A network parameter configuration verification method and system for a power station

Abstract

This invention discloses a method and system for verifying network parameter configurations in power plants, specifically relating to the field of parameter configuration verification technology. By constructing a hierarchical network model comprising device, subnet, and system layers, and combining this with a rule base to verify the consistency of static parameters, the basic correctness of the network configuration is validated. Subsequently, dynamic behavior is simulated using simulation tools to analyze the consistency and delay deviations of forwarding paths under different communication scenarios, evaluating the stability of communication paths under abnormal conditions. When instability is detected, the hierarchical partitioning model is used to gradually backtrack and locate the anomaly, accurately identifying erroneous configuration items from the system layer to the device layer. Based on the network configuration management system, correction suggestions are automatically generated, configuration updates are executed, and the correction effect is verified again through verification and simulation. This achieves accurate location and rapid repair of network configuration problems, effectively improving the reliability and stability of power plant communication networks in complex environments.

Description

Technical Field

[0001] This invention relates to the field of parameter configuration verification technology, and specifically to a method and system for verifying network parameter configuration in power plants. Background Technology

[0002] Network parameter configuration verification in power plants refers to the inspection and verification of communication network parameters within a power system to ensure the correctness, integrity, and consistency of the configuration, thereby guaranteeing the normal operation of the communication network. This technology is particularly important for the automation and stable operation of power systems, especially in smart grids and automated stations. In existing technologies, power plants typically rely on communication networks to transmit various data, such as protection information, monitoring data, and control commands. These network parameters include IP addresses, gateways, port numbers, routing policies, etc. Because power plant communication networks involve a large number of devices (such as protection devices, monitoring and control devices, and intelligent terminals) and complex topologies, network configuration errors can lead to communication failures or malfunctions. Traditional verification methods often rely on manual inspection or simple tools, but are prone to missed or false detections, especially when dealing with complex configurations. To address this issue, an increasing number of systems are introducing automated verification tools that improve verification efficiency and accuracy by comparing configuration files, simulating communication scenarios, or conducting real-time monitoring.

[0003] For example, in a smart power plant, a communication network is configured for protection devices and monitoring and control devices. This requires that each device's IP address be within a specific network segment and not conflict with others. Using a network parameter configuration verification tool, the system can automatically scan the configuration files of all devices, check whether the IP addresses conform to the specifications, and verify that the gateway settings are correct. If a device has an incorrect subnet mask or its IP address conflicts with other devices, the verification tool can quickly detect this and prompt for correction. Furthermore, when configuring Virtual Local Area Networks (VLANs), the verification tool can verify whether devices are correctly assigned to their designated VLANs, thereby avoiding the risk of unnecessary network broadcasts or data loss.

[0004] The existing technology has the following shortcomings:

[0005] In complex networks, there may be a need for communication between multiple subnets. Even if the IP configurations within each subnet are conflict-free, cross-subnet routing policies may lead to latent conflicts due to incorrect static route settings, route redundancy, or undetected loops. For example, communication data between two subnets may be unexpectedly forwarded through a third-party intermediary device (such as a switch or router), creating an unnecessary network broadcast storm. Furthermore, due to data flow anomalies caused by routing loops or broadcast storms, network parameter configuration verification tools may detect unexpected traffic paths or a large number of duplicate data packets. This may cause the tool to incorrectly identify network configuration conflicts (false positives) or fail to detect critical issues (missed detections) because it fails to capture the actual conflict paths. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for verifying network parameter configuration in power plants, in order to address the shortcomings in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for verifying network parameter configuration in power plants, comprising the following steps:

[0008] S1: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer;

[0009] S2: Based on the constructed network model, a rule base is used to perform consistency verification on static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration.

[0010] S3: After completing the static verification, simulate the dynamic behavior of the network in actual operation, generate data flow paths under different communication scenarios through simulation tools, judge the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compare the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data.

[0011] S4: Evaluate the stability of the communication path under abnormal conditions based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between the real-time traffic and the simulated data.

[0012] S5: When communication path becomes unstable, the detected anomalies are gradually traced back and located using the hierarchical partitioning model. The abnormal subnet is identified from the system layer, the abnormal configuration of the specific device is confirmed from the subnet layer, and finally the erroneous parameter configuration item is accurately located at the device layer.

[0013] S6: After anomaly localization is completed, generate correction suggestions, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, execute configuration updates through automated correction functions, and rerun static verification and dynamic simulation to verify the effectiveness of the correction.

[0014] Preferably, in S1, the device layer defines the IP address, subnet mask, gateway, and port number of each device; the subnet layer describes the routing policies and communication rules of each subnet; and the system layer is used to model the routing table, global topology, and protocol interaction across subnets.

[0015] Preferably, in S3, after analyzing the consistency of the forwarding path of the simulated data stream under different communication scenarios, a forwarding path anomaly index is generated. The method for obtaining the forwarding path anomaly index is as follows:

[0016] The communication network of a power plant is represented as a directed graph G = (V, E), where V represents the set of nodes and network devices; E is the set of edges, representing the connections between devices; and the edge weight w(e) represents the forwarding cost of the connection. The expected path P is calculated from the source node s to the target node t using the shortest path algorithm. expected The path is represented as a sequence of nodes: P expected = [s, v1, v2, ..., t]; where each node on the path represents the forwarding order of the data stream in sequence. Simulation path acquisition: output simulation path P from the simulation tool. simulated , represented as: P simulated = [s, v′1, v′2, ..., t]; Calculate the edit distance D(P) between the simulated path and the expected path. expected P simulated Edit distance represents the number of operations required to transform one path into another; operations include: insertion: adding a node to the path; deletion: removing a node from the path; and substitution: replacing one node in the path with another node.

[0017] Let P expected Length n, P simulated Define a dynamic programming matrix D(i,j) of length m: If c(i,j) = 0, then P expected [i] = P simulated [j], otherwise c(i,j)=1; D(n,m) is the path edit distance. Calculate the path deviation PD, defined as the ratio of the edit distance to the expected path length, expressed as: Among them, |P expected | represents the number of nodes in the expected path; the forwarding path anomaly index is defined as a comprehensive index weighted by path deviation, taking into account edge weight deviation: In the formula, MKH is the forwarding path anomaly index. This represents the sum of the weights of edges in the simulation path that are not in the expected path. Let w(e) be the sum of edge weights in the expected path, and w(e) be the weight of each edge in the path.

[0018] Preferably, in S3, after analyzing the deviation fluctuation between the transmission delay of real-time traffic and the expected delay of the simulation path, a delay deviation fluctuation index is generated. The method for obtaining the delay deviation fluctuation index is as follows:

[0019] Let the real-time acquisition latency be T. real-time = [t1, t2, ..., t N The simulation expected delay is T. simulated = [s1, s2, ..., s N ]; Calculate the time delay deviation δ N =|t N -s N | and construct the corresponding sequence: ΔT=[δ1,δ2,...,δ N ], δ i =t i -s i Let i = 1, 2, ..., N; the sequence will be used as input for wavelet transform, and the time delay deviation sequence ΔT will be decomposed into multi-level low-frequency and high-frequency components, expressed as: Low-frequency component A j D is used to capture the long-term trend of deviations. k Used to capture short-term fluctuations in the deviation; for each layer of high-frequency component D k Calculate energy: Where: D k [i] is the high-frequency component D k The i-th value in N k It is D k The number of data points is used to calculate the total energy E of the time delay deviation sequence. total The expression is: The time delay deviation fluctuation index is calculated by comparing the energy of the high-frequency components with the total energy. The expression is as follows: GBH is the delay deviation fluctuation index.

[0020] Preferably, in S4, based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between real-time traffic and simulated data, the stability of the communication path under abnormal conditions is evaluated, specifically as follows:

[0021] The forwarding path anomaly index and latency deviation fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to a machine learning model. The machine learning model uses the prediction of the stability value label of the communication path under abnormal conditions for each set of comprehensive feature vectors as the prediction objective, and minimizes the sum of prediction errors for the stability value labels of all communication paths under abnormal conditions as the training objective. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The stability value of the communication path under abnormal conditions is determined based on the model output. The machine learning model is a multinomial regression model.

[0022] Preferably, in S4, the stability value of the obtained communication path under abnormal conditions is compared with a preset stability value reference threshold based on historical data. If the stability value of the communication path under abnormal conditions is greater than or equal to the preset stability value reference threshold, it indicates that the communication path has high stability under abnormal conditions. In this case, no warning signal is generated, indicating that the path can maintain reliable communication under abnormal conditions. If the stability value of the communication path under abnormal conditions is less than the preset stability value reference threshold, it indicates that the communication path has low stability under abnormal conditions. In this case, a warning signal is generated, indicating that the path is easily affected under abnormal conditions and the communication path is unstable.

[0023] Preferably, in S5, when communication path instability occurs, the detected anomaly is traced back step by step using a hierarchical partitioning model. The abnormal subnet is identified at the system layer, the abnormal configuration of the specific device is confirmed at the subnet layer, and finally, the erroneous parameter configuration item is precisely located at the device layer. Specifically:

[0024] Map the communication path stability value S to the distribution of its subnet, and calculate the average stability value S for each subnet. 子网 The expression is: Where, N 路径 S is the number of communication paths within the subnet. i It is the stability value of the i-th path. If the average stability value of the subnet is less than the preset average stability threshold, the subnet is marked as an abnormal subnet.

[0025] Within the abnormal subnet, identify the devices causing path instability. Within the subnet, calculate the device impact index I for all communication paths involved by each device. 设备 The expression is: Where, N 路径，设备 It is the number of paths involving the device; S j S is the stability value of the j-th path. threshold This serves as a reference threshold for stability values. If the impact index of a device exceeds the device impact threshold, the device is considered to be malfunctioning.

[0026] Within the faulty device, locate the specific erroneous configuration item and examine each network configuration parameter P of the device. k Calculate the correlation C(P) of its impact on the path stability value S. k S), the expression is: Among them, Cov(P k S) is the parameter P k Covariance with stability value S; σ(P) k ), σ(S) are respectively P k and the standard deviation of S; when C(P) k If S is close to -1 or 1, it indicates that the parameter has a strong correlation with the stability value and is an abnormal parameter, so it is marked as an abnormal configuration item.

[0027] This invention also provides a network parameter configuration verification system for power plants, including a network modeling module, a static parameter verification module, a traffic comparison module, a stability assessment module, an anomaly backtracking and location module, and a correction and verification module:

[0028] Network Modeling Module: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer.

[0029] Static parameter verification module: Based on the constructed network model, the module uses a rule base to verify the consistency of static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration.

[0030] Traffic comparison module: After completing static verification, it simulates the dynamic behavior of the network in actual operation, generates data flow paths under different communication scenarios through simulation tools, judges the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compares the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data.

[0031] Stability assessment module: Based on the consistency of forwarding paths of simulated data streams under different communication scenarios and the delay deviation between real-time traffic and simulated data, the stability of communication paths under abnormal conditions is assessed.

[0032] Anomaly backtracking and localization module: When communication path becomes unstable, the module combines a hierarchical partitioning model to backtrack and locate the detected anomaly step by step. It identifies the abnormal subnet at the system layer, confirms the abnormal configuration of the specific device at the subnet layer, and finally pinpoints the erroneous parameter configuration item at the device layer.

[0033] Correction and Verification Module: After anomaly location is completed, correction suggestions are generated, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, configuration updates are executed through automated correction functions, and static verification and dynamic simulation are rerun to verify the effectiveness of the correction.

[0034] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0035] 1. This invention employs a layered and partitioned network model, dividing the network into device, subnet, and system layers. It combines a rule base to comprehensively validate static parameters, ensuring the correctness of the network configuration. Simultaneously, through dynamic behavior simulation and real-time traffic analysis, it evaluates forwarding path consistency and latency deviation, further quantifying the stability of communication paths under abnormal conditions. This method can accurately identify potentially unstable paths, generate stability assessment reports, and automatically diagnose and repair unstable paths.

[0036] 2. This invention introduces a machine learning-based multinomial regression model, using the forwarding path anomaly index and delay deviation fluctuation index as feature vectors to establish a path stability prediction model, achieving efficient prediction and early warning of communication path stability. Combined with a hierarchical partitioning model, it progressively backtracks from the system layer to the device layer to locate anomalies, accurately identifying erroneous network configuration items, and utilizing the network configuration management system to perform automated corrections. After correction, the correction effect is re-verified and validated, forming a complete closed-loop processing mechanism. This invention improves the efficiency and accuracy of network anomaly diagnosis and repair, significantly enhances the reliability and stability of power plant communication networks under complex conditions, and provides strong support for the safe operation of smart grids. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0038] Figure 1 This is a flowchart of the method of the present invention.

[0039] Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Example 1, please refer to Figure 1 As shown in this embodiment, a network parameter configuration verification method for power plants includes the following steps:

[0042] S1: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer;

[0043] S2: Based on the constructed network model, a rule base is used to perform consistency verification on static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration.

[0044] S3: After completing the static verification, simulate the dynamic behavior of the network in actual operation, generate data flow paths under different communication scenarios through simulation tools, judge the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compare the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data.

[0045] S4: Evaluate the stability of the communication path under abnormal conditions based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between the real-time traffic and the simulated data.

[0046] S5: When communication path becomes unstable, the detected anomalies are gradually traced back and located using the hierarchical partitioning model. The abnormal subnet is identified from the system layer, the abnormal configuration of the specific device is confirmed from the subnet layer, and finally the erroneous parameter configuration item is accurately located at the device layer.

[0047] S6: After anomaly localization is completed, generate correction suggestions, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, execute configuration updates through automated correction functions, and rerun static verification and dynamic simulation to verify the effectiveness of the correction.

[0048] In S1, based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed. This network model includes a device layer, a subnet layer, and a system layer, specifically:

[0049] The device layer covers the basic network configuration parameters of all physical devices, including but not limited to: Device 1: Protection device, IP address: 192.168.1.10, subnet mask: 255.255.255.0, gateway: 192.168.1.1, port number: 502 (Modbus TCP protocol); Device 2: Measurement and control device, IP address: 192.168.2.20, subnet mask: 255.255.255.0, gateway: 192.168.2.1, port number: 2404 (IEC 60870-5-104 protocol); Device 3: Smart terminal, IP address: 192.168.3.30, subnet mask: 255.255.255.0, gateway: 192.168.3.1, port number: 102 (IEC 60870-5-104 protocol). 61850 protocol MMS channel); The device layer collects the above device parameters through an automatic discovery tool and compares them with a predefined network rule base to ensure that the IP address and gateway are correctly allocated and without conflict.

[0050] At the subnet layer, devices are grouped into three logical subnets, and communication rules are defined within each subnet: Subnet 1 (Protection Subnet), containing protection devices and protection-related switches. Internal communication rules: All devices are only allowed to send protection signals via TCP / IP protocol; broadcast traffic is prohibited. Routing policy: Outbound traffic is uniformly forwarded through gateway 192.168.1.1. Subnet 2 (Monitoring Subnet), containing monitoring and control devices and related servers. Internal communication rules: Devices are allowed to publish monitoring data to the server; UDP protocol data traffic is limited to a maximum of 5Mbps. Routing policy: Inter-subnet communication is configured to the target subnet 192.168.3.0 / 24 through a static routing table. Subnet 3 (Control Subnet), containing intelligent terminals and scheduling devices. Internal communication rules: MMS and GOOSE messages according to the IEC 61850 protocol are allowed; all GOOSE messages must be transmitted with priority. Routing policy: Dynamic routing (OSPF) is supported to ensure high reliability and low latency of critical data flows. The subnet layer generates a communication rule table using network topology analysis tools and verifies whether the rules meet the set security and performance requirements.

[0051] The system layer is responsible for describing the network topology and cross-subnet communication paths of the entire plant: Global Topology Model: Subnet 1, Subnet 2, and Subnet 3 are connected to the router via the main switch. The router connects the plant's dispatch center and remote control center. The router supports dynamic routing protocols (such as OSPF) and static routing table configuration to enable communication between subnets and external networks. Routing Tables: Static Routing Table: 192.168.1.0 / 24 → Gateway 192.168.1.1; 192.168.2.0 / 24 → Gateway 192.168.2.1; 192.168.3.0 / 24 → Gateway 192.168.3.1. Dynamic Routing Table: Calculates the optimal path using the OSPF protocol. When the default gateway of a subnet fails, it automatically adjusts to the backup path. Supports the priority transmission strategy of MMS messages and GOOSE messages according to the IEC 61850 protocol to ensure the real-time performance of critical data flows. The monitoring subnet and the protection subnet are relayed through the control subnet, with the traffic path being: Subnet 1 → Subnet 3 → Subnet 2. The system layer integrates the routing policies and communication rules of each subnet, generating a global model of cross-subnet communication to guide dynamic simulation and parameter verification.

[0052] By simulating a gateway failure in the monitoring and control device, verify whether traffic from subnet 2 can reach the external dispatch center through the dynamic routing relay of subnet 3. Detect whether broadcast traffic from the protection subnet overflows into the control or monitoring subnet due to misconfiguration. Verify whether the system layer ensures that GOOSE messages are prioritized for transmission under high load scenarios to avoid delays.

[0053] S2: Based on the constructed network model, a rule base is used to perform consistency verification on static parameters, including checking whether network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration.

[0054] The network parameters of each device at the device layer are verified item by item using a rule base. Example verification rules: The IP address must be within the specified subnet range (e.g., subnet 1 range is 192.168.1.0 / 24). The gateway must be set to the subnet gateway matching the device IP (e.g., 192.168.1.1). The subnet mask must conform to the standard configuration (e.g., 255.255.255.0). For example: Device 1 (protection device): IP address is 192.168.1.10, gateway is 192.168.1.1, which conforms to the rules; Device 2 (monitoring and control device): IP address is configured as 192.168.3.25, gateway is 192.168.2.1, but it should belong to the subnet 2 range (192.168.2.0 / 24). The verification tool indicates that the gateway setting is incorrect and needs to be corrected to 192.168.3.1.

[0055] Analyze the routing tables at the subnet and system layers to ensure the integrity and conflict-free nature of the routing configuration. Example verification rules: Each subnet in the static routing table must have a unique destination address (no duplicates or conflicts); check for loops between subnets to prevent routes from getting stuck in infinite loops; check whether routes generated by dynamic routing protocols conflict with static routes. For example, at the system layer, the verification tool finds two static routes for 192.168.2.0 / 24: Route 1: 192.168.2.0 / 24 → Gateway 192.168.2.1; Route 2: 192.168.2.0 / 24 → Gateway 192.168.3.1. The tool determines this as redundant configuration and suggests keeping Route 1 and removing Route 2. During dynamic route checks, the routing table generated by the OSPF protocol is compared with the static routing table to confirm no conflicting paths.

[0056] At the subnet layer, based on predefined VLAN configuration rules, the system verifies whether devices are correctly assigned to their corresponding VLANs and checks whether the communication rules between VLANs comply with specifications. Example verification rules: Each device's VLAN ID must match its logical subnet; communication traffic between the protection subnet and the monitoring subnet must be isolated through a specific trunk VLAN. For example, device 1 (protection device) should belong to VLAN 10 (protection subnet), but the verification tool detects that it is configured as VLAN 20 (monitoring subnet), indicating an incorrect mapping between the device and the subnet. VLAN communication rule verification reveals that broadcast traffic from the protection subnet is unexpectedly transmitted to the monitoring subnet. The verification tool suggests adjusting the switch's VLAN partitioning rules to restrict cross-subnet broadcasts.

[0057] The gateway configuration of the monitoring and control device is incorrect; it needs to be adjusted to match its actual subnet. The static routing table has redundant configurations; optimization should retain only one valid path and eliminate potential conflicts. The VLAN allocation of the protection device is incorrect; it needs to be re-partitioned to ensure subnet isolation and correct communication rules.

[0058] S3: After completing the static verification, simulate the dynamic behavior of the network in actual operation, generate data flow paths under different communication scenarios through simulation tools, judge the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compare the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data.

[0059] Based on the actual operational needs of power plants, three typical communication scenarios are set up: Scenario 1: Protection devices send fault information to the dispatch center; Triggering condition: An abnormality occurs in a certain device (e.g., voltage over-limit). Expected data flow path: Protection subnet (device 1) → Router → Dispatch center (remote server). Scenario 2: Measurement and control devices upload real-time data to the monitoring server; Triggering condition: Measurement and control devices periodically upload monitoring data (e.g., power, frequency). Expected data flow path: Monitoring subnet (device 2) → Monitoring server (internal subnet). Scenario 3: The dispatch system issues control commands to intelligent terminals; Triggering condition: The dispatch center sends load adjustment commands. Expected data flow path: Dispatch center → Router → Control subnet (device 3).

[0060] Based on a hierarchical and partitioned network model, simulation tools (such as Mininet or the network simulator NS3) are used to simulate the above communication scenario and generate the actual forwarding path of the data flow:

[0061] The header information of the simulated data packet includes the source address, destination address, protocol type (such as TCP, UDP), and priority field; the data flow path is identified by the number of hops between devices and the network devices (switches, routers) on the path.

[0062] The simulated paths are compared with the expected paths to determine if the forwarding behavior is consistent. Scenario 1 Result: Simulated path: Device 1 (192.168.1.10) → Subnet 1 switch → Router (192.168.1.1) → Dispatch Center (10.0.0.1). Comparison result: The paths are completely consistent, and the simulation verification passes. Scenario 2 Result: Simulated path: Device 2 (192.168.2.20) → Subnet 2 switch → Monitoring server (192.168.2.100). Comparison result: The paths are completely consistent, but the simulation tool detected that UDP protocol traffic was occasionally mislabeled as low priority. QoS settings need to be adjusted to ensure that real-time data is transmitted with priority. Scenario 3 Result: Simulated path: Dispatch Center (10.0.0.1) → Router (192.168.3.1) → Subnet 3 switch → Device 3 (192.168.3.30). Comparison results: The paths are inconsistent. The simulation tool found that the router mistakenly forwarded the data stream to the subnet 1 switch, causing communication failure. The analysis revealed that the static route configuration was missing an entry for subnet 3, and the relevant route configuration should be added.

[0063] After analyzing the consistency of forwarding paths in simulated data streams under different communication scenarios, a forwarding path anomaly index is generated. The method for obtaining the forwarding path anomaly index is as follows:

[0064] The communication network of a power plant is represented as a directed graph G = (V, E), where V represents the set of nodes, which are network devices (such as switches, routers, and terminal devices). E is the set of edges, representing the connections between devices, and the edge weight w(e) represents the forwarding cost of the connection (such as latency, bandwidth consumption, or hop count). Using a shortest path algorithm (such as Dijkstra's algorithm or the Floyd-Warshall algorithm), the expected path P from the source node s to the destination node t is calculated. expected The path is represented as a sequence of nodes: P expected = [s, v1, v2, ..., t]; where each node on the path represents the forwarding order of the data stream in sequence. Simulation path acquisition:

[0065] Output simulation path P from the simulation tool simulated , represented as: P simulated =[s, v1 ′ v2 ′ [, ..., t]; Calculate the edit distance D(P) between the simulation path and the expected path. expeced P simulated Edit distance represents the number of operations required to transform one path into another. Operations include: Insertion: adding a node to the path; Deletion: removing a node from the path; Replacement: replacing one node in the path with another node.

[0066] Let P expected Length n, P simulated Define a dynamic programming matrix D(i,j) of length m: If c(i,j) = 0, then P expected [i] = P simulated [j], otherwise c(i,j)=1; D(n,m) is the path edit distance. Calculate the path deviation PD, defined as the ratio of the edit distance to the expected path length, expressed as: Among them, |P expected | represents the number of nodes in the expected path; the forwarding path anomaly index is defined as a comprehensive index weighted by path deviation, taking into account edge weight deviation: In the formula, MKH is the forwarding path anomaly index. This represents the sum of the weights of edges in the simulation path that are not in the expected path. The sum of edge weights in the expected path is given by w(e), where w(e) is the weight of each edge in the path (e.g., latency, hop count, bandwidth usage).

[0067] A higher forwarding path anomaly index indicates a worse consistency between the actual and expected forwarding paths of the simulated data stream. This may indicate serious configuration errors or abnormal behavior in the network, such as path deviation, missing routing table configurations, instability of dynamic routing, or packets being mistakenly forwarded to irrelevant nodes. Furthermore, deviations in edge weights (such as latency, hop count, or bandwidth consumption) can also significantly increase the anomaly index, further reflecting that the actual network performance is far below expectations. A high anomaly index typically indicates that communication reliability and efficiency may be severely affected, requiring priority investigation of problematic devices and configuration items.

[0068] Conversely, a smaller forwarding path anomaly index indicates that the actual forwarding path of the simulated data stream is highly consistent with the expected path, and the network is operating well. When the path deviation is close to zero, it means that the data packets pass through each node strictly according to the designed forwarding order, while a small weight deviation means that the transmission performance (such as latency and bandwidth utilization) meets expectations. A low anomaly index reflects the high reliability and stability of the communication network, indicating that the existing configuration and routing strategy are suitable for the current scenario and do not require major adjustments. Under these circumstances, the network can effectively support critical tasks such as real-time monitoring, protection, and control of power plants.

[0069] Use traffic acquisition tools (such as NetFlow, sFlow, or Wireshark) to monitor packet transmission between network devices in real time, recording key information: source and destination addresses (IP or MAC), transport protocol (such as TCP or UDP), packet size (bytes), and timestamps (accurate to milliseconds). Obtain expected traffic information from simulation paths generated by simulation tools (such as Mininet or NS3), including: the forwarding path (device sequence) for each data flow, transport protocol, source and destination addresses, expected traffic size, and expected latency and bandwidth utilization.

[0070] Compare the actual forwarding path of real-time traffic with the simulated path: Path consistency: Check whether the actual path of each data flow is included in the expected path; Path deviation: If the data flow deviates from the expected path, record the sequence of deviated nodes and the corresponding traffic percentage. Calculation formula: Path deviation degree PD: PD = Number of deviated nodes / Number of nodes in the simulated path. The higher the deviation degree, the greater the deviation between the actual transmission and the simulation result. Compare the real-time collected traffic size with the simulated traffic size to determine the deviation of the transmitted data: Traffic difference: ΔF = |Freal-time - Fsimulated|; where Freal-time is the real-time traffic size and Fsimulated is the simulated traffic size. Compare the transmission delay of real-time traffic with the expected delay of the simulated path and calculate the delay deviation ΔT: ΔT = Treal-time - Tsimulated; Compare the bandwidth usage of real-time and simulation to determine whether there is insufficient or excessive bandwidth utilization. Based on the comparison results, analyze the deviation between real-time traffic and simulation data: If there are unexpected forwarding nodes in the actual path, it may be due to routing configuration errors or network failures causing unexpected forwarding. If real-time traffic differs significantly from simulated traffic, it may be due to packet loss, retransmission, or traffic bursts. If the deviation in latency or bandwidth utilization exceeds the tolerance range, it may reflect network congestion, equipment overload, or unstable dynamic routing.

[0071] After analyzing the deviation fluctuation between the transmission delay of real-time traffic and the expected delay of the simulation path, a delay deviation fluctuation index is generated. The method for obtaining the delay deviation fluctuation index is as follows:

[0072] Let the real-time acquisition latency be T. real-time = [t1, t2, ..., t N The simulation expected delay is T. simulated = [s1, s2, ..., s N ]; Calculate the time delay deviation δ N =|t N -s N | and construct the corresponding sequence: ΔT=[δ1,δ2,...,δ N ], δ i =t i -s i Let i = 1, 2, ..., N; the sequence will be used as the input for wavelet transform. The time delay deviation sequence ΔT is decomposed using wavelet decomposition, selecting appropriate wavelet basis functions (such as Daubechies wavelet, Haar wavelet, etc.). ΔT is decomposed into multi-level low-frequency and high-frequency components, expressed as: Low-frequency component A j D is used to capture the long-term trend of deviations. k Used to capture short-term fluctuations in deviation, reflecting the jitter characteristics of the deviation.

[0073] For each layer of high-frequency component D k Calculate energy: Where: D k [i] is the high-frequency component D k The i-th value in N k It is D k The number of data points is used to calculate the total energy E of the time delay deviation sequence. total The expression is: The time delay deviation fluctuation index is calculated by comparing the energy of the high-frequency components with the total energy. The expression is as follows: GBH is the delay deviation fluctuation index.

[0074] A high volatility index indicates that short-term latency fluctuations account for a large proportion of the total latency deviation, meaning that network transmission performance is significantly affected by dynamic factors (such as sudden traffic spikes, network congestion, and equipment overload). In this situation, the latency performance of the communication path is difficult to predict, and the data stream may experience significant jitter and uneven transmission delays, leading to a decrease in the real-time performance and reliability of critical tasks. For data transmission scenarios requiring high real-time performance, such as power plants, a high volatility index suggests that the path is prone to instability under abnormal conditions, necessitating optimized traffic scheduling or increased network resource redundancy to enhance stability.

[0075] A low volatility index indicates that short-term fluctuations contribute little to the total delay deviation, suggesting that the network path has high resistance to interference when facing dynamic changes (such as traffic peaks or device switching). In this case, the data stream transmission delay is closer to the expected value, jitter is less, and the path exhibits good robustness and consistency. For the transmission of mission-critical data, such as protection signals and control commands in power systems, a low volatility index indicates that the communication path can remain stable under abnormal conditions, meeting real-time and reliability requirements without the need for major adjustments.

[0076] S4: Evaluate the stability of the communication path under abnormal conditions based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between the real-time traffic and the simulated data.

[0077] The forwarding path anomaly index and latency deviation fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to a machine learning model. The machine learning model uses the prediction of the stability value label of the communication path under abnormal conditions for each set of comprehensive feature vectors as the prediction objective, and minimizes the sum of prediction errors for the stability value labels of all communication paths under abnormal conditions as the training objective. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The stability value of the communication path under abnormal conditions is determined based on the model output. The machine learning model is a multinomial regression model.

[0078] The method for obtaining the stability value of the communication path under abnormal conditions is as follows: from the training data of the comprehensive feature vector of the trained machine learning model, obtain the corresponding function expression: S = F(MKH, GBH); where F is the output function of the model, MKH is the forwarding path anomaly index, GBH is the delay deviation fluctuation index, and S is the stability value of the communication path under abnormal conditions.

[0079] The stability value of the obtained communication path under abnormal conditions is compared with a preset stability reference threshold based on historical data. If the stability value of the communication path under abnormal conditions is greater than or equal to the preset stability reference threshold, it indicates that the communication path is highly stable under abnormal conditions, and no warning signal is generated, indicating that the path can maintain reliable communication under abnormal conditions. If the stability value of the communication path under abnormal conditions is less than the preset stability reference threshold, it indicates that the communication path is not stable under abnormal conditions, and a warning signal is generated, indicating that the path is easily affected under abnormal conditions and the communication path is unstable.

[0080] S5: When communication path becomes unstable, the detected anomalies are traced back step by step using the hierarchical partitioning model. The abnormal subnet is identified at the system layer, the abnormal configuration of the specific device is confirmed at the subnet layer, and finally the erroneous parameter configuration item is accurately located at the device layer.

[0081] Based on the global network topology, locate the subnet where the anomaly occurred. Calculate the anomaly path distribution:

[0082] Map the communication path stability value S to the distribution of its subnet, and calculate the average stability value S for each subnet. 子网 The expression is: Where, N 路径 S is the number of communication paths within the subnet. i This is the stability value of the i-th path. If the average stability value of the subnet is less than the preset average stability threshold, the subnet is marked as an abnormal subnet.

[0083] Within the abnormal subnet, identify the devices causing path instability. Within the subnet, calculate the device impact index I for all communication paths involved by each device. 设备 The expression is: Where, N 路径，设备 It is the number of paths involving the device; S j S is the stability value of the j-th path. threshold This serves as a reference threshold for stability. If the equipment's impact index exceeds this threshold, the equipment is considered to be malfunctioning.

[0084] Within the malfunctioning device, locate the specific incorrect configuration item (such as IP address, subnet mask, routing table entry, etc.). Analyze the correlation between configuration parameters and the malfunctioning path:

[0085] For each network configuration parameter P of the device k Calculate the correlation C(P) of its impact on the path stability value S. k S), the expression is: Among them, Cov(P k S) is the parameter P k Covariance with stability value S; σ(P) k ), σ(S) are respectively P k and the standard deviation of S;

[0086] When C(P) k If S is close to -1 or 1, it indicates that the parameter has a strong correlation with the stability value, is an abnormal parameter, and has a significant impact on the path stability value, so it is marked as an abnormal configuration item.

[0087] S6: After anomaly localization is completed, generate correction suggestions, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, execute configuration updates through automated correction functions, and rerun static verification and dynamic simulation to verify the effectiveness of the correction.

[0088] Based on the anomaly localization results, specific corrective suggestions are made for the erroneous configuration entries: If a device's routing table entry points to the wrong gateway, it is recommended to change it to the correct gateway address. For example, change 192.168.1.254 to 192.168.1.1. If a device is assigned to the wrong VLAN, such as a protection device being configured to a monitoring VLAN, it is recommended to adjust the VLAN configuration and assign the device to the correct VLAN (e.g., VLAN 10). If a device's IP address is duplicated with another device, it is recommended to reallocate an unused IP address and update the relevant routing table.

[0089] Before adjusting the configuration, analyze the potential impact of the correction to avoid creating new problems for other network components or data flows: Adjusting the routing table may cause changes to some data flow paths, so it is necessary to ensure that the new path does not introduce latency or bandwidth bottlenecks. Modifying VLAN configurations may affect the broadcast range of data, so it is necessary to verify whether the new configuration meets the isolation requirements. Adjusting IP addresses or gateway configurations may cause temporary communication interruptions, so it is necessary to assess the adjustment time window and avoid operations during peak traffic periods as much as possible. The generated correction recommendations include detailed steps for configuration adjustments, the possible scope of impact, and the expected effects after correction, forming a complete correction plan.

[0090] Automated remediation is achieved through the NCM system, generating automated configuration scripts (such as CLI commands or API calls) based on the remediation suggestions. The remediation scripts are then distributed to the target devices via NCM to complete parameter adjustments. NCM collects device status feedback to confirm successful configuration updates. Immediately after remediation, the basic operational status of the devices is verified: the routing table and VLAN configuration are checked to ensure they meet the remediation requirements; and device communication is confirmed to be normal, with no connection interruptions or data loss.

[0091] Rerun the static verification tool to perform consistency and integrity checks on the corrected configuration: confirm that the newly configured IP addresses, routing tables, and VLANs conform to predefined specifications; check for any new configuration conflicts or omissions. A successful static verification indicates that the basic configuration correctness is guaranteed. Run the dynamic behavior simulation tool to verify the actual impact of the correction on network performance: check whether the corrected data flow path is consistent with expectations; evaluate whether the correction improves latency deviation or bandwidth utilization to ensure performance targets are met; simulate different communication scenarios to confirm whether the correction eliminates existing anomalies and does not introduce new problems.

[0092] The success of the correction is determined based on the results of static verification and dynamic simulation: Correction Successful: If the verification and simulation results meet expectations, the correction scheme is effective, and the configuration adjustment is complete. Correction Failed: If anomalies still exist, the problem points need to be re-analyzed, new correction suggestions generated, and the process repeated. The correction process and its verification results are recorded in the network operation and maintenance system as a reference for future fault diagnosis and optimization.

[0093] In this embodiment, a hierarchical network model is constructed based on the topology of the power plant communication network, including the device layer, subnet layer, and system layer. Based on this, a rule base is used to statically validate network parameters, checking the consistency and completeness of configuration rules. After static validation, simulation tools are used to simulate dynamic network behavior, generating data flow paths under different communication scenarios. Real-time collected traffic is compared with the simulated paths to analyze forwarding path consistency and latency deviations. The stability of communication paths under abnormal conditions is comprehensively evaluated. When path instability occurs, the hierarchical partition model is used to gradually backtrack and locate the problem, from identifying abnormal subnets at the system layer, to confirming abnormal devices at the subnet layer, and finally accurately finding the erroneous configuration item at the device layer. After location, correction suggestions are generated, including configuration adjustments and impact analysis. Automated correction is executed through the network configuration management system, and static validation and dynamic simulation are performed again to verify the effectiveness of the correction, ensuring the final correctness of the network configuration and the stability of the communication paths.

[0094] Example 2, please refer to Figure 2As shown in this embodiment, a network parameter configuration verification system for power plants includes a network modeling module, a static parameter verification module, a traffic comparison module, a stability assessment module, an anomaly backtracking and location module, and a correction and verification module.

[0095] Network Modeling Module: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer.

[0096] Static parameter verification module: Based on the constructed network model, the module uses a rule base to verify the consistency of static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration.

[0097] Traffic comparison module: After completing static verification, it simulates the dynamic behavior of the network in actual operation, generates data flow paths under different communication scenarios through simulation tools, judges the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compares the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data.

[0098] Stability assessment module: Based on the consistency of forwarding paths of simulated data streams under different communication scenarios and the delay deviation between real-time traffic and simulated data, the stability of communication paths under abnormal conditions is assessed.

[0099] Anomaly backtracking and localization module: When communication path becomes unstable, the module combines a hierarchical partitioning model to backtrack and locate the detected anomaly step by step. It identifies the abnormal subnet at the system layer, confirms the abnormal configuration of the specific device at the subnet layer, and finally pinpoints the erroneous parameter configuration item at the device layer.

[0100] Correction and Verification Module: After anomaly location is completed, correction suggestions are generated, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, configuration updates are executed through automated correction functions, and static verification and dynamic simulation are rerun to verify the effectiveness of the correction.

[0101] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0102] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0103] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for verifying network parameter configuration in power plants, characterized in that: Includes the following steps: S1: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer; S2: Based on the constructed network model, a rule base is used to perform consistency verification on static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration. S3: After completing the static verification, simulate the dynamic behavior of the network in actual operation, generate data flow paths under different communication scenarios through simulation tools, judge the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compare the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data. S4: Evaluate the stability of the communication path under abnormal conditions based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between the real-time traffic and the simulated data. S5: When communication path becomes unstable, the detected anomalies are gradually traced back and located using the hierarchical partitioning model. The abnormal subnet is identified from the system layer, the abnormal configuration of the specific device is confirmed from the subnet layer, and finally the erroneous parameter configuration item is accurately located at the device layer. S6: After anomaly localization is completed, generate correction suggestions, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, execute configuration updates through automated correction functions, and rerun static verification and dynamic simulation to verify the effectiveness of the correction.

2. The method for verifying network parameter configuration in power plants according to claim 1, characterized in that: In S1, the device layer defines the IP address, subnet mask, gateway, and port number of each device; the subnet layer describes the routing policies and communication rules of each subnet; and the system layer is used to model the routing table, global topology, and protocol interaction across subnets.

3. The method for verifying network parameter configuration in power plants according to claim 1, characterized in that: In S3, after analyzing the consistency of the forwarding path of the simulated data stream under different communication scenarios, a forwarding path anomaly index is generated. The method for obtaining the forwarding path anomaly index is as follows: The communication network of a power plant is represented as a directed graph G = (V, E), where V represents the set of nodes and network devices; E is the set of edges, representing the connections between devices; and the edge weight w(e) represents the forwarding cost of the connection. The expected path P is calculated from the source node s to the target node t using the shortest path algorithm. expected The path is represented as a sequence of nodes: P expected = [s, v1, v2, ..., t]; where each node on the path represents the forwarding order of the data stream in sequence. Simulation path acquisition: output simulation path P from the simulation tool. simulated , represented as: P simulated = [s, v′1, v′2, ..., t]; Calculate the edit distance D(P) between the simulated path and the expected path. expected P simulated Edit distance represents the number of operations required to transform one path into another; operations include: insertion: adding a node to the path; deletion: removing a node from the path; and substitution: replacing one node in the path with another node. Let P expected Length n, P simulated Define a dynamic programming matrix D(i,j) of length m: If c(i,j) = 0, then P expected [i] = P simulated [j], otherwise c(i,j)=1; D(n,m) is the path edit distance. Calculate the path deviation PD, defined as the ratio of the edit distance to the expected path length, expressed as: Among them, |P expected | represents the number of nodes in the expected path; the forwarding path anomaly index is defined as a comprehensive index weighted by path deviation, taking into account edge weight deviation: In the formula, MKH is the forwarding path anomaly index. This represents the sum of the weights of edges in the simulation path that are not in the expected path. Let w(e) be the sum of edge weights in the expected path, and w(e) be the weight of each edge in the path.

4. The method for verifying network parameter configuration in power plants according to claim 3, characterized in that: In S3, a delay deviation fluctuation index is generated after analyzing the deviation between the transmission delay of real-time traffic and the expected delay of the simulation path. The method for obtaining the delay deviation fluctuation index is as follows: Let the real-time acquisition latency be T. real-time = [t1, t2, ..., t N The simulation expected delay is T. simulated = [s1, s2, ..., s N ]; Calculate the time delay deviation δ N =|t N -s N | and construct the corresponding sequence: ΔT=[δ1,δ2,...,δ N ], δ i =t i -s i , i = 1, 2, ..., N; The sequence will be used as input for wavelet transform. The time delay deviation sequence ΔT will be decomposed into wavelet components, which will be further decomposed into multi-level low-frequency and high-frequency components. The expression is as follows: Low-frequency component A j D is used to capture the long-term trend of deviations. k Used to capture short-term fluctuations in deviations; For each layer of high-frequency component D k Calculate energy: Where: D k [i] is the high-frequency component D k The i-th value in N k It is D k The number of data points is used to calculate the total energy E of the time delay deviation sequence. total The expression is: The time delay deviation fluctuation index is calculated by comparing the energy of the high-frequency components with the total energy. The expression is as follows: GBH is the delay deviation fluctuation index.

5. The method for verifying network parameter configuration in power plants according to claim 4, characterized in that: In S4, based on the consistency of the forwarding path of the simulated data stream under different communication scenarios and the delay deviation between real-time traffic and simulated data, the stability of the communication path under abnormal conditions is evaluated, specifically: The forwarding path anomaly index and latency deviation fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to a machine learning model. The machine learning model uses the prediction of the stability value label of the communication path under abnormal conditions for each set of comprehensive feature vectors as the prediction objective, and minimizes the sum of prediction errors for the stability value labels of all communication paths under abnormal conditions as the training objective. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The stability value of the communication path under abnormal conditions is determined based on the model output. The machine learning model is a multinomial regression model.

6. The method for verifying network parameter configuration in power plants according to claim 5, characterized in that: In S4, the stability value of the obtained communication path under abnormal conditions is compared with the preset stability value reference threshold based on historical data. If the stability value of the communication path under abnormal conditions is greater than or equal to the preset stability value reference threshold, it indicates that the communication path is highly stable under abnormal conditions. In this case, no warning signal is generated, indicating that the path can maintain reliable communication under abnormal conditions. If the stability value of the communication path under abnormal conditions is less than the preset stability value reference threshold, it indicates that the communication path is not stable under abnormal conditions. In this case, a warning signal is generated, indicating that the path is easily affected under abnormal conditions and the communication path is unstable.

7. A method for verifying network parameter configuration in power plants according to claim 6, characterized in that: In S5, when communication path instability occurs, the detected anomaly is traced back step by step using a hierarchical partitioning model. The abnormal subnet is identified at the system layer, the specific device's abnormal configuration is confirmed at the subnet layer, and finally, the erroneous parameter configuration item is precisely located at the device layer. Specifically: Map the communication path stability value S to the distribution of its subnet, and calculate the average stability value S for each subnet. 子网 The expression is: Where, N 路径 S is the number of communication paths within the subnet. i It is the stability value of the i-th path. If the average stability value of the subnet is less than the preset average stability threshold, the subnet is marked as an abnormal subnet. Within the abnormal subnet, identify the devices causing path instability. Within the subnet, calculate the device impact index I for all communication paths involved by each device. 设备 The expression is: Where, N 路径，设备 It is the number of paths involving the device; S j S is the stability value of the j-th path. threshold This serves as a reference threshold for stability values. If the impact index of a device exceeds the device impact threshold, the device is considered to be malfunctioning. Within the faulty device, locate the specific erroneous configuration item and examine each network configuration parameter P of the device. k Calculate the correlation C(P) of its impact on the path stability value S. k S), the expression is: Among them, Cov(P k S) is the parameter P k Covariance with stability value S; σ(P) k ), σ(S) are respectively P k and the standard deviation of S; when C(P) k If S is close to -1 or 1, it indicates that the parameter has a strong correlation with the stability value and is an abnormal parameter, so it is marked as an abnormal configuration item.

8. A network parameter configuration verification system for power plants, used to implement the network parameter configuration verification method for power plants as described in any one of claims 1-7, characterized in that: It includes a network modeling module, a static parameter verification module, a traffic comparison module, a stability assessment module, an anomaly backtracking and location module, and a correction and verification module. Network Modeling Module: Based on the topology of the power plant communication network, a hierarchical and partitioned network model is constructed, which includes a device layer, a subnet layer, and a system layer. Static parameter verification module: Based on the constructed network model, the module uses a rule base to verify the consistency of static parameters, including checking whether the network parameters conform to the allocation rules, whether there is redundancy or loops in the routing table, and whether the device is assigned to the correct VLAN, thereby verifying the correctness of the network configuration. Traffic comparison module: After completing static verification, it simulates the dynamic behavior of the network in actual operation, generates data flow paths under different communication scenarios through simulation tools, judges the consistency of the forwarding path of the simulated data flow under different communication scenarios, and compares the real-time collected network traffic with the simulated path to judge the delay deviation between the real-time traffic and the simulation data. Stability assessment module: Based on the consistency of forwarding paths of simulated data streams under different communication scenarios and the delay deviation between real-time traffic and simulated data, the stability of communication paths under abnormal conditions is assessed. Anomaly backtracking and localization module: When communication path becomes unstable, the module combines a hierarchical partitioning model to backtrack and locate the detected anomaly step by step. It identifies the abnormal subnet at the system layer, confirms the abnormal configuration of the specific device at the subnet layer, and finally pinpoints the erroneous parameter configuration item at the device layer. Correction and Verification Module: After anomaly location is completed, correction suggestions are generated, including configuration adjustment schemes and impact analysis. In conjunction with the network configuration management system, configuration updates are executed through automated correction functions, and static verification and dynamic simulation are rerun to verify the effectiveness of the correction.

Images