Method, device and equipment for determining fault loss power of photovoltaic power station and storage medium

Abstract

The application belongs to the technical field of photovoltaic technology, and discloses a method, device and equipment for determining fault loss power of a photovoltaic power station and a storage medium. The application first divides a fault influence interval corresponding to a fault photovoltaic unit to obtain a plurality of target time slices, so that fault loss power is calculated by time slice instead of day, thereby improving the calculation accuracy of photovoltaic fault loss power. Then, the initial loss power is corrected according to the fault relationship between a plurality of fault work orders in the same target time slice, so as to avoid the same power generation loss being repeatedly counted by a plurality of fault work orders, thereby improving the accuracy of photovoltaic fault loss power.

Description

Technical Field

[0001] This application relates to the field of photovoltaic technology, and in particular to a method, apparatus, equipment and storage medium for determining the fault loss of electricity in a photovoltaic power station. Background Technology

[0002] As photovoltaic power plants continue to expand in scale, the number of devices such as strings, combiner boxes, inverters, and arrays within these plants is constantly increasing. Equipment failures directly impact the power plant's power generation and revenue, thus requiring accurate calculation of the lost electricity due to failures. Currently, the failure date is typically determined based on the failure work order, and the lost electricity is calculated based on the difference between the standard power generation data and the actual power generation data on that date. This approach often uses the calendar day as the calculation unit, making it difficult to accurately handle scenarios such as failures occurring at a specific time within a day, failures resolving within a day, failures spanning multiple days, nighttime failures, failures before grid connection, or failures after grid disconnection. Using the entire day directly as the calculation object can easily include periods with no effective power generation capacity or periods unaffected by the failure in the loss calculation, leading to either an overestimation or underestimation of the calculated lost electricity. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, equipment, and storage medium for determining the power loss due to faults in photovoltaic power plants, aiming to solve the technical problem of low accuracy in determining the power loss due to faults in photovoltaic power plants.

[0004] To achieve the above objectives, this application provides a method for determining the fault-related power loss of a photovoltaic power plant, the method comprising the following steps: The fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station is divided to obtain multiple target time slices; Determine the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time segment; The initial power loss of the faulty photovoltaic unit in each target time slot is determined based on the standard power generation data and the actual power generation data. The initial power loss is corrected based on the fault relationships among multiple fault work orders within the same target time slice, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss.

[0005] Optionally, the step of dividing the fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station to obtain multiple target time slices includes: Determine the fault work order information corresponding to the faulty photovoltaic unit in the photovoltaic power station, and select the fault occurrence time and fault completion time from the fault work order information; The initial fault interval is determined based on the fault occurrence time and the fault completion time. The invalid time periods are removed from the initial fault interval to obtain the fault-affected interval; The fault-affected interval is divided according to a preset time granularity to obtain multiple target time slices.

[0006] Optionally, determining the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time slot includes: Historical meteorological similar time slots with similar meteorological characteristics to each target time slot are selected from historical time slots without work orders, and first candidate standard power generation data are generated based on the first power generation data of the faulty photovoltaic unit corresponding to the historical meteorological similar time slot. The benchmark object corresponding to the faulty photovoltaic unit is determined, and the second candidate standard power generation data is generated based on the second power generation data of the benchmark object in each target time slice. The meteorological data corresponding to each target time slice is input into the preset meteorological prediction model to obtain the third candidate standard power generation data; The standard power generation data corresponding to the faulty photovoltaic unit in each target time slot is determined based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data, and the actual power generation data corresponding to the faulty photovoltaic unit in each target time slot is determined.

[0007] Optionally, determining the benchmark object corresponding to the faulty photovoltaic unit includes: Determine the device level and fault object type corresponding to the faulty photovoltaic unit; Based on the equipment level and the fault object type, a benchmark object corresponding to the faulty photovoltaic unit is selected from the photovoltaic power station.

[0008] Optionally, determining the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data includes: Determine the first evaluation index corresponding to the first candidate standard power generation data, the second evaluation index corresponding to the second candidate standard power generation data, and the third evaluation index corresponding to the third candidate standard power generation data; The first weight, the second weight, and the third weight corresponding to the first candidate standard power generation data are determined based on the first evaluation index, the second evaluation index, and the third evaluation index. The first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data are weighted and fused according to the first weight, the second weight, and the third weight to obtain the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot.

[0009] Optionally, determining the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data includes: When the standard power generation data and the actual power generation data are power data, the initial power loss is calculated based on the standard power generation data, the actual power generation data, and the duration of each target time slice. When the standard power generation data and the actual power generation data are equivalent utilization hours, the initial power loss is calculated based on the standard power generation data, the actual power generation data, and the rated capacity corresponding to the photovoltaic fault unit.

[0010] Optionally, the step of correcting the initial power loss based on the fault relationship between multiple fault work orders within the same target time slice, and determining the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss, includes: Determine whether there are multiple fault work orders for the faulty photovoltaic unit within the same target time slice, or for multiple photovoltaic units at the same level of association with the faulty photovoltaic unit within the same target time slice; If there are multiple fault work orders, the fault relationships between each fault work order are determined. The fault relationships include time overlap relationships, equipment hierarchy relationships, and fault causal relationships. The initial power loss is corrected based on the time overlap relationship, the device hierarchy relationship, and the fault causal relationship, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss.

[0011] Optionally, the step of correcting the initial power loss based on the time overlap relationship, the device hierarchy relationship, and the fault causality relationship includes: Determine the target power generation impact range corresponding to the faulty photovoltaic unit, and determine the upstream power generation impact range corresponding to the upstream equipment of the faulty photovoltaic unit; When the influence range of the upper-level power generation covers the influence range of the target power generation, the overlapping time slice is determined according to the time overlap relationship, and the overlapping power loss corresponding to the overlapping time slice is removed from the initial power loss to obtain the corrected power loss. If the influence range of the superior power generation does not cover the influence range of the target power generation, it is determined whether there are multiple faults at the same level based on the equipment hierarchy. If there are multiple faults of the same level, the initial power loss is proportionally distributed to obtain the corrected power loss. If there are no multiple faults of the same level, then if the fault causal relationship exists, the initial power loss is corrected according to the fault causal relationship to obtain the corrected power loss.

[0012] Furthermore, to achieve the above objectives, this application also provides a device for determining the fault-related power loss of a photovoltaic power station, the device comprising: The interval division module is used to divide the fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station to obtain multiple target time slices; The data determination module is used to determine the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time segment; The power loss determination module is used to determine the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data. The power loss correction module is used to correct the initial power loss based on the fault relationship between multiple fault work orders within the same target time slice, and to determine the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

[0013] In addition, to achieve the above objectives, this application also proposes a device for determining the fault-related power loss of a photovoltaic power plant. The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the method for determining the fault-related power loss of a photovoltaic power plant as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for determining the fault loss power of a photovoltaic power station as described above.

[0015] This application divides the fault impact interval corresponding to a faulty photovoltaic unit within a photovoltaic power station into multiple target time slots. Then, it determines the standard power generation data and actual power generation data for each target time slot for the faulty photovoltaic unit. Based on these data, it determines the initial power loss for the faulty photovoltaic unit in each target time slot. Next, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, and finally determines the target power loss for the faulty photovoltaic unit based on the corrected power loss. This application first divides the fault impact interval corresponding to the faulty photovoltaic unit into multiple target time slots, refining the calculation of fault power loss from daily to time slot-based, thus improving the accuracy of photovoltaic fault power loss calculation. Then, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, avoiding duplicate statistics of the same power generation loss by multiple fault work orders, thereby improving the accuracy of photovoltaic fault power loss calculation. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the first embodiment of the method for determining the fault-related power loss of a photovoltaic power plant according to this application. Figure 2 This is a schematic diagram of the target time slice division process for an embodiment of the method for determining the fault loss power of a photovoltaic power plant according to this application. Figure 3 This is a flowchart illustrating the second embodiment of the method for determining the fault-related power loss of a photovoltaic power plant according to this application. Figure 4 This is a flowchart illustrating the selection of a benchmark object in one embodiment of the method for determining the fault loss power of a photovoltaic power plant according to this application. Figure 5 A flowchart illustrating the weighted fusion of candidate standard power generation data for one embodiment of the method for determining fault loss power of a photovoltaic power plant according to this application; Figure 6 This is a flowchart illustrating the third embodiment of the method for determining the fault loss power of a photovoltaic power plant according to this application. Figure 7This is a schematic diagram of the power loss correction process in one embodiment of the method for determining power loss due to faults in a photovoltaic power plant according to this application. Figure 8 This is a structural block diagram of the first embodiment of the photovoltaic power plant fault loss power determination device of this application; Figure 9 This is a schematic diagram of the structure of the device for determining the power loss due to faults in a photovoltaic power station, which is part of the hardware operating environment involved in the embodiments of this application.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] It should be noted that the executing entity of this application can be a computing service device with data processing, network communication, and program execution functions, such as a computer, or an electronic device capable of performing the above functions, such as a photovoltaic power station fault loss power determination device. The following description uses a photovoltaic power station fault loss power determination device as an example to illustrate this embodiment and the following embodiments.

[0023] Based on this, embodiments of this application provide a method for determining the fault-related power loss of a photovoltaic power plant, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the method for determining the fault-related power loss of a photovoltaic power plant according to this application.

[0024] In this embodiment, the method for determining the fault-related power loss of the photovoltaic power station includes the following steps: Step S10: Divide the fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station to obtain multiple target time slices.

[0025] Understandably, data related to faulty photovoltaic (PV) units within a PV power plant can be obtained, including at least fault work order information, equipment hierarchy information, historical power generation data, real-time power generation data, meteorological data, and operational status data. Fault work order information includes the faulty object, fault occurrence time, fault completion time, work order status, fault type, and fault level. Equipment hierarchy information includes the topological relationships between the power plant, array, inverter, combiner box, string, and module, as well as equipment type, rated capacity, installation location, orientation, and tilt angle. Historical power generation data includes historical power, historical power generation, equivalent utilization hours, and power generation efficiency. Real-time power generation data includes real-time power, real-time power generation, current, and voltage during the fault period. Meteorological data includes irradiance, peak sunshine hours, temperature, wind speed, humidity, and weather type. Operational status data includes grid-connected status, grid-disconnected status, shutdown status, power curtailment status, communication status, and alarm status.

[0026] It should be understood that the fault impact interval can be the time interval during which the faulty photovoltaic unit is faulty. The fault impact interval can be divided to obtain multiple target time slices.

[0027] Furthermore, in order to achieve the division of the fault impact range, in this embodiment, step S10 includes: determining the fault work order information corresponding to the faulty photovoltaic unit in the photovoltaic power station, and selecting the fault occurrence time and fault completion time from the fault work order information; determining the initial fault range based on the fault occurrence time and the fault completion time; removing invalid time periods from the initial fault range to obtain the fault impact range; and dividing the fault impact range according to a preset time granularity to obtain multiple target time slices.

[0028] Understandably, it's possible to determine the fault work order information corresponding to the faulty photovoltaic unit within the photovoltaic power station, and obtain the fault occurrence time and fault completion time of the faulty photovoltaic unit from the fault work order information. The fault occurrence time refers to the time when the faulty photovoltaic unit begins to experience a fault, and the fault completion time refers to the time when the faulty photovoltaic unit completes repairs. If a fault completion time exists, the initial fault interval is determined based on the fault occurrence time and the fault completion time; if the fault completion time is empty, the current time or the preset assessment deadline is used as the fault deadline, and the initial fault interval is determined based on the fault occurrence time and the fault deadline.

[0029] It should be understood that invalid time periods refer to periods without effective power generation capacity. Invalid time periods can be removed from the initial fault interval by combining the grid connection time, grid disconnection time and operating status data of the power station or equipment corresponding to the faulty photovoltaic unit. For example, time periods without radiation at night, time periods when the equipment is not connected to the grid, normal grid disconnection time periods, planned shutdown time periods, etc. The above invalid time periods are not used as the effective fault loss calculation time. The fault impact interval is obtained after removing invalid time periods from the initial fault interval.

[0030] In practical implementation, the preset time granularity can be 5 minutes, 15 minutes, 30 minutes, 1 hour, or other time granularities determined according to the data acquisition frequency. The fault impact interval can be divided according to the preset time granularity to obtain multiple target time slices, each with a duration equal to the aforementioned preset time granularity. (Refer to...) Figure 2 , Figure 2 This is a flowchart illustrating the target time slice division of an embodiment of the method for determining the power loss due to a fault in a photovoltaic power plant according to this application. An initial fault interval can be determined based on the fault occurrence time, fault completion time, current time, or assessment deadline. Then, the grid connection time, grid disconnection time, and operating status are read. Time periods such as nighttime, off-grid, off-grid, and planned outages are eliminated to obtain the fault-affected interval. This interval is then divided according to a preset time granularity to obtain target time slice 1, target time slice 2, ..., target time slice N. In this embodiment, the initial fault interval is determined based on the fault occurrence time, fault completion time, or assessment deadline. Combined with grid connection time, grid disconnection time, and operating status data, time periods without effective power generation capacity are eliminated. The remaining fault-affected interval is divided into multiple target time slices, refining the calculation of power loss due to fault from a daily basis to a time-slice basis.

[0031] Step S20: Determine the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time segment.

[0032] Understandably, the standard power generation data and actual power generation data of the faulty photovoltaic unit within each target time segment can be determined. The standard power generation data refers to the power generation data generated by the faulty photovoltaic unit when it is not faulty, while the actual power generation data refers to the power generation data generated by the faulty photovoltaic unit in real time.

[0033] Step S30: Determine the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data.

[0034] It should be understood that the initial power loss of the faulty photovoltaic unit in each target time slot can be determined based on standard power generation data and actual power generation data. The actual power generation data can be the average power, cumulative power generation, or equivalent utilization hours of the faulty photovoltaic unit in the target time slot. In one feasible embodiment, the initial power loss can be calculated based on the difference between the standard power generation data and the actual power generation data.

[0035] Furthermore, in order to accurately calculate the initial power loss, in this embodiment, step S30 includes: when the standard power generation data and the actual power generation data are power data, calculating the initial power loss based on the standard power generation data, the actual power generation data, and the duration of the time slice corresponding to each target time slice; when the standard power generation data and the actual power generation data are equivalent utilization hours, calculating the initial power loss based on the standard power generation data, the actual power generation data, and the rated capacity corresponding to the photovoltaic fault unit.

[0036] Understandably, when the standard power generation data and the actual power generation data are power data, the initial power loss can be calculated based on the standard power generation data, the actual power generation data, and the duration of each target time slice. The calculation formula is: Initial power loss = max(standard power - actual power, 0) × duration of time slice.

[0037] It should be understood that when the standard power generation data and the actual power generation data are equivalent utilization hours, the initial power loss can be calculated based on the standard power generation data, the actual power generation data, and the rated capacity corresponding to the photovoltaic fault unit. The calculation formula is: Initial power loss = max(standard equivalent utilization hours - actual equivalent utilization hours, 0) × rated capacity.

[0038] Step S40: Correct the initial power loss based on the fault relationship between multiple fault work orders within the same target time slice, and determine the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

[0039] In practical implementation, it can identify whether multiple fault work orders exist for the same faulty photovoltaic unit or multiple photovoltaic units with related hierarchical relationships within the same target time slice. If multiple fault work orders exist, the fault relationships between each fault work order can be determined, such as time overlap, equipment hierarchy, and fault causal relationships. The initial power loss can be corrected based on the fault relationships to obtain the corrected power loss. The corrected power loss of the faulty photovoltaic unit in each target time slice is accumulated to obtain the target power loss corresponding to the faulty photovoltaic unit.

[0040] This embodiment divides the fault impact interval corresponding to the faulty photovoltaic unit within the photovoltaic power station into multiple target time slots. Then, it determines the standard power generation data and actual power generation data for the faulty photovoltaic unit in each target time slot. Based on these data, it determines the initial power loss of the faulty photovoltaic unit in each target time slot. Next, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, and finally determines the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss. This embodiment first divides the fault impact interval corresponding to the faulty photovoltaic unit into multiple target time slots, refining the calculation of fault power loss from daily to time slot-based, thus improving the accuracy of photovoltaic fault power loss calculation. Then, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, avoiding duplicate statistics of the same power generation loss by multiple fault work orders, thereby improving the accuracy of photovoltaic fault power loss calculation.

[0041] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the method for determining the fault-related power loss of a photovoltaic power plant according to this application.

[0042] Based on the first embodiment described above, in this embodiment, step S20 includes: Step S201: Select historical meteorological similar time slots from the historical time slots without work orders that have meteorological characteristics similar to each target time slot, and generate first candidate standard power generation data based on the first power generation data of the faulty photovoltaic unit corresponding to the historical meteorological similar time slot.

[0043] Understandably, the meteorological characteristics of each target time slot can be determined, including features such as irradiance, peak sunshine hours, temperature, wind speed, humidity, and weather type. Historical meteorological similar time slots with similar meteorological characteristics are selected from historical time slots without work orders. First candidate standard power generation data is generated based on the first power generation data corresponding to these historical meteorological similar time slots. If there are multiple historical meteorological similar time slots, the average value of the first power generation data corresponding to each historical meteorological similar time slot can be used as the first candidate standard power generation data.

[0044] It should be understood that before generating standard power generation data, historical power generation data, real-time power generation data, meteorological data, and operational status data can be cleaned. Cleaning methods include, but are not limited to: 1. Removing abnormal data such as empty power generation, empty power output, negative power output, abnormal power fluctuations, and infinite values; 2. Interpolating or repairing short-term missing data based on adjacent time slices; 3. Marking time slices corresponding to communication anomalies, data acquisition anomalies, and metering anomalies; 4. Identifying non-fault-related impact states such as power curtailment, planned shutdowns, and proactive equipment shutdowns; 5. Marking meteorological anomaly time slices such as extreme weather, low radiation, heavy rain, sandstorms, and snow accumulation. Abnormal data and abnormal time slices can be removed using the above methods to obtain cleaned data, and the data used to generate standard power generation data subsequently is all cleaned data.

[0045] Step S202: Determine the benchmark object corresponding to the faulty photovoltaic unit, and generate second candidate standard power generation data based on the second power generation data of the benchmark object in each target time slice.

[0046] Understandably, the benchmark objects corresponding to the faulty photovoltaic units can be identified. Benchmark objects can be selected from fault-free photovoltaic equipment or fault-free photovoltaic power plants based on similarity characteristics such as equipment type, rated capacity, operating efficiency, geographical location, orientation, tilt angle, and historical power generation efficiency. Then, the second power generation data corresponding to the benchmark objects in each target time segment is used as the second candidate standard power generation data.

[0047] Furthermore, in this embodiment, determining the benchmark object corresponding to the faulty photovoltaic unit includes: determining the equipment level and fault object type corresponding to the faulty photovoltaic unit; and selecting the benchmark object corresponding to the faulty photovoltaic unit from the photovoltaic power station according to the equipment level and the fault object type.

[0048] It should be understood that the equipment level and fault object type corresponding to the faulty photovoltaic unit can be determined, and then a benchmark object corresponding to the faulty photovoltaic unit can be selected from the photovoltaic power station based on the equipment level and fault object type. For example, when the faulty photovoltaic unit is a string, the fault-free string under the same inverter or the same combiner box is preferred as the benchmark object; when the faulty photovoltaic unit is a combiner box, the fault-free combiner box under the same inverter is preferred as the benchmark object; when the faulty photovoltaic unit is an inverter, the fault-free inverter of the same type within the same array or the same power station is preferred as the benchmark object; when the faulty photovoltaic unit is an array, the fault-free array within the same power station is preferred as the benchmark object; when the faulty photovoltaic unit is a photovoltaic power station, similar photovoltaic power stations in the same area are preferred as the benchmark object.

[0049] In practical implementation, if no matching target exists within the priority level, the system selects candidate standard power generation data sources in the following order: from nearest to farthest, from the same level to across levels, and from measured benchmarks to model predictions. That is, benchmarks are selected sequentially according to the same level, region, and type. (Refer to...) Figure 4 , Figure 4 This is a schematic diagram illustrating the process of selecting a benchmark object in one embodiment of the method for determining the fault loss power of a photovoltaic power plant according to this application, as shown below. Figure 4 As shown, the system can identify the equipment level and fault object type of the faulty photovoltaic unit. When the faulty photovoltaic unit is a string, the fault-free string under the same inverter or unified combiner box is used as the benchmark object; when the faulty photovoltaic unit is a combiner box, the fault-free combiner box under the same inverter is used as the benchmark object; when the faulty photovoltaic unit is an inverter, the fault-free inverter of the same type in the same array or the same power station is used as the benchmark object; when the faulty photovoltaic unit is an array, the fault-free array in the same power station is used as the benchmark object; when the faulty photovoltaic unit is a photovoltaic power station, similar photovoltaic power stations in the same area are used as the benchmark object. Then, it is determined whether the benchmark object meets the requirements. If yes, a second candidate standard power generation data is generated; if not, historical similar time slices or predictive weather forecast models are added to generate a second candidate standard power generation data.

[0050] Step S203: Input the meteorological data corresponding to each target time slice into the preset meteorological prediction model to obtain the third candidate standard power generation data.

[0051] Understandably, the preset meteorological forecasting model can be pre-trained based on historical meteorological data, historical power generation data, and equipment attributes to characterize the mapping relationship between meteorological conditions and power generation capacity. In this embodiment, the meteorological data corresponding to the target time slice can be input into the preset meteorological forecasting model to obtain the third candidate standard power generation data.

[0052] Step S204: Determine the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data, and determine the actual power generation data corresponding to the faulty photovoltaic unit in each target time slot.

[0053] It should be understood that the first candidate standard power generation data is candidate standard power generation data generated from historical meteorological similar time slices, the second candidate standard power generation data is candidate standard power generation data generated from similar equipment at the same station or similar power stations in the same region, and the third candidate standard power generation data is candidate standard power generation data generated from power generation prediction models.

[0054] In a specific implementation, the standard power generation data of the faulty photovoltaic unit in each target time slot can be determined based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data. In a feasible embodiment, the first candidate standard power generation data, the second candidate standard power generation data, or the third candidate standard power generation data can be used as the standard power generation data; or, the standard power generation data can be determined based on two types of candidate standard power generation data; or, the standard power generation data can be determined based on three types of candidate standard power generation data.

[0055] Further, in this embodiment, determining the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data includes: determining a first evaluation index corresponding to the first candidate standard power generation data, a second evaluation index corresponding to the second candidate standard power generation data, and a third evaluation index corresponding to the third candidate standard power generation data; determining a first weight corresponding to the first candidate standard power generation data, a second weight corresponding to the second candidate standard power generation data, and a third weight corresponding to the third candidate standard power generation data based on the first evaluation index, the second evaluation index, and the third evaluation index; and performing weighted fusion of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data based on the first weight, the second weight, and the third weight to obtain the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot.

[0056] Understandably, the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot can be determined based on the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data. Specifically, a first evaluation index corresponding to the first candidate standard power generation data, a second evaluation index corresponding to the second candidate standard power generation data, and a third evaluation index corresponding to the third candidate standard power generation data can be determined. Evaluation indicators may include data completeness, meteorological similarity, equipment similarity, spatial distance, temporal distance, number of benchmark objects, historical prediction error of the model, and dispersion of candidate values, etc.

[0057] It should be understood that the first weight, the second weight, and the third weight of the power generation data corresponding to the first candidate standard can be determined based on the first evaluation index, the second evaluation index, and the third evaluation index. For example, the higher the meteorological similarity, the higher the equipment similarity, the higher the data completeness, and the lower the historical prediction error of the model, the higher the fusion weight of the corresponding candidate standard power generation data; the greater the spatial distance, the greater the temporal distance, and the higher the dispersion of the candidate values, the lower the corresponding fusion weight.

[0058] In specific implementation, the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data can be weighted and fused according to the first weight, the second weight, and the third weight to obtain the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot. The aforementioned first weight, second weight, and third weight can be dynamically updated according to the data quality and model error of the target time slot. (Refer to...) Figure 5 , Figure 5 This is a flowchart illustrating the weighted fusion of candidate standard power generation data in one embodiment of the method for determining fault loss power in a photovoltaic power plant according to this application. Figure 5 As shown, the first candidate standard power generation data can be determined based on historical meteorological similar time slices, the second candidate standard power generation data can be determined based on similar equipment at the same station or similar power stations in the region, and the third candidate standard power generation data can be determined based on the meteorological prediction model. The evaluation indicators corresponding to each candidate standard power generation data are calculated. The evaluation indicators include data completeness, meteorological similarity, equipment similarity, spatial distance, temporal distance, number of benchmark objects, historical prediction error of the model, and dispersion of candidate values. Then, the fusion weight is determined according to the evaluation indicators. Finally, the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data are weighted and fused to obtain the standard power generation data of the faulty photovoltaic unit corresponding to each target time slice.

[0059] This embodiment selects historical meteorological time slots with similar meteorological characteristics to each target time slot from historical time slots without work orders. It then generates first candidate standard power generation data based on the first power generation data of the faulty photovoltaic unit corresponding to the historical meteorological time slot. Next, it determines the benchmark object corresponding to the faulty photovoltaic unit and generates second candidate standard power generation data based on the second power generation data of the benchmark object corresponding to each target time slot. Finally, it inputs the meteorological data corresponding to each target time slot into a preset meteorological prediction model to obtain third candidate standard power generation data. Finally, it determines the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot based on at least one of the first, second, and third candidate standard power generation data, and determines the actual power generation data of the faulty photovoltaic unit corresponding to each target time slot. This embodiment, by determining the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot based on at least one of the first, second, and third candidate standard power generation data, can reduce the impact of abnormal single data sources, insufficient samples, or differences in benchmark objects on the standard power generation data, and improve the accuracy of the standard power generation data in representing normal power generation capacity.

[0060] refer to Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of the method for determining the fault-related power loss of a photovoltaic power plant according to this application.

[0061] Based on the above embodiments, in this embodiment, step S40 includes: Step S401: Determine whether there are multiple fault work orders for the faulty photovoltaic unit within the same target time slice or for multiple photovoltaic units at the same target time slice that are associated with the faulty photovoltaic unit.

[0062] It is understandable that it is possible to determine whether there are multiple fault work orders for the same faulty photovoltaic unit within the same target time slice, or for multiple photovoltaic units that are related to the faulty photovoltaic unit within the same target time slice.

[0063] Step S402: If there are multiple fault work orders, determine the fault relationship between each fault work order. The fault relationship includes time overlap relationship, equipment hierarchy relationship and fault causal relationship.

[0064] It should be understood that if there are multiple fault work orders, the fault relationships between each fault work order should be determined. Fault relationships may include time overlap relationships, equipment hierarchy relationships, and fault causal relationships. Time overlap relationships may be the overlapping time slices between fault work orders, equipment hierarchy relationships may be the equipment hierarchy corresponding to the fault work order, and fault causal relationships may be mutually influential faults.

[0065] Step S403: Correct the initial power loss based on the time overlap relationship, the device hierarchy relationship, and the fault causal relationship, and determine the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

[0066] Furthermore, to effectively correct the initial power loss, in this embodiment, the correction of the initial power loss based on the time overlap relationship, the device hierarchy relationship, and the fault causality relationship includes: determining the target power generation influence range corresponding to the faulty photovoltaic unit, and determining the upper-level power generation influence range corresponding to the upper-level device of the faulty photovoltaic unit; if the upper-level power generation influence range covers the target power generation influence range, determining an overlapping time slice according to the time overlap relationship, and removing the overlapping power loss corresponding to the overlapping time slice from the initial power loss to obtain the corrected power loss; if the upper-level power generation influence range does not cover the target power generation influence range, determining whether there are multiple faults of the same level according to the device hierarchy relationship; if there are multiple faults of the same level, proportionally allocating the initial power loss to obtain the corrected power loss; if there are no multiple faults of the same level, correcting the initial power loss according to the fault causality relationship to obtain the corrected power loss.

[0067] Understandably, the target power generation impact range corresponding to the faulty photovoltaic unit can be determined, and the upper-level power generation impact range corresponding to the upper-level equipment of the faulty photovoltaic unit can be determined. When the upper-level power generation impact range covers the target power generation impact range, the overlapping time slot is determined according to the time overlap relationship, and the overlapping loss power corresponding to the overlapping time slot is removed from the initial loss power to obtain the corrected loss power, thus avoiding double counting. For example, during the inverter failure, its subordinate strings cannot generate power normally, so the loss in that time slot is preferentially attributed to the inverter failure.

[0068] It should be understood that when the influence range of the upper-level power generation does not cover the influence range of the target power generation, the initial power loss can be proportionally allocated based on the equipment hierarchy to determine whether there are multiple faults of the same level, i.e. whether multiple faults of the same level jointly cause power generation loss in the same time slice. In a feasible embodiment, the initial power loss can be proportionally allocated based on the influence capacity, duration of the fault, severity level of the fault, or contribution rate of historical faults corresponding to each fault.

[0069] In practical implementation, if there are no multiple faults of the same level, then in the case of a causal relationship between faults, the initial power loss is corrected according to the causal relationship to obtain the corrected power loss. That is, when there is a causal relationship between fault work orders, the subsequent loss caused by the preceding fault will be attributed to the preceding fault according to a preset attribution rule, or it will be shared between the preceding fault and the subsequent fault. (Reference) Figure 7 , Figure 7 This is a schematic flowchart illustrating the power loss correction process of one embodiment of the method for determining power loss due to faults in a photovoltaic power plant according to this application. Figure 7 As shown, for multiple fault work orders within the same target time slice, the system can identify time overlap, equipment hierarchy, and fault impact range. If the upper-level equipment covers the lower-level equipment, the overlapping loss is preferentially attributed to the upper-level equipment fault. If the upper-level equipment does not cover the lower-level equipment, it determines whether there are multiple faults of the same level. If so, the loss is allocated according to the affected capacity, duration, severity level, or historical contribution rate. If not, it determines whether there is a causal relationship. If so, the loss is assigned or allocated according to preset rules. If not, the total loss is calculated and verified to be unique, and the corrected loss power corresponding to each faulty photovoltaic unit is obtained.

[0070] This embodiment determines whether multiple fault work orders exist for a faulty photovoltaic unit within the same target time slice, or for multiple photovoltaic units at the same related level within the same target time slice. If multiple fault work orders exist, the fault relationships between these work orders are determined. These relationships include time overlap, equipment hierarchy, and causal relationships. The initial power loss is then corrected based on these relationships, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss. This embodiment determines the time overlap, equipment hierarchy, and fault impact range among multiple fault work orders within the same target time slice, and deduplicates and distributes the power loss according to rules such as superior coverage, concurrency at the same level, or causal association. This avoids the same power generation loss being repeatedly counted by multiple fault work orders, improving the accuracy of power loss calculation and work order responsibility attribution in multi-fault scenarios.

[0071] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the photovoltaic power plant fault loss power determination device of this application.

[0072] like Figure 8 As shown in the embodiment of this application, the device for determining the fault loss power of a photovoltaic power station includes: The interval division module 10 is used to divide the fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station to obtain multiple target time slices; Data determination module 20 is used to determine the standard power generation data and actual power generation data of the faulty photovoltaic unit in each target time segment; The power loss determination module 30 is used to determine the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data. The power loss correction module 40 is used to correct the initial power loss based on the fault relationship between multiple fault work orders within the same target time slice, and to determine the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

[0073] This embodiment divides the fault impact interval corresponding to the faulty photovoltaic unit within the photovoltaic power station into multiple target time slots. Then, it determines the standard power generation data and actual power generation data for the faulty photovoltaic unit in each target time slot. Based on these data, it determines the initial power loss of the faulty photovoltaic unit in each target time slot. Next, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, and finally determines the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss. This embodiment first divides the fault impact interval corresponding to the faulty photovoltaic unit into multiple target time slots, refining the calculation of fault power loss from daily to time slot-based, thus improving the accuracy of photovoltaic fault power loss calculation. Then, it corrects the initial power loss based on the fault relationships between multiple fault work orders within the same target time slot, avoiding duplicate statistics of the same power generation loss by multiple fault work orders, thereby improving the accuracy of photovoltaic fault power loss calculation.

[0074] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In practical applications, those skilled in the art can select some or all of it to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0075] In addition, for technical details not described in detail in this embodiment, please refer to the method for determining the fault power loss of a photovoltaic power station provided in any embodiment of this application, which will not be repeated here.

[0076] Based on the first embodiment of the photovoltaic power plant fault loss power determination device described in this application, a second embodiment of the photovoltaic power plant fault loss power determination device of this application is proposed.

[0077] In this embodiment, the interval division module 10 is further used to determine the fault work order information corresponding to the faulty photovoltaic unit in the photovoltaic power station, and select the fault occurrence time and fault completion time from the fault work order information; determine the initial fault interval based on the fault occurrence time and the fault completion time; remove invalid time periods from the initial fault interval to obtain the fault impact interval; and divide the fault impact interval according to the preset time granularity to obtain multiple target time slices.

[0078] Furthermore, the data determination module 20 is also used to filter historical meteorological similar time slots with similar meteorological characteristics to each target time slot from historical time slots without work orders, and generate first candidate standard power generation data based on the first power generation data of the faulty photovoltaic unit corresponding to the historical meteorological similar time slot; determine the benchmark object corresponding to the faulty photovoltaic unit, and generate second candidate standard power generation data based on the second power generation data of the benchmark object corresponding to each target time slot; input the meteorological data corresponding to each target time slot into a preset meteorological prediction model to obtain third candidate standard power generation data; determine the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data, and determine the actual power generation data of the faulty photovoltaic unit corresponding to each target time slot.

[0079] Furthermore, the data determination module 20 is also used to determine the equipment level and fault object type corresponding to the faulty photovoltaic unit; and to select a benchmark object corresponding to the faulty photovoltaic unit from the photovoltaic power station according to the equipment level and the fault object type.

[0080] Furthermore, the data determination module 20 is also used to determine a first evaluation index corresponding to the first candidate standard power generation data, a second evaluation index corresponding to the second candidate standard power generation data, and a third evaluation index corresponding to the third candidate standard power generation data; determine a first weight corresponding to the first candidate standard power generation data, a second weight corresponding to the second candidate standard power generation data, and a third weight corresponding to the third candidate standard power generation data based on the first evaluation index, the second evaluation index, and the third evaluation index; and perform weighted fusion of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data based on the first weight, the second weight, and the third weight to obtain the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot.

[0081] Furthermore, the power loss determination module 30 is also used to calculate the initial power loss based on the standard power generation data, the actual power generation data, and the duration of each target time slice when the standard power generation data and the actual power generation data are power data; and to calculate the initial power loss based on the standard power generation data, the actual power generation data, and the rated capacity corresponding to the photovoltaic fault unit when the standard power generation data and the actual power generation data are equivalent utilization hours.

[0082] Furthermore, the power loss correction module 40 is also used to determine whether there are multiple fault work orders for the faulty photovoltaic unit within the same target time slice or for multiple photovoltaic units with an associated level with the faulty photovoltaic unit within the same target time slice; if there are multiple fault work orders, the fault relationship between each fault work order is determined, the fault relationship includes time overlap relationship, equipment level relationship and fault causal relationship; the initial power loss is corrected based on the time overlap relationship, the equipment level relationship and the fault causal relationship, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss.

[0083] Furthermore, the power loss correction module 40 is also used to determine the target power generation impact range corresponding to the faulty photovoltaic unit, and to determine the upper-level power generation impact range corresponding to the upper-level equipment of the faulty photovoltaic unit; if the upper-level power generation impact range covers the target power generation impact range, an overlapping time slice is determined according to the time overlap relationship, and the overlapping power loss corresponding to the overlapping time slice is removed from the initial power loss to obtain the corrected power loss; if the upper-level power generation impact range does not cover the target power generation impact range, it is determined whether there are multiple faults of the same level according to the equipment hierarchy relationship; if there are multiple faults of the same level, the initial power loss is proportionally allocated to obtain the corrected power loss; if there are no multiple faults of the same level, if there is a fault causal relationship, the initial power loss is corrected according to the fault causal relationship to obtain the corrected power loss.

[0084] Other embodiments or specific implementations of the photovoltaic power plant fault loss power determination device of this application can be referred to the above-mentioned method embodiments, and will not be repeated here.

[0085] This application provides a device for determining the power loss due to a fault in a photovoltaic power plant. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the method for determining the power loss due to a fault in a photovoltaic power plant as described in Embodiment 1 above.

[0086] The following is for reference. Figure 9The diagram illustrates a structural schematic of a photovoltaic power plant fault loss power determination device suitable for implementing embodiments of this application. The photovoltaic power plant fault loss power determination device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9 The illustrated device for determining the power loss due to a fault in a photovoltaic power plant is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0087] like Figure 9 As shown, the photovoltaic power plant fault loss power determination device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the photovoltaic power plant fault loss power determination device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the photovoltaic power plant fault loss determination device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a photovoltaic power plant fault loss determination device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0088] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0089] The photovoltaic power plant fault loss power determination device provided in this application adopts the photovoltaic power plant fault loss power determination method in the above embodiments, which can solve the technical problem of low accuracy of photovoltaic fault loss power. Compared with the prior art, the beneficial effects of the photovoltaic power plant fault loss power determination device provided in this application are the same as the beneficial effects of the photovoltaic power plant fault loss power determination method provided in the above embodiments, and other technical features of the photovoltaic power plant fault loss power determination device are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0090] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0092] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the method for determining the fault loss power of a photovoltaic power station in the above embodiments.

[0093] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0094] The aforementioned computer-readable storage medium may be included in the fault loss power determination device of the photovoltaic power plant; or it may exist independently and not be installed in the fault loss power determination device of the photovoltaic power plant.

[0095] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a photovoltaic power plant fault loss power determination device, the photovoltaic power plant fault loss power determination device: divides the fault impact interval corresponding to the faulty photovoltaic unit within the photovoltaic power plant to obtain multiple target time slots; determines the standard power generation data and actual power generation data corresponding to the faulty photovoltaic unit in each target time slot; determines the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data; corrects the initial power loss based on the fault relationship between multiple fault work orders within the same target time slot; and determines the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

[0096] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Python, Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0098] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0099] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for determining the fault loss power of a photovoltaic power plant, thereby solving the technical problem of low accuracy in determining photovoltaic fault loss power. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the method for determining the fault loss power of a photovoltaic power plant provided in the above embodiments, and will not be repeated here.

[0100] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for determining the fault loss power of a photovoltaic power station, characterized in that, The method includes the following steps: The fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station is divided to obtain multiple target time slices; Determine the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time segment; The initial power loss of the faulty photovoltaic unit in each target time slot is determined based on the standard power generation data and the actual power generation data. The initial power loss is corrected based on the fault relationships among multiple fault work orders within the same target time slice, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss.

2. The method for determining the fault loss power of a photovoltaic power station as described in claim 1, characterized in that, The process involves dividing the fault impact interval corresponding to the faulty photovoltaic unit within the photovoltaic power station to obtain multiple target time slices, including: Determine the fault work order information corresponding to the faulty photovoltaic unit in the photovoltaic power station, and select the fault occurrence time and fault completion time from the fault work order information; The initial fault interval is determined based on the fault occurrence time and the fault completion time. The invalid time periods are removed from the initial fault interval to obtain the fault-affected interval; The fault-affected interval is divided according to a preset time granularity to obtain multiple target time slices.

3. The method for determining the fault loss power of a photovoltaic power station as described in claim 1, characterized in that, The determination of the standard power generation data and actual power generation data of the faulty photovoltaic unit for each target time slot includes: Historical meteorological similar time slots with similar meteorological characteristics to each target time slot are selected from historical time slots without work orders, and first candidate standard power generation data are generated based on the first power generation data of the faulty photovoltaic unit corresponding to the historical meteorological similar time slot. The benchmark object corresponding to the faulty photovoltaic unit is determined, and the second candidate standard power generation data is generated based on the second power generation data of the benchmark object in each target time slice. The meteorological data corresponding to each target time slice is input into the preset meteorological prediction model to obtain the third candidate standard power generation data; The standard power generation data corresponding to the faulty photovoltaic unit in each target time slot is determined based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data, and the actual power generation data corresponding to the faulty photovoltaic unit in each target time slot is determined.

4. The method for determining the fault loss power of a photovoltaic power station as described in claim 3, characterized in that, The process of determining the benchmark object corresponding to the faulty photovoltaic unit includes: Determine the device level and fault object type corresponding to the faulty photovoltaic unit; Based on the equipment level and the fault object type, a benchmark object corresponding to the faulty photovoltaic unit is selected from the photovoltaic power station.

5. The method for determining the fault loss power of a photovoltaic power station as described in claim 3, characterized in that, The step of determining the standard power generation data corresponding to the faulty photovoltaic unit in each target time slot based on at least one of the first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data includes: Determine the first evaluation index corresponding to the first candidate standard power generation data, the second evaluation index corresponding to the second candidate standard power generation data, and the third evaluation index corresponding to the third candidate standard power generation data; The first weight, the second weight, and the third weight corresponding to the first candidate standard power generation data are determined based on the first evaluation index, the second evaluation index, and the third evaluation index. The first candidate standard power generation data, the second candidate standard power generation data, and the third candidate standard power generation data are weighted and fused according to the first weight, the second weight, and the third weight to obtain the standard power generation data of the faulty photovoltaic unit corresponding to each target time slot.

6. The method for determining the fault loss power of a photovoltaic power plant as described in any one of claims 1 to 5, characterized in that, The step of determining the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data includes: When the standard power generation data and the actual power generation data are power data, the initial power loss is calculated based on the standard power generation data, the actual power generation data, and the duration of each target time slice. When the standard power generation data and the actual power generation data are equivalent utilization hours, the initial power loss is calculated based on the standard power generation data, the actual power generation data, and the rated capacity corresponding to the photovoltaic fault unit.

7. The method for determining the fault loss power of a photovoltaic power plant as described in any one of claims 1 to 5, characterized in that, The step of correcting the initial power loss based on the fault relationships among multiple fault work orders within the same target time slice, and determining the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss, includes: Determine whether there are multiple fault work orders for the faulty photovoltaic unit within the same target time slice, or for multiple photovoltaic units at the same level of association with the faulty photovoltaic unit within the same target time slice; If there are multiple fault work orders, the fault relationships between each fault work order are determined. The fault relationships include time overlap relationships, equipment hierarchy relationships, and fault causal relationships. The initial power loss is corrected based on the time overlap relationship, the device hierarchy relationship, and the fault causal relationship, and the target power loss corresponding to the faulty photovoltaic unit is determined based on the corrected power loss.

8. The method for determining the fault loss power of a photovoltaic power station as described in claim 7, characterized in that, The correction of the initial power loss based on the time overlap relationship, the device hierarchy relationship, and the fault causality relationship includes: Determine the target power generation impact range corresponding to the faulty photovoltaic unit, and determine the upstream power generation impact range corresponding to the upstream equipment of the faulty photovoltaic unit; When the influence range of the upper-level power generation covers the influence range of the target power generation, the overlapping time slice is determined according to the time overlap relationship, and the overlapping power loss corresponding to the overlapping time slice is removed from the initial power loss to obtain the corrected power loss. If the influence range of the superior power generation does not cover the influence range of the target power generation, it is determined whether there are multiple faults at the same level based on the equipment hierarchy. If there are multiple faults of the same level, the initial power loss is proportionally distributed to obtain the corrected power loss. If there are no multiple faults of the same level, then if the fault causal relationship exists, the initial power loss is corrected according to the fault causal relationship to obtain the corrected power loss.

9. A device for determining the fault loss power of a photovoltaic power station, characterized in that, The device for determining the power loss due to faults in the photovoltaic power station includes: The interval division module is used to divide the fault impact interval corresponding to the faulty photovoltaic unit in the photovoltaic power station to obtain multiple target time slices; The data determination module is used to determine the standard power generation data and actual power generation data of the faulty photovoltaic unit at each target time segment; The power loss determination module is used to determine the initial power loss of the faulty photovoltaic unit in each target time slot based on the standard power generation data and the actual power generation data. The power loss correction module is used to correct the initial power loss based on the fault relationship between multiple fault work orders within the same target time slice, and to determine the target power loss corresponding to the faulty photovoltaic unit based on the corrected power loss.

10. A device for determining the fault loss power of a photovoltaic power station, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for determining the fault loss power of a photovoltaic power plant as described in any one of claims 1 to 8.

11. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the method for determining the fault loss power of a photovoltaic power station as described in any one of claims 1 to 8.

Images