Photovoltaic string low-performance operation insight analysis system and method based on big data

Abstract

The invention provides a big data-based photovoltaic string performance degradation low performance operation insight analysis system and method. The system collects electrical numbers and production state data of string inverters or DC combiner boxes and photovoltaic strings; analyzing an electrical relationship between the photovoltaic string and superior equipment according to the number to determine a power generation analysis unit; after data time is aligned, preprocessing is carried out, and effective model input data of the preparation performance analysis operation model is checked; calculating a power generation performance evaluation index corresponding to each power generation analysis unit by using the performance analysis operation model; and optimizing a power generation service string structure based on the calculated power generation performance evaluation indexes, and deciding operation and maintenance processing schemes matched with different evaluation index grades. According to the scheme, the defect of insufficient reliability of an analysis result in the prior art can be overcome, the abnormal low-efficiency state in the numerous strings is analyzed by adopting a special data processing and analysis algorithm, improvement measures are put forward accordingly, and the overall performance of a photovoltaic system can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic string performance analysis, and in particular to a photovoltaic string low-performance operation insight analysis system and method based on big data. Background Art

[0002] Under lighting conditions, the panels of photovoltaic cells absorb light energy, and opposite charges accumulate at both ends of the panels, which in turn generates an electromotive force at both ends of the panels, thereby realizing the conversion of light energy into electrical energy. As an important device for energy conversion, photovoltaic modules are subject to factors such as surface contamination and module performance degradation, which may affect their power generation benefits. In theory, the power generation power (or current / voltage value) of the strings under the same power generation unit should always remain consistent or have only a slight difference under the same working conditions. However, certain environmental and human factors may cause the strings to fail to generate full power, which will significantly reduce the power generation efficiency of the photovoltaic power station. Effectively identifying inefficient strings through professional string inefficiency algorithms is important for improving power generation efficiency.

[0003] There are some methods for identifying low-performance status of photovoltaic strings in existing research. The main identification idea is: starting from the actual historical period string data of the photovoltaic strings themselves, combining the clustering algorithm to identify the string data with the set characteristics, so as to infer the corresponding inefficient strings, and based on this, identify the abnormal photovoltaic strings for processing, so as to promote the economic and efficient operation and maintenance of the power station to a certain extent. For example, the patent document CN113919419A provides a method for identifying inefficient photovoltaic strings. The method obtains the current and voltage string data of each photovoltaic string with a preset time length in the historical period; after processing, the abnormal data is identified and eliminated; the string data contained in the first preset period is screened in the eliminated string data to obtain the number of photovoltaic strings after screening; and the clustering object is selected to identify the inefficient photovoltaic strings in the photovoltaic equipment. Although it overcomes the influence of abnormal values ​​on the identification results to a certain extent, the current and voltage data of the photovoltaic strings are limited, and it is difficult to provide a comprehensive data basis for the clustering algorithm, which leads to defects in the accuracy of the identification results. In addition, there are studies on the inefficiency identification and power improvement of photovoltaic components. For example, patent document CN117713688A provides a method for inefficiency identification and power improvement of photovoltaic components in multiple directions and inclinations. The solution stores the preprocessed data in the cloud space and uses the TensorFlow deep learning framework to build an MLP-Mixer model; the output results of the MLP-Mixer model are integrated with the prior knowledge of the photovoltaic power station to form a second data set, and then the XGBoost model is established; when applied, the real-time operation data of the photovoltaic power station is collected and the real-time operation data is passed to the MLP-Mixer model. The MLP-Mixer model is used to identify inefficient strings, and maintenance recommendations are generated through the XGBoost model. The abnormal maintenance recommendation analysis model is established by combining the recognition results and prior knowledge, but the analysis results depend on the recognition results. The accuracy of the inefficient string information identified based only on the string data of the historical period is difficult to guarantee, resulting in insufficient reliability of the maintenance recommendation analysis results. In addition, some PV equipment uses alarm information to identify inefficient PV modules or manually identifies inefficient PV modules based on the equipment's power generation curve. However, the method of using alarm information lacks accuracy. General equipment remote signal alarms usually do not report the status of inefficient string operation. Checking the equipment's power generation curve consumes a lot of labor costs and on-site operation time costs, and these traditional methods can lead to missed judgments and misjudgments, and cannot meet the operational needs of the photovoltaic field well.

[0004] The information disclosed in the background technology section of the present invention is only intended to deepen the understanding of the general background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a photovoltaic string low-performance operation insight analysis system based on big data. The application of this solution can overcome the defect of insufficient reliability of the analysis results of the prior art, and adopt a special data processing and analysis algorithm to analyze the abnormal and inefficient state of many strings, effectively screen out the poor power generation strings and issue early warnings and propose improvement measures accordingly, which is conducive to the effective improvement of the overall performance of the photovoltaic system; the system collects the electrical number and production status data of the string inverter or DC combiner box and the photovoltaic string; determines the power generation analysis unit according to the number analysis of the electrical relationship between the photovoltaic string and the upper-level equipment; aligns the data time and performs preprocessing and verification to prepare the effective model input data of the performance analysis operation model; uses the performance analysis operation model to calculate the power generation performance evaluation index corresponding to each power generation analysis unit; based on the calculated power generation performance evaluation index, the power generation business string structure is optimized, and the operation and maintenance processing scheme matching different evaluation index levels is decided. Preferably, in one embodiment, the system includes:

[0006] A data collection module configured to obtain electrical serial numbers and production status data of all string inverters or DC combiner boxes and photovoltaic strings in the photovoltaic station to be analyzed;

[0007] A unit structure determination module configured to analyze the electrical relationship between the photovoltaic string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the photovoltaic string and its upper device;

[0008] A data processing module configured to align the time of the acquired data of different electrical numbers, pre-process the data and perform verification based on the pre-processed data to prepare valid model input data for the performance analysis operation model;

[0009] The string performance analysis module is configured to start the constructed performance analysis operation model according to the set analysis operation start time, input the valid model input data of the station to be analyzed to determine the power generation performance evaluation index corresponding to each power generation analysis unit;

[0010] The business optimization application module is configured to preferentially mark the power generation business string structure based on the calculated power generation performance evaluation index, and decide on the operation and maintenance processing plan that matches the different evaluation index levels.

[0011] In an optional embodiment, the data processing module includes a data time alignment and division unit, which is configured to use the same adjacent moment data information model to perform time alignment processing on the collected equipment timing production status data, and select power generation status data objects for storage according to preset valid data time periods and analysis nodes.

[0012] Furthermore, in one embodiment, the data processing module includes a data preprocessing unit for performing data cleaning and data completion processing on the data object; the data completion processing includes supplementing missing data values ​​using an interpolation method.

[0013] In a preferred embodiment, the data processing module includes a validity checking unit, which performs a check based on the preprocessed data according to the following logic to prepare valid model input data for the performance analysis operation model:

[0014] Determine whether the data volume of each photovoltaic string corresponding to different analysis nodes meets the set data volume conditions, select the photovoltaic string data that does not meet the data volume conditions, and use the remaining photovoltaic string data as standby power generation status data;

[0015] Determine whether the number of photovoltaic strings under the power generation analysis unit corresponding to the standby power generation status data meets the set string quantity condition, select the power generation analysis unit that meets the string quantity condition, and use its standby power generation status data as the effective model input data.

[0016] In one embodiment, when the string performance model analysis module calculates the power generation performance evaluation indicators of different power generation analysis units, the analysis model start time is first set, and the time when the irradiance at the location of the photovoltaic station is greater than the set condition for the last time each day is set as the calculation start time point of the daily performance analysis operation model.

[0017] Furthermore, in one embodiment, the string performance analysis module calculates the average value and standard deviation of the capacity utilization of different power generation analysis units at the upper level of the multiple photovoltaic strings based on the performance analysis operation model as the power generation performance evaluation index.

[0018] The performance analysis calculation model adopts the following logic:

[0019]

[0020] Among them, σ is the standard deviation of the daily average capacity utilization rate of the photovoltaic strings corresponding to the current power generation analysis unit, m is the number of strings under the power generation analysis unit, represents the average daily capacity utilization rate of the ith string in the power generation analysis unit, It is the result of averaging the daily capacity utilization average of all strings under the power generation analysis unit. represents the average value of the daily capacity utilization of each string, n represents the number of string capacity utilizations calculated by a single analysis node every day, η j represents the capacity utilization data of the jth analysis node every day, η represents the capacity utilization of a single analysis node of a PV string, VI represents the DC side power of the PV string of a single analysis node, and Wp represents the installed capacity of the PV string.

[0021] Preferably, in one embodiment, the business optimization application module includes a string structure optimization unit, which is configured to eliminate low-performance photovoltaic strings based on the comparative analysis results of power generation performance evaluation indicators and set optimization standards, thereby achieving optimization and marking of the power generation operation string structure.

[0022] In an optional embodiment, the business optimization application module includes an operation and maintenance plan decision unit, which is configured to determine different levels of performance evaluation levels based on set performance indicator division rules. Different performance evaluation levels use different forms of warning and display corresponding to different degrees of performance degradation states to match operation and maintenance processing plans with different degrees of urgency.

[0023] Preferably, in one embodiment, the system also includes an operation and maintenance effect analysis module, which is configured to mark the photovoltaic strings that adopt the operation and maintenance plan and record the operation and maintenance information, update the data tags of the operation and maintenance strings and compare the power generation performance evaluation indicators of the power generation analysis unit before and after the operation and maintenance, analyze the optimization effect of the operation and maintenance plan, and provide data support for the operation and maintenance plan decision-making unit.

[0024] Based on the application of the system described in any one or more of the above embodiments, the present invention further provides a photovoltaic string performance degradation low performance operation insight analysis method based on big data, which is applied to the system described in any one or more of the above embodiments. In a preferred embodiment, the method includes:

[0025] The data collection module is used to obtain the electrical serial numbers of the string inverters or DC combiner boxes of the entire photovoltaic station to be analyzed and the photovoltaic string production status data corresponding to the measurement points of the entire station;

[0026] Analyze the electrical relationship between the PV string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the PV string and its upper equipment;

[0027] After aligning the time of the acquired data of different electrical numbers, preprocessing the data and checking based on the preprocessed data to prepare valid model input data for the performance analysis operation model;

[0028] The constructed performance analysis operation model is started according to the set analysis operation start time, and the valid model input data of the station to be analyzed is input to determine the power generation performance evaluation index corresponding to each power generation analysis unit;

[0029] The power generation business string structure is preferentially marked based on the calculated power generation performance evaluation index, and the operation and maintenance processing scheme matching different evaluation index levels is decided.

[0030] Based on other aspects of the method described in any one or more of the above embodiments, the present invention further provides a storage medium storing program codes that can implement the method described in the above embodiments.

[0031] Compared with the closest prior art, the present invention also has the following beneficial effects:

[0032] The present invention provides a photovoltaic string low performance operation insight analysis system based on big data, including a data collection module, a unit structure determination module, a data processing module, a string performance analysis module and a business optimization application module;

[0033] When the system is used, it collects the electrical numbers and production status data of the string inverter or DC junction box and the photovoltaic strings; determines the power generation analysis unit according to the number analysis of the electrical relationship between the photovoltaic strings and the upper-level equipment; aligns the data time and performs preprocessing and verifies the effective model input data for preparing the performance analysis operation model; uses the performance analysis operation model to calculate the power generation performance evaluation index corresponding to each power generation analysis unit; based on the calculated power generation performance evaluation index, the power generation business string structure is optimized, and the operation and maintenance processing scheme matching different evaluation index levels is decided; the present invention uses the established performance analysis operation module to calculate the performance evaluation index to perform insight analysis on the low-performance operation strings in the station; deeply analyzes the performance characteristics of the low performance of the photovoltaic strings in the standard deviation, and gives the appropriate warning level and corresponding processing method to the low-performance strings found out according to business experience and on-site measurements, so as to improve the insight recognition accuracy of low-performance operation and save computing resources and processing measures resources caused by misjudgment.

[0034] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0036] Figure 1 This is a schematic diagram of the structure of a photovoltaic string low-performance operation insight analysis system based on big data provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram of the operation flow of a photovoltaic string low-performance operation insight analysis method based on big data provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will describe the implementation methods of the present invention in detail in conjunction with the accompanying drawings and embodiments, so that the implementers of the present invention can fully understand how the present invention applies technical means to solve technical problems and achieve the implementation process of technical effects and implement the present invention specifically according to the above implementation process. It should be noted that as long as there is no conflict, the various embodiments and various features of the embodiments in the present invention can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0039] Although the flowcharts describe the operations as sequential processes, many of the operations may be performed in parallel, concurrently, or simultaneously. The order of the operations may be rearranged. A process may be terminated when its operations are completed, but may also have additional steps not included in the accompanying drawings. A process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0040] Computer devices include user devices and network devices. Among them, user devices or clients include but are not limited to computers, smart phones, PDAs (Personal Digital Assistants), etc.; network devices include but are not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Computer devices can be run alone to implement the present invention, or they can be connected to the network and implement the present invention through interactive operations with other computer devices in the network. The network where the computer device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, etc.

[0041] The terms "first", "second", etc. may be used herein to describe various units, but these units should not be limited by these terms, and these terms are used only to distinguish one unit from another unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or there can be intermediate units.

[0042] The terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms "one", "one" and "item" used herein are also intended to include plural numbers. It should also be understood that the terms "include" and / or "comprise" used herein specify the existence of stated features, integers, steps, operations, units and / or components, without excluding the existence or addition of one or more other features, integers, steps, operations, units, components and / or combinations thereof.

[0043] During operation, multiple photovoltaic cell modules are usually connected in series to form a photovoltaic string. Multiple photovoltaic strings are further connected in parallel to form an overall power generation unit. Multiple power generation units support the operation of photovoltaic projects. In theory, the power generation power (or current / voltage value) of the strings under the same power generation unit should always be consistent or have only a slight difference under the same working conditions. However, certain environmental, human and other factors will cause the strings to fail to generate full power, which will significantly reduce the power generation efficiency of the photovoltaic power station. Effectively identifying inefficient strings through professional string inefficiency algorithms plays an important role in improving power generation efficiency.

[0044] There are some methods for identifying inefficient photovoltaic strings in existing research. The main identification ideas are: starting from the actual historical period string data of the photovoltaic strings themselves, after removing abnormal values ​​and screening based on the historical period string data, using it as the benchmark data combined with the clustering algorithm to identify the string data with set characteristics, so as to infer the corresponding inefficient strings, and based on this, identifying abnormal photovoltaic strings for processing, thereby promoting economic and efficient operation and maintenance of power stations to a certain extent. For example, patent document CN113919419A provides a method for identifying inefficient photovoltaic strings, which obtains the current and voltage string data of each photovoltaic string with a preset time length in the historical period; identifies and removes abnormal data after processing; screens the string data contained in the first preset period in the removed string data, and obtains the number of photovoltaic strings after screening; selects clustering objects to identify inefficient photovoltaic strings in photovoltaic equipment. Although it overcomes the influence of abnormal values ​​on the identification results to a certain extent, the current and voltage data of photovoltaic strings are limited, and it is difficult to provide a comprehensive data basis for the clustering algorithm, which leads to defects in the accuracy of the identification results.

[0045] In addition, there are studies on the inefficiency identification and power improvement of photovoltaic equipment components. For example, patent document CN117713688A provides a method for inefficiency identification and power improvement of photovoltaic components in multiple directions and inclinations. The solution collects historical operation data of photovoltaic power stations, stores the preprocessed data in the cloud space for further processing, and uses the TensorFlow deep learning framework to build an MLP-Mixer model; integrates the output results of the MLP-Mixer model with the prior knowledge of the photovoltaic power station to form a second data set, and then establishes an XGBoost model; when applied, collects real-time operation data of the photovoltaic power station, and passes the real-time operation data into the MLP-Mixer model. The MLP-Mixer model is used to identify inefficient strings, and the XGBoost model is used to generate maintenance recommendations. The abnormal maintenance recommendation analysis model is established by combining the recognition results and prior knowledge, but the analysis results depend on the recognition results. The accuracy of the inefficient string information identified based only on the string data of the historical period is difficult to guarantee, resulting in insufficient reliability of the maintenance recommendation analysis results.

[0046] In addition, some PV equipment uses alarm information to identify inefficient PV modules or manually identifies inefficient PV modules based on the equipment's power generation curve. However, the method of using alarm information lacks accuracy. General equipment remote signal alarms usually do not report the status of inefficient string operation. Checking the equipment's power generation curve consumes a lot of labor costs and on-site operation time costs, and these traditional methods can lead to missed judgments and misjudgments.

[0047] In order to solve the above problems, the present invention utilizes power generation performance big data processing technology combined with a matching algorithm model to perform string inefficiency analysis, which can improve the comprehensiveness and reliability of the string inefficiency analysis results; after judging the stability of string power by combining power generation performance big data processing logic and algorithm model, poor power generation strings can be effectively screened out and early warnings can be issued accordingly, which is key for users to discover problem strings at the first time and arrange maintenance in time.

[0048] In the big data-based photovoltaic string low-performance operation insight analysis system and method proposed in this application, the current, voltage, capacity data of the photovoltaic strings under the DC combiner box or string inverter of the whole field and the irradiance data of the station are first obtained; the electrical relationship between the strings of the whole field and their upper equipment is sorted out according to the electrical number information of each string, and a digital model of the power generation unit is formed as a power generation analysis unit; data within the effective power generation time period is selected unit by unit, all data are pre-processed, and the data quality is judged and optimized, and then the performance analysis operation module is established to calculate the performance evaluation index to perform insight analysis on the low-performance operation strings in the station; for the low-performance strings that are insightful, appropriate warning levels and corresponding processing methods are given according to business experience and on-site measurements. In the present invention, by deeply understanding the performance characteristics of the low performance of photovoltaic strings in the standard deviation, combined with the construction of the string electrical digital model, the effective insight of low-performance operation is improved, and misjudgment and loss of a large amount of computing resources are reduced.

[0049] Next, the structural components, connection modes and functional principles of the system of the embodiment of the present invention are described in detail based on the drawings. Although the logical order of each operation is shown in the process of describing the operating principle of the system structure, in some cases, the operations shown or described can be performed in a different order than here.

[0050] Embodiment 1

[0051] Figure 1 The schematic diagram of the structure of the photovoltaic string low performance operation insight analysis system based on big data provided by the first embodiment of the present invention is shown. Figure 1 It can be seen that the system includes:

[0052] A data collection module configured to obtain electrical serial numbers and production status data of all string inverters or DC combiner boxes and photovoltaic strings in the photovoltaic station to be analyzed;

[0053] A unit structure determination module configured to analyze the electrical relationship between the photovoltaic string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the photovoltaic string and its upper device;

[0054] A data processing module configured to align the time of the acquired data of different electrical numbers, pre-process the data and perform verification based on the pre-processed data to prepare valid model input data for the performance analysis operation model;

[0055] The string performance analysis module is configured to start the constructed performance analysis operation model according to the set analysis operation start time, input the valid model input data of the station to be analyzed to determine the power generation performance evaluation index corresponding to each power generation analysis unit;

[0056] The business optimization application module is configured to preferentially mark the power generation business string structure based on the calculated power generation performance evaluation index, and decide on the operation and maintenance processing plan that matches the different evaluation index levels.

[0057] The photovoltaic string low-performance operation insight analysis system based on big data of the embodiment of the present invention is applied to monitor and collect the working status information of the photovoltaic strings in real time, adopt specific data processing and analysis algorithms to identify the abnormal and inefficient states hidden in tens of millions of strings, and propose improvement measures accordingly, thereby effectively improving the overall performance of the photovoltaic system.

[0058] In an optional embodiment, the photovoltaic string production status data includes photovoltaic string number data, string current and voltage data, meteorological irradiance data, collector line power data and unit string installed capacity data;

[0059] In actual application, the following operations are performed through the data collection module:

[0060] Obtain the electrical number of the DC combiner box or string inverter for the entire site (depending on the actual electrical structure of the PV site) and the electrical number of the string.

[0061] Obtain current and voltage data of different PV strings under the DC combiner box or string inverter based on corresponding measurement points;

[0062] Acquire the real-time irradiance data in the meteorological station of the photovoltaic field to be analyzed based on the corresponding measuring points;

[0063] Collect active power data of different collector lines of the photovoltaic station to be analyzed based on corresponding measuring points;

[0064] Obtain basic parameters of installed capacity of different strings.

[0065] The unit structure determination module analyzes the electrical numbers of the photovoltaic strings and the string inverter or the DC combiner box, determines the upper-level equipment that matches each photovoltaic string, and constructs a power generation unit digital model as a power generation analysis unit based on the docking relationship between the photovoltaic string and its upper-level equipment;

[0066] In actual application, the electrical numbers of the combiner box or string inverter (depending on the actual electrical structure of the photovoltaic station) and the electrical numbers of the strings are sorted out; a digital model of the power generation unit that connects the string with its superior equipment is constructed, and each digital model of the power generation unit is used as a power generation analysis unit.

[0067] For example, when the embodiment of the present invention is applied in a 4.2MWp photovoltaic project constructed by the National Railway Test Center, the parent device (string inverter or DC combiner box) of all photovoltaic strings is used as a power generation analysis unit to perform photovoltaic string power performance calculations.

[0068] The data processing module is configured to align the time of the acquired data of different electrical numbers, pre-process the data and perform verification based on the pre-processed data to prepare valid model input data for the performance analysis operation model.

[0069] The data processing module includes a data time alignment and division unit, which is configured to use the same adjacent moment data information model to perform time alignment processing on the collected equipment time series production status data, and select power generation status data objects for storage according to preset valid data time periods and analysis nodes.

[0070] The valid data period determines the length of the use window of production status data during operation, that is, the data range used for calculation of the daily performance analysis operation model; in a preferred embodiment, the power generation status data within the daily station valid data period is selected as the valid power generation status data, and the daily station valid data (collection) period is set to the period from the first time the irradiance at the location is greater than the set value to the last time the irradiance at the location of the station is greater than the set value; in a preferred embodiment, the set value can be set to 120W / ㎡. In actual application, the set value is flexibly set according to seasonal factors, meteorological factors and geographical factors. When necessary, based on the technical logic of the present invention, technicians can set the set value to other values ​​or data ranges as needed.

[0071] In an optional embodiment, after aligning the time of all data, each set time interval is set as an analysis node to decide the time for storing the data object; the set time interval can be set to 5 minutes. In actual application, the set time interval is flexibly set according to the performance analysis status of each power generation analysis unit and the expected analysis needs. If necessary, based on the technical logic of the present invention, technicians can set the set time interval to other values ​​or data ranges as needed.

[0072] Based on this, the data closest to the exact time every 5 minutes can be selected for application. Usually, the first data every 5 minutes is selected for storage as the collected power generation status data object.

[0073] On the other hand, in the case where a photovoltaic power station has multiple power generation analysis units, technicians can set the set time interval of each power generation analysis unit to different values ​​according to the dynamic performance analysis status of the power generation analysis unit (such as the performance analysis results of the previous day) and the expected analysis needs (requirements). For example, for a power generation analysis unit whose dynamic performance analysis status shows a low performance trend, its set time interval can be set shorter than that of a power generation analysis unit with normal performance according to the needs, so as to form sufficiently dense and effective power generation status data; and for a power generation analysis unit that shows high performance or normal performance within the set time period, its set time interval can be set longer as appropriate, so as to dynamically save data acquisition resources and computing resources without affecting the reliability of the analysis results.

[0074] The data processing module includes a data preprocessing unit, which is used to perform data cleaning and data completion processing on the data object.

[0075] In an optional embodiment, during the process of preprocessing the data, the data preprocessing unit makes a data quality judgment on the collected data, and performs data cleaning and data completion processing based on the judgment result. The data cleaning processing includes eliminating constant values ​​and out-of-limit values; the data completion processing includes using interpolation method to supplement missing data values.

[0076] The data processing module includes a validity checking unit, which performs a check based on the preprocessed data according to the following logic to prepare valid model input data for the performance analysis operation model:

[0077] Determine whether the data volume of each photovoltaic string corresponding to different analysis nodes meets the set data volume conditions, select the photovoltaic string data that does not meet the data volume conditions, and use the remaining photovoltaic string data as standby power generation status data;

[0078] Determine whether the number of photovoltaic strings under the power generation analysis unit corresponding to the standby power generation status data meets the set string quantity conditions, select the power generation analysis unit that meets the string quantity conditions, and use its standby power generation status data as the valid model input data; if not, it indicates that the current standby power generation status of the power generation analysis unit does not meet the input data quality requirements of the performance analysis calculation model.

[0079] Through the technical means of the above-mentioned embodiments, it is possible to effectively avoid interference with the accuracy and authenticity of the performance model calculation results caused by data quality problems and insufficient data volume.

[0080] The string performance analysis module is configured to start the constructed performance analysis operation model according to the set analysis operation start time, and use the effective model input data of the selected station to be analyzed as the operation input to determine the power generation performance evaluation index corresponding to each power generation analysis unit.

[0081] In the process of calculating the power generation performance evaluation indicators of different power generation analysis units by the string performance model analysis module, the analysis model start time is first set. In an optional embodiment, the time when the irradiance at the location of the photovoltaic station is greater than the set condition (such as 120W / ㎡) for the last time each day is set as the calculation start time point of the daily performance analysis operation model.

[0082] The string performance analysis module calculates the average value and standard deviation of the capacity utilization of different power generation analysis units of multiple photovoltaic strings based on the performance analysis operation model as the power generation performance evaluation index.

[0083] The performance analysis calculation model adopts the following logic:

[0084]

[0085]

[0086] Among them, σ is the standard deviation of the daily average capacity utilization rate of the photovoltaic strings corresponding to the current power generation analysis unit, m is the number of strings under the power generation analysis unit, represents the average daily capacity utilization rate of the ith string in the power generation analysis unit, It is the result of averaging the daily capacity utilization average of all strings under the power generation analysis unit. represents the average value of the daily capacity utilization of each string, n represents the number of string capacity utilizations calculated by a single analysis node every day, η j represents the capacity utilization data of the jth analysis node every day, η represents the capacity utilization of a single analysis node of a PV string (every 5 minutes), VI represents the DC side power of the PV string of a single analysis node, and Wp represents the installed capacity of the PV string.

[0087] The performance analysis operation model based on the embodiment of the present invention first calculates the capacity utilization rate corresponding to the data of each analysis node in the daily effective power generation section of each string, and further calculates the average daily capacity utilization rate of each string. Then, based on the average daily capacity utilization rate, the daily capacity utilization rate average value is introduced as the average value of all strings under the power generation analysis unit, and the standard deviation index of the capacity utilization rate mean data distribution is calculated as the power generation performance evaluation index corresponding to the power generation analysis unit.

[0088] The business optimization application module is configured to preferentially mark the power generation business string structure based on the calculated power generation performance evaluation index, and decide on the operation and maintenance processing plan that matches the different evaluation index levels.

[0089] The business optimization application module includes a string structure optimization unit, which is configured to eliminate low-performance photovoltaic strings by comparing and analyzing the power generation performance evaluation index with the set optimization standard, so as to achieve the optimal marking of the power generation operation string structure.

[0090] The string structure optimization unit uses the following logic to combine the power generation performance evaluation index with the set optimization standard to compare and analyze the results and eliminate low-performance photovoltaic strings:

[0091] The dynamically calculated power generation performance evaluation index is compared with the set optimization standard. If the power generation performance evaluation index does not meet the set optimization standard, the photovoltaic string with the smallest average value of daily capacity utilization is selected from the power generation analysis unit as the current low-performance photovoltaic string. After elimination, the power generation performance evaluation index of the power generation analysis unit is recalculated based on the valid model input data of the remaining photovoltaic strings. The low-performance photovoltaic strings are judged and selected for elimination in a cyclic manner until the calculated power generation performance evaluation index of the power generation analysis unit meets the set optimization standard. The remaining photovoltaic strings are marked as high-performance power generation operation string structures, which is convenient for the site to carry out targeted scheduling operations according to demand.

[0092] In actual application, if the calculated standard deviation conclusion does not meet the optimization criteria (for example, the standard deviation conclusion is less than 5%), the obtained standard deviation conclusion can be marked on the string with the lowest daily average capacity utilization, and then the string is eliminated, and the calculation is performed again based on the remaining strings in the power generation analysis unit. The cycle is compared with the set optimization criteria and the obtained standard deviation conclusion is marked on the string with the lowest daily average capacity utilization in this calculation, until the last standard deviation conclusion meets the optimization criteria and the cycle is stopped.

[0093] The business optimization application module includes an operation and maintenance solution decision unit, which is configured to determine different levels of performance evaluation levels based on set performance indicator division rules. Different performance evaluation levels use different forms of warning and display corresponding to different degrees of performance degradation states to match operation and maintenance processing solutions with different urgency levels.

[0094] In an optional embodiment, the standard deviation value distribution intervals corresponding to different levels of performance evaluation grades can be set as performance indicator division rules based on the analysis of the model operation results of the historical stage combined with the corresponding on-site measurement experience. For example, the performance indicator division rule can be set as follows: when the standard deviation results are ≤5%, >5% and ≤10%, >10% and ≤20%, and >20%, respectively, there are four performance evaluation grades, namely the first, second, third and fourth, corresponding to the degree of performance attenuation from low to high, and corresponding to the four warning levels of normal, slightly inefficient, moderately inefficient, and severely inefficient, which correspond to the degree of low-performance operation of the string; different warning levels correspond to different operation and maintenance methods.

[0095] When the model calculates that a certain string is abnormal, the system will automatically trigger an alarm, which will be displayed in the form of a light-emitting sign on the interface, and a report containing an analysis of the cause of the fault and suggested solutions will be generated. The report is detailed and easy to understand, allowing operation and maintenance personnel to take quick action.

[0096] The system also includes an operation and maintenance effect analysis module, which is configured to mark the strings that adopt the operation and maintenance plan and record the operation and maintenance information, compare the power generation performance evaluation indicators of the power generation analysis unit before and after the operation and maintenance, and record the effect of each measure taken; analyze the optimization effect of the operation and maintenance plan, and provide data support for the operation and maintenance plan decision-making unit. Accordingly, the photovoltaic strings that have undergone operation and maintenance should be marked in a timely manner, and the low-performance marks should be removed to participate in the evaluation process of the power generation analysis unit and the optimization process of the power generation string structure.

[0097] The photovoltaic string low-performance operation insight analysis system based on big data provided by the embodiment of the present invention responds to the user's operation instructions through a visual interactive interface to display result information, and the user can query the performance analysis calculation results of the photovoltaic string of the demand equipment through the interactive interface.

[0098] Through the data elimination mechanism, normal photovoltaic string objects and information are eliminated, and the output results can intuitively display the problem strings and the problem types or levels. In an optional embodiment, the strings with poor power generation can be screened out based on the visual interface and different levels of warnings can be displayed. At the same time, different types and levels of attenuation type warnings can be rendered in a variety of colors on the visual interface; based on the intuitive output information, it can ensure that users can promptly handle and eliminate the problem strings in the first place, improve power generation efficiency and ensure stable operation.

[0099] The embodiment of the present invention utilizes big data in combination with an algorithm model to perform string inefficiency analysis, thereby effectively improving the comprehensiveness and reliability of the string inefficiency analysis results; further refining the classification according to the identified string inefficiency levels, rationally arranging operation and maintenance, and more accurately guiding string operation and maintenance work; further reducing the cost of operation and maintenance work, and improving the efficiency of photovoltaic string operation and maintenance.

[0100] In the photovoltaic string low-performance operation insight analysis system based on big data provided by the embodiment of the present invention, each module or unit structure can operate independently or in combination according to actual data processing requirements and model calculation requirements to achieve corresponding technical effects.

[0101] Embodiment 2

[0102] The system is described in detail in the embodiments disclosed in the above invention. Based on other aspects of the system described in any one or more embodiments, the present invention also provides a method for analyzing the low performance operation of photovoltaic strings based on big data, which is applied to the system for analyzing the low performance operation of photovoltaic strings based on big data described in any one or more embodiments. Specific embodiments are given below for detailed description.

[0103] Specifically, Figure 2 FIG. 4 is a flow chart of a method for analyzing photovoltaic string low performance operation based on big data provided in an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0104] Data collection steps: Obtain the electrical serial numbers and production status data of all string inverters or DC combiner boxes and photovoltaic strings in the photovoltaic station to be analyzed;

[0105] Unit structure determination step: Analyze the electrical relationship between the PV string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the PV string and its upper equipment;

[0106] Data processing step: after aligning the time of the acquired data, preprocessing the data and checking based on the preprocessed data to prepare valid model input data for the performance analysis operation model;

[0107] String performance analysis steps: start the constructed performance analysis operation model according to the set analysis operation start time, input the valid model input data of the station to be analyzed to determine the power generation performance evaluation index corresponding to each power generation analysis unit;

[0108] Business optimization application steps: Based on the calculated power generation performance evaluation indicators, the power generation business string structure is preferentially marked, and the operation and maintenance processing solutions that match different evaluation indicator levels are decided.

[0109] In an optional embodiment, the data processing step includes:

[0110] The same adjacent moment data information model is used to perform time alignment processing on the collected equipment time series production status data, and the power generation status data objects are selected for storage according to the preset valid data period and analysis nodes.

[0111] Furthermore, in one embodiment, the data processing step includes:

[0112] Data preprocessing step: used to perform data cleaning and data completion processing on the data object; the data completion processing includes using interpolation method to supplement the missing data values.

[0113] In a preferred embodiment, the data preprocessing step further includes:

[0114] Validity verification step: Verification based on preprocessed data to prepare valid model input data for the performance analysis operation model, including the following operations:

[0115] Determine whether the data volume of each photovoltaic string corresponding to different analysis nodes meets the set data volume conditions, select the photovoltaic string data that does not meet the data volume conditions, and use the remaining photovoltaic string data as standby power generation status data;

[0116] Determine whether the number of photovoltaic strings under the power generation analysis unit corresponding to the standby power generation status data meets the set string quantity condition, select the power generation analysis unit that meets the string quantity condition, and use its standby power generation status data as the effective model input data.

[0117] In one embodiment, the string performance model analysis step includes:

[0118] Set the start time of the analysis model, and set the last time the irradiance at the location of the photovoltaic station is greater than the set condition as the calculation start time point of the daily performance analysis operation model.

[0119] Furthermore, in one embodiment, the string performance analysis step includes:

[0120] Based on the performance analysis operation model, the average value and standard deviation of the capacity utilization rate of different power generation analysis units above the multi-PV string are calculated as the power generation performance evaluation index.

[0121] The string performance analysis step uses the following performance analysis calculation model:

[0122]

[0123] Among them, σ is the standard deviation of the daily average capacity utilization rate of the photovoltaic strings corresponding to the current power generation analysis unit, m is the number of strings under the power generation analysis unit, represents the average daily capacity utilization rate of the ith string in the power generation analysis unit, It is the result of averaging the daily capacity utilization average of all strings under the power generation analysis unit. represents the average value of the daily capacity utilization of each string, n represents the number of string capacity utilizations calculated by a single analysis node every day, η j represents the capacity utilization data of the jth analysis node every day, η represents the capacity utilization of a single analysis node of a PV string, VI represents the DC side power of the PV string of a single analysis node, and Wp represents the installed capacity of the PV string.

[0124] Preferably, in one embodiment, the service optimization application step includes:

[0125] Steps for optimizing the string structure: Combine the power generation performance evaluation index with the set optimization standard to compare and analyze the results and eliminate low-performance photovoltaic strings, so as to achieve the optimization and marking of the string structure for power generation operations.

[0126] In an optional embodiment, the service optimization application step further includes:

[0127] Operation and maintenance plan decision-making steps: Determine different levels of performance evaluation levels based on the set performance indicator classification rules. Corresponding to different degrees of performance degradation, different performance evaluation levels use different forms of warning and display to match operation and maintenance processing plans with different degrees of urgency.

[0128] Preferably, in one embodiment, the method further includes an operation and maintenance effect analysis step: marking the photovoltaic strings that adopt the operation and maintenance plan and recording the operation and maintenance information, updating the data tags of the operation and maintenance strings and comparing the power generation performance evaluation indicators of the power generation analysis unit before and after the operation and maintenance, analyzing the optimization effect of the operation and maintenance plan, and providing data support for the operation and maintenance plan decision-making unit.

[0129] For the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0130] It should be pointed out that in other embodiments of the present invention, the method can also obtain a new big data-based photovoltaic string low-performance operation insight analysis method by combining one or several of the above-mentioned embodiments, so as to achieve comprehensive and reliable monitoring of the performance of photovoltaic equipment components.

[0131] Embodiment 3

[0132] It should be noted that, based on the method in any one or more of the above-mentioned embodiments of the present invention, the present invention also provides a storage medium, on which is stored a program code that can implement the method as described in any one or more of the above-mentioned embodiments, and when the code is executed by the operating system, it can implement the above-mentioned big data-based photovoltaic string low-performance operation insight analysis method.

[0133] It should be understood that the embodiments disclosed in the present invention are not limited to the specific structures, processing steps or materials disclosed herein, but should be extended to equivalent substitutions of these features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0134] The "one embodiment" mentioned in the specification means that a particular feature, structure or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. Therefore, the phrase "one embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0135] Although the embodiments disclosed in the present invention are as above, the above contents are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A photovoltaic string performance degradation and low performance operation insight analysis system based on big data, characterized in that: The system comprises: A data collection module configured to obtain electrical serial numbers and production status data of all string inverters or DC combiner boxes and photovoltaic strings in the photovoltaic station to be analyzed; A unit structure determination module configured to analyze the electrical relationship between the photovoltaic string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the photovoltaic string and its upper device; A data processing module configured to pre-process the data after aligning the time of the acquired data and to perform verification based on the pre-processed data to prepare valid model input data for the performance analysis operation model; The string performance analysis module is configured to start the constructed performance analysis operation model according to the set analysis operation start time, input the valid model input data of the station to be analyzed to determine the power generation performance evaluation index corresponding to each power generation analysis unit; The business optimization application module is configured to preferentially mark the power generation business string structure based on the calculated power generation performance evaluation index, and decide on the operation and maintenance processing plan that matches the different evaluation index levels.

2. The system according to claim 1, characterized in that The data processing module includes a data time alignment and division unit, which is configured to use the same adjacent moment data information model to perform time alignment processing on the collected equipment time series production status data, and select power generation status data objects for storage according to preset valid data time periods and analysis nodes.

3. The system according to claim 2, characterized in that The data processing module includes a data preprocessing unit, which is used to perform data cleaning and data completion processing on the data object; the data completion processing includes using an interpolation method to supplement missing data values.

4. The system according to claim 3, characterized in that The data processing module includes a validity checking unit, which performs a check based on the preprocessed data according to the following logic to prepare valid model input data for the performance analysis operation model: Determine whether the data volume of each photovoltaic string corresponding to different analysis nodes meets the set data volume conditions, select the photovoltaic string data that does not meet the data volume conditions, and use the remaining photovoltaic string data as standby power generation status data; Determine whether the number of photovoltaic strings under the power generation analysis unit corresponding to the standby power generation status data meets the set string quantity condition, select the power generation analysis unit that meets the string quantity condition, and use its standby power generation status data as the effective model input data.

5. The system according to claim 1 or 4, characterized in that: In the process of calculating the power generation performance evaluation indicators of different power generation analysis units by the string performance model analysis module, the analysis model start time is first set, and the time when the irradiance at the location of the photovoltaic station is greater than the set condition for the last time each day is set as the calculation start time point of the daily performance analysis operation model.

6. The system according to claim 5, characterized in that The string performance analysis module calculates the average value and standard deviation of the capacity utilization of different power generation analysis units of multiple photovoltaic strings based on the performance analysis operation model as the power generation performance evaluation index. The performance analysis calculation model adopts the following logic: Among them, σ is the standard deviation of the daily average capacity utilization rate of the photovoltaic strings corresponding to the current power generation analysis unit, m is the number of strings under the power generation analysis unit, represents the average daily capacity utilization rate of the ith string in the power generation analysis unit, It is the result of averaging the daily capacity utilization average of all strings under the power generation analysis unit. represents the average value of the daily capacity utilization of each string, n represents the number of string capacity utilizations calculated by a single analysis node every day, η j represents the capacity utilization data of the jth analysis node every day, η represents the capacity utilization of a single analysis node of a PV string, VI represents the DC side power of the PV string of a single analysis node, and Wp represents the installed capacity of the PV string.

7. The system according to claim 1 or 6, characterized in that: The business optimization application module includes a string structure optimization unit, which is configured to eliminate low-performance photovoltaic strings by comparing the power generation performance evaluation index with the set optimization standard analysis results, so as to achieve the optimization and marking of the power generation operation string structure.

8. The system according to claim 7, characterized in that The business optimization application module includes an operation and maintenance solution decision unit, which is configured to determine different levels of performance evaluation levels based on set performance indicator division rules. Different performance evaluation levels use different forms of warning and display corresponding to different degrees of performance degradation states to match operation and maintenance processing solutions with different urgency levels.

9. The system according to claim 8, characterized in that The system also includes an operation and maintenance effect analysis module, which is configured to mark the photovoltaic strings that adopt the operation and maintenance plan and record the operation and maintenance information, update the data tags of the operation and maintenance strings and compare the power generation performance evaluation indicators of the power generation analysis unit before and after the operation and maintenance, analyze the optimization effect of the operation and maintenance plan, and provide data support for the operation and maintenance plan decision-making unit.

10. A photovoltaic string performance degradation low performance operation insight analysis method based on big data, characterized in that: The method is applied to the system according to any one of claims 1 to 9, and the method comprises: The data collection module is used to obtain the electrical serial numbers of the string inverters or DC combiner boxes of the entire photovoltaic station to be analyzed and the photovoltaic string production status data corresponding to the measurement points of the entire station; Analyze the electrical relationship between the PV string and the upper string inverter or DC combiner box according to the electrical number, and determine the power generation analysis unit based on the digital model of the power generation unit corresponding to the PV string and its upper equipment; After aligning the time of the acquired data of different electrical numbers, preprocessing the data and checking based on the preprocessed data to prepare valid model input data for the performance analysis operation model; The constructed performance analysis operation model is started according to the set analysis operation start time, and the valid model input data of the station to be analyzed is input to determine the power generation performance evaluation index corresponding to each power generation analysis unit; The power generation business string structure is preferentially marked based on the calculated power generation performance evaluation index, and the operation and maintenance processing scheme matching different evaluation index levels is decided.

11. A storage medium, characterized in that: The storage medium stores program codes for implementing the method as claimed in claim 10.

Images