Photovoltaic inverter full efficiency evaluation method

Abstract

A photovoltaic inverter full efficiency evaluation method is disclosed, in the method, historical data of photovoltaic inverter operation is collected as analysis sample, efficiency / power model and efficiency / voltage model are constructed, discrete efficiency data is generated from the historical data, a rule model is constructed to clean and filter the efficiency data, to obtain discrete second efficiency data meeting the rules, a characteristic quantification model is constructed, to identify efficiency characteristics with continuity and uniqueness from the discrete second efficiency data, a photovoltaic inverter full efficiency index model representing photovoltaic inverter full efficiency is constructed based on the efficiency characteristics, and the photovoltaic inverter full efficiency is evaluated via the photovoltaic inverter full efficiency index model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic inverter operation monitoring, and particularly relates to a photovoltaic inverter full efficiency evaluation method. BACKGROUND

[0002] The quality of the operation collected data of the photovoltaic inverter is poor, and cannot meet the technical requirements of the standard efficiency evaluation. The conventional photovoltaic inverter full efficiency test and evaluation method needs to additionally increase detection equipment support, and therefore, the efficiency test and evaluation have the disadvantages of high cost, low efficiency, poor on-site operability and the like, cannot adapt to the needs of the rapid development of the photovoltaic power generation industry, are not practically recognized and widely used in the production process, and lead to a long-term blank state of the photovoltaic inverter efficiency evaluation and related work. Due to the lack of efficiency evaluation, low-efficiency inverters and low-energy components cannot be effectively identified, which brings huge economic losses to the photovoltaic power generation industry.

[0003] The above information disclosed in the background section is only used to enhance the understanding of the background of the present application, and therefore can contain information that is not prior art known to those of ordinary skill in the art. SUMMARY

[0004] The purpose of the present application is to provide a photovoltaic inverter full efficiency evaluation method. In order to achieve the above purpose, the present application provides the following technical solution:

[0005] The photovoltaic inverter full efficiency evaluation method of the present application comprises:

[0006] Step S1: collecting historical data of photovoltaic inverter operation as an analysis sample, wherein the historical data comprises a time tag, an inverter direct current side voltage, an inverter direct current side current, an inverter alternating current measured active power, and an inverter alternating current measured reactive power,

[0007] Step S2: constructing an efficiency / power model and an efficiency / voltage model to generate discrete efficiency data from the historical data,

[0008] Step S3: constructing a rule model to clean and screen the efficiency data to obtain discrete second efficiency data meeting the rules,

[0009] Step S4: constructing a characteristic quantification model to identify efficiency characteristics with continuity and uniqueness from the discrete second efficiency data,

[0010] Step S5: constructing a photovoltaic inverter full efficiency index model representing the photovoltaic inverter full efficiency based on the efficiency characteristics, and evaluating the photovoltaic inverter full efficiency via the photovoltaic inverter full efficiency index model.

[0011] The photovoltaic inverter full efficiency evaluation method, in step S1, the historical data sampling interval is 1 minute to 10 minutes.

[0012] The photovoltaic inverter full efficiency evaluation method, in step S2, the efficiency / power model is constructed based on the inverter AC active power or apparent power and the inverter DC side power.

[0013] The photovoltaic inverter full efficiency evaluation method, in step S2, the efficiency / voltage model is constructed based on the inverter AC active power or apparent power, the inverter DC side power and the DC side voltage.

[0014] The photovoltaic inverter full efficiency evaluation method, in step S3, the rule model includes an efficiency distribution model for eliminating power caused by errors or sensor failures and constant power, a power distribution model for eliminating unreasonable efficiency data under photovoltaic power conditions, and an aggregation degree model for eliminating a predetermined proportion of invalid data.

[0015] The photovoltaic inverter full efficiency evaluation method, in step S3, the aggregation degree model eliminates a predetermined proportion of invalid data based on fuzzy theory, and further, the predetermined proportion is 30%.

[0016] The photovoltaic inverter full efficiency evaluation method, the number of second efficiency data is at least 1000, and the number of data sampling interval is 10 minutes based on the seasonal effective sample number.

[0017] The photovoltaic inverter full efficiency evaluation method, the characteristic quantification model learns and trains in a "feedforward neural network" based on the second efficiency data, and finally obtains the correlation between the power conversion efficiency of the inverter and the DC power and the correlation between the power conversion efficiency of the inverter and the DC voltage.

[0018] In the above technical solution, the photovoltaic inverter full efficiency evaluation method provided by the application has the following beneficial effects: a method for evaluating the overall comprehensive power generation efficiency of the inverter and the module and the relative power generation capacity of the module by using the operation history data of the photovoltaic inverter is established, which can effectively quantify and identify the full efficiency of the photovoltaic inverter, effectively identify low-efficiency inverters and low-energy modules, and guide the design of the photovoltaic inverter, which is conducive to energy saving and environmental protection, has the characteristics of low cost and wide coverage, and can provide quantitative basis for operation and maintenance decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a continuity and uniqueness efficiency characteristic diagram of a photovoltaic inverter full efficiency evaluation method. DETAILED DESCRIPTION

[0021] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the accompanying drawings in the embodiments of the present application to briefly introduce the technical solutions in the embodiments of the present application. Figure 1 The technical solutions in the embodiments of the present application are described clearly and completely, obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0022] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0023] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0024] In the description of the present application, it is understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0025] In addition, the terms "first", "second", etc. are used only for descriptive purposes and are not to be construed as indicating or implying relative importance or an ordered ranking of the indicated technical features. Thus, features defined with "first", "second" can include one or more of the features explicitly or implicitly. In the description of the present application, the meaning of "a plurality" is two or more, unless otherwise explicitly specified and limited.

[0026] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "fixing" and the like should be understood broadly, for example, it can be fixed connection, or detachable connection, or integrated; it can be directly connected, or indirectly connected through an intermediate medium, it can be the internal communication of two elements or the interaction relationship of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0027] In the present application, unless otherwise explicitly specified and limited, the "first" feature is "on" or "under" the "second" feature, which can include the direct contact of the first and second features, or the contact of the first and second features through another feature between them. Moreover, the first feature "on", "above" and "above" the second feature includes the first feature directly above and obliquely above the second feature, or only indicates that the first feature is higher than the second feature in horizontal height. The first feature "below", "below" and "below" the second feature includes the first feature directly below and obliquely below the second feature, or only indicates that the first feature is lower than the second feature in horizontal height.

[0028] In order for those skilled in the art to better understand the technical solutions of the present application, the present application will be further described in detail below with reference to the drawings.

[0029] A full efficiency evaluation method of a photovoltaic inverter includes the following steps:

[0030] Step S1: Collecting historical data of photovoltaic inverter operation as analysis samples, the historical data including time scale, inverter DC side voltage, inverter DC side current, inverter AC measured active power, inverter AC measured reactive power,

[0031] Step S2: Building efficiency / power model and efficiency / voltage model, generating discrete efficiency data from the historical data,

[0032] Step S3: Building a rule model to clean and filter the efficiency data to obtain discrete second efficiency data meeting the rules,

[0033] Step S4: Building a characteristic quantification model to identify efficiency characteristics with continuity and uniqueness from the discrete second efficiency data,

[0034] Step S5: constructing a photovoltaic inverter full efficiency index model representing photovoltaic inverter full efficiency based on the efficiency characteristics, and evaluating photovoltaic inverter full efficiency via the photovoltaic inverter full efficiency index model.

[0035] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the historical data sampling interval is 1 minute to 10 minutes in step S1.

[0036] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the efficiency / power model is constructed based on inverter AC active power or apparent power and inverter DC side power in step S2.

[0037] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the efficiency / voltage model is constructed based on inverter AC active power or apparent power, inverter DC side power and DC side voltage.

[0038] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the rule model includes an efficiency distribution model for eliminating power and constant power caused by errors or sensor failures, a power distribution model for eliminating unreasonable efficiency data under photovoltaic power conditions, and an aggregation degree model for eliminating a predetermined proportion of invalid data.

[0039] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the aggregation degree model eliminates invalid data accounting for a preset proportion of the total number based on fuzzy theory.

[0040] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the number of second efficiency data is at least 1000, and the number is the number of valid samples per quarter based on a data sampling interval of 10 minutes.

[0041] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the characteristic quantification module learns and trains in a "feedforward neural network" based on the second efficiency data, and finally obtains the correlation between inverter power conversion efficiency and DC power and the correlation between inverter power conversion efficiency and DC voltage.

[0042] The application only reads basic electric quantity data of the inverter AC / DC side, and establishes an inverter full efficiency mathematical model, a component power generation capacity comparison mathematical model, a regularized model and a full efficiency characteristic quantization model according to the photovoltaic inverter power generation principle. The basic electric quantity data is calculated by the inverter full efficiency mathematical model to obtain discrete full efficiency data, is calculated by the regularized model to obtain regular discrete full efficiency data, is calculated by the full efficiency characteristic quantization model to obtain continuous and unique inverter full efficiency characteristic description, is calculated by the component power generation capacity comparison mathematical model to obtain two quantization indexes of inverter and component overall comprehensive power generation efficiency and component relative power generation capacity ratio. Through the description of the inverter full efficiency characteristic curve, the efficiency characteristics of the inverter under different working conditions can be directly observed. The two indexes of inverter and component overall comprehensive power generation efficiency and component relative power generation capacity ratio can quantitatively reflect the power generation capacity of the photovoltaic component. The method can realize decoupling evaluation of the photovoltaic inverter efficiency and the photovoltaic component power generation capacity, and further calculate the theoretical potential of photovoltaic upgrading and efficiency increasing according to the quantization indexes, thereby providing quantitative basis for operation and maintenance decision-making.

[0043] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the inverter operation history data is used as the analysis sample, and test instruments and field tests are not needed. The history data includes time scale, inverter DC side voltage, inverter DC side current, inverter AC measured active power, inverter AC measured reactive power and other main operation data. The data sampling interval is 1 minute to 10 minutes, 1 minute is the best, and 10 minutes is the worst.

[0044] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, the model is constructed to generate discrete efficiency data from the history data. According to the photovoltaic power generation principle and the inverter working principle, the model includes an "efficiency / power" model, an "efficiency / voltage" model and the like. The model generated data reflects the distribution of the inverter "DC / AC" power conversion efficiency in the DC power generation power and DC voltage two-dimensional coordinate reference system.

[0045] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, a rule model is constructed to clean and select data. The rule model is used to eliminate data that does not conform to the photovoltaic power generation principle and the inverter working principle, so that the effective data samples play a leading role in the subsequent algorithm and truly reflect the power conversion efficiency characteristics of the inverter and the power generation capacity of the "photovoltaic-inverter system". The rule model includes an "efficiency distribution" model, a "power distribution" model, and an "aggregation degree" model. The "efficiency distribution" model is used to eliminate unreasonable efficiency and constant efficiency data caused by sampling errors or sensor failures. The "power distribution" model is used to eliminate unreasonable efficiency data under certain photovoltaic power conditions. The "aggregation degree" model is based on fuzzy theory and is used to extract the most likely effective data and eliminate a certain proportion of "ineffective or possibly ineffective" data to increase the proportion of "effective data" retained in the effective data samples. Taking a 10-minute data sampling interval as an example, the number of effective samples reaches 4300, and the data quality is excellent. It is not recommended to use less than 1000 effective samples per season.

[0046] In the preferred embodiment of the photovoltaic inverter full efficiency evaluation method, Figure 1 A photovoltaic inverter full efficiency evaluation method with continuity and uniqueness of efficiency characteristics. A characteristic quantization model is constructed to identify continuous and unique inverter full efficiency characteristics from discrete data. The characteristic quantization model includes an "efficiency / power" model and an "efficiency / voltage" model. The effective data samples are learned and trained in a "feedforward neural network" to obtain the relationship between the inverter power conversion efficiency and the direct current power, and the relationship between the inverter power conversion efficiency and the direct current voltage. The characteristics are described in a continuous and unique curve manner, which is intuitive and easy to compare the characteristics of inverters with other inverters. Because the curve is unique, the values of each point on the curve are also unique, providing convenience for more numerical analysis.

[0047] In the preferred embodiment of the full efficiency evaluation method of the photovoltaic inverter, the independent evaluation index is established to realize decoupling evaluation of the photovoltaic module power generation capacity and the inverter efficiency. The power generation capacity index model is based on the quantized output of the "efficiency / power" model and the "efficiency / voltage" model characteristics, and is used to reflect the comprehensive power generation capacity of the inverter under specific photovoltaic power generation parameter conditions. The index provides a more intuitive numerical value for comparing the power generation capacity of the inverter, combines the real photovoltaic power generation parameter conditions, makes up for the deficiency of the "efficiency / power characteristic" in simply reflecting the performance characteristics of the inverter, and quantitatively reflects the power generation capacity of the overall system composed of the photovoltaic-inverter. Finally, it should be pointed out that the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0048] The foregoing merely describes some exemplary embodiments of the present application by way of illustration, and it is needless to say that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present application. Therefore, the above drawings and descriptions are illustrative in nature and should not be understood as limiting the scope of protection of the claims of the present application.

Claims

1. A method for full efficiency evaluation of a photovoltaic inverter, characterized in that, It comprises the following steps: Step S1: Collecting historical data of photovoltaic inverter operation as analysis samples, the historical data including time scale, inverter DC side voltage, inverter DC side current, inverter AC side active power, inverter AC side reactive power, Step S2: Building efficiency / power model and efficiency / voltage model, generating discrete efficiency data from the historical data, the efficiency / power model being built based on inverter AC side active power or apparent power and inverter DC side power, Step S3: Building a rule model to clean and filter the efficiency data to obtain discrete second efficiency data meeting the rules, the rule model including an efficiency distribution model for eliminating error or sensor failure caused power and constant power, a power distribution model for eliminating unreasonable efficiency data under photovoltaic power conditions, and an aggregation degree model for eliminating a predetermined proportion of invalid data, Step S4: Building a characteristic quantification model to identify efficiency characteristics with continuity and uniqueness from the discrete second efficiency data, Step S5: Building a photovoltaic inverter total efficiency index model representing photovoltaic inverter total efficiency based on the efficiency characteristics, evaluating photovoltaic inverter total efficiency via the photovoltaic inverter total efficiency index model, obtaining the correlation between inverter power conversion efficiency and DC power and the correlation between inverter power conversion efficiency and DC voltage in a curve with continuity and uniqueness, and intuitively seeing the efficiency characteristics of the inverter under different working conditions through the description of the inverter total efficiency characteristic curve.

2. A method for evaluating the overall efficiency of a photovoltaic inverter according to claim 1, characterized in that, In step S1, the historical data sampling interval is 1 minute to 10 minutes.

3. A method for evaluating the overall efficiency of a photovoltaic inverter according to claim 1, characterized in that, In step S2, the efficiency / voltage model is built based on inverter AC side active power or apparent power, inverter DC side power and DC side voltage.

4. The method of claim 1, wherein, In step S3, the aggregation degree model eliminates a predetermined proportion of invalid data based on fuzzy theory.

5. A method for evaluating the overall efficiency of a photovoltaic inverter according to claim 1, characterized in that, The number of second efficiency data is at least 1000, and the number is based on the number of seasonal valid samples with a data sampling interval of 10 minutes.

6. A method for evaluating the overall efficiency of a photovoltaic inverter according to claim 1, characterized in that, The characteristic quantification model learns and trains in a "feedforward neural network" based on the second efficiency data, and finally obtains the correlation between inverter power conversion efficiency and DC power and the correlation between inverter power conversion efficiency and DC voltage.

Images