A photovoltaic inverter group operation state dynamic evaluation method and related device

Abstract

This invention provides a method and related device for dynamic evaluation of the operating status of a photovoltaic inverter group, belonging to the field of photovoltaic power generation operation and maintenance and intelligent diagnostic technology. It includes: constructing a multi-dimensional state feature set based on collected wind farm data; wherein the data includes environmental information, operating data of each inverter, thermal information and communication status, and spatial arrangement information of the inverter group; the multi-dimensional state feature set includes performance deviation characteristics, zonal irradiance impact correction characteristics, spatiotemporal consistency characteristics, trend and fluctuation characteristics, thermal anomaly propagation characteristics, and communication reliability characteristics; and determining anomalies in the photovoltaic inverter group based on the multi-dimensional state feature set. This invention, by integrating multi-dimensional features, can accurately distinguish between environmental disturbances and equipment performance degradation, reduce false alarms and missed alarms, and achieve dynamic evaluation of the inverter group's operating status, anomaly identification, and early warning of potential hazards, thereby improving the intelligence level and operational reliability of photovoltaic power plant operation and maintenance.

Description

Technical Field

[0001] This invention belongs to the field of photovoltaic power generation operation and maintenance and intelligent diagnosis technology, specifically involving a method and related device for dynamic evaluation of the operating status of a photovoltaic inverter group. Background Technology

[0002] Photovoltaic power plants typically consist of large-scale inverter clusters, with each inverter deployed across complex terrain. As the core equipment for photovoltaic power conversion and grid connection, the operating status of the inverters directly impacts the overall power generation performance and reliability of the plant. Therefore, real-time monitoring, anomaly detection, and fault location of inverter clusters are important research directions in the field of photovoltaic power plant operation and maintenance.

[0003] Current inverter fault detection methods largely rely on the output deviation of individual devices or fixed alarm thresholds, lacking a comprehensive assessment of environmental changes, neighborhood relationships, and communication status. Under complex operating conditions such as rapid changes in cloud cover, localized equipment degradation, or temperature rise diffusion, false alarms and missed alarms frequently occur. Furthermore, traditional diagnostic methods struggle to distinguish between localized faults and overall disturbances, lacking the ability to provide early warnings of potential hazards, resulting in equipment failures often only being discovered after they have severely impacted power generation.

[0004] Based on the above situation, there is an urgent need in this field for an intelligent diagnostic technology for inverter groups that can comprehensively consider factors such as environmental rationality, electrical and spatial correlation, dynamic operation trends, thermal anomaly propagation, and communication reliability, so as to achieve accurate identification of inverter anomalies, fault location, and early warning of potential risks, thereby improving the overall operational reliability and maintenance efficiency of photovoltaic power plants. Summary of the Invention

[0005] The purpose of this invention is to provide a method and related apparatus for dynamic evaluation of the operating status of photovoltaic inverter groups, which solves the above-mentioned shortcomings in the prior art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a method for dynamic evaluation and anomaly identification of the operating status of a photovoltaic inverter group, comprising the following steps: Based on the collected wind farm data, a multi-dimensional state feature set is constructed. The data includes environmental information of the wind farm, operating data, thermal information and communication status of each inverter, and spatial arrangement information of the inverter group. The multi-dimensional state feature set includes performance deviation features, zonal irradiance impact correction features, graph spatiotemporal consistency features, trend and fluctuation features, thermal anomaly propagation features, and communication reliability features. Anomalies in photovoltaic inverter groups are determined based on a multidimensional set of state features.

[0007] Preferably, the specific method for constructing performance deviation characteristics is as follows: Based on the irradiance and component temperature information in the environmental information, combined with the photovoltaic array rating information and inverter conversion capability, the reference output level that the inverter should have under the current environment is estimated. By comparing the obtained reference output level with the actual grid-connected output level, the performance deviation characteristics used to measure the inverter's output capability deviation are obtained.

[0008] Preferably, the specific method for constructing the partitioned irradiation effect correction features is as follows: Based on the installation orientation and positional relationship of the photovoltaic array in the spatial layout information, and the topography of the wind farm or the shading information of the photovoltaic array in the environmental information, the light reception status of the photovoltaic array corresponding to the inverter at the current moment is determined. Based on the light reception conditions, it is determined whether the corresponding photovoltaic array is blocked. When the photovoltaic array is blocked, the output power reduction corresponding to the performance deviation characteristics is reasonably marked and / or corrected to form the regional irradiance effect correction characteristics.

[0009] Preferably, the method for constructing graph spatiotemporal consistency features is as follows: Construct the association graph structure of the inverter group; Based on the correlation diagram structure, compare the performance deviation trends of the current inverter with its spatially adjacent or grouped electrical devices. Calculate the consistency index based on the trend of performance deviation changes; Consistency indices are used as spatiotemporal consistency features of graphs.

[0010] Preferably, the method for constructing trend and fluctuation characteristics is as follows: Obtain the trajectory curve of performance deviation characteristics over time; Long-term trend changes and short-term fluctuations are extracted from the trajectory curve to form trend and fluctuation characteristics.

[0011] Preferably, the method for constructing the propagation characteristics of thermal anomalies is as follows: Based on thermal information, calculate the temperature rise deviation index of the current inverter; Based on the constructed thermal correlation neighborhood set of the inverter, for the current inverter, the temperature change sequence of multiple inverters in its neighborhood is selected, and the neighborhood temperature change trend consistency index is calculated. Based on the temperature rise deviation index and the temperature change trend consistency index, determine whether the current inverter thermal anomaly has propagation characteristics; By comprehensively characterizing the matching relationship between temperature rise deviation index, temperature change trend consistency index, and thermal anomaly propagation characteristics, thermal anomaly propagation features are constructed.

[0012] Preferably, the method for constructing communication reliability characteristics is as follows: The reliability of data transmission is evaluated based on the communication status of the inverter, and communication reliability characteristics are constructed based on the evaluation results.

[0013] Preferably, anomalies in the photovoltaic inverter group are determined based on a multi-dimensional set of state features. Specifically, the method is as follows: The obtained performance deviation characteristics, zonal irradiation impact correction characteristics, spatiotemporal consistency characteristics, trend and fluctuation characteristics, thermal anomaly propagation characteristics and communication reliability characteristics are fused together to form an anomaly risk value; Anomaly risk values ​​are used as thresholds to determine anomalies in photovoltaic inverter groups.

[0014] Secondly, the present invention provides a dynamic evaluation system for the operating status of a photovoltaic inverter group, comprising: The feature set construction unit is configured to construct a multi-dimensional state feature set based on the collected wind farm data information; wherein, the data information includes the wind farm's environmental information, the operating data, thermal information and communication status of each inverter, and the spatial arrangement information of the inverter group; the multi-dimensional state feature set includes performance deviation features, zonal irradiance impact correction features, graph spatiotemporal consistency features, trend and fluctuation features, thermal anomaly propagation features, and communication reliability features; The anomaly detection unit is configured to detect anomalies in the photovoltaic inverter group based on a multi-dimensional set of state features.

[0015] Thirdly, the present invention provides an electronic device including a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the electronic device performs the method described thereon.

[0016] Compared with the prior art, the beneficial effects of the present invention are: This invention provides a method for dynamic evaluation and anomaly identification of photovoltaic inverter group operation status. By collecting wind farm environmental information, inverter operation data, thermal information, communication status, and spatial layout information, a multi-dimensional state feature set is constructed, including performance deviation characteristics, zonal irradiance impact correction characteristics, spatiotemporal consistency characteristics, trend and fluctuation characteristics, thermal anomaly propagation characteristics, and communication reliability characteristics. Anomalies in the inverter group are then determined based on this feature set. Compared to traditional single-device output deviation or fixed threshold alarm methods described in the background art, this method can effectively distinguish between power changes caused by reasonable environmental disturbances and actual equipment performance degradation, enabling accurate local fault location from overall disturbances. Simultaneously, this invention can identify signs of continuous degradation or potential thermal fault propagation trends in inverter operation, achieving early warning of equipment hazards and improving the proactive operation and maintenance capabilities of the power plant. The introduction of a communication reliability assessment mechanism can prevent misjudgments when communication status is abnormal, giving the system higher robustness and reliability. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating Embodiment 1 of the present invention.

[0018] Figure 2 This is a schematic diagram of the modules in Embodiment 2 of the present invention. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0023] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0025] Example 1 This embodiment provides a method for dynamic assessment and anomaly identification of photovoltaic inverter group operation status. This method employs an edge-cloud collaborative processing architecture, collecting inverter operation information, establishing a set of status features, fusing multimodal evidence and dynamic threshold judgments to achieve real-time health assessment and fault classification at the inverter group level. The system connects to existing monitoring platforms via standard communication protocols, requiring no modification to the primary equipment structure of the power plant, and possesses good compatibility and scalability.

[0026] like Figure 1 As shown, the method in this embodiment mainly includes the following functional flow: The system centrally collects and manages the operational measurement data of all inverters in the power station in a unified time series. Then, it constructs inverter performance status characteristics by combining environmental conditions such as irradiance and temperature, and introduces shading analysis, graph spatiotemporal relationship, trend characteristics, thermal diffusion characteristics, and communication consistency checks. On this basis, it fuses evidence of multi-dimensional features to form anomaly confidence. Finally, it identifies and classifies anomalies by dynamically judging thresholds and changing trends, so as to accurately determine the type and scope of inverter faults and provide alarm information and operation and maintenance suggestions.

[0027] Through the above process, this embodiment can achieve highly reliable anomaly detection under complex operating conditions such as rapid weather disturbances, communication fluctuations, and slow equipment degradation, effectively reducing false alarm rates and providing early warnings of potential risks; specifically as follows: Step 1, Data Acquisition and Synchronization Collect data information from the wind farm, including environmental information of the wind farm, operating data, thermal information and communication status of each inverter, and spatial layout information of the inverter group; In this embodiment, environmental information includes irradiance, component temperature, wind farm topography and landforms, and information on obstructions corresponding to the photovoltaic array; operating data includes AC side power, voltage and frequency, DC side voltage, current and component channel output power; communication status includes packet loss and message delay; thermal information includes inverter internal power module temperature, radiator temperature, internal temperature, air duct temperature, fan speed and thermal protection status. The collected data are standardized with a unified time base to ensure that data from each inverter can be correlated and analyzed according to a consistent time scale. For missing or abrupt data, quality labeling and correction are performed using reliability assessment and alternative compensation methods to prevent subsequent analysis from being interfered with by data anomalies.

[0028] Step 2, State Feature Construction Under edge-cloud collaboration, a multi-dimensional set of state features for anomaly identification is constructed based on data information. This step includes the following specific steps: S1, Construction of Performance Deviation Features Based on environmental information including irradiance and component temperature, a reference output level for the inverter under the current environment is estimated according to the photovoltaic array's rated information and the inverter's conversion capacity. This reference output is then compared with the actual grid-connected output to form a performance deviation characteristic used to measure the inverter's output capacity deviation.

[0029] This feature is used to identify situations where the equipment operates at too low, too high, or at an abnormal operating point, serving as a basis for subsequent judgments.

[0030] S2, Construction of Modified Features for Partial Irradiation Effects Based on the installation orientation and location of the photovoltaic array, as well as the topography or other obstructions at the power station site, determine the current light-receiving status of the photovoltaic array corresponding to the inverter.

[0031] Based on the light conditions, it is determined whether the corresponding photovoltaic array is blocked. When the photovoltaic array is blocked, the output power reduction corresponding to the performance deviation characteristics is reasonably marked and / or corrected to form the regional irradiance effect correction characteristics. When the photovoltaic array is shaded and the degree of shading can be estimated using a shading model, the corresponding output power reduction in the performance deviation characteristics is corrected; otherwise, the corresponding output power reduction in the performance deviation characteristics is not corrected.

[0032] This irradiation effect correction feature is used to distinguish between normal output fluctuations caused by natural shading and anomalies caused by equipment performance degradation, which can significantly reduce the generation of false shading alarms in communication protocol alarms.

[0033] S3, Construction of Graph Spatiotemporal Consistency Features Based on the spatial arrangement and electrical connection topology of inverters, an association graph structure for the inverter group is constructed. Combined with changes in operating state over time, the state consistency among the inverters is analyzed, thereby constructing the spatiotemporal consistency characteristics of the graph. The specific process includes the following: First, based on the physical installation location and electrical connection topology of the inverters, an association graph structure of the inverter group is established, in which each inverter is a node in the graph, and the connection relationship between nodes is determined according to their spatial proximity or electrical connection relationship, forming an inverter neighborhood set.

[0034] Secondly, for any inverter to be analyzed, the change sequence of its performance deviation characteristics within a continuous time window is extracted, and the performance deviation change sequence of each inverter in its neighborhood is obtained simultaneously. The sequences are then time-aligned to ensure comparability.

[0035] Furthermore, a consistency index is calculated by comparing the performance deviation trends of the inverter under analysis and its neighboring inverters within the time window. This consistency index characterizes the degree of coordination among the inverters over time, and its calculation method includes comparing whether the direction of change is consistent, whether the magnitude of change is similar, and whether the change process is synchronous, thereby obtaining a numerical index for measuring consistency.

[0036] Based on this, when the performance deviation of the inverter to be analyzed is significantly inconsistent with that of its neighboring inverters, it is determined that the inverter has a local anomaly risk; when multiple adjacent inverters show a consistent trend of change, it is determined that the change is more likely to be caused by environmental disturbances.

[0037] Finally, the consistency index is used as a graph spatiotemporal consistency feature to reflect the degree of coordination between the operating states of each device in the inverter group in space and time, and serves as an important input for subsequent anomaly fusion judgment.

[0038] S4, Construction of Trend and Volatility Characteristics The trajectory of performance deviation characteristics over time is analyzed to extract long-term trend changes and short-term fluctuations, forming trend and fluctuation characteristics. The long-term trend is used to identify slow equipment degradation, such as increased internal wear and reduced heat dissipation performance; the short-term fluctuations are used to identify random operating fluctuations or unstable operating points.

[0039] This feature expands detection capabilities, enabling the system to identify devices that have not yet caused significant performance degradation but have already shown a tendency to degrade.

[0040] S5, Construction of Thermal Anomaly Propagation Characteristics Based on the thermal information and spatial correlation of inverter groups, the generation of thermal anomalies and their propagation trend within the group are modeled and analyzed to construct thermal anomaly propagation characteristics. The specific process includes the following: First, internal thermal information data is collected from each inverter. The thermal information includes at least the power module temperature, radiator temperature, internal ambient temperature, air duct temperature, and fan operating status parameters. The above data is then processed for time synchronization to form a temperature state sequence of each inverter under a unified time reference.

[0041] Secondly, for a single inverter, based on the correspondence between its temperature state sequence and operating power, the temperature rise deviation index is calculated. Specifically, the current temperature value is compared with the historical reference temperature or the average temperature of similar equipment under the same load conditions to obtain the temperature rise deviation, which is used to characterize whether the inverter has abnormal heat dissipation performance.

[0042] Furthermore, based on the spatial proximity and electrical connection topology between inverters, a set of inverter thermal correlation neighborhoods is constructed. For any inverter to be analyzed, temperature change sequences of multiple inverters within its neighborhood are selected, and a neighborhood temperature change trend consistency index is calculated. This consistency index is obtained by comparing the correlation between the direction and magnitude of temperature changes of adjacent inverters, and is used to characterize the degree of spatial coordination of heat changes.

[0043] Based on this, by combining the single-unit temperature rise deviation index and the neighborhood temperature change consistency index, it is determined whether the thermal anomaly has propagation characteristics: when a certain inverter has a temperature rise anomaly and the inverters in its neighborhood show a similar temperature rise trend over time, it is determined that there is a thermal anomaly propagation trend; when the temperature rise of the neighboring equipment is obvious and the current inverter has not yet shown a significant performance degradation, the inverter is marked as being in a potential thermal impact state.

[0044] Finally, the matching relationship between the single-unit temperature rise deviation index, the neighborhood temperature change consistency index, and the thermal anomaly propagation characteristics is comprehensively characterized to construct thermal anomaly propagation characteristics, which are used to reflect the spatial diffusion risk of thermal anomalies in the inverter group and serve as an important input for subsequent anomaly fusion judgment.

[0045] S6, Construction of Communication Reliability Features The reliability of data transmission is assessed by detecting packet loss, latency jitter, and packet skipping in the network channel. If the device status shows no obvious abnormalities but only communication indicators deteriorate, it is marked as a communication anomaly to avoid mistakenly identifying data transmission problems as device malfunctions.

[0046] For example, when a large number of inverter fault data packets are lost but the operating trends of devices in the same group are consistent, this feature confirms that the fault judgment is delayed.

[0047] S7, Formation of State Feature Set All the features specifically designed for performance anomaly analysis are combined to form an inverter state feature vector, which serves as the input for anomaly fusion judgment in subsequent processes. Each feature is updated in real time at the edge or cloud, enabling the system to promptly reflect changes in the inverter's operating status.

[0048] Step 3, Multimodal anomaly fusion After constructing the state features, the evidentiary relationships between the features are comprehensively determined. The system integrates and evaluates information from multiple sources, including performance deviations, occlusion correction results, consistency performance, trend changes, thermal anomaly correlations, and communication status, to determine the consistency of equipment anomaly signs across different evidentiary dimensions.

[0049] Specifically, if multiple characteristics exhibit trends consistent with the fault mechanism, such as significant performance degradation, inconsistency with the operating performance of neighboring inverters, and abnormal temperature rise, the system determines that the probability of a fault has increased. If one characteristic is abnormal but the others remain normal, the system reduces the reliability of that result to avoid false alarms caused by a single noise source.

[0050] The fusion results are generated in the form of anomaly risk values, which are used for subsequent threshold determination and classification steps.

[0051] Step 4, Adaptive Threshold and Trend Detection Used to determine the boundaries of anomaly detection, ensuring that it still has reasonable identification capabilities under different seasons, irradiation conditions and operation and maintenance strategies.

[0052] First, based on the statistical analysis of the recent operating characteristics of the inverter group, the alarm threshold is dynamically adjusted to reflect the actual operating baseline of the current power station. When the overall equipment status is within the normal fluctuation range, the abnormal trigger condition is higher; when the overall fluctuation intensifies, the system actively tightens the threshold to improve sensitivity.

[0053] Simultaneously, this step identifies changes in the equipment's operating status to determine whether its behavior has undergone a sudden or abrupt shift. An abnormal event is only triggered when both the changing trend and the risk of anomalies indicate a deviation from the normal state, thus effectively suppressing false alarms caused by short-term disturbances.

[0054] Step 5, Anomaly Identification and Alarm Output Once an abnormal event is triggered, this step further determines the type and severity of the abnormality based on its characteristic manifestations.

[0055] Examples of decision logic include: S1. If the output capacity of the equipment decreases and is significantly different from that of the neighboring equipment, it is determined to be a performance abnormality or a generator string fault. S2. If the equipment temperature continues to rise and is accompanied by synchronous changes in the temperature of related equipment, it is determined to be a degradation of heat dissipation performance or a potential thermal failure. S3, if the main issue is a deterioration in communication indicators but other characteristics are normal, then it is judged as an abnormal communication quality rather than a device failure. S4. If a rapid change in equipment characteristics occurs simultaneously with a protection action, it is determined to be a rapid hard fault. After identifying the fault type, the system sends the abnormal alarm content to the monitoring center, and marks the equipment location, the scope of the fault impact, and handling suggestions, such as suggesting reduced operation, planned maintenance, or emergency shutdown.

[0056] This step enables rapid location and classification of equipment faults, allowing maintenance personnel to take appropriate measures based on the urgency of different anomalies.

[0057] In summary, the photovoltaic inverter group dynamic evaluation and anomaly identification method provided in this embodiment forms a complete process from real-time monitoring to equipment fault location through steps such as data acquisition and synchronization, state feature construction, multi-modal fusion, adaptive threshold determination, and anomaly classification output. This method can accurately distinguish between local anomalies and legitimate fluctuations caused by the environment during inverter operation, reducing false alarm rates. It also possesses the ability to identify equipment degradation trends and potential thermal faults in advance, thereby improving the reliability and maintenance efficiency of power plant operation.

[0058] This method can be deployed in new or existing photovoltaic power plants. Without changing the electrical structure and protection system, it can achieve intelligent operation and maintenance improvement through software, and has good industrial applicability.

[0059] Example 2 This embodiment provides a dynamic evaluation system for the operating status of a photovoltaic inverter group, including: The feature set construction unit is configured to construct a multi-dimensional state feature set based on the collected wind farm data information; wherein, the data information includes the wind farm's environmental information, the operating data, thermal information and communication status of each inverter, and the spatial arrangement information of the inverter group; the multi-dimensional state feature set includes performance deviation features, zonal irradiance impact correction features, graph spatiotemporal consistency features, trend and fluctuation features, thermal anomaly propagation features, and communication reliability features; The anomaly detection unit is configured to detect anomalies in the photovoltaic inverter group based on a multi-dimensional set of state features.

[0060] Example 3 This embodiment also provides a computing device. The computing device includes a bus, a processor, a memory, and a communication interface. The processor, memory, and communication interface communicate with each other via the bus. The computing device can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memory in the computing device.

[0061] A bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, a bus can include a path for transmitting information between various components of a computing device (e.g., memory, processor, communication interfaces).

[0062] The processor may include any one or more of the following: central processing unit (CPU), graphics processing unit (GPU), tensor processing unit (TPU), application specific integrated circuit (ASIC), field-programmable gate array (FPGA), microprocessor (MP), or digital signal processor (DSP).

[0063] Memory can include volatile memory, such as random access memory (RAM). Processors can also include non-volatile memory. volatile memory, such as read-only memory (ROM). ROM (memory only), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0064] The memory stores executable program code, which the processor executes to implement the functions of the aforementioned units, thereby achieving, for example, the method described in Embodiment 1. That is, the memory may store instructions for the methods and functions relating to the computing device in any of the above embodiments.

[0065] The communication interface uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between computing devices and other devices or communication networks.

[0066] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for dynamic assessment of operating state of a group of photovoltaic inverters, characterized in that, Includes the following steps: Based on the collected wind farm data, a multi-dimensional state feature set is constructed. The data includes environmental information of the wind farm, operating data, thermal information and communication status of each inverter, and spatial arrangement information of the inverter group. The multi-dimensional state feature set includes performance deviation features, zonal irradiance impact correction features, graph spatiotemporal consistency features, trend and fluctuation features, thermal anomaly propagation features, and communication reliability features. Anomalies in photovoltaic inverter groups are determined based on a multidimensional set of state features.

2. The method of claim 1, wherein, The specific method for constructing performance deviation characteristics is as follows: Based on the irradiance and component temperature information in the environmental information, combined with the photovoltaic array rating information and inverter conversion capability, the reference output level that the inverter should have under the current environment is estimated. By comparing the obtained reference output level with the actual grid-connected output level, the performance deviation characteristics used to measure the inverter's output capability deviation are obtained.

3. The method of claim 1, wherein, The specific method for constructing the partitioned irradiation effect correction features is as follows: Based on the installation orientation and positional relationship of the photovoltaic array in the spatial layout information, and the topography of the wind farm or the shading information of the photovoltaic array in the environmental information, the light reception status of the photovoltaic array corresponding to the inverter at the current moment is determined. Based on the light reception conditions, it is determined whether the corresponding photovoltaic array is blocked. When the photovoltaic array is blocked, the output power reduction corresponding to the performance deviation characteristics is reasonably marked and / or corrected to form the regional irradiance effect correction characteristics.

4. The method of claim 1, wherein, The method for constructing graph spatiotemporal consistency features is as follows: Construct the association graph structure of the inverter group; Based on the correlation diagram structure, compare the performance deviation trends of the current inverter with its spatially adjacent or grouped electrical devices. Calculate the consistency index based on the trend of performance deviation changes; Consistency indices are used as spatiotemporal consistency features of graphs.

5. The method of claim 1, wherein, The method for constructing trend and volatility characteristics is as follows: Obtain the trajectory curve of performance deviation characteristics over time; Long-term trend changes and short-term fluctuations are extracted from the trajectory curve to form trend and fluctuation characteristics.

6. The method of claim 1, wherein, The method for constructing the propagation characteristics of thermal anomalies is as follows: Based on thermal information, calculate the temperature rise deviation index of the current inverter; Based on the constructed thermal correlation neighborhood set of the inverter, for the current inverter, the temperature change sequence of multiple inverters in its neighborhood is selected, and the neighborhood temperature change trend consistency index is calculated. Based on the temperature rise deviation index and the temperature change trend consistency index, determine whether the current inverter thermal anomaly has propagation characteristics; By comprehensively characterizing the matching relationship between temperature rise deviation index, temperature change trend consistency index, and thermal anomaly propagation characteristics, thermal anomaly propagation features are constructed.

7. The method of claim 1, wherein, The method for constructing communication reliability features is as follows: The reliability of data transmission is evaluated based on the communication status of the inverter, and communication reliability characteristics are constructed based on the evaluation results.

8. The method for dynamic evaluation of the operating status of a photovoltaic inverter group according to claim 1, characterized in that, Anomalies in photovoltaic inverter groups are determined based on a multi-dimensional set of state features. The specific method is as follows: The obtained performance deviation characteristics, zonal irradiation impact correction characteristics, spatiotemporal consistency characteristics, trend and fluctuation characteristics, thermal anomaly propagation characteristics and communication reliability characteristics are fused together to form an anomaly risk value; Anomaly risk values ​​are used as thresholds to determine anomalies in photovoltaic inverter groups.

9. A dynamic evaluation system for the operating status of a photovoltaic inverter group, characterized in that, include: The feature set construction unit is configured to construct a multi-dimensional state feature set based on the collected wind farm data information; wherein, the data information includes the wind farm's environmental information, the operating data, thermal information and communication status of each inverter, and the spatial arrangement information of the inverter group; the multi-dimensional state feature set includes performance deviation features, zonal irradiance impact correction features, graph spatiotemporal consistency features, trend and fluctuation features, thermal anomaly propagation features, and communication reliability features; The anomaly detection unit is configured to detect anomalies in the photovoltaic inverter group based on a multi-dimensional set of state features.

10. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1 to 8.

Images