New energy photovoltaic station temperature observation and restoration method, system, equipment and medium
Patent Information
- Application Number
- CN202511057886.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-30
- Publication Date
- 2025-11-21
AI Technical Summary
现有温度修复方法未能充分挖掘区域温度场的空间协同变化规律，导致云层突变和热斑干扰等场景下修复结果失真，且单次修复模型易引发误差逐级累积，难以应对非均匀遮挡的复杂工况。
采用迭代重构修复方法，通过EOF分解获取模态信息，剔除错误观测资料，进行迭代重构，直至差值小于阈值，结合模态内迭代和模态间递进，实现对光伏站温度的精确修复。
显著提升了极端波动场景下的修复精度和鲁棒性，有效解决了误差累积问题，提高了光伏站温度观测的准确性和连续性。
Smart Images
Figure CN120994944A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power generation monitoring technology, and in particular to a method, system, equipment and medium for temperature observation and repair of new energy photovoltaic stations. Background Technology
[0002] New energy power generation systems are highly dependent on meteorological resources. Their inherent intermittency and volatility require high-precision meteorological monitoring to improve power generation forecasting and grid stability. As a core parameter affecting power generation efficiency, the accuracy and continuity of photovoltaic panel temperature observation data are directly related to new energy consumption, power forecast accuracy, and refined operation and management of power plants.
[0003] In the operation monitoring of new energy photovoltaic power plants, accurate observation of photovoltaic panel temperature is crucial for optimizing power generation efficiency and protecting equipment. However, existing temperature restoration methods have significant limitations: traditional spatial interpolation techniques (such as inverse distance weighting and kriging) utilize geographical proximity but fail to fully explore the spatial coordinated changes in the regional temperature field, leading to distortion of restoration results in scenarios such as sudden cloud formations and hot spot interference. At the same time, single-stage restoration models lack residual iteration suppression mechanisms, which easily lead to the gradual accumulation of errors. Especially for problems with missing spatial correlation, existing methods cannot dynamically correlate the reconstructed values of the target site with the structural characteristics of the temperature fields of neighboring sites, making it difficult to cope with complex operating conditions of non-uniform shading. Summary of the Invention
[0004] This invention provides a method, system, equipment, and medium for temperature monitoring and repair of new energy photovoltaic stations, thereby effectively solving the problems pointed out in the background art.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0006] A method for temperature monitoring and repair of a new energy photovoltaic station includes:
[0007] S1, to obtain observational data on the temperature of photovoltaic panels in new energy photovoltaic stations;
[0008] S2, Based on the observation data, after removing erroneous observation data, construct an iterative reconstruction and repair matrix;
[0009] S3, perform EOF decomposition on the iterative reconstruction and repair matrix to obtain the first mode information;
[0010] S4, Based on the first modal information, the erroneous observation data is reconstructed to obtain the reconstructed data values;
[0011] S5, Substitute the data reconstruction value into the iterative reconstruction repair matrix, and repeat S3-S4 until the absolute value of the difference between the two reconstruction values is less than the empirical threshold, and take the data reconstruction value of the latter as the first modality reconstruction result.
[0012] S6, subtract the current round's iterative reconstruction repair matrix from the first modal reconstruction result element by element, and use the difference as the input for the next round's iterative reconstruction repair matrix. Repeat the modal decomposition and reconstruction process until the absolute value of all differences is lower than the global convergence threshold. The output iterative reconstruction repair matrix is the final temperature repair value.
[0013] Furthermore, the observation data includes time-series temperature values from individual photovoltaic panel monitoring points.
[0014] Furthermore, the iterative reconstruction and repair matrix is A. p×n , is represented as:
[0015]
[0016] Where p is the total number of times, n is the number of photovoltaic sites, m is the site number where the target error value is located, x is the time number where the target error value is located, and T i,j This represents the effective temperature observation value at the j-th station at the i-th time.
[0017] Further, the iterative reconstruction and repair matrix is decomposed using EOF to obtain a spatial mode matrix and a temporal coefficient matrix, wherein the spatial mode matrix contains the spatial mode vector of the first mode, and the temporal coefficient matrix contains the temporal coefficient vector of the first mode, as shown in the formula:
[0018]
[0019] in, Let T be the mode vector at temperature T. Let V be the system vector, k represents the k-th mode, and V p×p Z is the spatial mode matrix. p×n This is the time coefficient matrix.
[0020] Furthermore, based on the spatial mode vector and temporal coefficient vector of the first mode, data reconstruction is performed on the erroneous observation data to generate the first mode reconstruction result, as shown in the formula:
[0021]
[0022] in, The target station temperature value after first-mode reconstruction, v 1,1 The coefficients of the first mode at the target time x, z 1，m The weight of the first modality at site m, where m is the target site index and x is the target site index.
[0023] Furthermore, the iterative reconstruction and repair matrix contains temperature observation data from three consecutive days.
[0024] Furthermore, modal iterative reconstruction is a two-level iterative mechanism, including intra-modal iteration and inter-modal progression.
[0025] Furthermore, the intra-modal iteration includes repeated decomposition, reconstruction, and convergence verification of a single mode; the inter-modal progression is that after mode k converges, the output value is input into mode k+1 for iteration.
[0026] A temperature monitoring and repair system for a new energy photovoltaic station includes:
[0027] The data acquisition module acquires observational data on the temperature of photovoltaic panels in new energy photovoltaic stations;
[0028] The repair matrix construction module, based on the observation data, removes erroneous observations and constructs an iteratively reconstructed repair matrix;
[0029] The EOF decomposition module performs EOF decomposition on the iterative reconstruction and repair matrix to obtain the first mode information;
[0030] The data reconstruction module reconstructs the erroneous observation data based on the first modal information to obtain the reconstructed data values;
[0031] The reconstruction result acquisition module inputs the data reconstruction value into the iterative reconstruction repair matrix until the absolute value of the difference between two reconstruction values is less than an empirical threshold, and then takes the data reconstruction value of the latter as the first modality reconstruction result.
[0032] The temperature acquisition module is repaired by updating the iterative reconstruction repair matrix based on the first modal reconstruction result and iteratively executing until the final repair temperature value is obtained.
[0033] The present invention also includes a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described above.
[0034] The present invention also includes a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described above.
[0035] The technical solution of this invention can achieve the following technical effects:
[0036] It effectively solves the problem of error accumulation caused by neglecting spatial correlation in the temperature repair of photovoltaic stations. By integrating the spatial structure characteristics of the temperature fields of adjacent stations with the iterative correction mechanism, it significantly improves the repair accuracy and robustness under extreme fluctuation scenarios. Attached Figure Description
[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1 This is a flowchart illustrating a method for temperature monitoring and repair of a new energy photovoltaic station.
[0039] Figure 2 This is a schematic diagram of the structure of the computer device of the present invention. Detailed Implementation
[0040] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.
[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0042] Example 1
[0043] like Figure 1 As shown, this invention provides a method for temperature observation and repair of a new energy photovoltaic station, the method comprising:
[0044] S1, to obtain observational data on the temperature of photovoltaic panels in new energy photovoltaic stations;
[0045] S2, based on the observation data, after removing erroneous observation data, construct an iterative reconstruction and repair matrix;
[0046] S3, perform EOF decomposition on the iterative reconstruction repair matrix to obtain the first mode information;
[0047] S4. Based on the information of the first mode, the erroneous observation data is reconstructed to obtain the reconstructed data values;
[0048] S5, Substitute the data reconstruction value into the iterative reconstruction repair matrix, and repeat S3-S4 until the absolute value of the difference between the two reconstruction values is less than the empirical threshold, and take the data reconstruction value of the latter as the first mode reconstruction result.
[0049] S6. Subtract the current round's iterative reconstruction repair matrix from the first modal reconstruction result element by element. Use the difference as the input for the next round's iterative reconstruction repair matrix. Repeat the modal decomposition and reconstruction process until the absolute value of all differences is lower than the global convergence threshold. The output iterative reconstruction repair matrix is the final temperature repair value.
[0050] Specifically, the temperature observation quality control method proposed by Shao Yuxing et al. is first used to accurately identify erroneous temperature observations of photovoltaic panels. To avoid loss of generality, the process of repairing the temperature observation of a randomly selected erroneous photovoltaic panel is described below.
[0051] Temperature observations of all photovoltaic panels within the space were selected, with the total number of observation stations denoted as p. First, all identified erroneous observations were removed. Each photovoltaic station conducted 39 observations daily (between 7:00 and 16:30), with a time resolution of 15 minutes. To further enhance the data's description of diurnal variation characteristics, 117 consecutive 15-minute observations over three days were selected for reconstruction at each observation point. Assuming the goal is to repair the temperature observation data of a photovoltaic panel at time 12, these 117 time periods are selected as: the photovoltaic panel's observed temperature from 07:00 to 17:00 on the current day and the two days prior and following, denoted as T. i,j Where i = 1, 2, ..., 117 represents the selection of observation data from 117 time periods, and j = n represents the selection of n stations for reconstruction. To enhance the small-scale anomaly characteristics between erroneous data and its surrounding temperature observations, let T... x,m =0, perform EOF decomposition on the above matrix A; the first mode of EOF obtains the average characteristics of the temperature data, so the first mode is not affected by the outlier 0, and the temperature field is reconstructed using the first mode; after obtaining Then, substitute it into the original data matrix A. p×n To form a new data matrix A 1 ,Right now:
[0052]
[0053] Performing another EOF decomposition on the matrix yields:
[0054]
[0055] Similarly, the temperature at point p obtained based on the reconstruction of the first mode is also obtained, i.e.:
[0056]
[0057] The above process needs to be repeated until the difference between the temperatures at point m in the x-th time interval between two reconstructions is less than a specified threshold. Assume that the requirement is met after t1 iterations.
[0058]
[0059] It is assumed that the average characteristics represented by the first mode can be completely preserved, which also means that the average characteristics of the temperature at point p at time x are also well reproduced. In this invention, ε is 1×10. -5 .
[0060] Iterative reconstruction involves substituting the first modality reconstruction data into step 2 to form a new data matrix, repeating step 5 to obtain the second modality reconstruction data; and then iteratively reconstructing to obtain the final photovoltaic panel error data reconstruction value.
[0061] As a preferred embodiment of the above, the observation data includes time-series temperature values of each photovoltaic panel monitoring point.
[0062] As a preferred embodiment of the above, the iterative reconstruction repair matrix is A. p×n , is represented as:
[0063]
[0064] Where p is the total number of times, n is the number of photovoltaic sites, m is the site number where the target error value is located, x is the time number where the target error value is located, and T i,j This represents the effective temperature observation value at the j-th station at the i-th time.
[0065] Specifically, this matrix is a structured representation of spatiotemporal temperature observation data, used to drive an iterative repair algorithm based on EOF decomposition. Its row direction represents the time dimension (total number of times p), and the column direction represents the spatial dimension (number of effective photovoltaic sites n). Each element carries temperature information for a specific spatiotemporal node.
[0066] As a preferred embodiment of the above, the iterative reconstruction and repair matrix is decomposed using EOF to obtain a spatial mode matrix and a time coefficient matrix, wherein the spatial mode matrix contains the spatial mode vector of the first mode, and the time coefficient matrix contains the time coefficient vector of the first mode, as shown in the formula:
[0067]
[0068] in, Let T be the mode vector at temperature T. Let V be the system vector, k represents the k-th mode, and V p×p Z is the spatial mode matrix. p×n This is the time coefficient matrix.
[0069] Specifically, to enhance the small-scale anomaly characteristics between erroneous data and its surrounding temperature observations, let T... x,m =0, for the above matrix A p×n Perform EOF decomposition.
[0070] As a preferred embodiment of the above, based on the spatial mode vector and time coefficient vector of the first mode, data reconstruction is performed on the erroneous observation data to generate the first mode reconstruction result, as shown in the formula:
[0071]
[0072] in, The target station temperature value after first-mode reconstruction, v 1，1 The coefficients of the first mode at the target time x, z 1，m The first modality has a weight at site m, where n is the target site number and x is the target site index.
[0073] As a preferred embodiment of the above, the iterative reconstruction and repair matrix contains temperature observation data for three consecutive days.
[0074] Specifically, a three-day time window (72 hours) can simultaneously cover the complete evolution cycle of typical weather systems (such as frontal passage and cloud migration) and stable diurnal thermodynamic responses. This satisfies the statistical requirement of Empirical Orthogonal Decomposition (EOF) for the minimum effective sample size (usually ≥30 time series points) and can separate short-period noise from the true thermodynamic trend through spatiotemporal continuity. At the same time, the cross-day correlation of the three-day data provides residual recursion constraints for modal iteration—the reconstruction residual of the previous day can be used as the physical regularization term of the next day, significantly reducing the iteration ambiguity caused by local outliers. Ultimately, while ensuring computational efficiency, it achieves the coordinated repair and adaptive suppression of multi-scale temperature fluctuation characteristics.
[0075] As a preferred embodiment of the above, the modal iterative reconstruction is a two-level iterative mechanism, including: intra-modal iteration and inter-modal progression.
[0076] As a preferred embodiment of the above, intramodal iteration includes repeated decomposition, reconstruction, and convergence verification of a single mode; intermodal progression involves inputting the output value into mode k+1 for iteration after mode k converges.
[0077] Specifically, intramodal iteration focuses on the successive optimization process of the residuals after a single empirical orthogonal decomposition (EOF). Through cyclic correction of the residual sequence and dynamic updating of the convergence criterion, it gradually approximates the spatial pattern of the true temperature field. Intermodal progression further separates the secondary dominant spatial features in the residuals of previous modes, achieving hierarchical capture and collaborative reconstruction of temperature fluctuations at different scales. Finally, through weighted fusion of multimodal spatial response functions, it adaptively suppresses anomalous interference caused by sudden changes in local hot spots or cloud shadows. Intramodal iteration achieves local optimization by cyclically decomposing, reconstructing, and verifying the convergence of the current mode—taking mode k as an example, firstly, empirical orthogonal decomposition (EOF) is performed on the residual field to extract the spatial mode, then the temperature distribution is reconstructed and the residual ε is calculated.k If ||ε k If the value is greater than the preset tolerance, the iteration is repeated with the residual as the new input until convergence; for intermodal progression, after mode k converges, the residual ε is output. k The iterative process of inputting mode k+1 as the initial value achieves cross-scale collaborative correction by separating secondary dominant spatial features (such as hot spot gradient and cloud shadow mutation) layer by layer. Finally, the spatial response functions of each mode are fused to output robust repair results, which significantly improves the adaptive suppression capability against abnormal interference.
[0078] Example 2
[0079] Based on the same inventive concept as the temperature observation and repair method for a new energy photovoltaic station described in the foregoing embodiments, the present invention also provides a temperature observation and repair system for a new energy photovoltaic station, the system comprising:
[0080] The data acquisition module acquires observational data on the temperature of photovoltaic panels in new energy photovoltaic stations;
[0081] The repair matrix construction module, based on observation data, removes erroneous observations and constructs an iteratively reconstructed repair matrix;
[0082] The EOF decomposition module performs EOF decomposition on the iterative reconstruction and repair matrix to obtain the first mode information.
[0083] The data reconstruction module reconstructs erroneous observation data based on the first mode information to obtain reconstructed data values;
[0084] The reconstruction result acquisition module inputs the data reconstruction value into the iterative reconstruction repair matrix until the absolute value of the difference between two reconstruction values is less than the empirical threshold, and then takes the data reconstruction value of the latter as the first modality reconstruction result.
[0085] The repair temperature acquisition module updates and reconstructs the repair matrix based on the reconstruction results of the first mode, and iterates until the final repair temperature value is obtained.
[0086] The evaluation system described above in this invention can effectively realize the temperature observation and repair method for new energy photovoltaic stations, and the technical effects it can achieve are as described in the above embodiments, which will not be repeated here.
[0087] like Figure 2 The diagram shows a schematic of the structure of a computer device provided in this application embodiment. A computer device 400 provided in this application embodiment includes a processor 410 and a memory 420. The memory 420 stores a computer program executable by the processor 410. When the computer program is executed by the processor 410, it performs the method described above.
[0088] This application embodiment also provides a storage medium 430, on which a computer program is stored, and the computer program is executed by a processor 410 to perform the above method.
[0089] The storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0090] Although this application has been described in conjunction with specific features and embodiments, it will be apparent that various modifications and combinations can be made therein without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of the application as defined herein, and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this application.
[0091] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.
Claims
1. A method for temperature monitoring and repair of a new energy photovoltaic station, characterized in that, include: S1, to obtain observational data on the temperature of photovoltaic panels in new energy photovoltaic stations; S2, Based on the observation data, after removing erroneous observation data, construct an iterative reconstruction and repair matrix; S3, perform EOF decomposition on the iterative reconstruction and repair matrix to obtain the first mode information; S4, Based on the first modal information, the erroneous observation data is reconstructed to obtain the reconstructed data values; S5, Substitute the data reconstruction value into the iterative reconstruction repair matrix, and repeat S3-S4 until the absolute value of the difference between the two reconstruction values is less than the empirical threshold, and take the data reconstruction value of the latter as the first modality reconstruction result. S6, subtract the current round's iterative reconstruction repair matrix from the first modal reconstruction result element by element, and use the difference as the input for the next round's iterative reconstruction repair matrix. Repeat the modal decomposition and reconstruction process until the absolute value of all differences is lower than the global convergence threshold. The output iterative reconstruction repair matrix is the final temperature repair value.
2. The method for temperature observation and repair of a new energy photovoltaic station according to claim 1, characterized in that, The observation data includes time-series temperature values from individual photovoltaic panel monitoring points.
3. The method for temperature observation and repair of new energy photovoltaic stations according to claim 1, characterized in that, The iterative reconstruction and repair matrix is A. p×n , is represented as: Where p is the total number of times, n is the number of photovoltaic sites, m is the site number where the target error value is located, x is the time number where the target error value is located, and T i,j This represents the effective temperature observation value at the j-th station at the i-th time.
4. The method for temperature observation and repair of a new energy photovoltaic station according to claim 1 or 3, characterized in that, The iterative reconstruction and repair matrix is decomposed using EOF to obtain a spatial mode matrix and a temporal coefficient matrix. The spatial mode matrix contains the spatial mode vector of the first mode, and the temporal coefficient matrix contains the temporal coefficient vector of the first mode. The formula is as follows: in, Let T be the mode vector at temperature T. Let V be the system vector, k represents the k-th mode, and V p×p Z is the spatial mode matrix. p×n This is the time coefficient matrix.
5. The method for temperature observation and repair of a new energy photovoltaic station according to claim 1, characterized in that, Based on the spatial mode vector and time coefficient vector of the first mode, the erroneous observation data is reconstructed to generate the first mode reconstruction result, as shown in the formula: in, The target station temperature value after first-mode reconstruction, v 1，1 The coefficients of the first mode at the target time x, z 1，m The weight of the first modality at site m, where m is the target site index and x is the target site index.
6. The method for temperature observation and repair of a new energy photovoltaic station according to claim 1, characterized in that, The iterative reconstruction and repair matrix contains temperature observation data from three consecutive days.
7. The method for temperature observation and repair of a new energy photovoltaic station according to claim 1, characterized in that, Modal iterative reconstruction is a two-level iterative mechanism, including intra-modal iteration and inter-modal progression.
8. The method for temperature observation and repair of a new energy photovoltaic station according to claim 7, characterized in that, The intramodal iteration includes repeated decomposition, reconstruction, and convergence verification of a single mode; the intermodal progression is that after mode k converges, the output value is input into mode k+1 for iteration.
9. A temperature monitoring and repair system for a new energy photovoltaic station, characterized in that, include: The data acquisition module acquires observational data on the temperature of photovoltaic panels in new energy photovoltaic stations; The repair matrix construction module, based on the observation data, removes erroneous observations and constructs an iteratively reconstructed repair matrix; The EOF decomposition module performs EOF decomposition on the iterative reconstruction and repair matrix to obtain the first mode information; The data reconstruction module reconstructs the erroneous observation data based on the first modal information to obtain the reconstructed data values; The reconstruction result acquisition module inputs the data reconstruction value into the iterative reconstruction repair matrix until the absolute value of the difference between two reconstruction values is less than an empirical threshold, and then takes the data reconstruction value of the latter as the first modality reconstruction result. The temperature acquisition module is repaired by updating the iterative reconstruction repair matrix based on the first modal reconstruction result and iteratively executing until the final repair temperature value is obtained.
10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.
11. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1-7.