Distributed power fault fast diagnosis system for smart grid

Abstract

The application provides a distributed power failure rapid diagnosis system for a smart grid, which comprises n power monitoring nodes, a diagnosis node distribution module and m diagnosis nodes; the n power monitoring nodes are arranged at designated positions of the smart grid; a first power monitoring node acquires first identification information of the first power monitoring node, acquires power operation data in a preset time period, and sends the first identification information and the power operation data to the diagnosis node distribution module; the first power monitoring node is any power monitoring node in the n power monitoring nodes; the diagnosis node distribution module determines a first diagnosis node according to the first identification information and the power operation data, and sends the power operation data to the first diagnosis node; the first diagnosis node performs power failure diagnosis according to the power operation data, and obtains a target power failure diagnosis result. The power failure diagnosis efficiency of the smart grid can be improved by adopting the embodiment of the application.

Description

Technical Field

[0001] This application relates to the field of smart grid technology or artificial intelligence technology, specifically to a distributed power fault rapid diagnosis system for smart grids. Background Technology

[0002] With the rapid development of power grid technology, smart grids have entered our lives. A smart grid can be simply understood as the intelligentization of the power grid. Specifically, a smart grid is a technological application within the power grid, built upon an integrated, high-speed, two-way communication network, utilizing advanced equipment technology, advanced sensing and measurement technology, advanced control methods, and advanced decision support system technology.

[0003] Currently, the efficiency of power fault diagnosis in smart grids is relatively low. Therefore, the problem of how to improve the efficiency of power fault diagnosis in smart grids urgently needs to be solved. Summary of the Invention

[0004] This application provides a distributed power fault rapid diagnosis system for smart grids, which can improve the efficiency of power fault diagnosis in smart grids.

[0005] In a first aspect, embodiments of this application provide a distributed power fault rapid diagnosis system for smart grids. The system includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; all n power monitoring nodes are configured at designated locations within the smart grid; n and m are both integers greater than 1; wherein...

[0006] The first power monitoring node is used to obtain the first identification information of the first power monitoring node, obtain power operation data for a preset time period, and send the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes;

[0007] The diagnostic node allocation module is used to determine a first diagnostic node based on the first identification information and the power operation data, and to send the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes;

[0008] The first diagnostic node is used to perform power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result.

[0009] Implementing the embodiments of this application has the following beneficial effects:

[0010] As can be seen, the distributed power fault rapid diagnosis system for smart grids described in this application embodiment includes: n power monitoring nodes, a diagnosis node allocation module, and m diagnosis nodes; the n power monitoring nodes are all set at designated locations in the smart grid; n and m are both integers greater than 1; the first power monitoring node obtains its first identification information, obtains power operation data for a preset time period, and sends the first identification information and power operation data to the diagnosis node allocation module; the first power monitoring node is any one of the n power monitoring nodes; the diagnosis node allocation module determines the first diagnosis node based on the first identification information and power operation data, and sends the power operation data to the first diagnosis node; the first diagnosis node is at least one of the m diagnosis nodes; the first diagnosis node performs power fault diagnosis based on the power operation data and obtains the target power fault diagnosis result. On the one hand, the diagnosis node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate power operation data according to the situation of these power operation data. On the other hand, allocating corresponding diagnosis nodes based on the source of power operation data and the stability of power operation can further ensure the accuracy and efficiency of subsequent power fault diagnosis. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the architecture of a distributed power fault rapid diagnosis system for smart grids provided in an embodiment of this application;

[0013] Figure 2 This is a schematic diagram of a smart grid architecture provided in an embodiment of this application;

[0014] Figure 3 This is a flowchart illustrating a method for rapid diagnosis of distributed power faults in smart grids, as provided in an embodiment of this application.

[0015] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0016] Figure 5 This is a block diagram of the functional units of a distributed power fault rapid diagnosis device for smart grids provided in an embodiment of this application. Detailed Implementation

[0017] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not limited to the listed steps or units, but in one possible example includes steps or units not listed, or in one possible example includes other steps or units inherent to these processes, methods, products, or apparatuses.

[0018] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0020] The power monitoring nodes, diagnostic node allocation modules, diagnostic devices, and diagnostic nodes involved in the embodiments of this application may include any electronic device with communication functions. Electronic devices may include, but are not limited to: smartphones, tablets, smart robots, vehicle-mounted devices, smart transformers, smart gateways, smart switches, smart power equipment, smart distribution boxes, smart power generation equipment, smart charging piles, wearable devices, computing devices or other processing devices connected to a wireless modem, as well as various forms of user equipment (UE), mobile stations (MS), terminal devices, etc., without limitation. Electronic devices may also be servers (such as edge servers or cloud servers) or computer clusters, such as distributed computer clusters.

[0021] Please see Figure 1 , Figure 1This is a schematic diagram of the architecture of a distributed power fault rapid diagnosis system for smart grids provided in an embodiment of this application. The distributed power fault rapid diagnosis system for smart grids includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; where...

[0022] The first power monitoring node is used to obtain the first identification information of the first power monitoring node, obtain power operation data for a preset time period, and send the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes;

[0023] The diagnostic node allocation module is used to determine a first diagnostic node based on the first identification information and the power operation data, and to send the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes;

[0024] The first diagnostic node is used to perform power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result.

[0025] In this embodiment, each of the n power monitoring nodes is responsible for monitoring the power operation status of a region. The diagnostic node allocation module is used to allocate diagnostic nodes based on the power operation data and the corresponding power monitoring node status. The diagnostic nodes perform power fault diagnosis based on the power operation data. Specifically, they can diagnose whether a power fault exists, the level of the power fault, and possible causes or locations of the power fault, etc., which are not limited here.

[0026] In specific implementation, such as Figure 1 As shown, a distributed power fault rapid diagnosis system may include: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes. The n power monitoring nodes are all set to designated locations within the smart grid. Both n and m are integers greater than 1. The n power monitoring nodes, the diagnostic node allocation module, and the m diagnostic nodes are interconnected. Taking the first power monitoring node as an example, the first power monitoring node is any one of the n power monitoring nodes. The first identification information of the first power monitoring node may include at least one of the following: device number, physical address, IP address, device location, etc., which are not limited here. The first identification information of the first power monitoring node is used to uniquely identify the first power monitoring node.

[0027] In this application, power operation data is used to characterize the power operation status at a specified location within the smart grid. This specified location can be pre-set or a system default. In this embodiment, the power operation data may include at least one of the following: voltage, current, power, temperature, frequency, electrical energy, etc., without limitation. The power operation data may include one or more types of power operation data. When multiple types of power operation data exist, they can be integrated into a single power operation data set. For example, the weight of each type of power operation data can be determined, and these data sets can be weighted to obtain the final power operation data set.

[0028] The preset time period can be set in advance or set by system default. The length of the preset time period is closely related to the actual electricity consumption; a shorter time period is used for higher electricity consumption, and a longer time period is used for lower electricity consumption.

[0029] In specific implementation, the first power monitoring node obtains its first identification information, acquires power operation data for a preset time period, and sends the first identification information and the power operation data to the diagnostic node allocation module. The diagnostic node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate the power operation data to ensure the accuracy and efficiency of subsequent power fault diagnosis.

[0030] Next, the diagnostic node allocation module can determine the first diagnostic node based on the first identification information and the power operation data, and send the power operation data to the first diagnostic node. The first diagnostic node is at least one of the m diagnostic nodes. Since the first identification information reflects the source of the power operation data, and the power operation data reflects the stability of power operation to a certain extent, the corresponding diagnostic node can be allocated based on the source of the power operation data and the stability of power operation, which can further ensure the accuracy and efficiency of subsequent power fault diagnosis.

[0031] Finally, the first diagnostic node can perform power fault diagnosis based on power operation data to obtain the target power fault diagnosis result, thus ensuring the accuracy and speed of subsequent power fault diagnosis.

[0032] The number of diagnostic node allocation modules can be one or more. The number of diagnostic nodes included in the first diagnostic node can be one or more.

[0033] For example, Figure 2As shown, a smart grid may include multiple distributed power fault rapid diagnosis systems. The specific number of distributed power fault rapid diagnosis systems depends on the scale of the smart grid. Each distributed power fault rapid diagnosis system is responsible for power fault diagnosis in at least one area of ​​the smart grid.

[0034] Optionally, in determining the first diagnostic node based on the first identification information and the power operation data, the diagnostic node allocation module is specifically used for:

[0035] Based on the preset mapping relationship between identification information and diagnostic node identification, determine k diagnostic node identifications corresponding to the first identification information, where k is a positive integer;

[0036] Determine the k diagnostic nodes corresponding to the k diagnostic node identifiers;

[0037] Determine the first data volume of the power operation data;

[0038] Determine the first stability assessment value of the power operation data;

[0039] The first diagnostic node is obtained by filtering the k diagnostic nodes based on the first data volume and the first stability evaluation value.

[0040] In this embodiment, since different diagnostic nodes have different diagnostic capabilities and advantages, corresponding diagnostic nodes can be adapted to different power monitoring nodes based on experience. That is, a preset mapping relationship between identification information and diagnostic node identification can be stored in advance. Then, according to the preset mapping relationship between identification information and diagnostic node identification, k diagnostic node identifications corresponding to the first identification information are determined, where k is a positive integer less than m. The k diagnostic nodes corresponding to the k diagnostic node identifications are determined. In this way, a tacit relationship between diagnostic nodes and power monitoring nodes can be established to ensure the accuracy and speed of subsequent power fault diagnosis.

[0041] Next, the first data volume of the power operation data can be determined. The first data volume can characterize the data complexity or the size of the data. Of course, the first data volume also reflects the demand for computing resources to a certain extent. The first stability assessment value of the power operation data can also be determined. The first stability assessment value characterizes the power operation stability of the area under the responsibility of the first power monitoring node, that is, it characterizes the regional characteristics of the area under the responsibility of the first power monitoring node.

[0042] Finally, k diagnostic nodes can be filtered based on the first data volume and the first stability assessment value to obtain the first diagnostic node. This allows for further filtering of diagnostic nodes that meet the requirements of computing power resources and the regional characteristics of the area under the responsibility of the first power monitoring node.

[0043] Optionally, in the step of performing power fault diagnosis based on the power operation data to obtain a target power fault diagnosis result, the first diagnostic node is used to:

[0044] Obtain the first attribute information of the power operation data;

[0045] Determine the first power fault diagnosis model corresponding to the first attribute information and the first model parameters corresponding to the first attribute information;

[0046] Determine the first adjustment parameter corresponding to the first stability assessment value;

[0047] The first model parameters are adjusted according to the first adjustment parameter to obtain the second model parameters;

[0048] Based on the first power fault diagnosis model and the parameters of the second model, power fault diagnosis is performed on the power operation data to obtain the target power fault diagnosis result.

[0049] The first attribute information of power operation data may include at least one of the following: the source of power operation data, the type of power data, etc., without limitation. The first attribute information of power operation data characterizes the data characteristics of the power operation data itself.

[0050] In a specific implementation, a mapping relationship between the attribute information of the power operation data and the power fault diagnosis model can be pre-stored. Then, the first power fault diagnosis model corresponding to the first attribute information can be determined based on the mapping relationship. In this way, a power fault diagnosis model corresponding to the data characteristics of the power operation data itself can be determined.

[0051] The power fault diagnosis model can be preset or set by the system default, and there is no limitation here. For example, the power fault diagnosis model can include at least one of the following: neural network model, deep learning model, large model (such as ChatGPT), etc., and there is no limitation here.

[0052] Correspondingly, the mapping relationship between the preset attribute information of power operation data and the model parameters of the first power fault diagnosis model can be stored in advance. Then, the first model parameters corresponding to the first attribute information can be determined based on the mapping relationship. In this way, the first model parameters of the first power fault diagnosis model corresponding to the data characteristics of the power operation data itself can be determined, which helps to ensure the model performance.

[0053] Next, a pre-stored mapping relationship between preset stability assessment values ​​and adjustment parameters can be stored. The range of values ​​for these adjustment parameters can be preset or set by system default. For example, the range of adjustment parameters can be -0.1 to 0.1. Then, based on the first adjustment parameter corresponding to the first stability assessment value, some or all of the model parameters of the first model parameter can be adjusted according to the first adjustment parameter to obtain the second model parameter. For example, the second model parameter = (1 + first adjustment parameter) * first model parameter. Then, power fault diagnosis is performed on the power operation data according to the first power fault diagnosis model and the second model parameter to obtain the target power fault diagnosis result. In this way, the model parameters can be dynamically adjusted based on the regional characteristics (power operation stability of the region) of the area under the responsibility of the first power monitoring node, which helps to reduce the fluctuation of the fault diagnosis result. Thus, while ensuring the speed of fault diagnosis, the accuracy of power fault diagnosis can also be guaranteed.

[0054] Optionally, the power operation data includes p power operation data points, each corresponding to a sampling time; regarding determining the first stability assessment value of the power operation data, the diagnostic node allocation module is specifically used for:

[0055] Based on the p power operation data and a sampling time corresponding to each power operation data, a first fitted straight line and a first fitted curve segment corresponding to the preset time period are obtained by fitting the data.

[0056] Obtain the absolute value of the slope of the first fitted line to get the first absolute value;

[0057] Determine the maximum and minimum values ​​in the first fitted curve segment to obtain multiple maximum and multiple minimum values;

[0058] The first standard deviation is obtained by calculating the standard deviation based on the plurality of maxima and the plurality of minima.

[0059] Based on the plurality of maxima and the plurality of minima, the time interval between adjacent maxima and minima is determined, resulting in a plurality of time intervals;

[0060] The second standard deviation is obtained by calculating the standard deviation based on the multiple time intervals.

[0061] The first stability assessment value is determined based on the first absolute value, the first standard deviation, and the second standard deviation.

[0062] In the specific implementation, the power operation data can include p power operation data points, each power operation data point corresponding to a sampling time, where p is an integer greater than 1.

[0063] In this embodiment, fitting can be performed based on p power operation data and a sampling time corresponding to each power operation data to obtain a first fitting straight line and a first fitting curve segment corresponding to a preset time period. That is, p power operation data and each power operation data can be regarded as p coordinate points. The p coordinate points are mapped to a coordinate system, where the horizontal axis of the coordinate system is time and the vertical axis is power operation data. Based on the p coordinate points, a fitting operation can be performed to obtain the first fitting straight line and the first fitting curve segment corresponding to the preset time period.

[0064] In practice, the absolute value of the slope of the first fitted straight line can be obtained, yielding the first absolute value. This first absolute value reflects, to some extent, the stability of the power operation in the horizontal dimension. Correspondingly, the maxima and minima in the first fitted curve segment can also be determined, resulting in multiple maxima and multiple minima. Then, the standard deviation is calculated based on these multiple maxima and multiple minima to obtain the first standard deviation. The first standard deviation reflects, to some extent, the stability of the power operation in the vertical dimension.

[0065] Correspondingly, the time intervals between adjacent maxima and minima are determined based on multiple maxima and minima, resulting in multiple time intervals. Each time interval can represent half a cycle of power operation. Furthermore, the standard deviation can be calculated based on these multiple time intervals to obtain a second standard deviation, which reflects the periodic stability of power operation to a certain extent.

[0066] Finally, the first stability assessment value can be determined based on the first absolute value, the first standard deviation, and the second standard deviation. This means that the regional characteristics of the area under the responsibility of the first power monitoring node can be deeply assessed based on the stability of power operation in the horizontal dimension, the stability of power operation in the vertical dimension, and the periodic stability of power operation. This helps to screen out diagnostic nodes that meet the requirements of computing resources and the regional characteristics of the area under the responsibility of the first power monitoring node.

[0067] Optionally, in determining the first stability assessment value based on the first absolute value, the first standard deviation, and the second standard deviation, the diagnostic node allocation module is specifically used for:

[0068] Determine the first reference stability assessment value corresponding to the first absolute value;

[0069] Determine the second reference stability assessment value corresponding to the first standard deviation;

[0070] A first weight pair corresponding to the second standard deviation is determined, the first weight pair including a first weight corresponding to the first reference stability assessment value and a second weight corresponding to the second reference stability assessment value; the sum of the first weight and the second weight is 1;

[0071] The first stability evaluation value is obtained by weighting the first weight pair, the first reference stability evaluation value, and the second reference stability evaluation value.

[0072] In a specific implementation, a pre-defined mapping relationship between absolute values ​​and stability evaluation values ​​can be stored in advance. Based on this mapping relationship, a first reference stability evaluation value corresponding to the first absolute value can be determined. Correspondingly, a pre-defined mapping relationship between standard deviations and stability evaluation values ​​can also be stored in advance. Based on this mapping relationship, a second reference stability evaluation value corresponding to the first standard deviation can be determined.

[0073] Furthermore, a pre-stored mapping relationship between a preset standard deviation (a periodically related standard deviation) and weight pairs can be stored. Each weight pair can include two weights, corresponding to a first reference stability assessment value and a second reference stability assessment value, respectively, and the sum of these two weights is 1. Then, based on this mapping relationship, a first weight pair corresponding to the second standard deviation can be determined. This first weight pair can include a first weight corresponding to the first reference stability assessment value and a second weight corresponding to the second reference stability assessment value; the sum of the first and second weights is 1. In this way, the weight pairs can be deeply adapted to the periodic stability of the power operation.

[0074] Finally, the first stability assessment value can be obtained by weighting the first weight pair, the first reference stability assessment value, and the second reference stability assessment value, as follows: First weight * First reference stability assessment value + Second weight * Second reference stability assessment value = First stability assessment value. In this way, the regional characteristics of the area under the responsibility of the first power monitoring node can be deeply evaluated based on the stability of power operation in the horizontal dimension, the stability of power operation in the vertical dimension, and the periodic stability of power operation. That is, the power operation stability of the area, which helps to screen out diagnostic nodes that meet the requirements of computing power resources and the regional characteristics of the area under the responsibility of the first power monitoring node.

[0075] Optionally, in the step of filtering the k diagnostic nodes based on the first data volume and the first stability evaluation value to obtain the first diagnostic node, the diagnostic node allocation module is specifically used for:

[0076] Determine the fit between each of the k diagnostic nodes and the first stability evaluation value to obtain k fits.

[0077] Select k fitness scores that are greater than the first threshold to obtain a fitness scores, where a is a positive integer less than or equal to k.

[0078] Determine the diagnostic nodes corresponding to the a fitness scores to obtain a diagnostic nodes;

[0079] Determine the remaining available computing resources corresponding to the a diagnostic nodes to obtain a remaining available computing resources;

[0080] Determine the reference computing resource quantity corresponding to the first data quantity;

[0081] The first diagnostic node is determined based on the a remaining available computing resources and the reference computing resources.

[0082] In specific implementation, the fit between each of the k diagnostic nodes and the first stability evaluation value can be determined, resulting in k fit values. Specifically, the reference stability evaluation value corresponding to each diagnostic node can be obtained, i.e., a preset mapping relationship between diagnostic nodes and stability evaluation values ​​can be stored in advance. Based on this mapping relationship, the reference stability evaluation value of each diagnostic node can be determined, and then the difference between the reference stability evaluation value and the first stability evaluation value can be determined. The larger the difference, the larger the fit, and vice versa. That is, a preset mapping relationship between the difference and the fit can be stored in advance, and the fit value corresponding to the difference can be determined based on this mapping relationship. The fit value reflects the data processing capability of the diagnostic node to a certain extent. In this way, suitable diagnostic nodes can be selected based on the data processing of each diagnostic node.

[0083] The first threshold can be preset or set by the system default, and the first threshold can be related to the first attribute information.

[0084] Furthermore, we can select the fitness scores greater than the first threshold from the k fitness scores to obtain a fitness scores, where a is a positive integer less than or equal to k. Then, we can determine the diagnostic nodes corresponding to the a fitness scores to obtain a diagnostic nodes. That is, based on the data processing of each diagnostic node, we can initially screen out suitable diagnostic nodes.

[0085] Furthermore, the remaining available computing resources corresponding to *a* diagnostic nodes can be determined, resulting in *a* remaining available computing resources, which reflect the computing power resource status of the diagnostic nodes. In specific implementations, a pre-stored mapping relationship between preset data volumes and computing resource volumes can be used. Based on this mapping relationship, a reference computing resource volume corresponding to the first data volume can be determined. This reference computing resource volume reflects the computing power resource requirement corresponding to the first data volume. Then, the first diagnostic node can be determined based on the *a* remaining available computing resources and the reference computing resource volume. In other words, the optimal diagnostic node can be further selected based on the computing power resource status of the diagnostic node and the computing power resource requirement corresponding to the first data volume. This means selecting diagnostic nodes whose depth matches the computing power resource requirement and the regional characteristics of the area responsible for the first power monitoring node, thereby helping to ensure the speed and accuracy of power fault diagnosis.

[0086] Optionally, in determining the first diagnostic node based on the a remaining available computing resources and the reference computing resources, the diagnostic node allocation module is specifically used for:

[0087] When the reference computing resource quantity is less than or equal to the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the diagnostic node corresponding to the first remaining available computing resource quantity is taken as the first diagnostic node, and the first remaining available computing resource quantity is any remaining available computing resource quantity among the a remaining available computing resource quantities that is greater than or equal to the reference computing resource quantity.

[0088] or,

[0089] When the reference computing resource quantity is greater than the largest remaining available computing resource quantity among the a remaining available computing resource quantities, b remaining available computing resource quantities are determined, and the sum of the b remaining available computing resource quantities is greater than or equal to the reference computing resource quantity; b is an integer greater than or equal to 2;

[0090] Obtain the diagnostic nodes corresponding to the b remaining available computing resources to obtain b diagnostic nodes, and determine the first diagnostic node based on the b diagnostic nodes.

[0091] In specific implementation, when the reference computing resource quantity is less than or equal to the largest remaining available computing resource quantity among a remaining available computing resource quantities, the diagnostic node corresponding to the first remaining available computing resource quantity can be used as the first diagnostic node. The first remaining available computing resource quantity is any remaining available computing resource quantity among a remaining available computing resource quantities that is greater than or equal to the reference computing resource quantity. That is, one diagnostic node can satisfy the requirements of ensuring the speed and accuracy of power fault diagnosis. Therefore, only one diagnostic node can be used for power fault diagnosis, ensuring the speed and accuracy of power fault diagnosis.

[0092] Correspondingly, when the reference computing resources are greater than the largest remaining available computing resources among the a remaining available computing resources, it indicates that a diagnostic node cannot quickly complete the power fault diagnosis. In this case, b remaining available computing resources can be determined, and the sum of these b remaining available computing resources is greater than or equal to the reference computing resources. Here, b is an integer greater than or equal to 2. Then, the diagnostic nodes corresponding to the b remaining available computing resources are obtained, resulting in b diagnostic nodes. Based on these b diagnostic nodes, the first diagnostic node is determined. That is, the first diagnostic node includes b diagnostic nodes. The optimal diagnostic node can be further selected based on the computing power resources of the diagnostic nodes and the computing power resource requirements corresponding to the first data volume. In other words, the diagnostic node whose depth meets the computing power resource requirements and the regional characteristics of the area responsible for the first power monitoring node is selected. This helps to ensure the speed and accuracy of power fault diagnosis.

[0093] Optionally, in the process of sending the power operation data to the first diagnostic node, the diagnostic node allocation module is specifically used for:

[0094] When the reference computing resource quantity is less than or equal to the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the power operation data is directly sent to the first diagnostic node;

[0095] When the reference computing resource quantity is greater than the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the remaining available computing resource quantity of each of the b diagnostic nodes is obtained to obtain b remaining available computing resource quantities.

[0096] Based on the b remaining available computing resources, determine b-1 sampling parameters;

[0097] The power operation data is sampled based on the b-1 sampling parameters to obtain b-1 sampled power operation data and remaining power operation data;

[0098] The b-1 sampled power operation data and the remaining power operation data are respectively sent to the b diagnostic nodes.

[0099] In specific implementation, when the reference computing resource quantity is less than or equal to the maximum remaining available computing resource quantity among a remaining available computing resource quantities, that is, when the number of first diagnostic nodes is 1, the power operation data can be directly sent to the first diagnostic node, that is, the power fault diagnosis is completed through one diagnostic node.

[0100] The sampling parameters may include sampling priority and / or sampling interval (i.e., sampling time interval).

[0101] Correspondingly, if the reference computing resources are greater than the largest remaining available computing resources among the *a* remaining available computing resources, it indicates that a diagnostic node cannot complete rapid power fault diagnosis. Therefore, the remaining available computing resources of each of the *b* diagnostic nodes can be obtained, resulting in *b* remaining available computing resources. Then, *b-1* sampling parameters are determined based on these *b-1* sampling parameters. Power operation data is then sampled based on these *b-1* sampling parameters, resulting in *b-1* sampled power operation data and remaining power operation data. Specifically, sampling can be performed on the power operation data first to obtain a sampling result and the remaining power operation data. In the next sampling, the remaining power operation data can be sampled directly. This process continues. Since each sampling yields a sampling result and the remaining power operation data, only b-1 samplings are needed to obtain b-1 sampled power operation data and the remaining power operation data. Finally, the b-1 sampled power operation data and the remaining power operation data can be sent to b diagnostic nodes. The b diagnostic nodes can then use their corresponding power operation data to perform power fault diagnosis, obtaining b power fault diagnosis results. These b power fault diagnosis results are then integrated to obtain the target power fault diagnosis result.

[0102] In practice, b diagnostic nodes can perform power fault diagnosis synchronously, and then the results of the b power fault diagnosis are aggregated to the target diagnostic node. The target diagnostic node integrates the results of the b power fault diagnosis to obtain the target power fault diagnosis result. The target diagnostic node is one of the b diagnostic nodes.

[0103] In specific implementation, the fitness scores of b diagnostic nodes can be obtained, resulting in b fitness scores. The mean of these b fitness scores is determined, and the difference between each of the b fitness scores and the mean is determined, resulting in b differences. A pre-defined mapping relationship between these differences and fine-tuning parameters can be stored. The range of these fine-tuning parameters can be preset or set by the system default. For example, the range of the fine-tuning parameters is -0.02 to 0.02. Based on this mapping relationship, the fine-tuning parameter corresponding to each of the b differences is determined, resulting in b fine-tuning parameters. These b fine-tuning parameters can then be used to adjust the parameters of the second model. Fine-tuning is performed to obtain b third model parameters, where the third model parameter = (1 + fine-tuning parameter) * second model parameter. Then, based on the first power fault diagnosis model and the b third model parameters, power fault diagnosis is performed on the corresponding power operation data of each diagnosis node to obtain b power fault diagnosis results. The b power fault diagnosis results are integrated to obtain the target power fault diagnosis result. In this way, the model parameters can be further optimized by deeply considering the characteristics of each diagnosis node, which helps to ensure the adaptability between the diagnosis node and the power operation data, and thus ensures the accuracy of power fault diagnosis.

[0104] Optionally, in determining b-1 sampling parameters based on the b remaining available computing resources, the diagnostic node allocation module is specifically used for:

[0105] The sum of the remaining available computing resources of the b is determined to obtain the total remaining available computing resources;

[0106] Determine the ratio between the b remaining available computing resources and the total remaining available computing resources to obtain b ratio values;

[0107] b priorities are determined based on the b remaining available computing resources, with higher priorities being those with larger remaining available computing resources.

[0108] The b-1 sampling parameters are determined based on the b priorities and the b proportions.

[0109] In practice, the sum of b remaining available computing resources can be determined to obtain the total remaining available computing resources. Then, the ratio between the b remaining available computing resources and the total remaining available computing resources can be determined to obtain b ratio values. Based on the b remaining available computing resources, b priorities can be determined. The larger the remaining available computing resources, the higher the priority. Of course, the larger the ratio value, the larger the amount of data obtained from the power operation data. Then, b-1 sampling parameters can be determined based on the b priorities and b ratio values. In this way, it can be ensured that diagnostic nodes with sufficient computing resources are sampled first and obtain the power operation data corresponding to their computing resources.

[0110] Optionally, in determining the b-1 sampling parameters based on the b priorities and the b ratio values, the diagnostic node allocation module is specifically used for:

[0111] Based on the aforementioned b priorities, determine b-1 sampling priorities;

[0112] b-1 sampling intervals are determined based on the b-1 sampling priorities, and each sampling interval corresponds to the corresponding sampling priority and the amount of remaining available computing resources corresponding to that sampling priority.

[0113] The b-1 sampling parameters are determined based on the b-1 sampling priorities and the b-1 sampling intervals.

[0114] In the specific implementation, since the power operation data is sampled first to obtain a sampling result and the remaining power operation data, the remaining power operation data can be sampled directly in the next sampling. This process continues. Since each sampling will yield a sampling result and the remaining power operation data, only b-1 samplings are needed to obtain b-1 sampled power operation data and the remaining power operation data. Therefore, b-1 sampling priorities can be determined based on b priorities. The higher the priority, the higher the sampling priority. b-1 sampling intervals are then determined based on the b-1 sampling priorities. Specifically, b-1 sampling parameters can be determined based on the b-1 sampling priorities and b-1 sampling intervals. That is, each sampling parameter corresponds to a sampling priority and a sampling interval.

[0115] In the specific implementation, each sampling interval corresponds to a corresponding sampling priority and the amount of remaining available computing resources corresponding to that sampling priority, so as to ensure that diagnostic nodes with sufficient computing resources are sampled first and obtain power operation data corresponding to their computing resources.

[0116] As can be seen, the distributed power fault rapid diagnosis system for smart grids described in this application embodiment includes: n power monitoring nodes, a diagnosis node allocation module, and m diagnosis nodes; the n power monitoring nodes are all set at designated locations in the smart grid; n and m are both integers greater than 1; the first power monitoring node obtains its first identification information, obtains power operation data for a preset time period, and sends the first identification information and power operation data to the diagnosis node allocation module; the first power monitoring node is any one of the n power monitoring nodes; the diagnosis node allocation module determines the first diagnosis node based on the first identification information and power operation data, and sends the power operation data to the first diagnosis node; the first diagnosis node is at least one of the m diagnosis nodes; the first diagnosis node performs power fault diagnosis based on the power operation data and obtains the target power fault diagnosis result. On the one hand, the diagnosis node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate power operation data according to the situation of these power operation data. On the other hand, allocating corresponding diagnosis nodes based on the source of power operation data and the stability of power operation can further ensure the accuracy and efficiency of subsequent power fault diagnosis.

[0117] Please see Figure 3 , Figure 3 This is a flowchart illustrating a rapid diagnosis method for distributed power faults in smart grids provided in an embodiment of this application, applicable to, for example... Figure 1 The distributed power fault rapid diagnosis system for smart grids shown includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; the distributed power fault rapid diagnosis method for smart grids includes:

[0118] 301. The first power monitoring node obtains its first identification information, obtains power operation data for a preset time period, and sends the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes.

[0119] 302. The diagnostic node allocation module determines the first diagnostic node based on the first identification information and the power operation data, and sends the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes.

[0120] 303. The first diagnostic node performs power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result.

[0121] The specific descriptions of steps 301-303 above can be found in the above descriptions. Figure 1 The relevant parts of the distributed power fault rapid diagnosis system for smart grids described herein will not be elaborated upon here.

[0122] As can be seen, the distributed power fault rapid diagnosis method for smart grids described in this application embodiment is applied to a distributed power fault rapid diagnosis system for smart grids. This system includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; a first power monitoring node obtains its first identification information, acquires power operation data for a preset time period, and sends the first identification information and power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes; the diagnostic node allocation module determines the first diagnostic node based on the first identification information and power operation data, and sends the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes; the first diagnostic node performs power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result. On the one hand, the diagnostic node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate data based on the status of this power operation data. On the other hand, allocating corresponding diagnostic nodes based on the source of the power operation data and the stability of power operation further ensures the accuracy and efficiency of subsequent power fault diagnosis.

[0123] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. In this embodiment, the electronic device is applied to a distributed power fault rapid diagnosis system for smart grids. The system includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; the n power monitoring nodes are all set at designated locations within the smart grid; n and m are both integers greater than 1; the program includes instructions for performing the following steps:

[0124] The first power monitoring node obtains its first identification information, acquires power operation data for a preset time period, and sends the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes.

[0125] The diagnostic node allocation module determines the first diagnostic node based on the first identification information and the power operation data, and sends the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes.

[0126] The first diagnostic node performs power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result.

[0127] The electronic device can be used to achieve the above. Figure 1 The full functionality of the distributed power fault rapid diagnosis system for smart grids described herein will not be elaborated upon here.

[0128] As can be seen, the electronic device described in this application embodiment is applied to a distributed power fault rapid diagnosis system for smart grids. This system includes: n power monitoring nodes, a diagnosis node allocation module, and m diagnosis nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; a first power monitoring node obtains its first identification information, acquires power operation data for a preset time period, and sends the first identification information and power operation data to the diagnosis node allocation module; the first power monitoring node is any one of the n power monitoring nodes; the diagnosis node allocation module determines the first diagnosis node based on the first identification information and power operation data, and sends the power operation data to the first diagnosis node; the first diagnosis node is at least one of the m diagnosis nodes; the first diagnosis node performs power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result. On the one hand, the diagnosis node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate data based on the status of this power operation data. On the other hand, allocating corresponding diagnosis nodes based on the source of the power operation data and the stability of power operation further ensures the accuracy and efficiency of subsequent power fault diagnosis.

[0129] Figure 5 This is a functional unit block diagram of a distributed power fault rapid diagnosis device 500 for smart grids, as described in this application embodiment. The distributed power fault rapid diagnosis device 500 is applied to a distributed power fault rapid diagnosis system for smart grids. The system includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; the n power monitoring nodes are all set at designated locations within the smart grid; n and m are both integers greater than 1; the distributed power fault rapid diagnosis device 500 for smart grids includes: a monitoring unit 501, an allocation unit 502, and a diagnostic unit 503, wherein...

[0130] The monitoring unit 501 is used to obtain the first identification information of the first power monitoring node through the first power monitoring node, obtain power operation data for a preset time period, and send the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes.

[0131] The allocation unit 502 is used to determine a first diagnostic node based on the first identification information and the power operation data through the diagnostic node allocation module, and send the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes.

[0132] The diagnostic unit 503 is used to perform power fault diagnosis based on the power operation data through the first diagnostic node to obtain the target power fault diagnosis result.

[0133] As can be seen, the distributed power fault rapid diagnosis device for smart grids described in this application embodiment is applied to a distributed power fault rapid diagnosis system for smart grids. This system includes: n power monitoring nodes, a diagnosis node allocation module, and m diagnosis nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; a first power monitoring node obtains its first identification information, acquires power operation data for a preset time period, and sends the first identification information and power operation data to the diagnosis node allocation module; the first power monitoring node is any one of the n power monitoring nodes; the diagnosis node allocation module determines the first diagnosis node based on the first identification information and power operation data, and sends the power operation data to the first diagnosis node; the first diagnosis node is at least one of the m diagnosis nodes; the first diagnosis node performs power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result. On the one hand, the diagnosis node allocation module, as a aggregation node, can receive power operation data from one or more power monitoring nodes and intelligently allocate data based on the status of this power operation data. On the other hand, allocating corresponding diagnosis nodes based on the source of the power operation data and the stability of power operation further ensures the accuracy and efficiency of subsequent power fault diagnosis.

[0134] It is understood that the functions of each program module of the distributed power fault rapid diagnosis device for smart grids in this embodiment can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can be referred to the relevant descriptions in the above method embodiments, and will not be repeated here.

[0135] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0136] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0137] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0138] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0140] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0142] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0143] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0144] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A distributed power fault rapid diagnosis system for smart grids, characterized in that, The system includes: n power monitoring nodes, a diagnostic node allocation module, and m diagnostic nodes; all n power monitoring nodes are set to designated locations within the smart grid; n and m are both integers greater than 1; where, The first power monitoring node is used to obtain the first identification information of the first power monitoring node, obtain power operation data for a preset time period, and send the first identification information and the power operation data to the diagnostic node allocation module; the first power monitoring node is any one of the n power monitoring nodes; The diagnostic node allocation module is used to determine a first diagnostic node based on the first identification information and the power operation data, and to send the power operation data to the first diagnostic node; the first diagnostic node is at least one of the m diagnostic nodes; The first diagnostic node is used to perform power fault diagnosis based on the power operation data to obtain the target power fault diagnosis result; In determining the first diagnostic node based on the first identification information and the power operation data, the diagnostic node allocation module is specifically used for: Based on the preset mapping relationship between identification information and diagnostic node identification, determine k diagnostic node identifications corresponding to the first identification information, where k is a positive integer; Determine the k diagnostic nodes corresponding to the k diagnostic node identifiers; Determine the first data volume of the power operation data; Determine the first stability assessment value of the power operation data; The first diagnostic node is obtained by filtering the k diagnostic nodes based on the first data volume and the first stability evaluation value.

2. The system according to claim 1, characterized in that, In the process of performing power fault diagnosis based on the power operation data to obtain a target power fault diagnosis result, the first diagnostic node is used for: Obtain the first attribute information of the power operation data; Determine the first power fault diagnosis model corresponding to the first attribute information and the first model parameters corresponding to the first attribute information; Determine the first adjustment parameter corresponding to the first stability assessment value; The first model parameters are adjusted according to the first adjustment parameter to obtain the second model parameters; Based on the first power fault diagnosis model and the parameters of the second model, power fault diagnosis is performed on the power operation data to obtain the target power fault diagnosis result.

3. The system according to claim 1 or 2, characterized in that, The power operation data includes p power operation data points, each corresponding to a sampling time; regarding determining the first stability assessment value of the power operation data, the diagnostic node allocation module is specifically used for: Based on the p power operation data and a sampling time corresponding to each power operation data, a first fitted straight line and a first fitted curve segment corresponding to the preset time period are obtained by fitting the data. Obtain the absolute value of the slope of the first fitted line to get the first absolute value; Determine the maximum and minimum values ​​in the first fitted curve segment to obtain multiple maximum and multiple minimum values; The first standard deviation is obtained by calculating the standard deviation based on the plurality of maxima and the plurality of minima. Based on the plurality of maxima and the plurality of minima, the time interval between adjacent maxima and minima is determined, resulting in a plurality of time intervals; The second standard deviation is obtained by calculating the standard deviation based on the multiple time intervals. The first stability assessment value is determined based on the first absolute value, the first standard deviation, and the second standard deviation.

4. The system according to claim 3, characterized in that, In determining the first stability assessment value based on the first absolute value, the first standard deviation, and the second standard deviation, the diagnostic node allocation module is specifically used for: Determine the first reference stability assessment value corresponding to the first absolute value; Determine the second reference stability assessment value corresponding to the first standard deviation; Determine the first weight pair corresponding to the second standard deviation, wherein the first weight pair includes the first weight corresponding to the first reference stability assessment value and the second weight corresponding to the second reference stability assessment value; The sum of the first weight and the second weight is 1; The first stability evaluation value is obtained by weighting the first weight pair, the first reference stability evaluation value, and the second reference stability evaluation value.

5. The system according to claim 1 or 2, characterized in that, In the process of filtering the k diagnostic nodes based on the first data volume and the first stability evaluation value to obtain the first diagnostic node, the diagnostic node allocation module is specifically used for: Determine the fit between each of the k diagnostic nodes and the first stability evaluation value to obtain k fits. Select k fitness scores that are greater than the first threshold to obtain a fitness scores, where a is a positive integer less than or equal to k. Determine the diagnostic nodes corresponding to the a fitness scores to obtain a diagnostic nodes; Determine the remaining available computing resources corresponding to the a diagnostic nodes to obtain a remaining available computing resources; Determine the reference computing resource quantity corresponding to the first data quantity; The first diagnostic node is determined based on the a remaining available computing resources and the reference computing resources.

6. The system according to claim 5, characterized in that, In determining the first diagnostic node based on the a remaining available computing resources and the reference computing resources, the diagnostic node allocation module is specifically used for: When the reference computing resource quantity is less than or equal to the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the diagnostic node corresponding to the first remaining available computing resource quantity is taken as the first diagnostic node, and the first remaining available computing resource quantity is any remaining available computing resource quantity among the a remaining available computing resource quantities that is greater than or equal to the reference computing resource quantity. or, When the reference computing resource quantity is greater than the largest remaining available computing resource quantity among the a remaining available computing resource quantities, b remaining available computing resource quantities are determined, and the sum of the b remaining available computing resource quantities is greater than or equal to the reference computing resource quantity; b is an integer greater than or equal to 2; Obtain the diagnostic nodes corresponding to the b remaining available computing resources to obtain b diagnostic nodes, and determine the first diagnostic node based on the b diagnostic nodes.

7. The system according to claim 6, characterized in that, In the process of sending the power operation data to the first diagnostic node, the diagnostic node allocation module is specifically used for: When the reference computing resource quantity is less than or equal to the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the power operation data is directly sent to the first diagnostic node; When the reference computing resource quantity is greater than the maximum remaining available computing resource quantity among the a remaining available computing resource quantities, the remaining available computing resource quantity of each of the b diagnostic nodes is obtained to obtain b remaining available computing resource quantities. Based on the b remaining available computing resources, determine b-1 sampling parameters; The power operation data is sampled based on the b-1 sampling parameters to obtain b-1 sampled power operation data and remaining power operation data; The b-1 sampled power operation data and the remaining power operation data are respectively sent to the b diagnostic nodes.

8. The system according to claim 7, characterized in that, In determining b-1 sampling parameters based on the b remaining available computing resources, the diagnostic node allocation module is specifically used for: The sum of the remaining available computing resources of the b is determined to obtain the total remaining available computing resources; Determine the ratio between the b remaining available computing resources and the total remaining available computing resources to obtain b ratio values; b priorities are determined based on the b remaining available computing resources, with higher priorities being those with larger remaining available computing resources. The b-1 sampling parameters are determined based on the b priorities and the b proportions.

9. The system according to claim 8, characterized in that, In determining the b-1 sampling parameters based on the b priorities and the b ratio values, the diagnostic node allocation module is specifically used for: Based on the aforementioned b priorities, determine b-1 sampling priorities; b-1 sampling intervals are determined based on the b-1 sampling priorities, and each sampling interval corresponds to the corresponding sampling priority and the amount of remaining available computing resources corresponding to that sampling priority. The b-1 sampling parameters are determined based on the b-1 sampling priorities and the b-1 sampling intervals.

Images