Intelligent substation network fault diagnosis and positioning method and system based on data analysis

Abstract

The invention discloses an intelligent substation network fault diagnosis and positioning method and system based on data analysis, and relates to the technical field of electric power automation, and the method comprises the steps: monitoring a flowing path of high-voltage electric energy and the network performance of a transformer in real time, and obtaining a first network evaluation index through calculating the hazard index and duration of each abnormal intrusion; meanwhile, a second network evaluation index is obtained by calculating the network packet loss rate and the bandwidth occupancy rate of the transformer and the attenuation rate of the network traffic of the adjacent transformer; combining the two indexes to obtain a comprehensive network evaluation index which is used for judging whether the intelligent substation network has a fault or not and positioning a fault source; if the first network evaluation index exceeds the standard, indicating abnormal network intrusion; if the network evaluation of a certain transformer in two continuous periods is abnormal, indicating that the network at the transformer is abnormal; comprehensive monitoring and accurate fault positioning of the intelligent substation network are realized, and the stability and safety of the network are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power automation, and in particular to a method and system for diagnosing and locating network faults of an intelligent substation based on data analysis. Background Art

[0002] With the rapid development of smart grids, smart substations are key nodes in the power system, and the security and stability of their networks are crucial to the reliable operation of the entire power grid. Smart substations integrate advanced sensor technology, communication technology, and information technology to achieve real-time monitoring and control of power flow, equipment status, and network performance. However, with the expansion of network scale and the increase in complexity, the potential risks and challenges faced by smart substation networks are becoming increasingly prominent.

[0003] As an important bridge connecting various smart devices and systems, the smart substation network faces multiple intrusion risks from both outside and inside. Network attackers may exploit system vulnerabilities or improper configurations to launch malicious attacks on the substation network, resulting in serious consequences such as data leakage, system paralysis, and even power outages. Therefore, real-time monitoring of network intrusions and accurate assessment of the hazard index of abnormal intrusions have become important means to ensure the network security of smart substations.

[0004] Transformers in smart substations are key equipment for power transmission and conversion. The stability of their network performance directly affects the operating efficiency of the entire substation and even the power grid. However, in actual operation, due to factors such as equipment aging, load changes, and communication interference, the network performance of transformers may fluctuate, manifested in increased packet loss rate, high bandwidth occupancy, and network traffic attenuation between adjacent transformers. If these performance fluctuations are not discovered and handled in a timely manner, they may gradually accumulate and cause more serious network failures.

[0005] Traditional smart substation network fault diagnosis methods mainly rely on manual inspections and regular testing, which have disadvantages such as low efficiency, slow response, and susceptibility to interference from human factors. At the same time, traditional methods often find it difficult to achieve comprehensive monitoring and precise positioning of network intrusions and transformer network performance fluctuations, and cannot meet the smart grid's requirements for real-time, accuracy, and intelligence. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In response to the technical problems in the background technology, the present invention proposes a smart substation network fault diagnosis and positioning method and system based on data analysis, which monitors the high-voltage power flow route and transformer network performance in real time, calculates the abnormal intrusion hazard index and duration to obtain a first network evaluation index, and calculates the second network evaluation index through the number of message sending and receiving, bandwidth occupancy rate and network traffic attenuation rate, and combines the two to judge and locate network faults; thereby solving the technical problems recorded in the background technology.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0010] A method and system for diagnosing and locating network faults of smart substations based on data analysis, including:

[0011] When high voltage electricity enters the smart substation, the flow route of high voltage electricity is monitored in real time and the transformers it passes through are recorded; a monitoring cycle is set to monitor the network performance data of the smart substation network and transformers in real time during each monitoring cycle;

[0012] Based on the network intrusion data detected in the current monitoring period and the network intrusion record data of the historical monitoring period, the hazard index Ha of each abnormal intrusion type occurring in the smart substation network in the current monitoring period is calculated. i , the hazard index Ha of each abnormal intrusion i The corresponding duration t i Combined to obtain the first network evaluation index FNei of the smart substation network in the current monitoring period;

[0013] The network packet loss rate Wlp of each transformer in the fault analysis queue is calculated by the number of messages sent and received in each monitoring cycle. j ; Calculate the bandwidth occupancy rate Bu of each transformer by detecting the network traffic on the router corresponding to each transformer in the fault analysis queue j and the decay rate of the adjacent transformer network flow Tar j,j+1 ; Combine the above data to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period;

[0014] The first network evaluation index FNei and the second network evaluation index SNei of the smart substation network in the current monitoring period are combined to obtain the comprehensive network evaluation index Nei; according to the relationship between the comprehensive network evaluation index Nei and the comprehensive network evaluation index threshold Nei0, it is judged whether a network fault occurs in the smart substation network in the current monitoring period; if it is judged that a network fault occurs, the source of the network fault is located according to the relationship between the first network evaluation index FNei, the second network evaluation index SNei and the corresponding threshold.

[0015] Specifically, when the smart substation receives a signal that high-voltage electric energy is entering, the power sensor in each transformer is turned on to monitor the flow route of the high-voltage electric energy, and the transformers passed through in the flow route are stored in the fault analysis queue in the order of the entry of the high-voltage electric energy; a monitoring cycle is set with a cycle interval of T, and within each monitoring cycle, the smart substation network is monitored for abnormal intrusion signals, as well as network performance data of all transformers in the fault analysis queue, including the number of GOOSE or SV messages on the sending and receiving ends of each transformer and the total flow in the router corresponding to each transformer.

[0016] Specifically, when the network analysis tool detects an abnormal intrusion signal in the current smart substation network within a certain monitoring cycle, the total number of times the current abnormal type has occurred in the past monitoring cycles is counted from the network intrusion record table of the historical monitoring cycle. i , and obtain abnormal traffic data in the current cycle through network traffic analysis tools i ;

[0017] The total number of times each abnormal intrusion occurred in the past monitoring cycle c i The abnormal traffic data of each abnormal intrusion i Combined, we get the hazard index Ha of each abnormal intrusion i , the expression is: Among them, m i Indicates the total number of abnormal signals for each abnormal intrusion, L i It represents the network traffic data when no abnormal intrusion is detected, and i represents the i-th abnormal intrusion.

[0018] Furthermore, the duration data t′ of each abnormal intrusion in each monitoring cycle is obtained t , and the calculated hazard index Ha of each type of abnormal intrusion i Combined, the first network evaluation index FNei of the smart substation network in the current monitoring period is obtained, and the expression is:

[0019]

[0020] Wherein, n represents the total number of abnormal intrusions detected in the current monitoring period, and abnormal intrusions of the same type in the monitoring period are counted as different abnormal intrusion times.

[0021] Specifically, at the sending end of each transformer in the fault analysis queue, the number of GOOSE or SV messages in each monitoring cycle is recorded. At the receiving end of each transformer in the fault analysis queue, record the number of messages successfully received in the same monitoring cycle Then the packet loss rate Wlp of each transformer network in the current monitoring period is j , the expression is:

[0022] Specifically, a network analysis tool is used to obtain the total flow rate f in the router corresponding to each transformer in the fault analysis queue during the monitoring period. j , according to the expression Calculate the average bandwidth occupancy of the router corresponding to each transformer in the current monitoring period; combine the average bandwidth occupancy of the routers corresponding to all transformers in the current monitoring period to obtain the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring period Where m is the number of transformers in the fault analysis queue;

[0023] Through the expression Calculate the decay rate Tar of the network flow of adjacent transformers during the current monitoring period j,j+1 .

[0024] Furthermore, the calculated packet loss rate Wlp of each transformer network in the current monitoring period is j , the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring cycle Bu j and the decay rate of the adjacent transformer network flow Tar j,j+1 Combined, the network evaluation index SNei of each transformer in the current cycle is obtained j , and then combine the network evaluation indexes of all transformers in the fault analysis queue to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period, expressed as:

[0025]

[0026] Among them, α1, α2, and α3 are the packet loss rates Wlp j , bandwidth occupancy rate Bu j 、Network traffic attenuation rate Tar j,j+1 The preset weight coefficients, and α1>α3>α2, α1+α2+α3=1, SNei j =1-α1*Wlpj +α2*Bu j +α3*Tar j,j+1 。

[0027] Furthermore, the first network evaluation index FNei and the second network evaluation index SNei of the intelligent substation network in the current monitoring period are combined to obtain the comprehensive network evaluation index Nei of the intelligent substation network in the current monitoring period. The expression is as follows:

[0028]

[0029] Among them, β1 and β2 are the preset proportionality coefficients of the first network evaluation index FNei and the second network evaluation index SNei respectively, and 0 < β2 < β1 < 1; a network evaluation index threshold Nei0 is set. If Nei ≤ Nei0, it is determined that a network fault has occurred in the intelligent substation network in the current monitoring period.

[0030] Furthermore, after it is determined that a network fault has occurred in the intelligent substation network, the first network evaluation index FNei and the second network evaluation index SNei calculated in the monitoring period when the network fault is determined are extracted. The first network evaluation index FNei is combined with the preset first network evaluation index threshold FNei0. If FNei < FNei0, a signal that the source of the intelligent substation network fault is abnormal network intrusion is sent to the system;

[0031] The network evaluation index SNei of each transformer in the fault analysis queue in the current period j is combined with the preset first network evaluation index threshold SNei0. All transformers with SNei j < SNei0 are marked as suspected network faults. If the o-th transformer is marked as a suspected network fault in two consecutive monitoring periods, a signal that the source of the intelligent substation network fault is network abnormality at the o-th transformer is sent to the system. There can be multiple transformers with network abnormalities simultaneously.

[0032] An intelligent substation network fault diagnosis and location system based on data analysis includes:

[0033] A data acquisition module. Sensor groups are installed on each transformer in the intelligent substation. After the intelligent substation receives a signal that high-voltage electric energy enters, the flow route of the high-voltage electric energy is monitored; a network analysis tool is used to monitor the intelligent substation network in real time; several routers are set up, which are associated with each transformer one by one. The total flow and the number of transmitted packets in the router corresponding to each transformer are monitored through the network analysis tool;

[0034] The data analysis module includes a first data analysis unit and a second data analysis unit; wherein the first data analysis unit calculates the hazard index of each abnormal intrusion in the smart substation network during the current monitoring period, and obtains a first network evaluation index in combination with its duration; the second data analysis unit calculates the network packet loss rate, bandwidth occupancy rate and adjacent transformer network traffic attenuation rate of each transformer in the fault analysis queue, and obtains a second network evaluation index in combination with the above data;

[0035] The anomaly detection and positioning module combines the first and second network evaluation indexes to obtain a comprehensive network evaluation index, and determines whether the smart substation network has a fault based on the comprehensive network evaluation index; if it is determined to be a fault, the source of the fault is further located: if the first network evaluation index exceeds the standard, it indicates an abnormal network intrusion; if the network evaluation of a transformer is abnormal for two consecutive cycles, it indicates that the network at the transformer is abnormal.

[0036] (III) Beneficial effects

[0037] The present invention provides a method and system for diagnosing and locating network faults of intelligent substations based on data analysis, which has the following beneficial effects:

[0038] 1. By real-time monitoring of the flow route of high-voltage electric energy and transformer network performance data, it can not only effectively detect the intrusion risks in the smart substation network, such as network attacks and power leakage, but also evaluate the network status stability of each transformer and the attenuation of network traffic between adjacent transformers; it not only improves the security of the smart substation network, but also enhances its ability to diagnose and locate potential faults, providing strong support for timely maintenance measures and ensuring stable power supply;

[0039] 2. By comprehensively considering the network intrusion data in the current monitoring period, the network intrusion record data in the historical monitoring period, the degree of harm caused by abnormal intrusion (specifically the size of abnormal traffic) and the duration of each abnormal intrusion, a comprehensive assessment of the network status of the smart substation in the current monitoring period is achieved; this improves the accuracy and efficiency of network fault diagnosis, and can effectively locate abnormal intrusions in the network, providing strong data support for timely taking corresponding safety measures, thereby further enhancing the security and stability of the smart substation network;

[0040] 3. The network packet loss rate of the transformer is obtained by precisely calculating the number of messages sent and received in each monitoring cycle, and the bandwidth occupancy rate of the transformer and the attenuation rate of the network traffic of adjacent transformers are monitored in real time. The second network evaluation index of the smart substation network in the current monitoring cycle is obtained by combining these data; it provides a comprehensive and detailed network performance evaluation, which helps to timely discover and locate potential fault points in the network;

[0041] 4. By comprehensively considering the first network evaluation index and the second network evaluation index, the overall health status of the smart substation network can be reflected more comprehensively and accurately, and the accuracy and reliability of network fault diagnosis can be improved; by setting thresholds and making comparisons, it is possible to quickly determine whether the network has a fault and the source of the fault. Whether it is an abnormal network intrusion or a network anomaly at a specific transformer, it can be identified and located in a timely manner, which helps to quickly respond to and handle network faults and ensure the stable operation of the smart substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flowchart of the steps of the intelligent substation network fault diagnosis and location method based on data analysis provided by the present invention;

[0043] Figure 2 A schematic diagram of the structure of the intelligent substation network fault diagnosis and positioning system based on data analysis provided by the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] refer to Figure 1 The present invention provides a method for diagnosing and locating network faults of smart substations based on data analysis, comprising:

[0046] Step 1: When high voltage electricity enters the smart substation, the flow route of high voltage electricity is monitored in real time and the transformers passed through in the flow route are recorded; a monitoring cycle is set, and the network performance data of the smart substation network and the transformer are monitored in real time during each monitoring cycle;

[0047] The step 1 comprises the following steps:

[0048] Step 101: Each transformer in the smart substation is equipped with a sensor group and has a network traffic analysis interface; when the smart substation receives a signal that high-voltage electric energy is entering, the electric energy sensor in each transformer is turned on to monitor the flow route of the high-voltage electric energy, and the transformers passed by the flow route are stored in a fault analysis queue in the order of the high-voltage electric energy entering;

[0049] Step 102: Setting a monitoring cycle with a cycle interval of T, monitoring the smart substation network and the network performance data of all transformers in the fault analysis queue in each monitoring cycle;

[0050] Step 103: Monitor the smart substation network to timely detect the intrusion risks in the smart substation network, including network attack risks and power leakage risks. Specifically, use a network analysis tool to monitor the smart substation network in real time. When an abnormal intrusion signal is detected in the smart substation network, record the type of the abnormal intrusion signal and continuously track the abnormal signal in the abnormal intrusion.

[0051] Step 104: Monitor the network performance data of all transformers in the fault analysis queue to evaluate whether the network status of each transformer in the smart substation network is stable and the attenuation of the network traffic between adjacent transformers; specifically, calculate the packet loss rate of each transformer network by monitoring the number of GOOSE or SV messages on the sending and receiving ends of each transformer; set up several routers, which are associated with each transformer one-to-one, and monitor the total traffic in the router corresponding to each transformer through a network analysis tool;

[0052] When using, combine the contents in steps 101 to 104:

[0053] By real-time monitoring of the flow routes of high-voltage electric energy and transformer network performance data, it is not only possible to effectively detect intrusion risks in the smart substation network, such as network attacks and power leakage, but also to evaluate the network status stability of each transformer and the attenuation of network traffic between adjacent transformers; it not only improves the security of the smart substation network, but also enhances its ability to diagnose and locate potential faults, providing strong support for timely maintenance measures and ensuring stable power supply.

[0054] Step 2: Calculate the hazard index Ha of each abnormal intrusion type that occurs in the smart substation network during the current monitoring period based on the network intrusion data detected during the current monitoring period and the network intrusion record data during the historical monitoring period. i , the hazard index Ha of each abnormal intrusion i The corresponding duration t i Combined to obtain the first network evaluation index FNei of the smart substation network in the current monitoring period;

[0055] The step 2 comprises the following steps:

[0056] Step 201: When the network analysis tool detects an abnormal intrusion signal in the current smart substation network during a certain monitoring cycle, the type of the abnormality is analyzed, and the total number of times the current abnormal type has occurred in the past monitoring cycles is counted from the network intrusion record table of the historical monitoring cycle. i ;

[0057] Step 202: The abnormal intrusion has different degrees of harm, which is specifically manifested in the size of abnormal traffic in the smart substation network. When an abnormal intrusion signal is detected, the abnormal traffic data in the current cycle is obtained through the network traffic analysis tool. i ; The total number of times each abnormal intrusion occurred in the past monitoring cycle c i The abnormal traffic data of each abnormal intrusion i Combined, we get the hazard index Ha of each abnormal intrusion i , the expression is: Among them, m i Indicates the total number of abnormal signals for each abnormal intrusion, L i It represents the network traffic data when no abnormal intrusion is detected, and i represents the i-th abnormal intrusion;

[0058] Step 203: Obtain the duration data t′ of each abnormal intrusion in each monitoring period through a network analysis tool i , and the calculated hazard index Ha of each type of abnormal intrusion i Combined, the first network evaluation index FNei of the smart substation network in the current monitoring period is obtained, and the expression is:

[0059]

[0060] Wherein, n represents the total number of abnormal intrusions detected in the current monitoring period, and abnormal intrusions of the same type in the monitoring period are counted as different abnormal intrusion times.

[0061] When using, combine the contents in steps 201 to 203:

[0062] By comprehensively considering the network intrusion data in the current monitoring cycle, the network intrusion record data in the historical monitoring cycle, the degree of harm caused by abnormal intrusion (specifically the size of abnormal traffic) and the duration of each abnormal intrusion, a comprehensive assessment of the network status of the smart substation in the current monitoring cycle is achieved; this improves the accuracy and efficiency of network fault diagnosis, and can also effectively locate abnormal intrusions in the network, providing strong data support for timely adoption of corresponding safety measures, thereby further enhancing the security and stability of the smart substation network.

[0063] Step 3: Calculate the network packet loss rate Wlp of each transformer in the fault analysis queue by the number of messages sent and received in each monitoring cycle j ; Calculate the bandwidth occupancy rate Bu of each transformer by detecting the network traffic on the router corresponding to each transformer in the fault analysis queue j and the decay rate of the adjacent transformer network flow Tar j,j+1; Combine the above data to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period;

[0064] The step three comprises the following steps:

[0065] Step 301, the packet loss rate refers to the difference in ratio between the messages sent and the messages successfully received within a certain period of time; in the smart substation, the packet loss rate is calculated by monitoring the number of GOOSE and SV messages sent and received; specifically, at the sending end of each transformer in the fault analysis queue, the number of GOOSE or SV messages in each monitoring cycle is recorded. At the receiving end of each transformer in the fault analysis queue, record the number of messages successfully received in the same monitoring cycle Then the packet loss rate Wlp of each transformer network in the current monitoring period is j , the expression is:

[0066] Step 302: Bandwidth occupancy rate refers to the ratio of the actually used bandwidth to the total link capacity. In the smart substation network, this ratio reflects the utilization of network resources by transformers and other equipment during data transmission. By real-time monitoring of the bandwidth occupancy rate of each transformer, abnormal traffic in the network can be discovered in a timely manner. The network analysis tool is used to obtain the total traffic flow in the router corresponding to each transformer in the fault analysis queue during the monitoring period. j , according to the expression Calculate the average bandwidth occupancy of the router corresponding to each transformer in the current monitoring period; combine the average bandwidth occupancy of the routers corresponding to all transformers in the current monitoring period to obtain the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring period Where m is the number of transformers in the fault analysis queue;

[0067] Step 303, the attenuation rate of the network traffic of adjacent transformers refers to the ratio or rate at which the intensity of the network traffic transmitted between corresponding routers gradually decreases due to the existence of adjacent transformers or their specific influence in the network environment; specifically, it is expressed by the expression Calculate the decay rate Tar of the network flow of adjacent transformers during the current monitoring period j,j+1 ;

[0068] Step 304: calculate the packet loss rate Wlp of each transformer network in the current monitoring period j , the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring cycle Bu j and the decay rate of the adjacent transformer network flow Tar j,j+1Combined, the network evaluation index SNei of each transformer in the current cycle is obtained j , and then combine the network evaluation indexes of all transformers in the fault analysis queue to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period, expressed as:

[0069]

[0070] Among them, α1, α2, and α3 are the packet loss rates Wlp j , bandwidth occupancy rate Bu j 、Network traffic attenuation rate Tar j,j+1 The preset weight coefficients, and α1>α3>α2, α1+α2+α3=1, SNei j =1-α1*Wlp j +α2*Bu j +α3*Tar j,j+1 .

[0071] When used, combine the contents in steps 301 to 304:

[0072] The network packet loss rate of the transformer is obtained by precisely calculating the number of messages sent and received in each monitoring cycle, and the bandwidth occupancy rate of the transformer and the attenuation rate of the network traffic of adjacent transformers are monitored in real time. These data are combined to obtain the second network evaluation index of the smart substation network in the current monitoring cycle; a comprehensive and detailed network performance evaluation is provided, which helps to timely discover and locate potential fault points in the network.

[0073] Step 4: Combine the first network evaluation index FNei and the second network evaluation index SNei of the smart substation network in the current monitoring period to obtain a comprehensive network evaluation index Nei; determine whether a network fault occurs in the smart substation network in the current monitoring period according to the relationship between the comprehensive network evaluation index Nei and the comprehensive network evaluation index threshold Nei0; if a network fault occurs, locate the source of the network fault according to the relationship between the first network evaluation index SNei, the second network evaluation index SNei and the corresponding threshold;

[0074] The step 4 comprises the following steps:

[0075] Step 401: Combine the first network evaluation index FNei and the second network evaluation index SNei of the smart substation network in the current monitoring period to obtain the comprehensive network evaluation index Nei of the smart substation network in the current monitoring period, expressed as:

[0076]

[0077] Among them, β1 and β2 are the preset proportionality coefficients of the first network evaluation index SNei and the second network evaluation index SNei respectively, and 0 < β2 < β1 < 1; the smaller the comprehensive network evaluation index Nei is, the greater the probability that a network fault occurs in the intelligent substation network during the current monitoring period; a network evaluation index threshold Nei0 is set. If Nei ≤ Nei0, it is determined that a network fault has occurred in the intelligent substation network during the current monitoring period.

[0078] Step 402: After determining that a network fault has occurred in the intelligent substation network during the current monitoring period, it is necessary to locate the place where the network fault occurs. Specifically: extract the first network evaluation index FNei and the second network evaluation index SNei calculated for the monitoring period in which the network fault is determined. Combine the first network evaluation index FNei with the preset first network evaluation index threshold FNei0. If FNei < FNei0, it means that an abnormal network intrusion has occurred in the intelligent substation network during the current monitoring period, that is, the source of the network fault is an abnormal network intrusion, and send a signal to the system that the source of the intelligent substation network fault is an abnormal network intrusion.

[0079] The network evaluation index SNei of each transformer in the fault analysis queue during the current period j is combined with the preset first network evaluation index threshold SNei0, and all transformers with j SNei < SNei0 are marked as suspected network faults. If the o-th transformer is marked as a suspected network fault in two consecutive monitoring periods, it means that the transformer has a network anomaly, and send a signal to the system that the source of the intelligent substation network fault is the network anomaly at the o-th transformer. There can be multiple transformers with network anomalies at the same time.

[0080] When in use, combine the content in steps 401 to 402:

[0081] By comprehensively considering the first network evaluation index and the second network evaluation index, the overall health status of the intelligent substation network can be reflected more comprehensively and accurately, improving the accuracy and reliability of network fault diagnosis; by setting thresholds and making comparisons, it can be quickly determined whether a network fault has occurred and the source of the fault. Whether it is an abnormal network intrusion or a network anomaly at a specific transformer, it can be identified and located in a timely manner, which helps to quickly respond to and handle network faults and ensure the stable operation of the intelligent substation.

[0082] Reference Figure 2 , the present invention also provides an intelligent substation network fault diagnosis and location system based on data analysis, including:

[0083] Data acquisition module: Each transformer in the smart substation is equipped with a sensor group. After the smart substation receives a signal that high-voltage power is entering, it monitors the flow route of high-voltage power. It uses network analysis tools to monitor the smart substation network in real time. It sets up several routers, which are associated with each transformer one-to-one. It uses network analysis tools to monitor the total flow and the number of transmitted messages in the router corresponding to each transformer.

[0084] The data analysis module includes a first data analysis unit and a second data analysis unit; wherein the first data analysis unit calculates the hazard index of each abnormal intrusion in the smart substation network during the current monitoring period, and obtains a first network evaluation index in combination with its duration; the second data analysis unit calculates the network packet loss rate, bandwidth occupancy rate and adjacent transformer network traffic attenuation rate of each transformer in the fault analysis queue, and obtains a second network evaluation index in combination with the above data;

[0085] The anomaly detection and positioning module combines the first and second network evaluation indexes to obtain a comprehensive network evaluation index, and determines whether the smart substation network has a fault based on the comprehensive network evaluation index; if it is determined to be a fault, the source of the fault is further located: if the first network evaluation index exceeds the standard, it indicates an abnormal network intrusion; if the network evaluation of a transformer is abnormal for two consecutive cycles, it indicates that the network at the transformer is abnormal.

[0086] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer storage medium or transmitted via a computer storage medium.

[0087] Computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer storage media can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives (SSDs)).

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for diagnosing and locating network faults of smart substations based on data analysis, characterized in that: include: When high voltage electricity enters the smart substation, the flow route of high voltage electricity is monitored in real time and the transformers it passes through are recorded; Set monitoring cycles to monitor the network performance data of smart substations and transformers in real time during each monitoring cycle; Based on the network intrusion data detected in the current monitoring period and the network intrusion record data of the historical monitoring period, the hazard index Ha of each abnormal intrusion type occurring in the smart substation network in the current monitoring period is calculated. i , the hazard index Ha of each abnormal intrusion i The corresponding duration t i Combined to obtain the first network evaluation index FNei of the smart substation network in the current monitoring period; The network packet loss rate Wlp of each transformer in the fault analysis queue is calculated by the number of messages sent and received in each monitoring cycle. j ; Calculate the bandwidth occupancy rate Bu of each transformer by detecting the network traffic on the router corresponding to each transformer in the fault analysis queue j and the decay rate of the adjacent transformer network flow Tar j,j+1 ; Combine the above data to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period; The first network evaluation index FNei and the second network evaluation index SNei of the smart substation network in the current monitoring period are combined to obtain the comprehensive network evaluation index Nei; according to the relationship between the comprehensive network evaluation index Nei and the comprehensive network evaluation index threshold Nei0, it is judged whether a network fault occurs in the smart substation network in the current monitoring period; if it is judged that a network fault occurs, the source of the network fault is located according to the relationship between the first network evaluation index FNei, the second network evaluation index SNei and the corresponding threshold.

2. The method for diagnosing and locating network faults of smart substations based on data analysis according to claim 1, characterized in that: When the smart substation receives a signal that high-voltage power is entering, it turns on the power sensor in each transformer to monitor the flow route of the high-voltage power, and stores the transformers passed by the flow route in the fault analysis queue in the order of the high-voltage power entering; Set a monitoring cycle with a cycle interval of T. In each monitoring cycle, monitor whether there are abnormal intrusion signals in the smart substation network, as well as the network performance data of all transformers in the fault analysis queue, including the number of GOOSE or SV messages on the sending and receiving ends of each transformer and the total flow in the router corresponding to each transformer.

3. The method for diagnosing and locating network faults of smart substations based on data analysis according to claim 2, characterized in that: When the network analysis tool detects an abnormal intrusion signal in the current smart substation network during a certain monitoring cycle, the total number of times the current abnormal type has occurred in the past monitoring cycle is counted from the network intrusion record table of the historical monitoring cycle. i , and obtain abnormal traffic data in the current cycle through network traffic analysis tools i ; The total number of times each abnormal intrusion occurred in the past monitoring cycle c i The abnormal traffic data of each abnormal intrusion i Combined, we get the hazard index Ha of each abnormal intrusion i , the expression is: Among them, m i Indicates the total number of abnormal signals for each abnormal intrusion, L i It represents the network traffic data when no abnormal intrusion is detected, and i represents the i-th abnormal intrusion.

4. The method for diagnosing and locating network faults of smart substations based on data analysis according to claim 3, characterized in that: Obtain the duration data t′ of each abnormal intrusion in each monitoring cycle i , and the calculated hazard index Ha of each type of abnormal intrusion i Combined, the first network evaluation index FNei of the smart substation network in the current monitoring period is obtained, and the expression is: Wherein, n represents the total number of abnormal intrusions detected in the current monitoring period, and abnormal intrusions of the same type in the monitoring period are counted as different abnormal intrusion times.

5. The method for diagnosing and locating network faults of smart substations based on data analysis according to claim 4, characterized in that: At the sending end of each transformer in the fault analysis queue, record the number of GOOSE or SV messages in each monitoring cycle At the receiving end of each transformer in the fault analysis queue, record the number of messages successfully received in the same monitoring cycle Then the packet loss rate Wlp of each transformer network in the current monitoring period is j , the expression is:

6. The method for diagnosing and locating network faults of a smart substation based on data analysis according to claim 5, characterized in that: Use network analysis tools to obtain the total flow f in the router corresponding to each transformer in the fault analysis queue during the monitoring period j , according to the expression Calculate the average bandwidth occupancy of the router corresponding to each transformer in the current monitoring period; combine the average bandwidth occupancy of the routers corresponding to all transformers in the current monitoring period to obtain the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring period Where m is the number of transformers in the fault analysis queue; Through the expression Calculate the decay rate Tar of the network flow of adjacent transformers during the current monitoring period j,j+1 .

7. The method for diagnosing and locating network faults of a smart substation based on data analysis according to claim 6, characterized in that: The calculated packet loss rate Wlp of each transformer network in the current monitoring period j , the bandwidth occupancy rate of the router corresponding to each transformer in the current monitoring cycle Bu j and the decay rate of the adjacent transformer network flow Tar j,j+1 Combined, the network evaluation index SNei of each transformer in the current cycle is obtained j , and then combine the network evaluation indexes of all transformers in the fault analysis queue to obtain the second network evaluation index SNei of the smart substation network in the current monitoring period, expressed as: Among them, α1, α2, and α3 are the packet loss rates Wlp j , bandwidth occupancy rate Bu j 、Network traffic attenuation rate Tar j,j+1 The preset weight coefficients, and α1>α3>α2, α1+α2+α3=1, SNe ij =1-α1*Wlp j +α2*Bu j +α3*Tar j,j+1 .

8. The method for diagnosing and locating network faults of a smart substation based on data analysis according to claim 7, characterized in that: The first network evaluation index FNei and the second network evaluation index SNei of the smart substation network in the current monitoring period are combined to obtain the comprehensive network evaluation index Nei of the smart substation network in the current monitoring period, which is expressed as: Among them, β1 and β2 are preset proportional coefficients of the first network evaluation index FNei and the second network evaluation index SNei respectively, and 0<β2<β1<1; the network evaluation index threshold Nei0 is set, if Nei≤Nei0, it is judged that a network failure has occurred in the smart substation network during the current monitoring period.

9. The intelligent substation network fault diagnosis and location method based on data analysis according to claim 8, wherein: After it is determined that there is a network fault in the intelligent substation network, the first network evaluation index FNei and the second network evaluation index SNei calculated for the monitoring period in which the network fault is determined are extracted, and the first network evaluation index FNei is combined with the preset first network evaluation index threshold FNei0. If FNei < FNei0, a signal indicating that the source of the intelligent substation network fault is abnormal network intrusion is sent to the system; The network evaluation index SNei of each transformer in the fault analysis queue within the current cycle j is combined with the preset first network evaluation index threshold SNei0, and all SNei j transformers < SNei0 are marked as suspected network faults. If the o-th transformer is marked as a suspected network fault in two consecutive monitoring cycles, a signal indicating that the source of the intelligent substation network fault is a network anomaly at the o-th transformer is sent to the system. There can be multiple transformers with network anomalies simultaneously.

10. The intelligent substation network fault diagnosis and positioning system based on data analysis is characterized by: Including: A data acquisition module. Each transformer in the intelligent substation is equipped with a sensor group. After the intelligent substation receives a signal that high-voltage electric energy enters, the flow route of the high-voltage electric energy is monitored; Use network analysis tools to monitor the intelligent substation network in real time; set a number of routers, which are associated with each transformer one by one, and monitor the total traffic and the number of transmitted packets in the routers corresponding to each transformer through the network analysis tools; A data analysis module, including a first data analysis unit and a second data analysis unit; wherein, the first data analysis unit calculates the hazard index of each abnormal intrusion in the intelligent substation network during the current monitoring period, and obtains the first network evaluation index in combination with its duration; the second data analysis unit calculates the network packet loss rate, bandwidth occupancy rate and adjacent transformer network traffic attenuation rate of each transformer in the fault analysis queue, and obtains the second network evaluation index in combination with the above data; An abnormal detection and location module, which combines the first and second network evaluation indexes to obtain a comprehensive network evaluation index, and determines whether there is a fault in the intelligent substation network according to the comprehensive network evaluation index; if it is determined to be a fault, the fault source is further located: if the first network evaluation index exceeds the standard, it indicates abnormal network intrusion; If a certain transformer has abnormal network evaluation for two consecutive periods, it indicates that the network at that transformer is abnormal.

Images