A photovoltaic power station operation measurement and control method and system based on artificial intelligence

Abstract

The present invention relates to the field of monitoring technology. The present invention provides an artificial intelligence-based photovoltaic power station operation measurement and control method and system. The method comprises: obtaining status task information of at least one photovoltaic unit, the status task information comprising at least one of a current time series, a current state series, and a current task content; obtaining historical status task information of at least one photovoltaic unit, the historical status task information comprising a value of a historical time series, a historical state series, and a historical task content, wherein the historical task content is the same as the current task content; determining current fault information based on the current state series and the corresponding historical state series of at least one photovoltaic unit; and dispatching maintenance tasks based on the current fault information.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to an artificial intelligence-based photovoltaic power station operation measurement and control method and system. Background Art

[0002] In the operation of the photovoltaic power station management system, it is necessary to supervise and inspect the operation of each photovoltaic power station, and conduct a series of error corrections and re-inspections based on the inspection results to ensure the normal and reasonable operation of the photovoltaic power station and ensure the safety of the photovoltaic power station. In the process of supervising and inspecting the operation of distributed photovoltaic power stations, there are many locations involved, and the inspection items are complicated. The inspection plan is different due to the different equipment conditions of each photovoltaic power station.

[0003] Therefore, it is hoped to provide an artificial intelligence-based photovoltaic power station operation measurement and control method and system, which can promptly detect and judge fault errors, and through the precise determination of maintenance personnel, timely and accurate maintenance of photovoltaic units that may fail can be performed, which will help optimize maintenance plans, reduce downtime and maintenance costs, and improve the reliability and operating efficiency of photovoltaic stations. Summary of the invention

[0004] This manual provides an artificial intelligence-based photovoltaic power station operation measurement and control method and system, which can timely discover and judge fault errors, and through the accurate determination of maintenance personnel, timely and accurate maintenance of photovoltaic units that may fail can be performed, which helps to optimize maintenance plans, reduce downtime and maintenance costs, and improve the reliability and operation efficiency of photovoltaic stations.

[0005] One of the embodiments of the present specification provides an artificial intelligence-based photovoltaic power station operation measurement and control method, wherein the photovoltaic power station includes at least one photovoltaic unit, and is characterized in that the method includes: obtaining status task information of the at least one photovoltaic unit, the status task information including at least one of a current time series, a current state sequence, and a current task content; obtaining historical status task information of the at least one photovoltaic unit, the historical status task information including at least one of a historical time series, a historical state sequence, and a value of a historical task content, wherein the historical task content is the same as the current task content; determining current fault information based on the current state sequence of the at least one photovoltaic unit and the corresponding historical state sequence; and dispatching maintenance tasks based on the current fault information.

[0006] One of the embodiments of the present specification provides an artificial intelligence-based photovoltaic power station operation measurement and control system, the system comprising: a current module, used to obtain status task information of at least one photovoltaic unit, the status task information comprising at least one of a current time series, a current state sequence, and a current task content; a history module, used to obtain historical status task information of at least one photovoltaic unit, the historical status task information comprising at least one of a historical time series, a historical state sequence, and a value of a historical task content, wherein the historical task content is the same as the current task content; a sequence module, used to determine current fault information based on the current state sequence of the at least one photovoltaic unit and the corresponding historical state sequence; a dispatch module, used to dispatch maintenance tasks based on the current fault information.

[0007] One of the embodiments of the present specification provides an artificial intelligence-based photovoltaic power station operation measurement and control device, the device comprising a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device causes the device to implement the artificial intelligence-based photovoltaic power station operation measurement and control method as described in any one of the above items.

[0008] One of the embodiments of this specification provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs any one of the above-mentioned artificial intelligence-based photovoltaic power station operation measurement and control methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 It is a schematic diagram of an application scenario of an artificial intelligence-based photovoltaic power station operation measurement and control system according to some embodiments of this specification;

[0011] Figure 2 It is a module schematic diagram of a photovoltaic power station operation measurement and control system based on artificial intelligence according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of an artificial intelligence-based photovoltaic power station operation measurement and control method according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary flowchart for dispatching maintenance tasks according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 It is a schematic diagram of an application scenario of an artificial intelligence-based photovoltaic power station operation measurement and control system according to some embodiments of this specification.

[0019] In some embodiments, the scenario 100 involved in the artificial intelligence-based photovoltaic power station operation measurement and control system may include a processor 110 , a photovoltaic power station 120 , a storage device 130 , a network 140 , and a user terminal 150 .

[0020] In some embodiments, the processor 110 may be used to process information and / or data related to the scene 100, for example, to determine monitoring indicators and review indicators of the monitoring process based on monitoring data. In some embodiments, the processor 110 may be local or remote. For example, the processor 110 may access information and / or data stored in the storage device 130 or the user terminal 150 via the network 140. For another example, the processor 110 may be directly connected to the storage device 130 or the user terminal 150 to access the stored information and / or data.

[0021] In some embodiments, the processor 110 may process information and / or data related to the scene 100 to perform one or more functions described in the present application. For example, the processor 110 may process daily monitoring data based on a model to determine abnormal indicators.

[0022] The photovoltaic power station 120 may refer to all devices of all photovoltaic power stations included. The photovoltaic power station 120 may include at least one photovoltaic unit. A camera device is arranged near each photovoltaic unit to obtain the status of the photovoltaic unit.

[0023] The storage device 130 may be used to store data and / or instructions related to the operation and control of the photovoltaic power station based on artificial intelligence. In some embodiments, the storage device 130 may store data obtained / retrieved from the user terminal 150. In some embodiments, the storage device 130 may store data and / or instructions used by the processor 110 to execute or use to complete the exemplary methods described in this application. In some embodiments, the storage device 130 may be implemented on a cloud platform.

[0024] In some embodiments, the storage device 130 may be connected to the network 140 to communicate with one or more components of the scene 100 (e.g., the processor 110, the photovoltaic power plant 120, the user terminal 150). One or more components of the scene 100 may access data or instructions stored in the storage device 130 via the network 140. In some embodiments, the storage device 130 may be directly connected to or communicate with one or more components of the scene 100 (e.g., the processor 110, the photovoltaic power plant 120, the user terminal 150). In some embodiments, the storage device 130 may be part of the processor 110. In some embodiments, the storage device 130 may be a separate memory.

[0025] The network 140 can facilitate the exchange of information and / or data. In some embodiments, one or more components of the scene 100 (e.g., the processor 110, the photovoltaic power plant 120, the user terminal 150) can send information and / or data to other components of the scene 100 via the network 140. For example, the processor 110 can obtain daily monitoring data from the user terminal 150 via the network 140. In some embodiments, the network 140 can be a wired network or a wireless network, etc. or any combination thereof. As an example only, the network 140 can include a cable network. In some embodiments, the scene 100 can include one or more network access points. For example, a base station and / or a wireless access point, one or more components of the scene 100 can be connected to the network 140 to exchange data and / or information.

[0026] The user terminal 150 may be a user-operated device or other entity. In some embodiments, the user terminal 150 may be an artificial intelligence-based photovoltaic power station operation measurement and control executor, maintenance personnel, etc. In some embodiments, the user terminal 150 may include a mobile phone, a tablet computer, a laptop computer, etc. or any combination thereof. The user refers to the user / controller of the user terminal. In some embodiments, the user may upload the second monitoring data through the user terminal 150. In some embodiments, the user may obtain information through the user terminal 150.

[0027] Figure 2 It is a module diagram of an artificial intelligence-based photovoltaic power station operation measurement and control system according to some embodiments of this specification.

[0028] like Figure 2 As shown, the photovoltaic power station operation measurement and control system 200 based on artificial intelligence may include a current module 210 , a history module 220 , a sequence module 230 , and a dispatch module 240 .

[0029] The current module 210 is used to obtain the state task information of the at least one photovoltaic unit, and the state task information includes at least one of the current time sequence, the current state sequence, and the current task content;

[0030] The history module 220 is used to obtain the historical status task information of the at least one photovoltaic unit, wherein the historical status task information includes at least one of the values ​​of the historical time series, the historical status series and the historical task content, wherein the historical task content is the same as the current task content;

[0031] The sequence module 230 is used to determine current fault information based on the current state sequence and the corresponding historical state sequence of the at least one photovoltaic unit;

[0032] The dispatching module 240 is used to dispatch maintenance tasks based on the current fault information.

[0033] In some embodiments, the dispatch module 240 further includes: a task sequence determination module, used to determine the first task sequence of at least one staff member at the current time point; a candidate determination module, used to determine at least one candidate maintenance personnel based on the first task sequence of the at least one staff member; a target determination module, used to determine the target maintenance personnel from the at least one candidate maintenance personnel; and a maintenance task module, used to dispatch maintenance tasks to the target detection personnel.

[0034] In some embodiments, the target determination module further includes: a first acquisition module, used to acquire the salary information and task list information of the at least one candidate maintenance personnel, and determine the performance information of the at least one candidate maintenance personnel based on the salary information and the task list information; a feature determination module, used to determine the completion characteristics of the at least one candidate maintenance personnel based on the performance information, the salary information and the task list information of the at least one candidate maintenance personnel; a first prediction module, used to predict the first predicted completion time of the at least one candidate maintenance personnel based on the current maintenance task and the completion characteristics of the at least one candidate maintenance personnel; a sequence update module, used to determine an updated second task sequence based on the first task sequence of the at least one candidate maintenance personnel and the priority of the current maintenance task; a second prediction module, used to determine the second predicted completion time for each of the at least one candidate maintenance personnel to complete the current maintenance task based on the second task sequence; a time determination module, used to select the candidate maintenance personnel with the shortest second predicted completion time as the target maintenance personnel.

[0035] In some embodiments, the first acquisition module further includes: a comparison module, used to compare the preset tasks in the task list information and the salary information in the salary information; a corresponding determination module, used to determine the corresponding relationship between the completion status of the preset tasks and the salary; a performance determination module, used to determine the performance information based on the corresponding relationship between the task completion status and the salary.

[0036] It should be understood that the above modules are only simple examples of the relevant modules mainly involved in this specification, and do not represent the display of all relevant contents of this application. There are also some modules and units that are not shown in this module diagram, and they are not illustrated one by one here. Moreover, the above modules and units are not completely independent, and may also be cross-involved.

[0037] Figure 3 300 is an exemplary flow chart of a photovoltaic power station operation measurement and control method based on artificial intelligence according to some embodiments of this specification. Process 300 can be executed by a processor. Figure 3 As shown, process 300 may include the following steps:

[0038] Step 310, obtaining status task information of at least one photovoltaic unit, where the status task information includes at least one of a current time sequence, a current status sequence, and a current task content.

[0039] The state task information may refer to the information about the state adjustment command issued to the photovoltaic unit at the current time. The current time sequence may include the start time, completion time and at least one time point included in the current state task. In the current time sequence, the at least one time point included may be arranged in chronological order. The start time and completion time of the current state task may be set to the first time period. The time interval of at least one time point may be set manually or initially set by the system. The current task content may refer to the content of the completed state task. For example, the current task content may be to rotate 30° to the northwest. The current state sequence may refer to the sequence of postures of the photovoltaic unit in the process of completing the current state task. Each posture in the current state sequence may correspond to each time point in the current time sequence. The state sequence may be represented by a sequence of images of the postures of the current photovoltaic unit or a sequence of vectors representing the images.

[0040] By obtaining the real-time status task information of the PV unit, the operating status of the PV power station can be monitored in real time, and potential faults or abnormal conditions can be discovered in time.

[0041] Step 320, obtaining historical status task information of at least one photovoltaic unit, the historical status task information including at least one of the values ​​of historical time series, historical status series and historical task content, wherein the historical task content is the same as the current task content.

[0042] The historical task information may be information related to the normal completion of the historical status task of the current photovoltaic unit. The current time series may be determined according to the settings in the historical time series. The settings of the start time, completion time and time point of the current time series may correspond to the settings of the historical start time, historical completion time and historical time point in the historical time series. For example, if the start time in the historical time series is 9:00 am of the previous day, the start time in the current time series is 9:00 am.

[0043] Step 330 : determining current fault information based on a current state sequence and a corresponding historical state sequence of at least one photovoltaic unit.

[0044] In some embodiments, a current state sequence of at least one photovoltaic unit is compared with a state in a corresponding historical state sequence in similarity, and current fault information is determined based on the comparison result.

[0045] In some embodiments, the number of state groups in which the state exceeds the state threshold (i.e., the state is consistent) in the current state sequence and the historical state sequence can be compared, and the corresponding similarity score is determined based on the number of state groups according to a preset relationship, and the higher the number of state groups, the higher the corresponding similarity score. The preset relationship can be the corresponding relationship between the number of state groups divided by the number of time points in the current time sequence and the similarity score.

[0046] For example, the current state sequence 1 includes state 1-1, state 1-2, and state 1-3, and the corresponding historical state sequence 2 includes state 2-1, state 2-2, and state 2-3, where state 1-1 and state 2-1 correspond to the same time point, and other states are similar. If the photovoltaic unit has not failed, the states in the current state sequence 1 have corresponding relationships in the corresponding historical state sequence 2 (i.e., the states are consistent), and the similarity is extremely high. If the photovoltaic unit fails, then state 1-1 may correspond to state 2-1, and state 1-3 may correspond to state 2-2, and the similarity is reduced, which may be due to the delay in the deflection of the photovoltaic unit caused by the failure. By using the historical state task information for comparison and analysis, by comparing the similarity of the states in the current state sequence and the historical state sequence, the current fault information can be judged more accurately, which improves the accuracy and reliability of fault diagnosis.

[0047] The current fault information may include the possibility of a fault occurring in the current photovoltaic unit and the corresponding fault type.

[0048] In some embodiments, the current fault information may also be determined by the following steps:

[0049] S1, determining an extended time period and a second time period of at least one photovoltaic unit.

[0050] If the current photovoltaic unit does not complete the current state task within the specified first time period, it is necessary to further observe whether the photovoltaic unit can complete the state task in the future time period. If the state task is not completed within the extended time period, the possibility of failure of the photovoltaic unit is very high.

[0051] The extended time period may refer to a subsequent observation time period for the photovoltaic unit beyond the current completion time. The start time of the extended time period is the completion time of the current state task. The extended time period may also be set with at least one time point, and the time interval setting between each two adjacent time points may be the same as the time interval setting of the time points in the first time period.

[0052] In some embodiments, the sum of the extended time period and the first time period is used as the second time period. The start time of the second time period is the start time of the current time series, and the end time is the end time of the extended time period.

[0053] The second time period may be determined by a fault duration model. The fault duration model may be a machine learning model, such as a neural network model.

[0054] The input of the fault duration model may include the current photovoltaic unit model or number, the current state task content, and the output is the second time period. The fault duration model can be obtained through the first training sample, which may include the historical state task content, the photovoltaic unit model or number of the historical fault, and the label is the historical time required for the faulty photovoltaic unit to complete the historical state task content. The elements of the first training sample all correspond to the same photovoltaic unit.

[0055] The fault duration model can be used to determine how long it takes for a faulty PV unit to complete its status task. Since this time may be an average value, for a PV unit that may currently be faulty, within the second time period output by the fault duration model, the PV unit that may currently be faulty may complete its current status task or may not be able to complete its current status task.

[0056] S2, based on the second time period, obtaining an extended state sequence of at least one photovoltaic unit in the second time period.

[0057] The extended state sequence may include a state sequence corresponding to the second time period and a current state sequence corresponding to the first time period.

[0058] When the last state in the extended state sequence still cannot correspond to the completion state of the state task, it indicates that the current photovoltaic unit has a fault.

[0059] S3, respectively comparing a first similarity of states in a current state sequence and a corresponding historical state sequence, and a second similarity of states in an extended state sequence and the historical state sequence of at least one photovoltaic unit.

[0060] The first similarity and the second similarity may refer to the relevant description of the similarity of states in the current state sequence and the corresponding historical state sequence.

[0061] S4, determining fault information based on the first similarity, the second similarity, and the end state within the extended time period.

[0062] When the first similarity is high enough, it may be due to delay or weather, or a minor fault of the device itself (not enough to affect the fluctuation of the amount of electric energy converted by the current status task), and it can be considered that the current photovoltaic device does not need manual maintenance.

[0063] When the second similarity is higher than the similarity, it means that although the current photovoltaic unit has not completed the task in the first time period, it may continue to rotate to the designated position in the extended time period. At this time, the second similarity is higher than the first similarity.

[0064] When the second similarity is equal to the first similarity, it means that the current photovoltaic unit does not continue to rotate to the specified position within the extended time period, that is, a fault occurs.

[0065] In some embodiments, the likelihood of a fault may be determined by a machine learning model based on the first similarity, the second similarity, and the end state over an extended period of time.

[0066] In some embodiments, at least one state difference corresponding to each time point of the first time period and the historical time series is compared in sequence, and the time point and the corresponding state difference list of the state difference value are selected, and the fault possibility and the corresponding fault type are determined by the fault possibility model based on the time point and the corresponding state difference list. In some embodiments, a small state deviation (state similarity) may appear at the beginning time point due to accidental external factors or a minor fault of the self, then each corresponding time point thereafter will have a small state deviation of the same deviation value. For this, the fault type can be determined from the state image at the time point when the deflection occurs. For example, the current state sequence 1 of the first time period includes state 1-1, state 1-2, and state 1-3, and the corresponding historical state sequence 2 includes state 2-1, state 2-2, and state 2-3, wherein state 1-1 and state 2-1 correspond to the same time point, the state deviation between state 1-2 and state 2-2 is 98%, and the state deviation between 1-3 and state 2-3 is also 98%, and the possible state type can be determined based on the state image of the time point corresponding to state 1-2. This is because in the process of completing the state task, the components that may be mainly responsible for completing the task stage (for example, the components for lifting and rotating) are different. In some embodiments, as time goes by, the state deviation gradually increases and exceeds a certain threshold, the fault type will change again, and the current fault type can be determined by the preset state deviation value-fault type relationship.

[0067] The state difference can be represented by the distance between the current state vector and the historical state vector corresponding to the same time point. The longer the distance, the greater the difference between the current posture of the photovoltaic unit and the posture in the historical state sequence, that is, the posture of the photovoltaic unit that successfully completes the task at the same time point is greater.

[0068] In some embodiments of the present specification, by introducing an extended time period and state similarity analysis, the problems of short observation time period and low diagnostic accuracy in traditional methods are overcome, and photovoltaic unit faults can be diagnosed more accurately, and possible fault types and locations can be predicted, so that photovoltaic units that may fail can be promptly and accurately maintained, which helps to optimize maintenance plans, reduce downtime and maintenance costs, and improve the reliability and operating efficiency of photovoltaic stations.

[0069] Step 340: dispatch maintenance tasks based on the current fault information.

[0070] The maintenance task may be a task for the photovoltaic unit corresponding to the current fault information.

[0071] Figure 4 It is an exemplary flow chart of dispatching maintenance tasks according to some embodiments of the present specification. Process 400 may be executed by a processor.

[0072] The dispatching of maintenance tasks includes dispatching maintenance tasks to target inspection personnel.

[0073] like Figure 4 As shown, process 400 may include the following steps:

[0074] Step 410 , determining a first task sequence of at least one worker at the current time point.

[0075] Each task in the task sequence corresponds to a task level. The higher the level, the more difficult the task is to complete. The first task sequence may refer to an arrangement of tasks of at least one worker including the current time point in time order.

[0076] Step 420: determine at least one candidate maintenance personnel based on the first task sequence of at least one worker.

[0077] The candidate maintenance personnel may refer to the personnel whose workload at the current time point is lower than the workload threshold. The workload threshold may be determined manually. The workload may be expressed as the time required to complete the current task. The time corresponding to the workload may be determined by subtracting the time already used from the time allocated for the current task.

[0078] Step 430: determine a target maintenance personnel from at least one candidate maintenance personnel.

[0079] Target maintenance personnel refer to the personnel who perform maintenance on the faulty PV units.

[0080] In some embodiments, the target maintenance personnel may be determined by the following method:

[0081] Step 431, obtaining salary information and task list information of at least one candidate maintenance personnel, and determining performance information of at least one candidate maintenance personnel based on the salary information and task list information.

[0082] In some embodiments, the performance information can be determined by the salary information of the candidate maintenance personnel and the task list (including performance) of the month. Because sometimes the task list can only indicate the set task information, but the salary information can accurately determine the completion of the task. The performance information can refer to the task actually completed by the maintenance personnel.

[0083] The salary information of the candidate maintenance personnel is obtained from the salary record or salary system, where the salary information includes at least one of basic salary, bonus, subsidy and other salary conditions.

[0084] The task list information of the candidate maintenance personnel is obtained from the task allocation system or management software, and the task list information may include preset task information for the candidate maintenance personnel. The task list information of the candidate maintenance personnel includes at least one of task type, task description, and task completion status.

[0085] In some embodiments, in combination with the salary information and task list information, the performance information of the candidate maintenance personnel can be determined through the following steps: comparing the preset tasks in the task list information and the remuneration in the salary information; determining the correspondence between the completion of the preset tasks and the remuneration; and determining the performance information based on the correspondence between the completion of the preset tasks and the remuneration.

[0086] Step 432: Determine the completion characteristics of at least one candidate maintenance personnel based on the performance information, salary information, and task list information of at least one candidate maintenance personnel. The completion characteristics may include at least one of the possibility of the personnel completing the task within the specified time for the fault type and the corresponding resolution time.

[0087] Fault types can correspond to task types.

[0088] All features can be determined by machine learning models. Machine learning models can be obtained through historical data training.

[0089] Step 433: predict a first predicted completion time of at least one candidate maintenance personnel based on the current maintenance task and the completion characteristics of at least one candidate maintenance personnel.

[0090] The first predicted completion time is the time it takes for the staff to complete the current maintenance task.

[0091] Step 434: determine an updated second task sequence based on the first task sequence of at least one candidate maintenance personnel and the priority of the current maintenance task.

[0092] For example, the first task sequence of candidate maintenance worker A includes tasks A, B, C, and D in chronological order. A is completing task B, and the priority of the current task is higher than that of task C but lower than that of task D. Then the second task sequence is task A, task B, task C, the current maintenance task, and task D. The priority of maintenance tasks can be set manually.

[0093] Step 435 : determining a second predicted completion time for each of at least one candidate maintenance personnel to complete the current maintenance task based on the second task sequence.

[0094] The second predicted completion time can be determined by the corresponding time in the first task sequence and the first predicted completion time, as well as the second task sequence. For example, the first task sequence of candidate maintenance personnel A includes tasks A, B, C, and D sorted by time, and A is completing task B. The second task sequence is task A, task B, task C, the current maintenance task, and task D. The second predicted completion time can be the time required for the current task in the first task sequence + the estimated completion time of task C + the first predicted completion time.

[0095] Step 436: select the candidate maintenance personnel with the shortest second predicted completion time as the target maintenance personnel.

[0096] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0097] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0098] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0099] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0100] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0101] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0102] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0103] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A photovoltaic power station operation measurement and control method based on artificial intelligence, wherein the photovoltaic power station comprises at least one photovoltaic unit, characterized in that: The method comprises: Acquire status task information of the at least one photovoltaic unit, wherein the status task information includes at least one of a current time sequence, a current state sequence, and a current task content; Acquire historical status task information of the at least one photovoltaic unit, the historical status task information including at least one of a historical time series, a historical status series, and a value of a historical task content, wherein the historical task content is the same as the current task content; determining current fault information based on the current state sequence and the corresponding historical state sequence of the at least one photovoltaic unit; Based on the current fault information, a maintenance task is dispatched, wherein the dispatching of the maintenance task includes: Determine a first task sequence of at least one worker at a current time point; determining at least one candidate maintenance personnel based on the first task sequence of the at least one worker; determining a target maintenance personnel from the at least one candidate maintenance personnel; Perform maintenance tasks on the target maintenance personnel; wherein determining the target maintenance personnel from at least one candidate maintenance personnel comprises: Obtaining the salary information and task list information of the at least one candidate maintenance personnel, and determining the performance information of the at least one candidate maintenance personnel based on the salary information and the task list information, wherein the determining the performance information of the at least one candidate maintenance personnel includes: comparing the preset tasks in the task list information with the salary information in the salary information; determining the corresponding relationship between the completion of the preset tasks and the salary; determining the performance information according to the corresponding relationship between the completion of the preset tasks and the salary; Based on the performance information, salary information, and task list information of the at least one candidate maintenance personnel, determining the completion feature of the at least one candidate maintenance personnel through a machine learning model, wherein the completion feature includes at least one of the staff member's understanding of the fault type and the corresponding resolution time, and the possibility of completing the task within the specified time, wherein the fault type corresponds to the task type; Based on the current maintenance task and the completion characteristics of the at least one candidate maintenance personnel, predict a first predicted completion time of the at least one candidate maintenance personnel, where the first predicted completion time is the time it takes for the at least one candidate maintenance personnel to complete the current maintenance task; Determine an updated second task sequence based on the first task sequence of the at least one candidate maintenance personnel and the priority of the current maintenance task, wherein the second task sequence includes the first task sequence and the current maintenance task, and the current maintenance task is added to the first task sequence based on the priority; Based on the second task sequence, determining a second predicted completion time for each of the at least one candidate maintenance personnel to complete the current maintenance task, the second predicted completion time being determined by a corresponding time in the first task sequence and the first predicted completion time, and the second task sequence; The candidate maintenance personnel with the shortest second predicted completion time is used as the target maintenance personnel.

2. A photovoltaic power station operation measurement and control system based on artificial intelligence, wherein the photovoltaic power station comprises at least one photovoltaic unit, characterized in that: The system comprises: A current module, used to obtain the state task information of the at least one photovoltaic unit, wherein the state task information includes at least one of a current time sequence, a current state sequence, and a current task content; A history module, used to obtain historical status task information of the at least one photovoltaic unit, wherein the historical status task information includes at least one of a historical time series, a historical status series, and a value of a historical task content, wherein the historical task content is the same as the current task content; a sequence module for determining current fault information based on the current state sequence and the corresponding historical state sequence of the at least one photovoltaic unit; A dispatching module, used to dispatch maintenance tasks based on the current fault information, the dispatching module further comprising: A task sequence determination module, used to determine a first task sequence of at least one worker at a current time point; A candidate determination module, configured to determine at least one candidate maintenance personnel based on the first task sequence of the at least one worker; A target determination module, used to determine a target maintenance personnel from the at least one candidate maintenance personnel; The maintenance task module is used to assign maintenance tasks to the target maintenance personnel. Wherein, the target determination module further includes: A first acquisition module is used to acquire salary information and task list information of the at least one candidate maintenance personnel, and determine performance information of the at least one candidate maintenance personnel based on the salary information and the task list information, wherein the first acquisition module further includes: A comparison module, used to compare the preset tasks in the task list information with the salary information in the salary information; a corresponding determination module, used to determine the corresponding relationship between the completion of the preset tasks and the salary; a performance determination module, used to determine the performance information according to the completion of the preset tasks and the corresponding relationship between the salary; a feature determination module, configured to determine, based on the performance information of the at least one candidate maintenance personnel, the salary information, and the task list information, a completion feature of the at least one candidate maintenance personnel through a machine learning model, wherein the completion feature includes at least one of the possibility of the staff member completing the task within a specified time period for a fault type and a corresponding resolution time period, and the fault type corresponds to the task type; A first prediction module is used to predict a first predicted completion time of the at least one candidate maintenance personnel based on the current maintenance task and the completion characteristics of the at least one candidate maintenance personnel, wherein the first predicted completion time is the time length for the at least one candidate maintenance personnel to complete the current maintenance task; A sequence updating module, configured to determine an updated second task sequence based on the first task sequence of the at least one candidate maintenance personnel and the priority of the current maintenance task, wherein the second task sequence includes the first task sequence and the current maintenance task, and the current maintenance task is added to the first task sequence based on the priority; a second prediction module, for determining, based on the second task sequence, a second predicted completion time for each of the at least one candidate maintenance personnel to complete the current maintenance task, the second predicted completion time being determined by a corresponding time in the first task sequence and the first predicted completion time, and the second task sequence; A time determination module is used to select the candidate maintenance personnel with the shortest second predicted completion time as the target maintenance personnel.

3. A photovoltaic power station operation measurement and control device based on artificial intelligence, the device comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the photovoltaic power station operation measurement and control method based on artificial intelligence as described in claim 1.

4. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the photovoltaic power station operation measurement and control method based on artificial intelligence as claimed in claim 1.

Images