Photovoltaic power generation conversion rate evaluation method and system
Through the combination of NWP system and power generation prediction model, the real-time environment and power data of the photovoltaic power generation array are analyzed, which solves the problem of low credibility in the photovoltaic power generation conversion rate assessment, provides more accurate evaluation results, and improves grid-connected scheduling and failures The reference value of prediction.
Patent Information
- Application Number
- CN202310937147.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2043-07-28
AI Technical Summary
In the prior art, the predictive evaluation of photovoltaic power generation conversion rate is weak, and the evaluation results have low reference value for grid-connected scheduling management and photovoltaic power generation equipment failure prediction.
Real-time environmental data of the target photovoltaic array is obtained through the NWP system, the pre-constructed power generation power prediction model is input to obtain the power prediction results, and the conversion rate deviation analysis is performed based on real-time power information, and the conversion rate deviation index and stability index are obtained, and periodically collected Power data is used to output evaluation results.
It improves the credibility of photovoltaic power generation conversion rate assessment, provides high-value reference data for grid-connected scheduling and fault prediction, and enhances the reliability and practicality of the evaluation results.
Smart Images

Figure CN116960973B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of photovoltaic power generation technology, and in particular to a method and system for evaluating photovoltaic power generation conversion rate. Background Art
[0002] Under the dual pressure of energy crisis and environmental pollution, it is urgent to research and develop new energy to solve the future human demand for energy. New energy mainly includes wind energy, solar energy, ocean energy, geothermal energy, etc. Solar power generation includes solar thermal power generation and solar photovoltaic power generation. Among them, solar photovoltaic power generation is recognized by the whole society as the new energy technology with the most development potential and prospects in the world because of its unique advantages. Compared with traditional energy and other new energy sources, photovoltaic power generation has the following unique advantages: solar energy resources are very rich, with huge reserves, inexhaustible, and no need for transportation; the principle of photovoltaic power generation is the photovoltaic effect, which does not involve the process of converting mechanical energy into electromagnetic energy, is noiseless, and will not affect the daily life of surrounding residents; solar power generation is clean, environmentally friendly, and pollution-free; photovoltaic components have a long service life, stable operation, high reliability, and low maintenance costs. Combining the above advantages, solar power generation will become a more ideal form of power generation today and even in the future.
[0003] Photovoltaic power conversion rate refers to the ratio of converted electrical energy to received solar radiation energy. The higher the photovoltaic power conversion rate, the greater the electrical energy output per unit area, and the photovoltaic power generation power will also increase accordingly. At the same time, photovoltaic power generation power is also affected by factors such as light intensity and temperature. Based on the correlation between the two, the evaluation result of the conversion rate is obtained by reverse deduction under the condition of obtaining photovoltaic power generation.
[0004] In summary, there are technical problems in the prior art that the prediction and evaluation of photovoltaic power generation conversion rate has weak credibility and availability, and the evaluation results have low reference value for grid-connected scheduling management and photovoltaic power generation equipment failure prediction. Summary of the invention
[0005] Based on this, it is necessary to provide a photovoltaic power conversion rate evaluation method and system that can improve the credibility of the photovoltaic power generation conversion rate evaluation results, provide high-value reference data for the grid-connected scheduling and use of electricity obtained by photovoltaic power generation, and determine whether there are faults or defects in photovoltaic power generation equipment, in response to the above-mentioned technical problems.
[0006] In a first aspect, an embodiment of the present application provides a method for evaluating photovoltaic power generation conversion rate, the method comprising: obtaining a target layout position of a target photovoltaic array; obtaining target environmental data of the target layout position through an NWP system, the target environmental data comprising real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data; inputting the target environmental data into a pre-built power generation prediction model to obtain a target power prediction result; obtaining target real-time power information based on the target photovoltaic array; performing photovoltaic power generation conversion rate deviation analysis based on the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; performing periodic data collection on the target photovoltaic array at a preset power collection period to obtain a target power data set, wherein the target power data set comprises N target real-time power information; performing output power fluctuation analysis based on the target power data set to obtain a target stability index; and outputting the target conversion rate deviation index and the target stability index as the photovoltaic power generation conversion rate evaluation result of the target photovoltaic array.
[0007] In the second aspect, the embodiment of the present application also provides a photovoltaic power generation conversion rate evaluation system, the system comprising: a target layout position acquisition module, the target layout position acquisition module is used to obtain the target layout position of the target photovoltaic array; a target environment data acquisition module, the target environment data acquisition module is used to obtain the target environment data of the target layout position through the NWP system, the target environment data includes real-time irradiance data, real-time atmospheric temperature data, real-time relative humidity data; a target power prediction result acquisition module, the target power prediction result acquisition module is used to input the target environment data into a pre-built power generation prediction model to obtain a target power prediction result; a target real-time power information acquisition module, the target real-time power information acquisition module is used to obtain target real-time power information based on the target photovoltaic array; a photovoltaic power generation conversion rate deviation analysis module, the photovoltaic The power generation conversion rate deviation analysis module is used to perform photovoltaic power generation conversion rate deviation analysis based on the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; a target power data set acquisition module, the target power data set acquisition module is used to perform periodic data acquisition on the target photovoltaic array according to a preset power acquisition period to obtain a target power data set, wherein the target power data set includes N target real-time power information; a target stability index acquisition module, the target stability index acquisition module is used to perform output power fluctuation analysis based on the target power data set to obtain a target stability index; a photovoltaic power generation conversion rate evaluation result output module, the photovoltaic power generation conversion rate evaluation result output module is used to output the target conversion rate deviation index and the target stability index as the photovoltaic power generation conversion rate evaluation result of the target photovoltaic array.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] First, a target layout position of a target photovoltaic array is obtained; then, target environmental data of the target layout position is obtained through the NWP system, wherein the target environmental data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data; then, the target environmental data is input into a pre-constructed power generation prediction model to obtain a target power prediction result; then, target real-time power information is obtained according to the target photovoltaic array; photovoltaic power generation conversion rate deviation analysis is performed according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; then, periodic data collection is performed on the target photovoltaic array according to a preset power collection period to obtain a target power data set, wherein the target power data set includes N target real-time power information; output power fluctuation analysis is performed based on the target power data set to obtain a target stability index; and the target conversion rate deviation index and the target stability index are output as photovoltaic power generation conversion rate evaluation results of the target photovoltaic array. The invention solves the technical problems in the prior art of weak prediction and evaluation of photovoltaic power conversion rate, and low reference value of evaluation results for grid-connected dispatching management and photovoltaic power generation equipment fault prediction, thereby achieving the technical effect of improving the credibility of photovoltaic power conversion rate evaluation results, providing high-value reference data for grid-connected dispatching and use of electricity obtained by photovoltaic power generation, and judging whether photovoltaic power generation equipment has fault defects.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A schematic diagram of a process for evaluating a photovoltaic power generation conversion rate in an embodiment;
[0012] Figure 2 A schematic diagram of a process for obtaining a target power prediction result in a photovoltaic power generation conversion rate evaluation method in one embodiment;
[0013] Figure 3 The structure block diagram of a photovoltaic power generation conversion efficiency evaluation system in one embodiment.
[0014] Explanation of the accompanying drawings: target layout position acquisition module 11, target environment data acquisition module 12, target power prediction result acquisition module 13, target real-time power information acquisition module 14, photovoltaic power generation conversion rate deviation analysis module 15, target power data set acquisition module 16, target stability index acquisition module 17, photovoltaic power generation conversion rate evaluation result output module 18. DETAILED DESCRIPTION
[0015] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0016] After introducing the basic principles of the present application, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them. Example
[0017] like Figure 1 As shown, the present application provides a method for evaluating photovoltaic power generation conversion efficiency, the method comprising:
[0018] S100: Obtaining a target layout position of a target photovoltaic array;
[0019] S200: Obtaining target environment data of the target deployment location through the NWP system, wherein the target environment data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data;
[0020] Specifically, the photovoltaic power conversion rate refers to the ratio of the converted electrical energy to the received solar radiation energy. The photovoltaic array is the connection of multiple photovoltaic modules and more photovoltaic cells. The photovoltaic array is the largest photovoltaic power generation system. The target photovoltaic array here regards the entire power generation system as a whole, not just a photovoltaic panel; the target layout position refers to the geographical location information of the target photovoltaic array, obtains the longitude and latitude of the geographical location, and improves the recognition accuracy of the target layout position by the NWP system, where the NWP system is a numerical weather forecast system; the target environment data of the target layout position is obtained through the NWP system, where the target environment data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data. This step is mainly to collect the target layout position and obtain the target environment data to provide data support for subsequent research on the photovoltaic power conversion rate.
[0021] S300: Inputting the target environment data into a pre-built power generation prediction model to obtain a target power prediction result;
[0022] Specifically, firstly, a power generation prediction model is pre-constructed, and the power generation prediction model includes an input layer, a prediction unit activation layer, a power generation prediction layer and an output layer; wherein the input layer inputs the target environment data and transmits it to the power generation prediction layer; the power generation prediction layer determines what type the input target environment data belongs to, performs time identification on the target environment data, and obtains sensitive information of the target environment data; based on the sensitive information of the target environment data, the power generation prediction layer is activated, the power generation prediction layer activates the target power prediction unit, performs data analysis on the target environment data, and outputs the target power prediction result from the output layer.
[0023] like Figure 2 As shown, further, the steps of this application also include:
[0024] S310: The power generation prediction model includes an input layer, a prediction unit activation layer, a power generation prediction layer and an output layer, wherein the power generation prediction layer includes M power generation prediction units, where M is a positive integer;
[0025] Furthermore, the application steps also include:
[0026] S311: Collecting historical power generation record data of the target photovoltaic array, wherein the historical power generation record data includes a power generation data set and a power generation environment data set, and the power generation environment data set consists of an irradiance data set, an atmospheric temperature data set, and a relative humidity data set;
[0027] S312: Obtaining a season division time threshold, wherein the season division time threshold includes M environmental seasons and M time thresholds;
[0028] S313: dividing the historical power generation record data into M power generation record sub-data sets according to the season division time threshold, wherein each power generation record sub-data set has a season identifier and each power generation record sub-data set includes P groups of power generation record-irradiance record-atmospheric temperature record-relative humidity record;
[0029] S314: randomly extracting a first power generation record sub-dataset based on the M power generation record sub-datasets;
[0030] S315: constructing a power generation prediction space according to the power generation data set and the power generation environment data set, wherein the power generation prediction space dimension is the same as the power generation environment data set dimension;
[0031] S316: inputting the first power generation record sub-dataset into the power generation prediction space for data filling to obtain a first power generation prediction space;
[0032] S317: Obtain M power generation prediction spaces by analogy;
[0033] S318: Constructing the M power generation prediction units based on the M power generation prediction spaces.
[0034] Specifically, the historical power generation record data of the target photovoltaic array is collected through the NWP system, wherein the historical power generation record data refers to the power generation data set and the power generation environment data set of the photovoltaic array in the past period of time, the power generation data set refers to the collection of power generation data in the selected time period, and the power generation environment data set consists of an irradiance data set, an atmospheric temperature data set, and a relative humidity data set; the seasonal division time threshold is obtained, wherein the seasonal division time threshold includes M environmental seasons and M time thresholds, and the environmental season can be divided into four seasons: spring, summer, autumn, and winter; the time threshold refers to the number of days in each season at the target layout location; but due to the different target layout locations, for example, the target layout location is in the south, then If there are only three environmental seasons, namely spring, summer and autumn, then the time in autumn will be more than that in spring and summer; according to the season division time threshold, the historical power generation record data is divided into M power generation record sub-datasets, wherein the power generation record sub-dataset is a power generation power data set and a power generation environment data set within a period of time, where M can be 4, 8, 12, etc., that is, it can be divided into four seasons, namely spring, summer, autumn and winter, or it can be divided into early spring, late spring, early summer, late summer, early autumn, late autumn, early winter, late winter, etc. The more detailed the division, the more accurate the photovoltaic power generation conversion rate obtained in the end; wherein each power generation record sub-dataset has a divided season identifier, for example, in the historical power generation record data of the target photovoltaic array in spring, each power generation record The sub-datasets include P groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records, where p is a positive integer 1, 2, 3, etc. For example, in the divided spring season, spring is from January 1 to March 31, and 90 groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records are obtained by day as the time unit; based on the M power generation record sub-datasets, the first power generation record sub-dataset is randomly extracted, wherein the first power generation record sub-dataset is the first power generation record sub-dataset sorted according to the divided season time, for example, the first power generation record sub-dataset here refers to the generator rate sub-dataset of the spring season; a power generation prediction space is constructed according to the power generation data set and the power generation environment data set, wherein the The dimension of the power generation prediction space is the same as the data dimension of the power generation environment data set. The dimension of the power generation prediction space means that the irradiance, atmospheric temperature and relative humidity of the layout location of the power generation prediction are the same as the dimension of the power generation environment data set; the first power generation record sub-dataset is input into the power generation prediction space for data filling, that is, the power generation prediction space is regarded as a large space, and the first power generation record sub-dataset is regarded as a small space and embedded in the power generation prediction space to obtain the first power generation prediction space, and so on to obtain M power generation prediction spaces, wherein the M power generation prediction spaces are equal to the M environmental seasons; that is, the power generation prediction layer is constructed based on the M power generation prediction spaces.
[0035] S320: Inputting the target environment data into the prediction unit activation layer for time recognition to obtain target environment sensitive information;
[0036] Furthermore, the application steps also include:
[0037] S321: construct a keyword recognition model;
[0038] S322: embedding the keyword recognition model into the prediction unit activation layer;
[0039] S323: inputting the target environment data into the prediction unit activation layer, performing time recognition based on the keyword recognition model, and obtaining the target collection time of the target environment data;
[0040] S324: Traverse and compare the target acquisition time with the season division time threshold to obtain the target environmental sensitive information.
[0041] Specifically, a keyword recognition model is constructed, keywords are obtained according to the M divided environmental seasons, such as spring, summer, autumn, and winter, and then spring, summer, autumn, and winter are used as keywords. When the target environmental data is input into the prediction unit activation layer, keywords are extracted from the target environment, and then classified into the divided environment for time recognition; the keyword recognition model is embedded in the prediction unit activation layer, the target environmental data is input into the prediction unit activation layer, and time recognition is performed based on the keyword recognition model, that is, the input target environmental data is analyzed to which day of which season, and the target collection time of the target environmental data is obtained; the target collection time is traversed and compared with the season division time threshold to obtain the target environmental sensitive information, wherein the target environmental sensitive information refers to the environmental season in which the target collection time is located.
[0042] S330: Generate a prediction unit activation instruction according to the target environment sensitive information;
[0043] S340: activating a target power prediction unit in the power generation prediction layer based on the prediction unit activation instruction, wherein the target power prediction unit is an unspecified one of the M power generation prediction units;
[0044] S350: The target power prediction unit performs data analysis based on the target environment data and outputs the target power prediction result.
[0045] Furthermore, the application steps also include:
[0046] S351: Preset data screening thresholds, wherein the data screening thresholds include a radiation data screening threshold, a temperature data screening threshold, and a humidity data screening threshold;
[0047] S352: generating a target irradiance constraint interval according to the irradiance data screening threshold and the real-time irradiance data;
[0048] S353: generating a target temperature constraint interval according to the temperature data screening threshold and the real-time atmospheric temperature data;
[0049] S354: generating a target humidity constraint interval according to the humidity data screening threshold and the real-time relative humidity data;
[0050] S355: Inputting the target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval into the target power prediction unit for data screening, and obtaining L groups of power generation records - irradiance records - atmospheric temperature records - relative humidity records whose environmental data simultaneously fall into the target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval;
[0051] S356: Calculate the Euclidean distance between the target environment data and the L groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records to obtain L target Euclidean distances;
[0052] S357: Serializing the L target Euclidean distances, and extracting the power generation records corresponding to the extreme values of the Euclidean distances as the target power prediction results.
[0053] Specifically, a spatial rectangular coordinate system O-xyz is established, where the fixed point O is the origin of the coordinate system, x is temperature, y is irradiance, and z is humidity. A data screening threshold is preset, wherein the data screening threshold includes an irradiance data screening threshold, a temperature data screening threshold, and a humidity data screening threshold, wherein the preset data screening threshold is preset in combination with actual data and is set by the staff. For example, the temperature data screening threshold can be set to ±5°C, and then combined with the real-time atmospheric temperature data to generate a target temperature constraint interval, and the maximum and minimum values are marked on the x-axis; the target irradiance constraint interval and the target humidity constraint interval are obtained by analogy, and are marked on the y-axis and z-axis respectively; the target irradiance constraint interval, the target temperature constraint interval, and the target humidity constraint interval are input into the target power prediction unit for data screening, and L groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records whose environmental data simultaneously falls into the target irradiance constraint interval, the target temperature constraint interval, and the target humidity constraint interval are obtained, wherein L is a positive integer, and the Euclidean distance calculation formula is used:
[0054] ,
[0055] Get L target Euclidean distances, where , , Refers to real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data. , , It refers to the irradiance, atmospheric temperature, and relative humidity of the L groups, and the L target Euclidean distances are calculated; the L target Euclidean distances are serialized, and the power generation records corresponding to the extreme values of the Euclidean distances are extracted as the target power prediction results. Because if the table is set only according to the historical power generation record data and the target environmental data is brought in, the data obtained is inaccurate. Here, the coordinate system is established, the Euclidean distance is calculated, and the serialization process is performed to improve the credibility and accuracy of the photovoltaic power generation conversion rate evaluation results.
[0056] Specifically, the power generation prediction model includes an input layer, a prediction unit activation layer, a power generation prediction layer and an output layer, wherein the power generation prediction layer includes M power generation prediction units, M is a positive integer, wherein the input layer is for inputting the target environment data, the prediction unit activation layer is for analyzing the input target environment data, classifying it into the M divided environmental seasons, extracting keywords, analyzing the target collection time of the target environment data, inputting it into the corresponding M-th power generation prediction space in the power generation prediction layer, and outputting the target power prediction result according to the power generation prediction result; inputting the target environment data into the prediction unit activation layer for time recognition, that is, keyword recognition, obtaining target environment sensitive information, wherein the target environment sensitive information specifically refers to the target collection time of the target environment data; generating a prediction unit activation instruction according to the target collection time, wherein the prediction unit activation instruction refers to the time threshold for activating the season division in the prediction unit activation layer; activating the target power prediction unit in the power generation prediction layer based on the prediction unit activation instruction, the target power prediction unit performs data analysis based on the target environment data, and outputs the target power prediction result, wherein the target power prediction result is a threshold range, not a specific result. Here, by constructing the power generation prediction model, the target power prediction result is obtained, which provides data support for the subsequent photovoltaic power generation conversion rate deviation analysis.
[0057] S400: Obtaining target real-time power information based on the target photovoltaic array;
[0058] S500: Performing photovoltaic power generation conversion rate deviation analysis according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index;
[0059] Specifically, target real-time power information is obtained based on the target photovoltaic array, wherein the target photovoltaic array can directly read the target real-time power information, and photovoltaic power generation conversion rate deviation analysis is performed according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; the target power prediction result is used as the numerator to subtract the target real-time power information from the target power prediction result, and the target power prediction result is used as the denominator to obtain the target conversion rate deviation index, and the difference ratio can more accurately reflect the target conversion rate deviation index than simply finding the difference between the two.
[0060] S600: performing periodic data collection on the target photovoltaic array in a preset power collection period to obtain a target power data set, wherein the target power data set includes N pieces of target real-time power information;
[0061] Specifically, a preset power collection period is used to periodically collect data from the target photovoltaic array, that is, a power collection period is set by the staff, and there is no restriction here. For example, one hour is divided, and periodic data collection is performed on the target photovoltaic array every five minutes within one hour. The collected data are integrated to obtain a target power data set, that is, a power data set of the target photovoltaic array; wherein the target power data set includes N real-time power information of the targets.
[0062] S700: Perform output power fluctuation analysis based on the target power data set to obtain a target stability index;
[0063] Specifically, an output power fluctuation analysis is performed based on the target power data set, and the target power data set is input into a power fluctuation analysis function to obtain the target stability index.
[0064] Furthermore, the application steps include:
[0065] S710: Preset power stability threshold;
[0066] S720: Inputting the target power data set into a power fluctuation analysis function to obtain the target stability index;
[0067] S730: Calculate the deviation between the target stability index and the preset power stability threshold, and adjust the preset power collection period based on the deviation calculation result to obtain an optimized power collection period;
[0068] S740: Setting the output power collection frequency based on the deviation calculation result;
[0069] S750: Perform periodic data collection and output power fluctuation analysis on the target photovoltaic array based on the optimized power collection period and the output power collection frequency.
[0070] Specifically, a power stability threshold is preset, which is set by the staff and is not limited here. The target power data set is input into the power fluctuation analysis function to obtain the target stability index. Here, the power fluctuation analysis function is:
[0071] ,
[0072] in, For the The real-time power information of the target, is the average value of the real-time power information of N targets, is the number of target real-time power information, For the target stability index, calculate the deviation between the target stability index and the preset power stability threshold, adjust the preset power collection period based on the deviation calculation result to obtain the optimized power collection period, and set the output power collection frequency based on the deviation calculation result; based on the optimized power collection period and the output power collection frequency, perform periodic data collection and output power fluctuation analysis on the target photovoltaic array.
[0073] Furthermore, the application steps also include:
[0074] S760: Preset a conversion rate deviation threshold;
[0075] S770: Determine whether the target conversion rate deviation index satisfies the preset conversion rate deviation threshold, and determine whether the target stability index satisfies the preset power stability threshold;
[0076] S780: If the target stability index does not meet the preset power stability threshold, and the target conversion rate deviation index does not meet the preset conversion rate deviation threshold, a photovoltaic power generation early warning reminder is generated.
[0077] Specifically, a conversion rate deviation threshold is preset, where the conversion rate deviation threshold is numerically set based on the experience of experts in this field. In order to reduce the subjectivity of the data, reference data given by multiple experts are obtained, and the average is calculated to determine whether the target conversion rate deviation index meets the preset conversion rate deviation threshold, and whether the target stability index meets the preset power stability threshold; if the target stability index does not meet the preset power stability threshold, and the target conversion rate deviation index does not meet the preset conversion rate deviation threshold, a photovoltaic power generation early warning reminder is generated. If only the target stability index does not meet the preset power stability threshold, or only the target conversion rate deviation index does not meet the preset conversion rate deviation threshold, it may be caused by an environmental emergency, such as wind blowing, rising temperature, clouds passing through the sky, etc., so a photovoltaic power generation early warning reminder will only be generated if both conditions are met at the same time.
[0078] S800: Outputting the target conversion rate deviation index and the target stability index as a photovoltaic power generation conversion rate evaluation result of the target photovoltaic array.
[0079] Specifically, according to the target conversion rate deviation index and target stability index obtained above, the evaluation is performed from these two dimensions to obtain the evaluation result of the target photovoltaic power generation conversion rate. This application solves the problem that the prediction and evaluation of photovoltaic power generation conversion rate in the prior art are of low credibility and availability, and the evaluation results have low reference value for grid-connected scheduling management and photovoltaic power generation equipment failure prediction, and achieves the technical effect of improving the credibility of photovoltaic power generation conversion rate evaluation results, providing high-value reference data for the grid-connected scheduling and use of photovoltaic power generation and judging whether photovoltaic power generation equipment has fault defects. Example
[0080] like Figure 3 As shown, the present application also provides a photovoltaic power generation conversion rate evaluation system, wherein the system includes:
[0081] A target layout position obtaining module 11, wherein the target layout position obtaining module is used to obtain a target layout position of a target photovoltaic array;
[0082] A target environment data acquisition module 12, the target environment data acquisition module is used to obtain target environment data of the target deployment location through the NWP system, the target environment data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data;
[0083] A target power prediction result obtaining module 13, wherein the target power prediction result obtaining module is used to input the target environment data into a pre-built power generation prediction model to obtain a target power prediction result;
[0084] A target real-time power information obtaining module 14, wherein the target real-time power information obtaining module is used to obtain target real-time power information based on the target photovoltaic array;
[0085] A photovoltaic power generation conversion rate deviation analysis module 15, the photovoltaic power generation conversion rate deviation analysis module is used to perform photovoltaic power generation conversion rate deviation analysis according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index;
[0086] A target power data set acquisition module 16, the target power data set acquisition module is used to perform periodic data acquisition on the target photovoltaic array in a preset power acquisition period to obtain a target power data set, wherein the target power data set includes N target real-time power information;
[0087] A target stability index obtaining module 17, wherein the target stability index obtaining module is used to perform output power fluctuation analysis based on the target power data set to obtain a target stability index;
[0088] The photovoltaic power generation conversion rate evaluation result output module 18 is used to output the target conversion rate deviation index and the target stability index as the photovoltaic power generation conversion rate evaluation result of the target photovoltaic array.
[0089] Furthermore, the embodiment of the present application also includes:
[0090] A power generation prediction model module, wherein the power generation prediction model module is used for the power generation prediction model and includes an input layer, a prediction unit activation layer, a power generation prediction layer and an output layer, wherein the power generation prediction layer includes M power generation prediction units, where M is a positive integer;
[0091] A target environment sensitive information acquisition module, the target environment sensitive information acquisition module is used to input the target environment data into the prediction unit activation layer for time recognition, and obtain target environment sensitive information;
[0092] A prediction unit activation instruction generation module, the prediction unit activation instruction generation module is used to generate a prediction unit activation instruction according to the target environment sensitive information;
[0093] a target power prediction unit activation module, the target power prediction unit activation module being used to activate a target power prediction unit in the power generation prediction layer based on the prediction unit activation instruction, wherein the target power prediction unit is an unspecified one of the M power generation prediction units;
[0094] A target power prediction result output module is used by the target power prediction unit to perform data analysis based on the target environment data and output the target power prediction result.
[0095] Furthermore, the embodiment of the present application also includes:
[0096] A historical power generation record data acquisition module, the historical power generation record data acquisition module is used to collect the historical power generation record data of the target photovoltaic array, wherein the historical power generation record data includes a power generation data set and a power generation environment data set, and the power generation environment data set consists of an irradiance data set, an atmospheric temperature data set, and a relative humidity data set;
[0097] A season division time threshold acquisition module, wherein the season division time threshold acquisition module is used to obtain a season division time threshold, wherein the season division time threshold includes M environmental seasons and M time thresholds;
[0098] A power generation record sub-dataset acquisition module, the power generation record sub-dataset acquisition module is used to divide the historical power generation record data into M power generation record sub-datasets according to the season division time threshold, wherein each power generation record sub-dataset has a season identifier and each power generation record sub-dataset includes P groups of power generation record-irradiance record-atmospheric temperature record-relative humidity record;
[0099] A first power generation record sub-dataset extraction module, the first power generation record sub-dataset extraction module is used to randomly extract a first power generation record sub-dataset based on the M power generation record sub-datasets;
[0100] A power generation prediction space construction module, the power generation prediction space construction module is used to construct a power generation prediction space according to the power generation data set and the power generation environment data set, wherein the power generation prediction space dimension is the same as the power generation environment data set data dimension;
[0101] A first power generation prediction space acquisition module, the first power generation prediction space acquisition module is used to input the first power generation record sub-data set into the power generation prediction space for data filling, so as to obtain a first power generation prediction space;
[0102] A power generation prediction space acquisition module, wherein the power generation prediction space acquisition module is used to obtain M power generation prediction spaces in sequence and by analogy;
[0103] A power generation prediction unit construction module is used to construct the M power generation prediction units based on the M power generation prediction spaces.
[0104] Furthermore, the embodiment of the present application also includes:
[0105] A keyword recognition model building module, wherein the keyword recognition model building module is used to build a keyword recognition model;
[0106] A keyword recognition model embedding module, the keyword recognition model embedding module is used to embed the keyword recognition model into the prediction unit activation layer;
[0107] A target collection time acquisition module, the target collection time acquisition module is used to input the target environment data into the prediction unit activation layer, perform time recognition based on the keyword recognition model, and obtain the target collection time of the target environment data;
[0108] The target environment sensitive information acquisition module is used to traverse and compare the target acquisition time with the season division time threshold to obtain the target environment sensitive information.
[0109] Furthermore, the embodiment of the present application also includes:
[0110] A data screening threshold preset module, wherein the data screening threshold preset module is used to preset data screening thresholds, wherein the data screening thresholds include an irradiation data screening threshold, a temperature data screening threshold, and a humidity data screening threshold;
[0111] A target irradiance constraint interval generation module, the target irradiance constraint interval generation module is used to generate a target irradiance constraint interval according to the irradiance data screening threshold and the real-time irradiance data;
[0112] a target temperature constraint interval generation module, the target temperature constraint interval generation module being used to generate a target temperature constraint interval according to the temperature data screening threshold and the real-time atmospheric temperature data;
[0113] A target humidity constraint interval generation module, the target humidity constraint interval generation module is used to generate a target humidity constraint interval according to the humidity data screening threshold and the real-time relative humidity data;
[0114] A data screening module, the data screening module is used to input the target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval into the target power prediction unit for data screening, and obtain L groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records whose environmental data simultaneously fall into the target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval;
[0115] A target environment data calculation module, the target environment data calculation module is used to calculate the Euclidean distance between the target environment data and the L groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records, and obtain L target Euclidean distances;
[0116] The target power prediction result obtaining module is used to serialize the L target Euclidean distances and extract the power generation records corresponding to the extreme values of the Euclidean distances as the target power prediction results.
[0117] Furthermore, the embodiment of the present application also includes:
[0118] A power stability threshold preset module, wherein the power stability threshold preset module is used to preset a power stability threshold;
[0119] a target stability index obtaining module, the target stability index obtaining module being used to input the target power data set into a power fluctuation analysis function to obtain the target stability index;
[0120] An optimized power collection period acquisition module, the optimized power collection period acquisition module is used to calculate the deviation between the target stability index and the preset power stability threshold, and adjust the preset power collection period based on the deviation calculation result to obtain an optimized power collection period;
[0121] An output power acquisition frequency setting module, the output power acquisition frequency setting module is used to set the output power acquisition frequency based on the deviation calculation result;
[0122] An output power fluctuation analysis module is used to perform periodic data collection and output power fluctuation analysis on the target photovoltaic array based on the optimized power collection period and the output power collection frequency.
[0123] Furthermore, the embodiment of the present application also includes:
[0124] A conversion rate deviation threshold preset module, wherein the conversion rate milk tea threshold preset module is used to preset a conversion rate deviation threshold;
[0125] a target conversion rate deviation judgment module, the target conversion rate deviation judgment module is used to judge whether the target conversion rate deviation index meets the preset conversion rate deviation threshold, and judge whether the target stability index meets the preset power stability threshold;
[0126] A photovoltaic power generation early warning reminder generation module is used to generate a photovoltaic power generation early warning reminder if the target stability index does not meet the preset power stability threshold and the target conversion rate deviation index does not meet the preset conversion rate deviation threshold.
[0127] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0128] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for evaluating photovoltaic power generation conversion efficiency, characterized in that: The method comprises: Obtaining a target layout position of a target photovoltaic array; Obtain target environmental data of the target deployment location through the NWP system, wherein the target environmental data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data; Inputting the target environment data into a pre-built power generation prediction model to obtain a target power prediction result; Obtaining target real-time power information based on the target photovoltaic array; Perform photovoltaic power generation conversion rate deviation analysis according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; Performing periodic data collection on the target photovoltaic array in a preset power collection period to obtain a target power data set, wherein the target power data set includes N pieces of target real-time power information; Perform output power fluctuation analysis based on the target power data set to obtain a target stability index; Outputting the target conversion rate deviation index and the target stability index as a photovoltaic power generation conversion rate evaluation result of the target photovoltaic array; Inputting the target environment data into a pre-built power generation prediction model to obtain a target power prediction result includes: The power generation prediction model comprises an input layer, a prediction unit activation layer, a power generation prediction layer and an output layer, wherein the power generation prediction layer comprises M power generation prediction units, where M is a positive integer; Inputting the target environment data into the prediction unit activation layer for time recognition to obtain target environment sensitive information; generating a prediction unit activation instruction according to the target environment sensitive information; activating a target power prediction unit in the power generation prediction layer based on the prediction unit activation instruction, wherein the target power prediction unit is an unspecified one of the M power generation prediction units; The target power prediction unit performs data analysis based on the target environment data and outputs the target power prediction result; Collecting historical power generation record data of the target photovoltaic array, wherein the historical power generation record data includes a power generation data set and a power generation environment data set, and the power generation environment data set consists of an irradiance data set, an atmospheric temperature data set, and a relative humidity data set; Obtaining a season division time threshold, wherein the season division time threshold includes M environmental seasons and M time thresholds; Dividing the historical power generation record data into M power generation record sub-data sets according to the season division time threshold, wherein each power generation record sub-data set has a season identifier and each power generation record sub-data set includes P groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records; Randomly extracting a first power generation record sub-dataset based on the M power generation record sub-datasets; Constructing a power generation prediction space according to the power generation data set and the power generation environment data set, wherein the power generation prediction space dimension is the same as the power generation environment data set data dimension; Inputting the first power generation record sub-dataset into the power generation prediction space for data filling to obtain a first power generation prediction space; By analogy, M power generation prediction spaces are obtained; The M power generation prediction units are constructed based on the M power generation prediction spaces.
2. The method according to claim 1, characterized in that The target environment data is input into the prediction unit activation layer for time recognition to obtain target environment sensitive information, including: Build a keyword recognition model; embedding the keyword recognition model into the prediction unit activation layer; Inputting the target environment data into the prediction unit activation layer, performing time recognition based on the keyword recognition model, and obtaining the target collection time of the target environment data; The target acquisition time is traversed and compared with the seasonal division time threshold to obtain the target environmental sensitive information.
3. The method according to claim 1, characterized in that The target power prediction unit performs data analysis based on the target environment data and outputs the target power prediction result, including: Preset data screening thresholds, wherein the data screening thresholds include radiation data screening thresholds, temperature data screening thresholds, and humidity data screening thresholds; Generate a target irradiance constraint interval according to the irradiance data screening threshold and the real-time irradiance data; generating a target temperature constraint interval according to the temperature data screening threshold and the real-time atmospheric temperature data; generating a target humidity constraint interval according to the humidity data screening threshold and the real-time relative humidity data; The target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval are input into the target power prediction unit for data screening, and L groups of power generation records - irradiance records - atmospheric temperature records - relative humidity records are obtained, whose environmental data simultaneously fall into the target irradiance constraint interval, the target temperature constraint interval and the target humidity constraint interval; Calculating the Euclidean distances between the target environmental data and the L groups of power generation records-irradiance records-atmospheric temperature records-relative humidity records to obtain L target Euclidean distances; The L target Euclidean distances are serialized, and the generated power records corresponding to the extreme values of the Euclidean distances are extracted as the target power prediction results.
4. The method according to claim 1, characterized in that Performing output power fluctuation analysis based on the target power data set to obtain a target stability index includes: Preset power stability threshold; Inputting the target power data set into a power fluctuation analysis function to obtain the target stability index; Calculating the deviation between the target stability index and the preset power stability threshold, and adjusting the preset power collection period based on the deviation calculation result to obtain an optimized power collection period; Setting the output power collection frequency based on the deviation calculation result; Based on the optimized power collection period and the output power collection frequency, periodic data collection and output power fluctuation analysis are performed on the target photovoltaic array.
5. The method according to claim 4, characterized in that The method further comprises: Preset conversion rate deviation threshold; Determining whether the target conversion rate deviation index satisfies the preset conversion rate deviation threshold, and determining whether the target stability index satisfies the preset power stability threshold; If the target stability index does not meet the preset power stability threshold, and the target conversion rate deviation index does not meet the preset conversion rate deviation threshold, a photovoltaic power generation early warning reminder is generated.
6. A photovoltaic power generation conversion rate evaluation system, characterized in that: The system comprises: A target layout position obtaining module, wherein the target layout position obtaining module is used to obtain a target layout position of a target photovoltaic array; A target environment data acquisition module, the target environment data acquisition module is used to obtain target environment data of the target deployment location through the NWP system, the target environment data includes real-time irradiance data, real-time atmospheric temperature data, and real-time relative humidity data; A target power prediction result obtaining module, wherein the target power prediction result obtaining module is used to input the target environment data into a pre-built power generation prediction model to obtain a target power prediction result; A target real-time power information obtaining module, wherein the target real-time power information obtaining module is used to obtain target real-time power information based on the target photovoltaic array; A photovoltaic power generation conversion rate deviation analysis module, the photovoltaic power generation conversion rate deviation analysis module is used to perform photovoltaic power generation conversion rate deviation analysis according to the target power prediction result and the target real-time power information to obtain a target conversion rate deviation index; A target power data set acquisition module, the target power data set acquisition module is used to perform periodic data acquisition on the target photovoltaic array in a preset power acquisition period to obtain a target power data set, wherein the target power data set includes N target real-time power information; A target stability index obtaining module, wherein the target stability index obtaining module is used to perform output power fluctuation analysis based on the target power data set to obtain a target stability index; A photovoltaic power generation conversion rate evaluation result output module is used to output the target conversion rate deviation index and the target stability index as the photovoltaic power generation conversion rate evaluation result of the target photovoltaic array.
