of battery power generation data included in the power generation data sequence corresponding to the solar cell, outputting a first data fluctuation degree corresponding to the solar cell, calculating the absolute difference value of every two adjacent battery power generation data included in the power generation data sequence corresponding to the solar cell, outputting the data absolute difference value between every two adjacent battery power generation data, summing the data absolute difference values between every two adjacent battery power generation data, outputting a data difference value corresponding to the solar cell, and determining a second data fluctuation degree with a positive correlation according to the data difference value (namely, the second data fluctuation degree is positively correlated with the data difference value);
for each solar cell, fusing the first data fluctuation degree and the second data fluctuation degree corresponding to the solar cell, and outputting the power generation data fluctuation degree corresponding to the solar cell (for example, a weighted sum value between the first data fluctuation degree and the second data fluctuation degree may be used as the power generation data fluctuation degree).
It should be understood that, in some embodiments, for each of the solar cells described in the foregoing description, the step of performing, for each of the solar cells, calculation of a deviation degree of fit between each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell to output the deviation degree of fit corresponding to each piece of cell power generation data may specifically include the following details:
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating corresponding fitting data of data characteristic time corresponding to the battery power generation data according to a target fitting curve corresponding to the solar battery (that is, two variables may be included in the target fitting curve, and in the case of determining one variable, which is the data characteristic time, the other variable may be calculated, that is, fitting battery power generation data), so as to output fitting battery power generation data corresponding to the battery power generation data, wherein a two-dimensional coordinate point formed by the fitting battery power generation data and the corresponding data characteristic time is on the corresponding target fitting curve;
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating an absolute difference value of fitting battery power generation data corresponding to the battery power generation data and the battery power generation data to output a power generation data absolute difference value corresponding to the battery power generation data;
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, a ratio calculation is performed on the power generation data absolute difference corresponding to the battery power generation data and the battery power generation data to output a degree of fitting deviation corresponding to the battery power generation data (that is, a ratio between the power generation data absolute difference and the battery power generation data may be used as the degree of fitting deviation).
It should be understood that, in some embodiments, step S130 in the above description may specifically include the following details:
for every two solar cells, calculating the similarity of the two power generation data sequences corresponding to the two solar cells, and outputting the data sequence similarity between the two solar cells;
for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the data sequence similarity between the solar cell and each other solar cell, and outputting a second power generation abnormity degree corresponding to the solar cell;
for each of the solar cells, the first power generation abnormality degree and the second power generation abnormality degree corresponding to the solar cell are fused, and a target power generation abnormality degree corresponding to the solar cell is output (for example, a weighted sum value between the first power generation abnormality degree and the second power generation abnormality degree may be used as the target power generation abnormality degree, and a weighting coefficient corresponding to the first power generation abnormality degree may be larger than a weighting coefficient corresponding to the second power generation abnormality degree).
It should be understood that, in some embodiments, for each two solar cells described in the above description, the step of calculating the similarity between the two power generation data sequences corresponding to the two solar cells and outputting the similarity between the two power generation data sequences may specifically include the following details (the following steps are only for the two solar cells):
according to a target value (the target value may be configured according to actual requirements, for example, may be equal to half of the number of first battery power generation data included in one power generation data sequence, or may be other values, which is not specifically limited), randomly combining the first battery power generation data included in the first power generation data sequence to form a plurality of first power generation data sets corresponding to the first power generation data sequence, where the number of first battery power generation data included in each first power generation data set is equal to the target value, for each first power generation data set, screening each corresponding second battery power generation data from the second power generation data sequence according to the sequence position of each first battery power generation data included in the first power generation data sequence, to form a second power generation data set corresponding to the first power generation data set;
for each first power generation data set, determining target characteristic time corresponding to the first power generation data set according to data acquisition time corresponding to each first battery power generation data included in the first power generation data set, sequencing each first power generation data set according to the target characteristic time corresponding to each first power generation data set to form a first set sequence, for each second power generation data set, determining target characteristic time corresponding to the second power generation data set according to data acquisition time corresponding to each second battery power generation data included in the second power generation data set, and sequencing each second power generation data set according to the target characteristic time corresponding to each second power generation data set to form a second set sequence;
for each first power generation data set, respectively calculating an absolute difference value of every two first battery power generation data included in the first power generation data set to output a first absolute difference value set corresponding to the first power generation data set, then constructing and forming a first set internal feature vector corresponding to the first power generation data set according to each first absolute difference value included in the first absolute difference value set (when constructing the feature vector, each first absolute difference value may be arranged according to a corresponding size relationship), and constructing and forming a corresponding first set internal feature vector sequence according to a first set internal feature vector corresponding to each first power generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of every two pieces of second battery power generation data included in the second power generation data set to output a second absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set internal feature vector corresponding to the second power generation data set according to each second absolute difference value included in the second absolute difference value set, and constructing and forming a corresponding second set internal feature vector sequence according to a second set internal feature vector corresponding to each second power generation data set included in the second set sequence;
for each first electricity generation data set, respectively calculating an absolute difference value of each first battery electricity generation data included in the first electricity generation data set and each first battery electricity generation data included in an adjacent previous first electricity generation data set to output a third absolute difference value set corresponding to the first electricity generation data set, then constructing and forming a first set external feature vector corresponding to the first electricity generation data set according to each third absolute difference value included in the third absolute difference value set, and constructing and forming a corresponding first set external feature vector sequence according to the first set external feature vector corresponding to each first electricity generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of each second battery power generation data included in the second power generation data set and each second battery power generation data included in an adjacent previous second power generation data set to output a fourth absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set external feature vector corresponding to the second power generation data set according to each fourth absolute difference value included in the fourth absolute difference value set, and constructing and forming a corresponding second set external feature vector sequence according to a second set external feature vector corresponding to each second power generation data set included in the second set sequence;
calculating the similarity of the first set internal feature vector sequence and the second set internal feature vector sequence according to the vector similarity between the feature vectors of corresponding sequence positions (for example, an average value of the vector similarity between the feature vectors of each sequence position may be calculated, where the vector similarity may be calculated by performing an outer product calculation between the feature vectors), outputting the internal feature similarity, and (also according to the vector similarity between the feature vectors of the corresponding sequence positions), carrying out similarity calculation on the first set external feature vector sequence and the second set external feature vector sequence, outputting external feature similarity, fusing the internal feature similarity and the external feature similarity (such as weighted summation calculation and the like), and outputting the data sequence similarity between two solar cells corresponding to the two power generation data sequences.
It should be understood that, in other embodiments, for each two solar cells described in the above description, the step of calculating the similarity between the two power generation data sequences corresponding to the two solar cells and outputting the similarity between the data sequences of the two solar cells may specifically include the following details (the following steps are only for the two solar cells):
calculating a first similarity between a first power generation data sequence and a second power generation data sequence according to whether the battery power generation data corresponding to the sequence positions are the same or not, and outputting the first similarity between the first power generation data sequence and the second power generation data sequence (for example, a number ratio of the sequence positions having the same battery power generation data may be determined first, and the first similarity may have a positive correlation with the number ratio);
randomly combining first battery power generation data included in the first power generation data sequence according to a target value to form a plurality of first power generation data sets corresponding to the first power generation data sequence, wherein the number of the first battery power generation data included in each first power generation data set is equal to the target value, and screening each corresponding second battery power generation data from the second power generation data sequence according to the sequence position of each first battery power generation data included in the first power generation data sequence for each first power generation data set to form a second power generation data set corresponding to the first power generation data set;
for each first electricity generation data set, determining a target feature time corresponding to the first electricity generation data set according to data acquisition time corresponding to each first battery electricity generation data included in the first electricity generation data set, then sorting each first electricity generation data set according to the target feature time corresponding to each first electricity generation data set to form a first set sequence, for each second electricity generation data set, determining a target feature time corresponding to the second electricity generation data set according to data acquisition time corresponding to each second battery electricity generation data included in the second electricity generation data set, and then according to the target feature time corresponding to each second electricity generation data set (the target feature time may be an average value or a median value of the corresponding data acquisition times), sorting each second set of power generation data to form a second sequence of sets;
for each first electricity generation data set, fusing (such as mean value calculation and the like) each piece of first battery electricity generation data included in the first electricity generation data set, outputting target first battery electricity generation data corresponding to the first electricity generation data set, then according to the target first battery electricity generation data and target feature time corresponding to the first electricity generation data set, constructing and forming a first set feature vector corresponding to the first electricity generation data set (that is, in the first set feature vector, vector values of two dimensions, namely, a time dimension and an electricity generation data dimension, and according to the first set feature vector corresponding to each first electricity generation data set included in the first set sequence, constructing and forming a first set feature vector sequence corresponding to the first set sequence;
for each second power generation data set, fusing each piece of second battery power generation data included in the second power generation data set, outputting target second battery power generation data corresponding to the second power generation data set, then constructing and forming a second set feature vector corresponding to the second power generation data set according to the target second battery power generation data and target feature time corresponding to the second power generation data set (that is, vector values of two dimensions, namely a time dimension and a power generation data dimension, are also included in the second set feature vector), and then constructing and forming a second set feature vector sequence corresponding to the second set sequence according to the second set feature vector corresponding to each second power generation data set included in the second set sequence;
according to the vector similarity (as described in the foregoing), the similarity between the feature vectors of the corresponding sequence positions is calculated, a second similarity between the first power generation data sequence and the second power generation data sequence is output, the second similarity, the first similarity between the first power generation data sequence and the second power generation data sequence, and the data sequence similarity between the two solar cells corresponding to the two power generation data sequences are output.
It should be understood that, in some embodiments, for each of the solar cells described in the above description, the step of performing the second power generation abnormality analysis on the solar cell according to the data sequence similarity between the solar cell and each of the other solar cells, and outputting the second power generation abnormality degree corresponding to the solar cell may specifically include the following detailed steps:
for each solar cell, screening the data sequence similarity between the solar cell and each other solar cell, and outputting at least one target data sequence similarity corresponding to the solar cell, wherein in the data sequence similarity between the solar cell and each other solar cell, if at least one data sequence similarity greater than or equal to a similarity reference value exists, the data sequence similarity is marked as the target data sequence similarity, and if at least one data sequence similarity greater than or equal to the similarity reference value does not exist, the data sequence similarity with the maximum value is marked as the target data sequence similarity;
for each solar cell, marking other solar cells corresponding to each target data sequence similarity in at least one target data sequence similarity corresponding to the solar cell as related solar cells corresponding to the solar cell;
for each solar cell, according to the data sequence similarity between the solar cell and each corresponding relevant solar cell, the first power generation abnormality degree corresponding to each relevant solar cell is fused (for example, a weighting coefficient having a positive correlation may be determined according to the corresponding data sequence similarity, then the first power generation abnormality degree is subjected to weighted summation calculation according to the corresponding weighting coefficient to output a second power generation abnormality degree, and the sum of the weighting coefficients is equal to 1, so that the weighted average calculation may be performed), and the second power generation abnormality degree corresponding to the solar cell is output.
Referring to fig. 2, an embodiment of the present invention further provides a solar cell data exception handling system based on a cloud platform, which is applicable to the data processing cloud platform. The cloud platform-based solar cell data exception handling system can comprise a power generation data acquisition module, a power generation exception analysis module and a power generation exception degree determination module.
It should be understood that, in some embodiments, the power generation data collection module is configured to perform continuous power generation data collection on each solar cell to form a power generation data sequence corresponding to the solar cell, where the power generation data sequence includes a plurality of cell power generation data in a chronological relationship, and the number of the solar cells is multiple. The power generation abnormity analysis module is used for carrying out first power generation abnormity analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree indicates the power generation abnormity degree of the solar cell. The power generation abnormality degree determination module is used for carrying out second power generation abnormality analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormality degree corresponding to the solar cell, fusing the second power generation abnormality degree and the first power generation abnormality degree corresponding to the solar cell, and outputting a target power generation abnormality degree corresponding to the solar cell, wherein the target power generation abnormality degree indicates the power generation abnormality degree of the solar cell.
In summary, according to the solar cell data exception handling method and system based on the cloud platform provided by the invention, for each solar cell, the solar cell is subjected to continuous power generation data acquisition, and a corresponding power generation data sequence is formed. And for each solar cell, performing first power generation abnormity analysis according to the corresponding power generation data sequence, and outputting a corresponding first power generation abnormity degree. And for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a corresponding second power generation abnormity degree, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell. In the foregoing, not only the abnormality analysis is performed on the solar cell alone to obtain the first power generation abnormality degree, but also the correlated abnormality analysis is performed in combination with the battery power generation data of the other solar cells to obtain the second power generation abnormality degree, so that the target power generation abnormality degree can be determined in combination with the power generation abnormality degrees in both aspects, thereby improving the reliability of the abnormality processing on the solar cell data.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A solar cell data exception handling method based on a cloud platform is applied to a data processing cloud platform and comprises the following steps:
for each solar cell, continuously acquiring power generation data of the solar cell to form a power generation data sequence corresponding to the solar cell, wherein the power generation data sequence comprises a plurality of cell power generation data with time sequence relation, and a plurality of solar cells are provided;
for each solar cell, performing first power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell, and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree indicates the power generation abnormity degree of the solar cell;
for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormity degree corresponding to the solar cell, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell, wherein the target power generation abnormity degree indicates the power generation abnormity degree of the solar cell.
2. The cloud platform-based solar cell data exception handling method according to claim 1, wherein the step of performing continuous power generation data collection on each solar cell to form a power generation data sequence corresponding to the solar cell comprises:
for each solar cell, in the current power generation abnormity analysis period, issuing a data acquisition instruction to the data acquisition equipment corresponding to the solar cell at preset intervals, so that the data acquisition equipment acquires data of the solar cell according to the data acquisition instruction;
and for each solar cell, constructing and forming a power generation data sequence corresponding to the solar cell according to power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell.
3. The cloud platform-based solar cell data exception handling method according to claim 2, wherein the step of constructing a power generation data sequence corresponding to each solar cell according to each piece of cell power generation data collected by the data collection device corresponding to the solar cell for each solar cell includes:
for each solar cell, in the current power generation abnormity analysis period, sequentially receiving power generation data of each cell acquired by data acquisition equipment corresponding to the solar cell, and transmitting the power generation data of each cell to the data processing cloud platform after the data acquisition equipment acquires the power generation data of each cell;
for each solar cell, after receiving power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell, sequencing the received power generation data of each cell acquired by the data acquisition equipment corresponding to the solar cell according to the receiving time or the sending time corresponding to the power generation data of each cell to form a power generation data sequence corresponding to the solar cell.
4. The cloud platform-based solar cell data abnormality processing method according to claim 1, wherein the step of performing a first power generation abnormality analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and outputting a first power generation abnormality degree corresponding to the solar cell includes:
for each solar cell, determining the data fluctuation degree of the solar cell according to each cell power generation data included in the power generation data sequence corresponding to the solar cell so as to output the power generation data fluctuation degree corresponding to the solar cell;
for each solar cell, performing first power generation abnormity analysis on the solar cell according to the power generation data fluctuation degree corresponding to the solar cell, and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree is positively correlated with the power generation data fluctuation degree.
5. The cloud platform-based solar cell data exception handling method according to claim 4, wherein the step of determining the data fluctuation degree of each solar cell according to each cell power generation data included in the power generation data sequence corresponding to the solar cell for each solar cell so as to output the power generation data fluctuation degree corresponding to the solar cell comprises:
for each solar cell, fitting a curve according to power generation data of each cell included in the power generation data sequence corresponding to the solar cell and data characteristic time corresponding to the power generation data of each cell to form a target fitting curve corresponding to the solar cell, wherein the data characteristic time indicates data sending time or data receiving time corresponding to the power generation data of the corresponding cell;
for each solar cell, calculating the fitting deviation degree of each cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell respectively so as to output the fitting deviation degree corresponding to each cell power generation data;
for each solar cell, fusing the fitting deviation degree corresponding to each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell, outputting a first data fluctuation degree corresponding to the solar cell, respectively calculating the absolute difference value of every two adjacent pieces of cell power generation data included in the power generation data sequence corresponding to the solar cell, outputting the data absolute difference value between every two adjacent pieces of cell power generation data, then summing the data absolute difference values between every two adjacent pieces of cell power generation data, outputting a data difference value corresponding to the solar cell, and then determining a second data fluctuation degree with positive correlation according to the data difference value;
and for each solar cell, fusing the first data fluctuation degree and the second data fluctuation degree corresponding to the solar cell, and outputting the power generation data fluctuation degree corresponding to the solar cell.
6. The cloud platform-based solar cell data exception handling method according to claim 5, wherein the step of calculating, for each solar cell, a deviation degree of fit between each piece of cell power generation data included in the power generation data sequence corresponding to the solar cell and a target fitting curve corresponding to the solar cell to output the deviation degree of fit corresponding to each piece of cell power generation data includes:
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating corresponding fitting data of data characteristic time corresponding to the battery power generation data according to a target fitting curve corresponding to the solar battery so as to output the fitting battery power generation data corresponding to the battery power generation data, wherein two-dimensional coordinate points formed by the fitting battery power generation data and the corresponding data characteristic time are on the corresponding target fitting curve;
for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating the absolute difference value of the fitting battery power generation data corresponding to the battery power generation data and the battery power generation data to output the power generation data absolute difference value corresponding to the battery power generation data;
and for each piece of battery power generation data included in the power generation data sequence corresponding to each solar battery, calculating the ratio of the absolute difference of the power generation data corresponding to the battery power generation data so as to output the fitting deviation degree corresponding to the battery power generation data.
7. The cloud platform-based solar cell data abnormality processing method according to any one of claims 1 to 6, wherein the step of performing a second power generation abnormality analysis on each of the solar cells based on the power generation data series corresponding to the solar cell and the power generation data series corresponding to the other solar cells, outputting a second power generation abnormality degree corresponding to the solar cell, and fusing the second power generation abnormality degree and the first power generation abnormality degree corresponding to the solar cell to output a target power generation abnormality degree corresponding to the solar cell includes:
for every two solar cells, calculating the similarity of the two power generation data sequences corresponding to the two solar cells, and outputting the data sequence similarity between the two solar cells;
for each solar cell, carrying out second power generation abnormity analysis on the solar cell according to the data sequence similarity between the solar cell and each other solar cell, and outputting a second power generation abnormity degree corresponding to the solar cell;
and for each solar cell, fusing the first power generation abnormality degree and the second power generation abnormality degree corresponding to the solar cell and outputting the target power generation abnormality degree corresponding to the solar cell.
8. The cloud platform-based solar cell data anomaly processing method according to claim 7, wherein the step of calculating the similarity of the two power generation data sequences corresponding to the two solar cells for every two solar cells and outputting the data sequence similarity between the two solar cells comprises:
randomly combining first battery power generation data included in a first power generation data sequence according to a target value to form a plurality of first power generation data sets corresponding to the first power generation data sequence, wherein the quantity of the first battery power generation data included in each first power generation data set is equal to the target value, and screening each corresponding second battery power generation data from a second power generation data sequence according to the sequence position of each first battery power generation data included in the first power generation data sequence for each first power generation data set to form a second power generation data set corresponding to the first power generation data set;
for each first power generation data set, determining target characteristic time corresponding to the first power generation data set according to data acquisition time corresponding to each first battery power generation data included in the first power generation data set, sequencing each first power generation data set according to the target characteristic time corresponding to each first power generation data set to form a first set sequence, for each second power generation data set, determining target characteristic time corresponding to the second power generation data set according to data acquisition time corresponding to each second battery power generation data included in the second power generation data set, and sequencing each second power generation data set according to the target characteristic time corresponding to each second power generation data set to form a second set sequence;
for each first electricity generation data set, respectively calculating an absolute difference value of every two first battery electricity generation data included in the first electricity generation data set to output a first absolute difference value set corresponding to the first electricity generation data set, then constructing and forming a first set internal feature vector corresponding to the first electricity generation data set according to each first absolute difference value included in the first absolute difference value set, and constructing and forming a corresponding first set internal feature vector sequence according to the first set internal feature vector corresponding to each first electricity generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of every two pieces of second battery power generation data included in the second power generation data set to output a second absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set internal feature vector corresponding to the second power generation data set according to each second absolute difference value included in the second absolute difference value set, and constructing and forming a corresponding second set internal feature vector sequence according to a second set internal feature vector corresponding to each second power generation data set included in the second set sequence;
for each first electricity generation data set, respectively calculating an absolute difference value of each first battery electricity generation data included in the first electricity generation data set and each first battery electricity generation data included in an adjacent previous first electricity generation data set to output a third absolute difference value set corresponding to the first electricity generation data set, then constructing and forming a first set external feature vector corresponding to the first electricity generation data set according to each third absolute difference value included in the third absolute difference value set, and constructing and forming a corresponding first set external feature vector sequence according to the first set external feature vector corresponding to each first electricity generation data set included in the first set sequence;
for each second power generation data set, respectively calculating an absolute difference value of each second battery power generation data included in the second power generation data set and each second battery power generation data included in an adjacent previous second power generation data set to output a fourth absolute difference value set corresponding to the second power generation data set, then constructing and forming a second set external feature vector corresponding to the second power generation data set according to each fourth absolute difference value included in the fourth absolute difference value set, and constructing and forming a corresponding second set external feature vector sequence according to a second set external feature vector corresponding to each second power generation data set included in the second set sequence;
according to the vector similarity between the feature vectors corresponding to the sequence positions, calculating the similarity between the first set internal feature vector sequence and the second set internal feature vector sequence, outputting the internal feature similarity, calculating the similarity between the first set external feature vector sequence and the second set external feature vector sequence, outputting the external feature similarity, fusing the internal feature similarity and the external feature similarity, and outputting the data sequence similarity between two solar cells corresponding to the two power generation data sequences.
9. The cloud platform-based solar cell data abnormality processing method according to claim 7, wherein the step of performing a second power generation abnormality analysis on each of the solar cells according to a data sequence similarity between the solar cell and each of the other solar cells, and outputting a second power generation abnormality degree corresponding to the solar cell, includes:
for each solar cell, screening the data sequence similarity between the solar cell and each other solar cell, and outputting at least one target data sequence similarity corresponding to the solar cell, wherein in the data sequence similarity between the solar cell and each other solar cell, if at least one data sequence similarity greater than or equal to a similarity reference value exists, the data sequence similarity is marked as the target data sequence similarity, and if at least one data sequence similarity greater than or equal to the similarity reference value does not exist, the data sequence similarity with the maximum value is marked as the target data sequence similarity;
for each solar cell, marking other solar cells corresponding to each target data sequence similarity in at least one target data sequence similarity corresponding to the solar cell as related solar cells corresponding to the solar cell;
and for each solar cell, fusing the first power generation abnormality degree corresponding to each relevant solar cell according to the data sequence similarity between the solar cell and each corresponding relevant solar cell, and outputting the second power generation abnormality degree corresponding to the solar cell.
10. The solar cell data exception handling system based on the cloud platform is applied to a data processing cloud platform and comprises:
the system comprises a power generation data acquisition module, a power generation data acquisition module and a power generation data acquisition module, wherein the power generation data acquisition module is used for continuously acquiring power generation data of each solar cell to form a power generation data sequence corresponding to the solar cell, the power generation data sequence comprises a plurality of cell power generation data with time precedence relation, and a plurality of solar cells are arranged;
the power generation abnormity analysis module is used for carrying out first power generation abnormity analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and outputting a first power generation abnormity degree corresponding to the solar cell, wherein the first power generation abnormity degree indicates the power generation abnormity degree of the solar cell;
and the power generation abnormity degree determination module is used for carrying out second power generation abnormity analysis on each solar cell according to the power generation data sequence corresponding to the solar cell and the power generation data sequences corresponding to other solar cells, outputting a second power generation abnormity degree corresponding to the solar cell, fusing the second power generation abnormity degree and the first power generation abnormity degree corresponding to the solar cell, and outputting a target power generation abnormity degree corresponding to the solar cell, wherein the target power generation abnormity degree indicates the power generation abnormity degree of the solar cell.
CN202210894431.1A 2022-07-28 2022-07-28 Solar cell data exception handling method and system based on cloud platform Active CN115081552B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210894431.1A CN115081552B (en) 2022-07-28 2022-07-28 Solar cell data exception handling method and system based on cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210894431.1A CN115081552B (en) 2022-07-28 2022-07-28 Solar cell data exception handling method and system based on cloud platform

Publications (2)

Publication Number Publication Date
CN115081552A true CN115081552A (en) 2022-09-20
CN115081552B CN115081552B (en) 2022-11-11

Family

ID=83242729

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210894431.1A Active CN115081552B (en) 2022-07-28 2022-07-28 Solar cell data exception handling method and system based on cloud platform

Country Status (1)

Country Link
CN (1) CN115081552B (en)

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102004413B1 (en) * 2018-04-23 2019-07-26 주식회사 새론테크 Photovoltaic Power generation monitoring system including channel observing type connection board
CN111027723A (en) * 2019-12-10 2020-04-17 吉林建筑科技学院 Photovoltaic and building integrated system and method
KR102082148B1 (en) * 2019-09-23 2020-05-26 주식회사 코텍에너지 Solar power generating system and method having an automatic fire extinguisher
CN111566930A (en) * 2017-12-22 2020-08-21 住友电气工业株式会社 Determination device, photovoltaic power generation system, determination method, and determination program
CN112311078A (en) * 2020-11-04 2021-02-02 华侨大学 Solar load adjusting method and device based on information fusion
CN112529061A (en) * 2020-12-03 2021-03-19 新奥数能科技有限公司 Identification method and device for photovoltaic power abnormal data and terminal equipment
CN112651460A (en) * 2020-12-31 2021-04-13 新奥数能科技有限公司 Identification method and device for photovoltaic power abnormal data
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
CN113283113A (en) * 2021-06-11 2021-08-20 中国人民解放军国防科技大学 Spacecraft solar cell array power generation current prediction model training method, anomaly detection method, equipment and medium
CN113326667A (en) * 2021-08-03 2021-08-31 深圳格瑞特新能源有限公司 Solar cell panel fault diagnosis method and system
CN113625092A (en) * 2021-08-26 2021-11-09 段华 Electronic component performance data detection method
CN113888351A (en) * 2021-09-26 2022-01-04 华能酒泉风电有限责任公司 Power prediction method and device of photovoltaic system and electronic equipment
CN114137421A (en) * 2021-11-30 2022-03-04 蜂巢能源(上海)有限公司 Battery abnormality detection method, apparatus, device and storage medium
CN114614766A (en) * 2022-01-31 2022-06-10 扬州晶华新能源科技有限公司 Photovoltaic and photo-thermal integrated component abnormity detection method and test system
CN114662613A (en) * 2022-04-21 2022-06-24 杭州宇谷科技有限公司 Abnormal battery detection system and method based on elastic time series similarity network
CN114785280A (en) * 2022-04-28 2022-07-22 青海天创新能源科技有限公司 On-site detection method for power generation performance defects of solar cell module of photovoltaic power station
CN114785284A (en) * 2022-06-21 2022-07-22 一道新能源科技(衢州)有限公司 Solar cell fault analysis method and system

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111566930A (en) * 2017-12-22 2020-08-21 住友电气工业株式会社 Determination device, photovoltaic power generation system, determination method, and determination program
KR102004413B1 (en) * 2018-04-23 2019-07-26 주식회사 새론테크 Photovoltaic Power generation monitoring system including channel observing type connection board
KR102082148B1 (en) * 2019-09-23 2020-05-26 주식회사 코텍에너지 Solar power generating system and method having an automatic fire extinguisher
CN111027723A (en) * 2019-12-10 2020-04-17 吉林建筑科技学院 Photovoltaic and building integrated system and method
CN112311078A (en) * 2020-11-04 2021-02-02 华侨大学 Solar load adjusting method and device based on information fusion
CN112529061A (en) * 2020-12-03 2021-03-19 新奥数能科技有限公司 Identification method and device for photovoltaic power abnormal data and terminal equipment
CN112651460A (en) * 2020-12-31 2021-04-13 新奥数能科技有限公司 Identification method and device for photovoltaic power abnormal data
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
CN113283113A (en) * 2021-06-11 2021-08-20 中国人民解放军国防科技大学 Spacecraft solar cell array power generation current prediction model training method, anomaly detection method, equipment and medium
CN113326667A (en) * 2021-08-03 2021-08-31 深圳格瑞特新能源有限公司 Solar cell panel fault diagnosis method and system
CN113625092A (en) * 2021-08-26 2021-11-09 段华 Electronic component performance data detection method
CN113888351A (en) * 2021-09-26 2022-01-04 华能酒泉风电有限责任公司 Power prediction method and device of photovoltaic system and electronic equipment
CN114137421A (en) * 2021-11-30 2022-03-04 蜂巢能源(上海)有限公司 Battery abnormality detection method, apparatus, device and storage medium
CN114614766A (en) * 2022-01-31 2022-06-10 扬州晶华新能源科技有限公司 Photovoltaic and photo-thermal integrated component abnormity detection method and test system
CN114662613A (en) * 2022-04-21 2022-06-24 杭州宇谷科技有限公司 Abnormal battery detection system and method based on elastic time series similarity network
CN114785280A (en) * 2022-04-28 2022-07-22 青海天创新能源科技有限公司 On-site detection method for power generation performance defects of solar cell module of photovoltaic power station
CN114785284A (en) * 2022-06-21 2022-07-22 一道新能源科技(衢州)有限公司 Solar cell fault analysis method and system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
RUIZHEN YANG 等: "Electromagnetic Induction Heating and Image Fusion of Silicon Photovoltaic Cell Electrothermography and Electroluminescence", 《IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS》 *
YUNYAN WANG 等: "Defect detection of solar cell based on data augmentation", 《IPEC 2021》 *
吴悦 等: "基于可视化和数据融合的光伏电站电气设备异常运行状态检测方法", 《制造业自动化》 *
郑德国: "太阳能光伏阵列出力异常的分析和处理", 《上海电气技术》 *

Also Published As

Publication number Publication date
CN115081552B (en) 2022-11-11

Similar Documents

Publication Publication Date Title
CN106874135B (en) Method, device and equipment for detecting machine room fault
CN109815085B (en) Alarm data classification method and device, electronic equipment and storage medium
CN115412371A (en) Big data security protection method and system based on Internet of things and cloud platform
CN115482122A (en) Comprehensive energy consumption monitoring method and system applied to smart park
CN115800538A (en) Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence
CN115081552B (en) Solar cell data exception handling method and system based on cloud platform
CN115620243B (en) Pollution source monitoring method and system based on artificial intelligence and cloud platform
CN116109988B (en) Anomaly monitoring method and system based on artificial intelligence and unmanned aerial vehicle
CN116719309B (en) Abnormality alarm method and system for feed production control system
CN115001394B (en) Solar cell state monitoring method and system based on artificial intelligence
CN114418460B (en) Construction process information analysis method and construction management system applied to BIM
CN115270973A (en) Industrial pollution source monitoring method and system
CN114720812A (en) Method and system for processing and positioning faults of power distribution network
CN113676362A (en) Internet of things equipment binding method and system based on data processing
CN114978040B (en) Attenuation condition analysis method and system based on solar cell data
EP3460732B1 (en) Dispatching method and system based on multiple levels of steady state production rate in working benches
CN111427930A (en) Low-voltage photovoltaic energy storage microgrid device monitoring management system, method and device
CN115753776A (en) Solar cell data processing method and system
CN116827808B (en) Multi-equipment combined communication system, method and equipment based on industrial Internet of things
CN115174638B (en) Networking method and system for photovoltaic panel data acquisition equipment
CN114156495B (en) Laminated battery assembly processing method and system based on big data
US20210357703A1 (en) Systems and methods for fault classification in photovoltaic arrays using graph signal processing
CN117176992A (en) Internet-based monitoring video processing method and system
CN107274104A (en) A kind of electronic instrument management big data analysis method and system
CN116662415A (en) Intelligent matching method and system based on data mining

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: No. 43 Bailing South Road, Quzhou City, Zhejiang Province 324022

Patentee after: Yidao New Energy Technology Co.,Ltd.

Address before: 324022 room 604, building 3, Donggang Third Road, green industry cluster, Qujiang District, Quzhou City, Zhejiang Province

Patentee before: A New Energy Technology (Quzhou) Co.,Ltd.