DC power supply fault monitoring method, system and medium based on edge computing

Abstract

The present invention relates to the technical field of power supply monitoring, and specifically relates to a DC power supply fault monitoring method, system and medium based on edge computing. The method includes: obtaining the abnormal time period and the abnormal data corresponding to the abnormal time period of each electrical module in the DC power supply system; correcting the second abnormal time period of the remaining electrical modules to obtain an aligned time period, and when there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, regarding the remaining electrical modules as alternative nodes that affect the abnormality of the DC power supply module; determining the first possibility that the abnormal data of the DC power supply module is a real fault; when the first possibility is not less than the first threshold, determining the second possibility that the abnormal data of the alternative node is a real fault; determining the abnormal significance of the DC power supply module; and re-determining whether the DC power supply module is faulty. In this way, the present invention improves the accuracy of fault judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply monitoring, and particularly to a DC power supply fault monitoring method, system and medium based on edge computing. Background Art

[0002] The stable operation of a data center highly depends on continuous and reliable power supply. As one of the key infrastructures of a data center, the performance and reliability of a DC power supply system directly affect the overall operation efficiency and data security of the data center. Therefore, real-time monitoring of the operation status of the DC power supply system, and timely discovery and handling of potential power supply faults are important guarantees for ensuring the stable operation of the data center.

[0003] In some scenarios, traditional DC power supply system monitoring methods usually independently monitor each electrical module of the DC power supply, such as rectifier modules, inverter modules, battery modules, and DC power supply modules. When an abnormal condition occurs in an electrical module, the system will determine that there is a high fault risk in the DC power supply system. However, this monitoring method has obvious limitations: there is no strongly associated intelligent management unit among the electrical modules, resulting in isolated operation among the electrical modules and unable to achieve effective integration and collaborative analysis of information. This isolated operation mode is prone to misjudgment of the status of the DC power supply module. For example, a potential fault may be mistaken for a normal operation state, or a normal fluctuation may be misjudged as a fault risk. Thus, traditional DC power supply system monitoring methods have obvious deficiencies in the correlation among electrical modules and the accuracy of fault judgment, and it is difficult to ensure the stable operation of the data center power system. Summary of the Invention

[0004] In order to solve the technical problems that traditional DC power supply system monitoring methods have obvious deficiencies in the correlation among electrical modules and the accuracy of fault judgment, the purpose of the present invention is to provide a DC power supply fault monitoring method, system and medium based on edge computing, and the specific technical solutions adopted are as follows:

[0005] First aspect, an embodiment of the present invention provides a method for monitoring DC power supply faults based on edge computing, including: obtaining the abnormal time period and abnormal data corresponding to the abnormal time period of each electrical module in the DC power supply system; correcting the second abnormal time period of the remaining electrical modules according to the first abnormal time period of the DC power supply module in the electrical module to obtain an aligned time period, and when there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, regarding the remaining electrical modules as alternative nodes affecting the abnormality of the DC power supply module; determining the first possibility that the abnormal data of the DC power supply module is a real fault based on the second abnormal time period of the remaining electrical modules and the corresponding aligned time period; determining the second possibility that the abnormal data of the alternative node is a real fault when the first possibility is not less than the first threshold; determining the abnormal significance of the DC power supply module according to the first possibility, the order of the alternative nodes in the DC power supply system, and the corresponding second possibility; re-determining whether the DC power supply module fails according to the abnormal significance and the first threshold.

[0006] Optionally, determining the first possibility that the abnormal data of the DC power supply module is a real fault based on the second abnormal time period of the remaining electrical modules and the corresponding aligned time period includes: when there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, regarding the remaining electrical modules as alternative nodes affecting the abnormality of the DC power supply module and marking them as the first value, and when there is no overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, indicating that the remaining electrical modules have nothing to do with the abnormality of the DC power supply module and marking them as the second value, calculating the intersection between the second abnormal time period and the corresponding aligned time period, and the union between the second abnormal time period and the corresponding aligned time period; determining the first ratio between the intersection and the union as the coincidence of the abnormal time of the remaining electrical modules; calculating the first product between the first value or the second value and the coincidence, and normalizing the accumulated value of the first product using a positive correlation normalization function to obtain a normalized value; determining the first difference between the predetermined value and the normalized value as the first possibility.

[0007] Optionally, determining the abnormality significance of the DC power supply module according to the first possibility, the order of the alternative nodes in the DC power supply system, and the corresponding second possibility includes: obtaining the possibility sequence of each alternative node according to the order of the alternative nodes in the DC power supply system and the second possibility; selecting any one of the alternative nodes from the possibility sequence as the node to be analyzed, taking the alternative nodes before the node to be analyzed as the first electrical module set upstream of the node to be analyzed, and taking the alternative nodes after the node to be analyzed as the second electrical module set downstream of the node to be analyzed; determining the third possibility of the corrected fault of the node to be analyzed according to the second possibility corresponding to the node to be analyzed, the second possibility of the alternative nodes adjacent to the node to be analyzed, the first average possibility in the first electrical module set, and the second average possibility in the second electrical module set; selecting the maximum value in the third possibility as the reference possibility, and selecting the electrical modules adjacent to the DC power supply module as the third electrical module set of the DC power supply module; if the alternative node corresponding to the reference possibility belongs to the third electrical module set, determining the abnormality significance of the DC power supply module according to the first possibility and the third average possibility in the third electrical module set; if the alternative node corresponding to the reference possibility does not belong to the third electrical module set, determining the abnormality significance of the DC power supply module according to the first possibility, the reference possibility, and the third average possibility.

[0008] Optionally, determining the third possibility of the corrected fault of the node to be analyzed according to the second possibility corresponding to the node to be analyzed, the second possibility of the alternative nodes adjacent to the node to be analyzed, the first average possibility in the first electrical module set, and the second average possibility in the second electrical module set includes: calculating the second difference between the second average possibility and the first average possibility, and the third difference between the second possibility of the alternative node adjacent to the node to be analyzed and the second possibility of the alternative node adjacent to the node to be analyzed before the node to be analyzed; calculating the absolute value of the first sum value between the second difference and the third difference; determining that the second product of the absolute value of the first sum value and the second possibility corresponding to the node to be analyzed is the third possibility of the corrected fault of the node to be analyzed.

[0009] Optionally, determining the abnormality significance of the DC power supply module according to the first possibility and the third average possibility in the third electrical module set includes: determining that the second sum value between the first possibility and the third average possibility in the third electrical module set is the abnormality significance of the DC power supply module.

[0010] Optionally, determining the abnormality significance of the DC power supply module according to the first possibility, the reference possibility, and the third average possibility includes: calculating the absolute value of the reciprocal of the fourth difference between the reference possibility and the third average possibility, and normalizing the absolute value of the reciprocal of the fourth difference by using a positive correlation normalization function to obtain a normalized absolute value; calculating the third product between the normalized absolute value and the third average possibility; and determining that the third sum between the third product and the first possibility is the abnormality significance of the DC power supply module.

[0011] Optionally, re-determining whether the DC power supply module fails according to the abnormality significance and the first threshold includes: normalizing the abnormality significance to obtain a normalized abnormality significance; determining that the DC power supply module fails when the normalized abnormality significance is not less than the first threshold; and determining that the DC power supply module does not fail when the normalized abnormality significance is less than the first threshold.

[0012] Optionally, normalizing the abnormality significance includes: determining the reference possibility of the DC power supply module; calculating the fourth sum between the reference possibility and the first possibility; and determining that the second ratio between the abnormality significance and the fourth sum is the normalized abnormality significance.

[0013] In a second aspect, an embodiment of the present invention provides an edge-computing-based DC power supply fault monitoring system, including: a processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; the processor is configured to execute the program stored on the memory to implement the steps of the edge-computing-based DC power supply fault monitoring method as mentioned in the first aspect.

[0014] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the edge-computing-based DC power supply fault monitoring method as mentioned in the first aspect are implemented.

[0015] The present invention has the following beneficial effects: First, obtain the abnormal time period of each electrical module in the DC power supply system and the abnormal data corresponding to the abnormal time period; then correct the second abnormal time period of the remaining electrical modules according to the first abnormal time period of the DC power supply module in the electrical module to obtain an aligned time period. When there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, regard the remaining electrical modules as alternative nodes that affect the abnormality of the DC power supply module; Second, based on the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, determine the first possibility that the abnormal data of the DC power supply module is a real fault; when the first possibility is not less than the first threshold, determine the second possibility that the abnormal data of the alternative node is a real fault; and determine the abnormality significance of the DC power supply module according to the first possibility, the order of the alternative nodes in the DC power supply system, and the corresponding second possibility; Finally, re-determine whether the DC power supply module is faulty according to the abnormality significance and the first threshold.

[0016] In this way, the embodiment of the present invention can obtain the possibility that each electrical module is a real fault according to the abnormal time period and abnormal data of each electrical module in the DC power supply system, and determine the abnormality significance of the DC power supply module by combining the possibility of real faults under the mutual influence between each electrical module. Therefore, through the mutual influence between each electronic module, the fault of the DC power supply module is monitored and diagnosed multiple times, strengthening the correlation between electrical modules, ensuring the collaborative management between electrical modules, improving the accuracy of fault judgment, and ensuring the stable operation of the central power system. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a DC power supply fault monitoring method based on edge computing provided by an embodiment of the present invention.

[0019] Figure 2 It is a schematic diagram of the relationship between an edge server and edge nodes provided by an embodiment of the present invention.

[0020] Figure 3 It is a schematic diagram of the structure of a DC power supply fault monitoring system based on edge computing provided by an embodiment of the present invention. Detailed Embodiments

[0021] To further illustrate the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, with reference to the accompanying drawings and preferred embodiments, a method, system and medium for monitoring DC power supply faults based on edge computing according to the present invention, including its specific implementation manners, structures, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0023] The following specifically describes the specific solution of a method for monitoring DC power supply faults based on edge computing provided by the present invention with reference to the accompanying drawings. Embodiment

[0024] Please refer to Figure 1 , which shows a flowchart of a method for monitoring DC power supply faults based on edge computing provided by an embodiment of the present invention, including:

[0025] S101, obtaining the abnormal time period of each electrical module in the DC power supply system and the abnormal data corresponding to the abnormal time period.

[0026] Specifically, in the DC power supply system of the data center, there are electrical modules such as medium-voltage power distribution, transformers, low-voltage power distribution, uninterruptible power supplies, and DC power supplies. In the embodiments of the present invention, edge computing modules are built into these electrical modules as edge nodes. Corresponding sensors are installed in each electrical module, and the collected electrical data is transmitted to the corresponding edge node. Since different electrical modules in the DC power supply system respond differently to different data abnormalities, different sensors are installed to monitor each electrical module. The above-mentioned edge computing module has certain data processing capabilities, storage capabilities and communication interfaces, such as edge computing boxes, etc.

[0027] Furthermore, the specific installation of sensors for various types of electrical modules is as follows: for the medium-voltage power distribution electrical module, high-precision voltage sensors and current sensors are installed on the medium-voltage incoming and outgoing lines to monitor the operating current and voltage. For the transformer electrical module, temperature sensors are installed on the windings and cores of the transformer to monitor its operating temperature. For the low-voltage power distribution electrical module, residual current transformers are installed in the low-voltage outgoing circuit to monitor the residual current in the line. For the uninterruptible power supply electrical module, voltage sensors, current sensors, etc. are installed at both ends of the battery to monitor parameters such as the terminal voltage, charge and discharge current, and internal resistance of the battery. For the DC power supply electrical module, current sensors, voltage sensors, etc. are installed at the DC power supply to monitor the current and voltage at the input end of the DC power supply, the current and voltage at the output end, and the ripple voltage.

[0028] Further, after the data collected by the sensors of each electrical module are transmitted to the corresponding edge node, after the edge node obtains the data collected by the sensors of the electrical module, these data are input into a machine learning module, such as a Support Vector Machine (SVM) learning model, and the output is the abnormal data of the electrical module at this moment. In the machine learning model, a threshold is set to compare the data of each electrical module with the threshold, and the data are divided into normal data and abnormal data. If the data of the edge node are normal, the relevant data are not stored or uploaded. If the result is abnormal, the abnormal data at this moment are marked, and at the same time, the duration of the abnormal data is obtained, and the abnormal time period corresponding to the duration is uploaded to the edge server. The edge computing module of each electrical module analyzes the collected data and transmits the abnormal data to the edge server to obtain the abnormal time period corresponding to each electrical module and the abnormal data within the abnormal time period. Exemplarily, as Figure 2 shown Figure 2 FIG. 6 is a schematic diagram of the relationship between an edge server and edge nodes provided by an embodiment of the present invention. The edge computing modules in each edge node upload the data collected by the sensors in the corresponding electrical module to the edge server, and the edge server processes the abnormal data in the abnormal time periods of each electrical module.

[0029] S102. Correct the second abnormal time period of the remaining electrical modules according to the first abnormal time period of the DC power supply module in the electrical module to obtain an alignment time period. When there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding alignment time period, the remaining electrical modules are used as alternative nodes affecting the abnormality of the DC power supply module.

[0030] Specifically, each electronic module has a sequence in the DC power supply system, which is to supply power to the load in the order of medium-voltage power distribution, transformer, low-voltage power distribution, uninterruptible power supply, and DC power supply. Therefore, if the DC power supply module fails, there is a certain delay error in time. Therefore, in the embodiment of the present invention, the allowable delay error between adjacent edge nodes is set to tms, and t is taken as 5ms in the embodiment of the present invention.

[0031] Further, in the embodiment of the present invention, starting from the edge node of the DC power supply module, the upstream adjacent edge nodes corresponding to each edge node are obtained in the order of the power supply line. For example, the upstream adjacent edge node of the DC power supply module is the uninterruptible power supply, and then the low-voltage power distribution, etc. It should be noted that the actual adjacent upstream nodes are determined by the composition of the DC power supply system, and the embodiment of the present invention does not limit this here.

[0032] Further, in the embodiment of the present invention, the first abnormal time period when the DC power supply module has an abnormality is first obtained T 1, T 2], then the aligned time period after correction of the upstream edge node adjacent to the DC power supply module is T 1 - t , T 2 - t . Then, traversing continues upstream from the corrected aligned time period to the edge nodes to correct the time of each edge node and obtain the aligned time period of each edge node.

[0033] Further, if the other electrical modules of the DC power supply system fail, the abnormality of the DC power supply module is caused by the failure of the other electrical modules, which affects the input of the downstream electrical modules. In this case, there are also abnormal manifestations among the other electrical modules except the DC power supply module within the allowable delay error time, so there is time synchronization. Thus, the abnormal times of adjacent edge nodes are close. Therefore, the failure of the DC power supply module in the actual DC power supply system is not isolated. Due to the failure of the upstream electrical module, the downstream electrical module has an abnormality. Thus, the abnormal time period and the aligned time period of the other electrical modules show strong consistency. Based on this, in the embodiment of the present invention, an edge node of an electrical module other than the DC power supply module is selected, and the abnormal data uploaded by the edge node is obtained. If the abnormal time period uploaded by the edge node coincides with the aligned time period of the edge node, the edge node is a candidate node affecting the abnormality of the DC power supply module, which is marked as the first value in the embodiment of the present invention. If the abnormal time period uploaded by the edge node does not coincide with the aligned time period of the edge node, it means that the abnormal failure of the DC power supply module has nothing to do with the edge node, which is marked as the second value. The first value or the second value in the embodiment of the present invention is represented by L i wherein, the first value and the second value can be determined according to the actual situation. In the embodiment of the present invention, the first value is taken as 1 and the second value is taken as 0.

[0034] S103. Based on the second abnormal time period and the corresponding aligned time period of the other electrical modules, determine the first possibility that the abnormal data of the DC power supply module is a real fault.

[0035] Specifically, if there is an overlap between the abnormal time periods of all electrical modules other than the DC power supply module and their corresponding alignment time periods, and the abnormal time periods of the remaining edge nodes are highly consistent with the abnormal time periods of the edge nodes where the DC power supply module is located, it indicates that the possibility of the abnormality of the current remaining edge nodes of the electrical modules being affected by the failure of the DC power supply module is smaller, and the possibility of the upstream failure causing the monitoring of the DC power supply module to be abnormal is greater.

[0036] Further, as an optional embodiment of the present invention, the first possibility of determining that the abnormal data of the DC power supply module is a real failure based on the second abnormal time period and the corresponding alignment time period of the remaining electrical modules includes: when there is an overlap between the second abnormal time period and the corresponding alignment time period of the remaining electrical modules, regarding the remaining electrical modules as alternative nodes affecting the abnormality of the DC power supply module and marking them as the first value; when there is no overlap between the second abnormal time period and the corresponding alignment time period of the remaining electrical modules, indicating that the remaining electrical modules have nothing to do with the abnormality of the DC power supply module and marking them as the second value; calculating the intersection between the second abnormal time period and the corresponding alignment time period, and the union between the second abnormal time period and the corresponding alignment time period; determining the first ratio between the intersection and the union as the coincidence of the abnormal time of the remaining electrical modules; calculating the first product of the first value or the second value and the coincidence; normalizing the accumulated value of the first product using a positive correlation normalization function to obtain a normalized value; determining the first difference between the predetermined value and the normalized value as the first possibility.

[0037] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the coincidence of the abnormal time of the remaining electrical modules:

[0038]

[0039] In the above formula, represents the coincidence of the abnormal time of the edge node of the th remaining electrical module, reflecting the consistency in time. represents the second abnormal time period of the i th remaining electrical module among the non-DC power supply modules in the DC power supply system. represents the alignment time period of the i th remaining electrical module among the non-DC power supply modules in the DC power supply system. ∩ represents the intersection, and ∪ represents the union.

[0040] Further, in the embodiment of the present invention, the predetermined value can be taken as 1, and the embodiment of the present invention specifically uses the following formula to calculate the first possibility:

[0041]

[0042] In the above formula, p represents the first possibility that the abnormal data uploaded by the edge node of the DC power supply module is a real fault. represents a positive correlation normalization function, which is used to perform normalization processing. represents the value of whether the edge node of the th remaining electrical module is an alternative node, which can be a first value or a second value. represents the coincidence of the abnormal times of the edge nodes of the th remaining electrical module, reflecting the consistency in time. n represents the number of the remaining electrical modules other than the DC power supply module.

[0043] S104. When the first possibility is not less than the first threshold, determine the second possibility that the abnormal data of the alternative node is a real fault.

[0044] Specifically, the first threshold can be set according to the actual situation, and the embodiments of the present invention do not limit it here. If the first possibility is less than the first threshold, it means that the heating alignment time period of each electrical module in the DC power supply system and the actually occurring abnormal time period have a high coincidence, indicating that the fault of the monitored DC power supply module is caused by the adjustment of the normal power supply strategy of the DC power supply system, such as the change of normal power supply demand during peak power consumption periods, rather than a real fault. If the first possibility is not less than the first threshold, it means that the alignment effect is poor and the coincidence degree between the alignment time period and the abnormal time period is low. However, at this time, it may show that a certain electrical module in the DC power supply system fails, resulting in normal power supply basically upstream of this electrical module and a large degree of abnormality downstream of this electrical module. At this time, although the DC power supply module also has abnormal data uploaded, it actually shows the fault of the remaining electrical modules. Based on this, the embodiments of the present invention select the abnormal time period corresponding to the alternative node of the electrical module with the above label = the first value as the node to be analyzed, and perform the same analysis according to the method for calculating the first possibility that the abnormal data is a real fault recorded in the above embodiments of the present invention to obtain the second possibility that the abnormal data uploaded by this alternative node indicates that this electrical module is a real fault. It should be noted that when calculating the second possibility, the number n of the corresponding electrical module

[0045] Further, in the embodiment of the present invention, an electrical module whose edge node does not upload abnormal data is regarded as operating normally, and at this time, the probability of the corresponding true fault is 0. Thus, the probability of the true fault of each electrical module in the DC power supply system during the abnormal time period when the DC power supply module is abnormal is obtained.

[0046] S105. Determine the abnormality significance of the DC power supply module according to the first probability, the order of the alternative nodes in the DC power supply system, and the corresponding second probability.

[0047] Specifically, after obtaining the first probability of the DC power supply module and the second probabilities of the remaining electrical modules, the embodiment of the present invention determines the final abnormality significance of the DC power supply module according to the mutual influence between the electrical modules.

[0048] Further, as an optional embodiment of the present invention, determining the abnormality significance of the DC power supply module according to the first probability, the order of the alternative nodes in the DC power supply system, and the corresponding second probability includes: obtaining a probability sequence of each alternative node according to the order of the alternative nodes in the DC power supply system and the second probability; selecting any one alternative node from the probability sequence as the node to be analyzed, taking the alternative nodes before the node to be analyzed as the first set of electrical modules upstream of the node to be analyzed, and taking the alternative nodes after the node to be analyzed as the second set of electrical modules downstream of the node to be analyzed; determining the third probability of the corrected fault of the node to be analyzed according to the second probability corresponding to the node to be analyzed, the second probabilities of the alternative nodes adjacent to the node to be analyzed, the first average probability in the first set of electrical modules, and the second average probability in the second set of electrical modules; selecting the maximum value in the third probability as the reference probability, and selecting the electrical modules adjacent to the DC power supply module as the third set of electrical modules of the DC power supply module; if the alternative node corresponding to the reference probability belongs to the third set of electrical modules, determine the abnormality significance of the DC power supply module according to the first probability and the third average probability in the third set of electrical modules; if the alternative node corresponding to the reference probability does not belong to the third set of electrical modules, determine the abnormality significance of the DC power supply module according to the first probability, the reference probability, and the third average probability.

[0049] Specifically, in the embodiment of the present invention, according to the order of the electrical modules corresponding to the alternative nodes in the DC power supply system, a probability sequence of the second probability that the alternative nodes are true faults is obtained . Select the th edge node in the probability sequence as the node to be analyzed, and divide the electrical modules of the DC power supply system into two categories. One category is the first set of electrical modules C1 upstream of the th node to be analyzed, and the other category is the The second set of electrical modules C2 downstream of the node to be analyzed. At this time, if there is a significant change in the probability of failure before and after the node to be analyzed, and the change in the probability of failure of the edge nodes adjacent to the node to be analyzed is the most significant, it indicates that the electrical modules before the electrical module corresponding to the node to be analyzed are all operating normally, while there are significant abnormalities in the electrical modules after that, thus indicating that the subsequent electrical module abnormalities are affected by the abnormalities of the node to be analyzed. If the failure of the electrical module is caused by the failures of the remaining electrical modules, the probabilities of failure of the adjacent electrical modules are relatively high at this time, and the differences are relatively small, thus realizing correction.

[0050] Further, as an optional embodiment of the present invention, determining the third probability of the corrected failure of the node to be analyzed according to the second probability corresponding to the node to be analyzed, the second probabilities of the alternative nodes adjacent to the node to be analyzed, the first average probability in the first set of electrical modules, and the second average probability in the second set of electrical modules includes: calculating the second difference between the second average probability and the first average probability, and the third difference between the second probability of the alternative node adjacent to the node to be analyzed after and the second probability of the alternative node adjacent to the node to be analyzed before; calculating the absolute value of the first sum value between the second difference and the third difference; determining that the second product of the absolute value of the first sum value and the second probability corresponding to the node to be analyzed is the third probability of the corrected failure of the node to be analyzed.

[0051] Specifically, the embodiment of the present invention specifically calculates the third probability using the following formula:

[0052]

[0053] In the above formula, represents the third probability of the corrected failure of the th node to be analyzed. represents the second probability of the th node to be analyzed. represents the second probability of the alternative node adjacent to the th node to be analyzed before. represents the second probability of the alternative node adjacent to the th node to be analyzed after. p (C1) represents the first average probability in the first set of electrical modules C1. p (C2) represents the second average probability in the second set of electrical modules C2.

[0054] It should be noted that if there is no previous or next electrical module during the analysis of the node to be analyzed, the above analysis is not performed. Thus, the corrected fault possibility of the node to be analyzed in the middle position is obtained, that is, the node to be analyzed is not the first and last of the data sequence.

[0055] Furthermore, when the DC power supply module fails, especially in the case of a short circuit fault, it will cause a sharp increase in current, which will have a greater impact on switches, fuses, lines, etc. in the low-voltage power distribution module. Or when the output voltage of the DC power supply module is abnormal, the DC power supply module may not be able to charge normally or switch to the battery power supply mode, thus reducing the reliability of the entire DC power supply system. In addition, if the failure of the DC power supply system causes abnormal current, it may also damage components such as the inverter and battery of the DC power supply system. Therefore, the DC power supply system also affects the electrical modules adjacent to it. And as the number of electrical modules in the middle increases, the influence of the DC power supply module on the remaining electrical modules decreases. If an electrical module close to the DC power supply module fails, although the DC power supply module is normal at this time, there are relatively large potential faults, and a relatively high fault possibility should be given at this time.

[0056] Furthermore, in the embodiment of the present invention, the maximum value in the corrected third possibility is selected as the reference possibility. The electrical modules adjacent to the DC power supply module are selected as the third electrical module set M, such as the previous electrical module adjacent to the DC power supply module and the next electrical module adjacent to the DC power supply module.

[0057] Furthermore, if the corresponding electrical module belongs to the third electrical module set M, it indicates that the electrical module with the most significant abnormality has a relatively large abnormal transmission to the DC power supply module and may cause a fault in the DC power supply module. Or due to the fault of the DC power supply module having a relatively large interference on this electrical module, a relatively high abnormal significance should be given to the DC power supply module at this time. As an optional embodiment of the present invention, determining the abnormal significance of the DC power supply module according to the first possibility and the third average possibility in the third electrical module set includes: determining the second sum value between the first possibility and the third average possibility in the third electrical module set as the abnormal significance of the DC power supply module.

[0058] Specifically, the embodiment of the present invention specifically calculates the abnormal significance of the DC power supply module using the following formula:

[0059]

[0060] In the above formula, z is the abnormal significance of the DC power supply module. pIndicates the first possibility that the abnormal data uploaded by the edge node of the DC power supply module is a real fault. Indicates the third average possibility in the third electrical module set M.

[0061] Furthermore, if The corresponding electrical module does not belong to the third electrical module set M, indicating that the abnormal manifestations of the low-voltage power distribution and DC power supply modules are relatively insignificant. If there are significant differences and the anomalies in the third electrical module set M are significantly smaller, it means that although there are anomalies in the low-voltage power distribution and DC power supply modules, they are caused by the anomalies of the other electrical modules, and the anomalies of the other electrical modules have little impact on the low-voltage power distribution and DC power supply modules. At this time, it is considered that there is no fault. The anomaly significance of the corresponding DC power supply module is relatively small. As an optional embodiment of the present invention, determining the anomaly significance of the DC power supply module according to the first possibility, the reference possibility, and the third average possibility includes: calculating the absolute value of the reciprocal of the fourth difference between the reference possibility and the third average possibility, and normalizing the absolute value of the reciprocal of the fourth difference using a positive correlation normalization function to obtain a normalized absolute value; calculating the third product between the normalized absolute value and the third average possibility; determining the third sum value between the third product and the first possibility as the anomaly significance of the DC power supply module.

[0062] Specifically, the embodiment of the present invention specifically calculates the anomaly significance of the DC power supply module using the following formula:

[0063]

[0064] In the above formula, z is the anomaly significance of the DC power supply module. p Indicates the first possibility that the abnormal data uploaded by the edge node of the DC power supply module is a real fault. Indicates the third average possibility in the third electrical module set M. Indicates the reference possibility. represents a positive correlation normalization function, which is used to perform normalization processing.

[0065] S106. Re-determine whether the DC power supply module is faulty according to the anomaly significance and the first threshold.

[0066] Specifically, after obtaining the anomaly significance, as an optional embodiment of the present invention, re-determining whether the DC power supply module is faulty according to the anomaly significance and the first threshold includes: normalizing the anomaly significance to obtain a normalized anomaly significance; determining that the DC power supply module is faulty when the normalized anomaly significance is not less than the first threshold; and determining that the DC power supply module is not faulty when the normalized anomaly significance is less than the first threshold.

[0067] Among them, when normalizing the anomaly significance, first determine the reference possibility of the DC power supply module; then calculate the fourth sum value between the reference possibility and the first possibility; finally, determine the second ratio between the anomaly significance and the fourth sum value as the normalized anomaly significance.

[0068] Specifically, the embodiment of the present invention specifically calculates the normalized anomaly significance by using the following formula:

[0069] In the above formula, represents the normalized anomaly significance. z is the anomaly significance of the DC power supply module. p represents the first possibility that the abnormal data uploaded by the edge node of the DC power supply module is a real fault. represents the reference possibility.

[0070] After the edge server calculates the normalized anomaly significance, it sends the normalized anomaly significance to the edge node where the DC power supply module is located. The edge node where the DC power supply module is located re-compares the sent normalized anomaly significance with the first threshold. If the normalized anomaly significance is not less than the first threshold, it is considered that the DC power supply module fails. If the normalized anomaly significance is less than the first threshold, there is no DC power supply fault.

[0071] The embodiment of the present invention can obtain the possibility of each electrical module being a real fault according to the abnormal time period and abnormal data of each electrical module of the DC power supply system, and determine the anomaly significance of the DC power supply module in combination with the possibility of real faults under the mutual influence between each electrical module. Thus, the fault of the DC power supply module is monitored and diagnosed multiple times through the mutual influence between each electronic module, strengthening the correlation between electrical modules, ensuring the collaborative management between electrical modules, improving the accuracy of fault judgment, and ensuring the stable operation of the central power system.

[0072] Embodiment 2:

[0073] Corresponding to the DC power supply fault monitoring method based on edge computing provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the DC power supply fault monitoring method based on edge computing mentioned in the above embodiment.

[0074] It should be noted that the computer-readable storage medium provided in the embodiments of the present invention and the method for monitoring direct current power supply faults based on edge computing provided in the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned method for monitoring direct current power supply faults based on edge computing, and has the same or similar beneficial effects. The repeated parts will not be elaborated here.

[0075] Embodiment III:

[0076] Corresponding to the method for monitoring direct current power supply faults based on edge computing provided in the above embodiments, based on the same technical concept, the embodiments of the present invention also provide a system for monitoring direct current power supply faults based on edge computing. This system for monitoring direct current power supply faults based on edge computing is used to execute the above method for monitoring direct current power supply faults based on edge computing. Figure 3 The structural schematic diagram of a system for monitoring direct current power supply faults based on edge computing provided in another embodiment of the present invention is shown in Figure 3 as shown. The system for monitoring direct current power supply faults based on edge computing may vary greatly due to configuration or performance differences. It may include one or more processors 301 and a memory 302. The memory 302 is used to store computer programs that can run on the processor 301. The processor 301 is used to execute the programs stored in the memory 302 to implement each step in the above Figure 1 method embodiments. Among them, the memory 302 can be short-term storage or persistent storage. The application programs stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions for the system for monitoring direct current power supply faults based on edge computing.

[0077] Furthermore, the processor 301 can be set to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the system for monitoring direct current power supply faults based on edge computing. The system for monitoring direct current power supply faults based on edge computing may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0078] Specifically in this embodiment, the system for monitoring direct current power supply faults based on edge computing includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the bus. The memory is used to store computer programs. The processor is used to execute the programs stored in the memory to implement each step in the above Figure 1 method embodiments, and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not elaborate here.

[0079] It should be noted that the DC power supply fault monitoring system based on edge computing provided by the embodiments of the present invention and the DC power supply fault monitoring method based on edge computing provided by the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned DC power supply fault monitoring method based on edge computing, and has the same or similar beneficial effects. The repeated parts will not be elaborated again.

[0080] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A DC power supply fault monitoring method based on edge computing, characterized in that, The DC power supply fault monitoring method based on edge computing includes: Obtaining the abnormal time period of each electrical module in the DC power supply system and the abnormal data corresponding to the abnormal time period; Correcting the second abnormal time period of the remaining electrical modules according to the first abnormal time period of the DC power supply module in the electrical module to obtain an aligned time period. When there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, the remaining electrical modules are used as alternative nodes affecting the abnormality of the DC power supply module; Based on the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, determining the first possibility that the abnormal data of the DC power supply module is a real fault; When the first possibility is not less than the first threshold, determining the second possibility that the abnormal data of the alternative node is a real fault; Determining the abnormality significance of the DC power supply module according to the first possibility, the order of the alternative nodes in the DC power supply system, and the corresponding second possibility; Re-determining whether the DC power supply module is faulty according to the abnormality significance and the first threshold; The determining the first possibility that the abnormal data of the DC power supply module is a real fault based on the second abnormal time period of the remaining electrical modules and the corresponding aligned time period includes: When there is an overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, using the remaining electrical modules as alternative nodes affecting the abnormality of the DC power supply module and marking them as the first value. When there is no overlap between the second abnormal time period of the remaining electrical modules and the corresponding aligned time period, it means that the remaining electrical modules have nothing to do with the abnormality of the DC power supply module and are marked as the second value; Calculating the intersection between the second abnormal time period and the corresponding aligned time period, and the union between the second abnormal time period and the corresponding aligned time period; Determining the first ratio between the intersection and the union as the coincidence of the abnormal time of the remaining electrical modules; Calculating the first product between the first value or the second value and the coincidence, and normalizing the accumulated value of the first product using a positive correlation normalization function to obtain a normalized value; Determining the first difference between a predetermined value and the normalized value as the first possibility; The determining the abnormality significance of the DC power supply module according to the first possibility, the order of the alternative nodes in the DC power supply system, and the corresponding second possibility includes: Obtaining a possibility sequence of each alternative node according to the order of the alternative nodes in the DC power supply system and the second possibility; Selecting any alternative node from the possibility sequence as the node to be analyzed, using the alternative nodes before the node to be analyzed as the first set of electrical modules upstream of the node to be analyzed, and using the alternative nodes after the node to be analyzed as the second set of electrical modules downstream of the node to be analyzed; Determine a third possibility of the corrected fault of the node to be analyzed according to the second possibility corresponding to the node to be analyzed, the second possibilities of the alternative nodes adjacent to the node to be analyzed, the first average possibility in the first electrical module set, and the second average possibility in the second electrical module set; Select the maximum value in the third possibility as the reference possibility, and select the electrical modules adjacent to the DC power supply module as the third electrical module set of the DC power supply module; If the alternative node corresponding to the reference possibility belongs to the third electrical module set, determine the abnormality significance of the DC power supply module according to the first possibility and the third average possibility in the third electrical module set; If the alternative node corresponding to the reference possibility does not belong to the third electrical module set, determine the abnormality significance of the DC power supply module according to the first possibility, the reference possibility, and the third average possibility.

2. The method for monitoring DC power supply faults based on edge computing according to claim 1, wherein The determining the third possibility of the corrected fault of the node to be analyzed according to the second possibility corresponding to the node to be analyzed, the second possibilities of the alternative nodes adjacent to the node to be analyzed, the first average possibility in the first electrical module set, and the second average possibility in the second electrical module set includes: Calculate a second difference between the second average possibility and the first average possibility, and a third difference between the second possibility of the alternative node adjacent to the node to be analyzed and the second possibility of the alternative node adjacent to the node to be analyzed; Calculate the absolute value of the first sum value between the second difference and the third difference; Determine that the second product between the absolute value of the first sum value and the second possibility corresponding to the node to be analyzed is the third possibility of the corrected fault of the node to be analyzed.

3. The method for monitoring DC power supply faults based on edge computing according to claim 1, wherein The determining the abnormality significance of the DC power supply module according to the first possibility and the third average possibility in the third electrical module set includes: Determine that the second sum value between the first possibility and the third average possibility in the third electrical module set is the abnormality significance of the DC power supply module.

4. The method for monitoring the DC power supply fault based on edge computing according to claim 1, characterized in that, The determining the abnormality significance of the DC power supply module according to the first possibility, the reference possibility, and the third average possibility includes: Calculate the absolute value of the reciprocal of the fourth difference between the reference possibility and the third average possibility, and perform normalization processing on the absolute value of the reciprocal of the fourth difference by using a positive correlation normalization function to obtain a normalized absolute value; Calculate the third product between the normalized absolute value and the third average possibility; Determine that the third sum value between the third product and the first possibility is the abnormality significance of the DC power supply module.

5. The method for monitoring DC power supply faults based on edge computing according to any one of claims 1-4, characterized in that, The re-determining whether the DC power supply module is faulty according to the abnormality significance and the first threshold includes: Perform normalization processing on the abnormality significance to obtain a normalized abnormality significance; When the normalized abnormality significance is not less than the first threshold, determine that the DC power supply module is faulty; When the normalized anomaly significance is less than the first threshold, it is determined that the DC power supply module is not faulty.

6. The method for monitoring DC power supply faults based on edge computing according to claim 5, characterized in that, The normalization processing of the anomaly significance includes: Determine the reference probability of the DC power supply module; Calculate the fourth sum value between the reference probability and the first probability; Determine that the second ratio between the anomaly significance and the fourth sum value is the normalized anomaly significance.

7. A DC power supply fault monitoring system based on edge computing, characterized in that, Including: A processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; The processor is configured to execute the program stored on the memory to implement the steps of the edge computing-based DC power supply fault monitoring method according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the edge computing-based DC power supply fault monitoring method according to any one of claims 1 to 6 are implemented.

Images