Configuration-free and maintenance-free method and system for relay protection and fault information substations

Abstract

Disclosed in the present application are a configuration-free and maintenance-free method and system for relay protection and fault information substations, relating to the technical field of computer platform load balancing. The method comprises: acquiring all network node information by means of a relay protection and fault information master station, and constructing a network topology diagram; marking a newly added node in the network topology diagram; establishing communication with the marked network node, and uploading the original version of all data of the marked network node to a secure area I by means of a dispatching data network; performing account configuration on a plant side relay protection and fault information substation, and downloading configuration file data to the relay protection and fault information substation; parsing a packet at the relay protection and fault information master station; and establishing a protocol library at the relay protection and fault information master station, and performing protocol conversion and data parsing on the original version packet uploaded by the newly added node. The configuration-free and maintenance-free method for relay protection and fault information substations provided by the present application allows for the data received by the relay protection and fault information master station being completely consistent with the raw data of the plant side, thereby improving the working efficiency and reducing the working cost.

Description

Relay protection fault information substation configuration-free maintenance method and system TECHNICAL FIELD

[0001] The present application relates to the technical field of computer platform load balancing, in particular to a relay protection fault information substation configuration-free maintenance method and system. BACKGROUND

[0002] The relay protection fault information management system collects real-time / non-real-time operation, configuration and fault information of devices such as relay protection devices of a substation, provides a unified analysis platform for the relay protection devices, is beneficial to the dispatching department to quickly master the actual fault state of the power grid and the relay protection action behavior, timely analyze the power grid accident, correctly judge and quickly recover the system, and master the state of the relay protection device, effectively analyze the relay protection action, and improve the dispatching management and operation management level. The relay protection fault information substation is arranged at the plant station end, can collect real-time or non-real-time operation, configuration and fault information of intelligent devices such as relay protection devices and wave recorders in the substation, realize model analysis of different manufacturers, protocol conversion, information uploading and other functions.

[0003] The traditional relay protection fault information substation configuration method is to call the configuration file of the relay protection fault information substation at the plant station end, modify the configuration file through the configuration tools and configuration models of each relay protection fault information substation manufacturer, and the configuration content includes but is not limited to IP address, protocol type, data type, unit and other standardized configurations. After being modified by the staff, the configuration file is downloaded to the relay protection fault information substation, and after restarting, the relay protection fault information substation configuration file update and application can be realized.

[0004] The traditional relay protection fault information substation maintenance method mainly consists of the patrol of the appearance and running state of the relay protection fault information substation and the periodic backup of the configuration file.

[0005] The traditional relay protection fault information substation configuration and maintenance method mainly has the following problems:

[0006] 1. In the process of modifying the configuration file of the relay protection fault information substation, configuration errors, non-standard and non-uniform configurations are easily caused by on-site human errors, which leads to distorted and unrealistic data sent to the relay protection fault information master station. After the data sent by the plant station is configured in the relay protection fault information substation, there is a certain difference between the data received by the relay protection fault information master station and the original data of the plant station, and the data fidelity rate is only 90%.

[0007] 2. The maintenance and configuration tools of relay protection fault information substations of different manufacturers are not the same, and each maintenance and configuration tool cannot be used universally.

[0008] 3. When configuring 103 communication protocol, it is necessary to model through relay protection fault information substation, but different manufacturers relay protection fault information substation modeling ability exists difference, the data format, data authenticity, error rate after modeling are not the same according to equipment hardware parameters and software iteration, leading to serious shortage even unable to carry out for the high-level application development of data.

[0009] 4. When the fault and abnormal condition of relay protection fault information substation occur, the data sent by the station end cannot be configured at the main station end, when the data is interrupted, the full link cannot be checked quickly at the main station end, the communication interruption reason cannot be judged quickly, and the data sending accuracy of the substation cannot be monitored at the main station end in daily maintenance.

[0010] In summary, a relay protection fault information substation configuration-free and maintenance-free method is urgently needed, which sends the data of the relay protection device in the station through the relay protection fault information substation as it is, so that the data fidelity rate reaches 100%. SUMMARY

[0011] In view of the above problems, the present application is proposed.

[0012] Therefore, the technical problem solved by the present application is to solve the problem that the configuration tools of various substations of different manufacturers are different, and to realize data normalization processing for all protocols, check the full link at the main station end, and monitor the data accuracy of the substation.

[0013] To solve the above technical problems, the present application provides the following technical scheme: a relay protection fault information substation configuration-free and maintenance-free method, comprising:

[0014] Obtain all network node information through the relay protection main station, and build a network topology graph;

[0015] Mark the new node in the network topology graph;

[0016] Establish communication with the marked network node, and send all data of the marked network node to the safety I area through the dispatching data network;

[0017] Configure the station end relay protection fault information substation, and download the configuration file data to the relay protection fault information substation;

[0018] Parse the message at the relay protection main station;

[0019] Establish a protocol library at the relay protection main station, and convert the protocol and analyze the data for the original version of the message sent by the new node;

[0020] The obtaining all network node information comprises automatically discovering a newly added network node, aggregating all network nodes and neighbor information of the relay protection system through a message passing mechanism, and updating a feature representation of the node, wherein the feature representation of each known node represents information of adjacent nodes of the each known node;

[0021] The constructing network topology graph comprises constructing a node feature matrix H l) , representing an initial feature of each node in the relay protection system, l represents a layer number, an interval layer between station terminals is a 0th layer, a relay protection substation of the station terminal is a 1st layer, and a relay protection master station is a 2nd layer, l is an integer and l<=2;

[0022] An adjacent matrix A is established, and the adjacent matrix A is used to represent a connection relationship between nodes in a graph;

[0023] Information of adjacent nodes is aggregated through an aggregation graph convolution layer, and a node feature is updated, and the node feature is represented as,

[0024] Wherein, I N represents an N-dimensional unit matrix, A represents an adjacent matrix, represents a sum of the adjacent matrix A and the unit matrix I N , is a degree matrix of the adjacent matrix A, is an elementization application of the adjacent matrix A, i is a horizontal element in the matrix, j is a vertical element in the matrix, H (l) is a 1st layer node feature matrix, W (l) represents a weight matrix of the 1st layer, N represents a dimension of a matrix, D represents a standard value of the adjacent matrix A, H (0) =X, and H (2) =Z, X represents a basic feature of a node of a relay protection device of a 0th layer, Z represents a feature received by a relay protection master station of a 2nd layer after passing through a 1st layer, and ReLU is an activation function; An activation matrix of a newly added node is represented by H (l+1) , and information of the newly added node is output.

[0025] As a preferred scheme of the relay protection fault information substation maintenance-free method, wherein: the marking of the newly added node in the network topology graph comprises collecting and determining information of the newly added node to be marked, and distinguishing the newly added node from original network nodes in a color coding and text label manner;

[0026] The information of the newly added node is represented as,

[0027]

[0028] ​Where X represents the basic characteristics of the node of the relay protection device at layer 0, Z represents the characteristics received by the main station of the second layer after passing through layer 1, Y represents the label of the newly added node, and softmax and ReLU represent the activation functions respectively.

[0029] The color coding includes marking newly added nodes as red and existing nodes as green; the text label mainly includes parsing the IP of the newly added node, finding the network path of the plant station by looking up the routing protocol information of the plant station, finding the corresponding record in the routing table to determine the plant station, and labeling the newly added network node with the corresponding plant station name.

[0030] As a preferred embodiment of the relay protection fault information substation configuration-free and maintenance-free method of the present invention, wherein: the establishment of communication with the marked network node includes adopting TCP packet format and adding TCP packet header and packet trailer;

[0031] The TCP segment includes a preparatory segment and a data segment. The preparatory segment is a parameter in the TCP header used to establish communication between the master station, the substation, and the marked node. The target IP address in the TCP segment is represented in dotted decimal notation, divided into 4 segments of 8 bits each. Each byte in the segment represents a segment, with the lowest byte representing 25-32 bits and the highest byte representing 1-8 bits. When a segment needs to record all target IP addresses, the target IP is filled with 0.

[0032] In the target port number, the least significant byte comes first and the most significant byte comes last. When it is necessary to record all packets with all target port numbers, the target port number should be filled with 0.

[0033] The TCP header includes source port number, destination port number, sequence number, acknowledgment number, receive window, header fields, and option fields. It specifies the message length when establishing communication. The data segment message contains the data interaction between the marked new node and the protection master station. The data segment message contains all the data information of the protection device of the marked new node. The data is sent up in its original form after adding the TCP header. The TCP header is applicable to all relay protection protocols.

[0034] As a preferred embodiment of the relay protection fault information substation configuration-free and maintenance-free method of the present invention, the following steps are included: configuring the substation's information protection substation in the ledger includes configuring the port number and IP information of newly added nodes at the substation based on the source port number, destination port number, and IP address option fields in the TCP pre-segment message, combined with work ticket information and ( O The maintenance application data in the MS system includes the configuration interval name, protection model, and protection type information for the new node. Finally, the Baoxin substation ledger is configured in the Baoxin master station.

[0035] The lower configuration file data to the sub-station is dynamically negotiated by both sides of the communication based on the flow control technology sliding window size, in the establishment of TCP connection stage, the main station and the sub-station negotiate window size, at the same time, the main station reserves data buffer area;

[0036] The main station fills in the window size size1 in the transmission flag of ASDU105 message, and the sub-station fills back the size size2 that can be accepted in the transmission flag of the answer ASDU106 message, but must not exceed the size given by the main station; the main station sends size2 ASDU107 messages at one time, and waits for the ASDU108 message of the sub-station at one time;

[0037] The sub-station sends the data byte stream conforming to the window size according to the negotiation result, obtains the congestion degree n by using Markov decision process model, judges whether the congestion state appears, if the congestion state is judged, the window is reduced to 0.1x(10-n) times of the original, wherein n is the congestion degree of data, and the time interval of the time-out retransmission is expanded by 0.2n times.

[0038] As a preferred scheme of the relay protection fault information sub-station configuration-free maintenance method, wherein: the message analysis in the main station includes removing the TCP message head and tail in the main station, and obtaining the original data message of the new node, and the original data message refers to the original data of the protection device without configuration;

[0039] The protocol library includes the protocol analysis of all relay protection manufacturers in each stage in the main station, and the data of the relay protection device is classified, modeled and uniformly configured by using the protocol conversion technology.

[0040] Another object of the application is to provide a relay protection fault information sub-station configuration-free maintenance system, which can solve the problem that the maintenance and configuration tools of the traditional relay protection fault information sub-station maintenance system are different for different manufacturers, and the various maintenance and configuration tools cannot be universal.

[0041] To solve the above technical problems, the application provides the following technical scheme: a relay protection fault information substation configuration-free maintenance system, comprising a data acquisition module, a node marking module, a node communication module, a station account configuration module, a message analysis module and a protocol analysis module; the data acquisition module is used to acquire all network node information through a relay protection master station and construct a network topology graph; the node marking module is used to mark new nodes in the network topology graph; the node communication module is used to establish communication with the marked network nodes, and the marked network nodes send all original data of the marked network nodes to a safety I area through a dispatching data network after adding a TCP message head and tail to a TCP message; the station account configuration module is used to configure a station account of a relay protection substation at a power station end and download configuration file data to the relay protection substation; the message analysis module is used to analyze messages at the relay protection master station; and the protocol analysis module is used to establish a protocol library at the relay protection master station, and convert protocols and analyze data for original messages uploaded by new nodes.

[0042] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the relay protection fault information substation configuration-free maintenance method when executing the computer program.

[0043] A computer readable storage medium stores a computer program, and the computer program implements the steps of the relay protection fault information substation configuration-free maintenance method when executed by a processor.

[0044] The relay protection fault information substation configuration-free maintenance method provided by the application avoids the problems of configuration errors, non-standard configurations and non-uniform configurations caused by on-site manual errors during the process of modifying the configuration file of the relay protection fault information substation at the power station end, and realizes that the data received by the relay protection fault information master station is completely consistent with the original data at the power station end, and the data fidelity rate and the data standardization rate reach 100% after the data uploaded by the power station end is converted and configured in the relay protection fault information master station.

[0045] Through configuration-free and maintenance-free at the power station end, the problem that the maintenance and configuration tools of relay protection fault information substations of different manufacturers are different and not universal is eliminated, a unified protocol conversion library is adopted at the master station end, and the efficiency is higher.

[0046] Through configuration-free and maintenance-free at the power station end, the master station end establishes a protocol conversion library, reduces the requirement for the performance of the equipment at the power station end, avoids the differences in the modeling capabilities of relay protection fault information substations of different manufacturers, and ensures that high-level application development of data can be carried out.

[0047] The relay protection fault information substation is maintained free of charge by the station end, network nodes are automatically discovered and added in the relay protection network, the related staff is avoided from close combat, the different relay protection manufacturers' protocols, different communications and complex substation configurations are eliminated by the main station end large protocol library, the unified configuration tool is difficult to solve the problem, the work efficiency is improved, and the work cost is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0049] Fig. 1 is a whole flow chart of a relay protection fault information substation configuration-free maintenance method provided by an embodiment of the present application.

[0050] Fig. 2 is a whole structure diagram of a relay protection fault information substation configuration-free maintenance system provided by a second embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0052] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0053] Embodiment 1

[0054] Referring to Fig. 1, an embodiment of the present application provides a relay protection fault information substation configuration-free maintenance method, which comprises:

[0055] When a new interval is accessed in the relay protection fault information substation, the relay protection fault information substation configuration-free maintenance method mainly comprises: daily operation and relay protection fault information substation configuration-free maintenance method of new node;

[0056] The relay protection fault information substation configuration-free method of new node comprises:

[0057] S1: Obtain all network node information through the main network information platform and construct a network topology map.

[0058] Network nodes are relay protection devices connected to the power plant terminal information protection substation in the power system. Each relay protection device has an IP address, which is a unique network node.

[0059] The acquisition of all network node information includes automatically discovering new network nodes, aggregating all network nodes and their neighbor information in the security system through a message passing mechanism, updating the feature representation of nodes, and using the feature representation of each known node to represent the information of its neighboring nodes.

[0060] The construction of the network topology graph includes constructing the node feature matrix H. (l) , represents the initial characteristics of each node in the information protection system, l represents the layer number, the station-end interval layer is the 0th layer, the station-end information protection substation is the 1st layer, the information protection main station is the 2nd layer, l≤2 and is an integer;

[0061] Establish an adjacency matrix A, and use the adjacency matrix to represent the connection relationship between nodes in the graph;

[0062] The aggregation graph convolutional layer aggregates information from neighboring nodes and updates node features, as shown below.

[0063] Among them, I N Let A denote the N-dimensional identity matrix, and let A denote the adjacency matrix. Represent the adjacency matrix A and the identity matrix I N The sum of, yes The degree matrix, for The elemental application, where i is the horizontal element in the matrix, j is the vertical element in the matrix, and H (l) W is the feature matrix of the first-layer nodes. (l) This represents the weight matrix of layer 1. N represents the dimension of the matrix, D represents the standard value of the adjacency matrix A, and H represents the standard value of the adjacency matrix A. (0) =X,H (2) =Z, where X represents the basic characteristics of the node of the relay protection device at level 0, Z represents the characteristics received by the level 2 information protection master station after passing through level 1, and ReLU is the activation function;

[0064] Through H (l+1) The activation matrix represents the newly added node, and the information of the newly added node is output.

[0065] Considering Unnormalized and related to H (l) Performing multiplication will change the original feature distribution, affecting... The normalized matrix is represented as The normalization processing makes the processed matrix used for balancing the contribution of different degree station end protection device nodes to the aggregation of new node information.

[0066] The node feature matrix obtained by the main station of the signal protection station is superimposed with the network node information, which can effectively represent the activation matrix of the new node, and further determine the information of the new node. The conventional method for obtaining the new node information is usually obtained manually. The method automatically obtains the new node information through the algorithm of the node feature matrix, solves the problem that the main station personnel cannot automatically configure the new node through the algorithm, and further improves the work efficiency of obtaining the new node data.

[0067] S2: marking the new node in the network topology graph.

[0068] The marking of the new node in the network topology graph includes collecting and determining the information of the new node to be marked, substituting X and Z in S1 into S2 to obtain a label, and using color coding and text label to distinguish from the original network node;

[0069] The information of the new node is represented as

[0070] Wherein, X represents the basic feature of the node of the relay protection device of the 0th layer, Z represents the feature received by the main station of the signal protection station after the 1st layer, Y represents the label of the new node, softmax and ReLU represent activation functions respectively, the function of softmax is to convert the known node information of the relay protection device into the probability distribution of the new node, and the function of ReLU is to perform nonlinear transformation on the known node information of the relay protection device.

[0071] The traditional method is to manually increase the new node information and manually enter. According to the known node information, the method automatically obtains the new node information, and then automatically obtains the primary equipment name in combination with the OMS system and the power grid management platform.

[0072] The color coding includes marking the new node with red color and marking the original node with green color; the text label mainly includes analyzing the IP of the new node, confirming the network path of the belonging station by searching the information of the routing protocol of the substation of the signal protection station, and determining the belonging station in combination with the corresponding record in the routing table.

[0073] When a new station is added, if multiple network nodes cannot be matched to the corresponding station, then the IP of each new node is directly compared, the consistency of the IP is found by analyzing the routing forwarding table, the matching consistent IP is marked with the label of the new station, and the above new nodes are classified into the same new station.

[0074] The station label of the new station is determined by importing the maintenance application and work ticket data of the power grid management platform through the secondary intelligent operation and maintenance platform combined with the OMS system, and the substation name is determined. The secondary intelligent operation and maintenance platform at least includes a signal main station and has the function of interacting with the OMS system and the power grid management platform system.

[0075] The imported maintenance application and work ticket data of the power grid management platform includes the first step of intercepting all maintenance application information and work ticket information in the new connection time period, the second step of preliminarily screening the text information in the work ticket and the maintenance application, and the third step of further screening the work ticket and the maintenance application information containing the selected field "add", "transform", and "replace". The substation name and the primary equipment name of the new interval name in the above maintenance application and work ticket are extracted and given to the new node.

[0076] The OMS system at least has a maintenance application function, and the power grid management platform system at least has a work ticket function.

[0077] The new node is distinguished from the conventional node by color coding and text marking, and the substation name and the interval name of the new node are determined by combining the work ticket data of the power grid management platform and the maintenance application data of the OMS system. The substation name and the primary equipment name of the new interval do not need to be manually input, and the primary equipment account can be directly generated, which is convenient for subsequent communication and modeling.

[0078] In the color coding and text marking method of the conventional node, the text is generally manually input. Compared with the conventional node marking method, the method can obtain the work ticket data of the power grid management platform and the maintenance application data of the OMS system through the dispatching data network, and automatically identify the substation name and the interval name of the new node.

[0079] S3: Establish communication with the marked network node, and upload all data of the marked network node to the safe I area through the dispatching data network.

[0080] The data original is the data uploaded by the station end protection device.

[0081] The safe I area represents the production control area of the dispatching data network, and is used for the production and control business data flow of the power system.

[0082] The original version of the method is to use TCP message format, increase TCP message header, message tail, and the data between the header and the tail are the same as the original data.

[0083] The TCP message includes a preparation message segment and a data message segment. The preparation message segment is a parameter of the TCP message header for establishing communication transmission between the master station, the substation and the marked node. The target IP address in the TCP message is represented in "decimal point" form, with each 8 bits being a segment, a total of 4 segments. Each byte in the message represents a segment, with the lowest byte representing 25-32 bits and the highest byte representing 1-8 bits. When recording all target IP addresses, the target IP is filled with 0. The data message segment is the data received by the sending.

[0084] In the target port number, the low bits are in the front and the high bits are in the back. When recording all target port numbers, the target port number is filled with 0.

[0085] The TCP message header includes the source port number, the destination port number, the sequence number, the acknowledgement number, the receive window, the header field, and the option field. The length of the message is specified when the communication is established. The data segment message contains the data interaction between the marked new node and the protection master station. The data segment message contains all the data information of the protection device of the marked new node. The data is sent to the original version after adding the TCP message header. The TCP message header is applicable to all relay protection protocols.

[0086] The conventional protection substation data sending method is to perform protocol conversion, data analysis and modeling in the protection substation, and then send the data to the master station. The difference between this step and the conventional protection substation data sending method is that the TCP message header and tail are added to unify the data format of different protocols and different formats. That is, regardless of the content between the header and the tail, the format can be unified by adding the same header and tail. At the same time, the data in the TCP message does not need to be changed, thereby realizing the relay protection substation without protocol conversion, analysis and modeling at the station end, greatly saving the workload at the station end, and avoiding the setting of protocols, models and accounts at the station end.

[0087] S4: Configure the account of the protection substation at the station end and download the configuration file data to the protection substation.

[0088] The account configuration of the protection substation at the station end includes configuring the port number and IP information of the new node at the station end according to the source port number, destination port number and IP address option field information in the TCP preparation segment message, configuring the interval name, protection model and protection type information of the new node in combination with the work ticket information and the maintenance application data information in the OMS system, and finally configuring the protection substation account at the protection master station.

[0089] The lower configuration file data to the sub-station uses the dynamic negotiation of sliding window size between the two sides of communication, and the communication process is as follows: the main station fills the window size size1 in the transmission mark of ASDU 105 message, the sub-station fills the size size2 which can be accepted in the transmission mark of the answer ASDU 106 message, but it must not exceed the size given by the main station; then the main station sends size2 ASDU 107 messages at a time, and waits for the confirmation of the sub-station.

[0090] The lower configuration file data to the sub-station uses the dynamic negotiation of sliding window size between the two sides of communication based on flow control technology, which enables the sub-station to send multiple data packets from the station at the same time without receiving the confirmation from the main station, thereby greatly improving the network throughput.

[0091] In the TCP connection establishment stage, the main station and the sub-station negotiate the window size, and the main station reserves the data buffer area, and the specific negotiation process is as follows: the main station fills the window size size1 in the transmission mark of ASDU 105 message, the sub-station fills the size size2 which can be accepted in the transmission mark of the answer ASDU 106 message, but it must not exceed the size given by the main station; then the main station sends size2 ASDU 107 messages at a time, and waits for the confirmation of the sub-station.

[0092] The sub-station sends the data byte stream according to the negotiated result, obtains the congestion degree n, judges whether the congestion state appears, if the congestion state is judged, the window size is reduced to 0.1×(10-n) times of the original, wherein n is the congestion degree of data, and the time interval of retransmission is expanded by 0.2n times.

[0093] The main station integrates the data, determines the negotiation window size, network flow data and data buffer area state based on the source port number, destination port number and IP address option.

[0094] The source port number is the port number used by the source device in the TCP connection, which is obtained from the source port field of the TCP preparation segment message.

[0095] The destination port number is the port number used by the target device in the TCP connection, which is obtained from the destination port field of the TCP preparation segment message.

[0096] The IP address option contains the additional IP address option information configured by the network device, which is obtained from the IPP address option field of the TCP preparation segment message.

[0097] The window size is the TCP window size determined in the TCP connection establishment stage based on the source port number, destination port number and IP address option.

[0098] Determined by the exchange of ASDU 105 and ASDU 106 messages between the primary station and the secondary station, taking into account the maximum acceptable window size of both parties.

[0099] Network traffic data is real-time network traffic data monitored in TCP connections, obtained by analyzing the data byte stream exchanged between the primary station and the secondary station (ASDU 107 and ASDU 108 messages).

[0100] Data buffer status is the current status of the data buffer reserved for the primary station. Based on the ASDU 108 message confirmation reply of the secondary station, the usage of the buffer is updated.

[0101] Apply Markov decision process model:

[0102] The system state is defined by the data buffer status, network traffic data and window size, integrating network parameters to provide the necessary context for decision-making, represented as: State(t) = (Buffer status (t), Traff i c data (t), Size config (t))

[0103] Where State(t) represents the state at time t, t represents the time variable, represents a specific state or action at time t, Buffer status (t) represents the data buffer status at time t, indicating the usage of the primary station's buffer, Traffic data (t) represents the network traffic data captured at time t, reflecting the real-time data flow between the primary station and the secondary station, Size config (t) represents the TCP window size determined at time t according to the negotiation, based on port and IP configuration determined during connection establishment.

[0104] Based on the current state, select an action strategy to optimize TCP window size or adjust retransmission time strategy to respond to real-time network conditions and expected changes.

[0105] Define state transition function and reward function to quantify the change in state after each action and the benefits and costs of the action.

[0106] The transition function describes the change in state after taking action, represented as: T(State(t), Action(t))→State(t+1)

[0107] Where T represents the state transition function, describing the change in state after taking action, Action(t) represents the action taken at time t based on the current state, aiming to optimize network performance.

[0108] The reward function evaluates the reward or cost obtained as a result of the action, denoted as R(State(t), Action(t)) = -Cost of Congestion + Performance Benefit

[0109] where R denotes the reward function, which evaluates the reward or cost obtained as a result of the action, Cost of Congestion quantifies the negative impact due to network congestion, and Performance Benefit represents the positive benefit obtained as a result of the optimized action.

[0110] The congestion metric is quantified according to the computed expected reward, denoted as C(t) = -R(State(t), Action(t)) + γR(State(t+1), Action(t+1))

[0111] where C(t) denotes the congestion metric at time t, max Action denotes the selection of an action among all possible actions that maximizes the subsequent expected value, denotes the expectation operator, which computes the expected value of a random variable given a strategy and an action, denotes the summation symbol, which is used to accumulate values from time t to T (the termination time of the decision), and γ τ-t denotes the exponential form of the discount factor, which is a value between 0 and 1 that is used to reduce the importance of future rewards relative to immediate rewards. This factor ensures that the model is more sensitive to upcoming state changes, R(State(τ), Action(τ)) denotes the reward function, which evaluates the reward or cost obtained as a result of the action Action(τ) taken at time τ and the state State(τ) in which the system is, τ denotes a time index that is used to iterate over each time point from t to T, T denotes the termination time point, and denotes the limits within which decisions and evaluations are made within the time range t to T.

[0112] C(t) is normalized to a scale of 0-10, denoted as n = (C(t) - min(C)) / (max(C) - min(C)) * 10

[0113] where n denotes the normalized congestion metric, which has a value ranging from 0 to 10, min(C) denotes the minimum possible value of the congestion metric C(t), and max(C) denotes the maximum possible value of the congestion metric C(t).

[0114] If n ≥ 5, the congestion state is determined, and the sending window is reduced to 0.1 * (10 - n) times the original size, while the time interval for timeout retransmission is expanded by 0.2n times.

[0115] The sending window size is dynamically adjusted according to the value of the congestion indicator n. As n increases, i.e. the network congestion intensifies, the sending window decreases more significantly, reducing the number of data packets in the network and helping to alleviate congestion.

[0116] In high congestion situations, significantly reducing the sending window can prevent too much data from being transmitted simultaneously in the network, thereby reducing the packet loss rate and avoiding congestion spirals, preventing continuous data loss and further congestion caused by retransmission.

[0117] By directly linking n to window size adjustment, a method of precisely controlling traffic is provided, which can adjust the transmission rate according to real-time network conditions.

[0118] In lower congestion, a larger window is maintained to utilize available bandwidth, while in increasing congestion, the window is reduced, reducing packet loss and retransmission, thereby improving the utilization of network resources.

[0119] As the congestion indicator n increases, increasing the retransmission time interval can reduce the case of misjudging a short delay as a packet loss, and in network congestion, avoiding unnecessary retransmission can significantly reduce network burden.

[0120] By appropriately expanding the retransmission time interval, more time is allowed for data packets to reach their destination, especially in congested network environments, improving overall data transmission efficiency.

[0121] By adjusting the retransmission time according to the congestion level, the network can better adapt to changing network conditions, and expanding the retransmission time interval helps to reduce invalid and redundant retransmissions caused by misjudging the network state.

[0122] Traditional network congestion determination methods mainly determine by judging packet loss rate, delay measurement and bandwidth utilization.

[0123] In packet loss rate determination, the packet loss rate is monitored to determine if the network is congested. If the packet loss rate exceeds a certain threshold, it is considered that the network is congested. This method is simple and intuitive, but it cannot accurately reflect all types of network congestion, as packet loss can be caused by a variety of reasons, such as network configuration errors, hardware failures, etc.

[0124] Another method is to measure the round-trip time (RTT) of data packets. An increase in RTT usually means an increase in congestion on the network path. However, changes in RTT can also be caused by changes in links, routing optimization, and other factors, not just congestion.

[0125] By monitoring the bandwidth usage of the network to determine congestion. If the network traffic approaches or reaches the upper limit of the network bandwidth, it is considered that the network is congested. This method relies on accurate bandwidth measurement and may not be sensitive enough in a dynamically changing network environment.

[0126] These traditional methods, while effective in certain scenarios, are not timely or accurate enough in responding to network conditions under the complex network architecture and high-variability traffic conditions faced by the relay protection fault information substation.

[0127] The method of the present application dynamically adjusts network decisions by applying Markov Decision Process (MDP), not just based on static thresholds or single parameters, but considering multiple network state indicators. This makes the decision-making process more accurate and adaptable, enabling optimal responses to actual network conditions.

[0128] By integrating data buffer state, real-time traffic data, and window size parameters, a comprehensive network state view is provided, understanding and predicting network congestion. Compared to traditional methods, it can capture early signs of congestion.

[0129] Network management is no longer dependent on experience or simple thresholds, but a quantitative and adjustable process. Automatically adapt to changes in network conditions, real-time adjustment of network parameters to optimize performance.

[0130] Adjusting the sending window size to reduce the sending window to 0.1x(10-n) times is to reduce network load. In the early stage of network congestion, reducing the sending window can directly reduce the data transmission rate and reduce the number of data packets in the network. Directly respond to the current load of the network, prevent buffer overflow and router queue too long by reducing the amount of data sent, thereby avoiding causing more packet loss and delay. Dynamic balance of network traffic, by dynamically adjusting the window size, flexible adjustment of transmission rate according to real-time network state, not only alleviates the immediate network pressure, allows rapid recovery of transmission capacity when network conditions improve, maintains network throughput in the optimal state. Improve network efficiency and stability, the strategy of reducing window size, although it may cause network throughput to decline in the short term, but in the long run, helps to avoid excessive congestion of the network, reduces the additional burden caused by frequent packet loss and retransmission. Ultimately, the network runs more smoothly and stably.

[0131] The extended timeout retransmission time interval is extended by 0.2n times in order to adapt to network delay changes. When the network is congested, it is usually accompanied by an increase in delay. By extending the timeout retransmission time, the increase in delay can be adapted to, and unnecessary retransmission can be avoided when the data packet is actually still in transit. This strategy directly responds to changes in network delay, reduces retransmission due to misjudgment of delay, and thus reduces network load. Optimizing data transmission and network load, extending the retransmission time interval helps to reduce the additional network load caused by retransmission during network congestion. This method optimizes the data flow of the entire network by reducing repeated data transmission caused by congestion. Reducing unnecessary retransmission can effectively utilize network resources and improve the overall data transmission efficiency of the network. Maintaining the overall performance of the network, in the long run, reasonable setting of the retransmission time interval helps to maintain the network performance, avoids congestion deterioration, and ensures reliable data transmission, which helps the network to face unstable or unpredictable network conditions.

[0132] By intelligently adjusting the sending window and retransmission strategy, the use of network resources is optimized, the stability and reliability of the network are enhanced, and it is particularly suitable for the environment of the present application to reduce service interruption and delay caused by network problems.

[0133] The traditional stop-and-wait protocol requires each frame to be sent by the protected station to be stopped and waited for the confirmation of correct reception by the protected master station before the next frame can be sent. Compared with the traditional stop-and-wait protocol, the dynamic negotiation of sliding window size between the two communicating parties based on flow control technology can effectively improve the channel utilization by first negotiating and uploading all data, and simultaneously adjusting the window size according to the network state and adjusting the unconfirmed data.

[0134] The next bit flag in the download message is 0, indicating that the ASDU 107 transmission is complete;

[0135] The starting transmission position in the download message is the offset after block division according to the file size;

[0136] The transmission length of the message in the traditional communication establishment method has an upper limit, generally x bytes. When the byte limit is exceeded, the message will be parsed incorrectly. The communication transmission using the present method can dynamically negotiate between the two communicating parties according to the window size size1 set in the transmission flag of the ASDU 105 message and the size2 accepted by the ASDU 106 message to avoid exceeding the transmission byte limit as much as possible.

[0137] The difference between this step and the conventional account configuration is that the account of the newly added node is configured by combining the maintenance application data in the OMS system and the work ticket data of the power grid management platform, so as to avoid manual entry of account information.

[0138] The above is a preferred scheme of the message downloaded by the account configuration file, and the message mode for the account configuration file: / CONF / IEDList.xml is agreed to realize the downloading of the configuration file by the master station to the protection substation.

[0139] The account configuration file: / CONF / IEDList.xml.

[0140] The master station: ASDU 200 (communication with the device). The configuration content is shown in Table 1.

[0141] Table 1 shows the message mode of the communication message of the master station to the lower station:

[0142] S5: The master station of the protection analyzes the message;

[0143] The analysis of the message by the master station of the protection includes analyzing the message by the master station of the protection, removing the TCP message header and tail, and obtaining the original version data message of the new node. The original version data message refers to the original version data of the protection device without configuration, which can reflect the true situation of the protection device data and avoid the data distortion caused by the manual error configuration of the station end.

[0144] The difference between this step and the conventional data transmission of the protection substation is that the original version message and data of the protection device of the station end can be obtained by removing the TCP message header and tail after receiving the data of the station end, which effectively avoids the problems of data distortion and error code of the station end, and the station end does not need to configure the protection substation, thereby avoiding the problem of data uploading error caused by manual configuration error.

[0145] S6: The master station of the protection establishes a protocol library and performs protocol conversion and data analysis on the original version message uploaded by the new node.

[0146] The master station protocol library includes all stages of the protocols of the relay protection manufacturers, such as the NARUI 103 protocol, the SIFANG 103 protocol, the 61850 protocol, etc. The protocol analysis is performed at the master station, the existing protocol conversion technology is adopted, the data of the relay protection device is classified, modeled and uniformly configured.

[0147] The difference between this step and the conventional protocol conversion method is that the conventional protocol conversion is performed by the protection substation at the station end, and this method establishes a protocol library at the master station, fully utilizes the hardware resources of the master station, avoids the waste of resources, reduces the hardware configuration standard of the protection substation at the station end, saves the investment, and simultaneously realizes the original version uploading of the protection device message.

[0148] The maintenance-free method of the relay protection fault information substation in daily operation includes:

[0149] (1) Equipment state monitoring: Utilize temperature sensors and external substation equipment to monitor the running state of substation hardware (such as protection management machines, access devices, switches, etc.) and software health in real time, and upload these state information to the main station through communication interface.

[0150] Equipment state monitoring includes: collecting the temperature of the substation through an existing temperature sensor, judging the running state of the substation through the on-off state of the substation, for real-time detection and analysis of the comprehensive running state of hardware devices such as protection management machines, access devices, switches, etc. When the substation communication is interrupted, it is judged that the substation is abnormal. Combined with the temperature collected by the external substation, when the temperature is higher than the normal running temperature allowed value of the substation out of the factory, it is judged that the hardware of the substation is abnormal, and when the temperature is lower than the normal running temperature allowed value of the substation out of the factory, it is judged that the software of the substation is abnormal.

[0151] Real-time monitoring mechanism: Self-diagnosis and analysis function continuously collects state data of the above-mentioned hardware and software, ensuring rapid identification of potential faults or performance bottlenecks.

[0152] Communication interface and information transmission: An existing external substation uses standardized communication protocols (such as IEC61850, DL / T860, etc.) through a dedicated data interface to encrypt and package the real-time acquired hardware and software state information, and safely and reliably upload it to the main station.

[0153] Main station processing and display: After receiving the state data sent by the substation, the main station analyzes and integrates it, forms a detailed equipment file in the background database, and at the same time displays the hardware and software running state of each substation in a visual way on the operation and maintenance platform interface, providing basis for operation and maintenance decision.

[0154] (2) Remote access and control: Establish an independent operation and maintenance port in the substation, support establishing operation and maintenance channels with multiple main stations. The main station can realize functions such as downloading, uploading files, issuing configuration effective commands, executing network packet capture, and calling logs through the operation and maintenance channel.

[0155] The main station operation and maintenance personnel can remotely log in to the substation through the secondary intelligent operation and maintenance platform, and perform configuration management, software version update, fault troubleshooting and other operations. At the same time, a set of remote access mechanism based on double-factor authentication is established, including user identity verification and device authorization verification. When logging in through the secondary intelligent operation and maintenance platform, the user needs to input the username and password, and perform secondary verification through dynamic password or biometric identification. Only the legal user who passes the verification can obtain access permission to the specified substation.

[0156] (3) Remote data backup: Regular or on-demand remote data backup ensures that the substation system can quickly recover to normal operation state when necessary.

[0157] The remote data backup for the relay substation includes: periodic triggering of the remote backup and event triggering of the remote backup, the periodic triggering of the remote backup refers to that the relay substation collects and processes various protection information in real time, sets a period for remote data backup, and sends the data of the relay substation to the relay master station through the dispatching data network after encryption according to a preset period. The event triggering of the remote backup refers to that after the station end accident tripping, the relay substation calls data of the corresponding accident tripping device and sends it to the memory of the relay master station to form a data backup set.

[0158] Embodiment 2

[0159] Referring to FIG. 2, according to an embodiment of the present application, a relay protection fault information substation configuration-free maintenance system is provided, comprising:

[0160] a data acquisition module, a node marking module, a node communication module, a station account configuration module, a message analysis module and a protocol analysis module;

[0161] The data acquisition module is used to acquire all network node information through the relay master station and construct a network topology map;

[0162] The node marking module is used to mark the newly added nodes in the network topology map;

[0163] The node communication module is used to establish communication with the marked network nodes, and the marked network nodes send all original data of the marked network nodes to the safety I area through the dispatching data network after adding a TCP message head and tail through a TCP message;

[0164] The station account configuration module is used to configure the station end relay substation and download configuration file data to the relay substation;

[0165] The message analysis module is used to analyze the message at the relay master station;

[0166] The protocol analysis module is used to establish a protocol library at the relay master station, and perform protocol conversion and data analysis on the original message uploaded by the newly added nodes.

[0167] Embodiment 3

[0168] An embodiment of the present application is different from the previous two embodiments in that:

[0169] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0170] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or in conjunction with these instructions execution systems, apparatus or devices. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in connection with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0171] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting or otherwise processing, if necessary, in other suitable ways, to be electronically obtained and then stored in the computer memory.

[0172] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0173] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all should be covered in the scope of the claims of the present application.

Claims

1. A method for maintenance-free configuration of a substation of a protective relay fault information, characterized in that, The application relates to a network topology construction method based on a relay protection system. All network node information is acquired by a main station of a relay protection system, and a network topology graph is constructed; Newly-added nodes in the network topology graph are marked; Communication is established with the marked network nodes, and all data original versions of the marked network nodes are sent to a safe I area through a dispatching data network; A station account of a substation of the relay protection system is configured, and a configuration file data is downloaded to the substation of the relay protection system; Messages are analyzed at the main station of the relay protection system; A protocol library is established at the main station of the relay protection system, and protocol conversion and data analysis are carried out on the original version messages uploaded by the newly-added nodes; The all network node information acquisition comprises automatically discovering newly-added network nodes, aggregating all network nodes and neighbor information of the relay protection system through a message transmission mechanism, and updating the characteristic representation of the nodes, wherein the information of the adjacent nodes of each known node is represented by the characteristic representation of the node; The constructing network topology includes constructing a node feature matrix H (l) , which represents the initial features of each node in the security system, l represents the number of layers, the interval layer between the station end is the 0th layer, the security sub-station of the station end is the 1st layer, the security main station is the 2nd layer, l≤2 and is an integer; An adjacent matrix A is established, and the adjacent matrix is used to represent the connection relationship between the nodes in the graph; The information of the neighbor nodes is aggregated and the node features are updated by the aggregation graph convolution layer, denoted as, where I N denotes the N-dimensional identity matrix, A denotes the adjacency matrix, denotes the adjacency matrix A and the identity matrix I N ​ is matrix of degrees, For of the elements of the matrix, i is a horizontal element within the matrix, j is a vertical element within the matrix, H (l) is the first layer node feature matrix, W (l) represents the weight matrix of the first layer, N represents the dimension of the matrix, D represents the standard value of the adjacency matrix A, H (0) = X, H (2) = Z, X represents the basic features of the nodes of the relay protection device of the 0th layer, Z represents the features received by the 2nd layer protection and communication master station after passing through the 1st layer, and ReLU is an activation function; By H (l+1 ) characterizing the activation matrix of the new node, outputting the new node information.

2. The maintenance-free configuration-free method for a protective relaying fault information substation as claimed in claim 1, wherein: The marking of the newly-added nodes in the network topology graph comprises collecting and determining the information of the newly-added nodes to be marked, and distinguishing the original network nodes by using color coding and text labels; The information of the new node is expressed as, X represents the basic characteristics of the nodes of the relay protection device of the 0th layer, Z represents the characteristics received by the main station of the relay protection system after the 1st layer, Y represents the label of the newly-added nodes, and softmax and ReLU represent activation functions respectively; The color coding comprises marking the newly-added nodes as red and marking the original nodes as green; the text label mainly comprises analyzing the IP of the newly-added nodes, confirming the network path of the corresponding station by searching the information of the routing protocol of the substation of the relay protection system, determining the corresponding station by searching the corresponding record in the routing table, and marking the label of the corresponding station name on the newly-added network nodes.

3. The maintenance-free configuration of a relay protection fault information substation according to claim 2, characterized in that: The communication establishment with the marked network nodes comprises using a TCP message format, adding a TCP message header and a message tail; The TCP message comprises a preparation message segment and a data message segment; the preparation message segment is a parameter for establishing communication transmission among the main station, the substation and the marked nodes; the target IP address in the TCP message is represented by a decimal point and divided into four segments, each byte in the message represents a segment, the lowest byte represents 25-32 bits, and the highest byte represents 1-8 bits; when all target IP addresses need to be recorded in the message, the target IP is filled with 0; In the target port number, the low bits are in front and the high bits are in back; when all target port numbers need to be recorded in the message, the target port number is filled with 0; The TCP message header comprises a source port number, a destination port number, a serial number, an acknowledgement number, a receiving window, a header field and an option field; the length of the message is defined when the communication is established; the data segment message comprises direct data interaction between the marked new nodes and the main station of the relay protection system; the data segment message is all data information of the protection device of the marked new nodes; the data is added with the TCP message header and then uploaded in the original version; and the TCP message header is applicable to all relay protection protocols.

4. The maintenance-free configuration of a relay protection fault information substation according to claim 3, characterized in that: The station account configuration of the station end protection substation includes configuring the port number and IP information of the newly added node of the station end according to the source port number, destination port number and IP address option field information in the TCP preparation section message, configuring the bay name, protection model and protection type information of the newly added node in combination with the work ticket information and the maintenance application data information in the OMS system, and finally configuring the station account of the protection substation in the protection main station; The configuration file data is downloaded to the protection substation by dynamically negotiating the sliding window size of both parties based on the flow control technology, the protection main station and the protection substation negotiate the window size in the TCP connection establishment stage, and the protection main station reserves a data buffer area; The protection main station fills in the window size size1 in the transmission flag of the ASDU 105 message, the protection substation fills back the size size2 that it can accept in the transmission flag of the reply ASDU 106 message, but the size must not exceed the size given by the protection main station; the protection main station downloads size2 ASDU 107 messages at a time, and waits for an ASDU 108 message from the protection substation for confirmation; The protection substation sends the data byte stream conforming to the window size according to the negotiation result, obtains the congestion degree n by applying the Markov decision process model, judges whether the congestion state occurs, and if the congestion state is judged to occur, the window is reduced to 0.1×(10-n) times of the original window, wherein n is the congestion degree of the data, and the time interval of the time-out retransmission is expanded by 0.2n times.

5. The maintenance-free configuration of a relay protection fault information substation according to claim 4, characterized in that: The message is parsed in the protection main station, the TCP message header and tail are removed, the original data message of the newly added node is obtained, and the original data message refers to the original data of the protection device without configuration; The protocol library includes parsing the protocol of each stage of each relay protection manufacturer in the main station, and using the protocol conversion technology to classify, model and uniformly configure the data of the relay protection device.

6. A system for maintenance-free method of substation of relay protection fault information according to any one of claims 1 to 5, characterized in that, It comprises: a data acquisition module, a node marking module, a node communication module, a station account configuration module, a message parsing module and a protocol parsing module; The data acquisition module is used to obtain all network node information through the protection main station and construct a network topology graph; The node marking module is used to mark the newly added node in the network topology graph; The node communication module is used to establish communication with the marked network node, and the marked network node sends all data original versions of the marked network node to the safety I area through the dispatching data network after adding the TCP message header and tail to the TCP message; The station account configuration module is used to configure the station account of the station end protection substation and download the configuration file data to the protection substation; The message parsing module is used to parse the message in the protection main station; The protocol parsing module is used to establish a protocol library in the protection main station, and convert the protocol and parse the data for the original message uploaded by the newly added node. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the relay protection fault information substation configuration-free and maintenance-free method in any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the method for configuring and maintaining the relay protection fault information substation according to any one of claims 1 to 5.

Images