Cross-domain collaborative network management system deployment method for power ASON

Abstract

The invention discloses an electric power ASON-oriented cross-domain collaborative network management system deployment method, which relates to the technical field of electric power systems, and comprises the following steps of: acquiring operation state information of node equipment in real time through a system interface; establishing a topological structure diagram of the power communication network; abnormal conditions possibly occurring in the network are automatically identified, and fault early warning and repair suggestions are generated; scheduling, configuring and optimizing the network equipment; optimizing a network management deployment effect according to a cross-domain collaborative strategy; and after the equipment fault occurs, network recovery and repair are carried out. Real-time monitoring, fault early warning, automatic repairing and dynamic optimization of the electric power communication optical transmission network are achieved through the intelligent network management on-duty robot, the stability, reliability and efficiency of the network are remarkably improved, through cross-domain collaborative optimization and resource scheduling, the system can efficiently configure bandwidth, load balance and route selection, and the system is suitable for large-scale popularization and application. Manual intervention requirements are reduced, fault recovery is accelerated, and it is ensured that the network runs in the optimal state.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a method for deploying a cross-domain collaborative network management system for power ASON. Background Technology

[0002] With the digitalization and informatization of power systems, the Alignment and Transmission Network (ASON) serves as a core communication infrastructure, bearing the crucial responsibility of data transmission and information flow. Especially in power systems, network stability and real-time performance are paramount; any equipment failure or network anomaly can lead to system crashes, service interruptions, or equipment damage, impacting the normal operation of the power system.

[0003] Existing power communication network management systems typically face challenges such as difficulty in quickly locating equipment faults, insufficient network optimization, and difficulties in cross-domain collaboration. Traditional manual maintenance methods rely on manual inspection and adjustment, which are not only inefficient but also prone to errors. With the increasing number of network devices and the growing complexity of networks, efficient and real-time management of network devices, fault diagnosis, and resource optimization have become urgent needs for power communication networks. To address these challenges, we propose a cross-domain collaborative network management system deployment method for power ASON (Automatic Network Management System). Summary of the Invention

[0004] The purpose of this invention is to provide a method for deploying a cross-domain collaborative network management system for power ASON, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for deploying a cross-domain collaborative network management system for power ASON, comprising the following steps: Step 1: Deploy a network management robot within the power communication optical transmission network to obtain real-time operating status information of each node device through the system interface; Step 2: Based on the operating status information, establish the topology diagram of the power communication network, and use the network management duty robot to monitor the status of each communication node and obtain detailed performance indicators of each node, such as bandwidth utilization, transmission delay, and failure rate. Step 3: Based on node status data, automatically identify possible anomalies in the network, analyze their impact on the entire network service through algorithms, and generate fault warnings and repair suggestions; Step 4: Generate corresponding deployment strategies based on the analysis results, and use the network management robot to schedule, configure and optimize network devices, including but not limited to configuration of device bandwidth adjustment, load balancing and routing selection. Step 5: During network deployment, dynamically adjust equipment configuration and routing selection, and optimize network management deployment effectiveness based on cross-domain collaboration strategies; Step 6: After a device failure occurs, perform network recovery and repair.

[0006] Preferably, step 1 includes the following specific steps: Step 1.1: Connect to the optical transmission network via remote monitoring equipment and collect data from each node, including the device's bandwidth utilization, device response time, and traffic load information. Step 1.2: Set up an automated script to extract transmission performance data of each node from the network management system in real time and obtain the health status information of each node in real time, including device temperature, power status, and device faults. Step 1.3: Transmit the collected device information to the network management duty robot system for data cleaning and formatting processing for subsequent analysis and decision-making.

[0007] Preferably, step 2 includes the following specific steps: Step 2.1: Based on the IP address, location, and connection information of the node devices, construct the topology of the power communication network and establish connections with each node device through the network management system; Step 2.2: Based on the real-time status information obtained by the network management duty robot, update the topology map to ensure that the status information of the power communication network is synchronized with the actual network topology. Step 2.3: Perform performance tests on all nodes in the power communication network, including bandwidth, latency, and equipment health status. Monitor the operating status of each node in real time and respond to abnormal conditions.

[0008] Preferably, step 3 includes the following specific steps: Step 3.1: Collect real-time traffic data for each communication node and use data mining techniques to identify abnormal traffic fluctuations and predict potential fault risks. The judgment of abnormal traffic fluctuations is based on the following formula: △F(t) = F(t) - F avg (t); Where ΔF(t) represents the flow fluctuation of a node at time t, and F(t) represents the real-time flow of that node. avg (t) represents the average flow rate of the node during this time period. If ΔF(t) exceeds the set threshold, it is considered that an abnormal flow rate has occurred. Step 3.2: Based on the characteristics of abnormal traffic, set multiple thresholds, and trigger an early warning mechanism when the thresholds are exceeded, and start automatic repair or manual intervention measures. The specific threshold settings are based on the equipment operating mode and historical fault data to ensure timely response to network fluctuations. Step 3.3: Based on the real-time collected equipment health data, assess the overall health index of the power communication network and identify weak links in the network. The formula for calculating the health index is as follows: ; Where H represents the health index, and W... i R represents the importance weight of the i-th node. i Let n be the health score of the i-th node, and n be the number of nodes.

[0009] Preferably, the device scheduling and routing selection in step 4 are performed according to the following formula: ; Among them, C opt Cost(i) represents the total cost of optimized device scheduling and routing, where Cost(i) is the device maintenance cost of the i-th node and Distance(i) is the distance between the i-th node and the target device. This formula selects the optimal scheduling path and routing configuration by calculating the device scheduling cost and the distance between devices.

[0010] Preferably, the dynamic adjustment process in step 5 includes: By monitoring the real-time operating status data of the equipment, machine learning algorithms are used to predict the performance of cross-domain equipment, predict potential equipment failure points, and take measures in advance to reduce the risk of network interruption. Based on network load and device performance, dynamically adjust the device's operating mode, change bandwidth allocation and traffic management strategies, and ensure that the device can operate efficiently under different working conditions, avoiding network congestion and bandwidth bottlenecks.

[0011] Preferably, the cross-domain collaboration strategy in step 5 specifically includes: Based on the configuration requirements of different domains in the network, the network management policy is dynamically adjusted to ensure efficient collaboration between domains. The specific process includes selecting the optimal cross-domain resource configuration scheme to maximize the utilization efficiency of cross-domain devices. Intelligent algorithms are used to evaluate device performance and network load, and dynamic adjustments are made to cross-domain resources based on the evaluation results. Specifically, this includes cross-domain collaborative optimization through network topology adjustment, traffic allocation optimization, and bandwidth balancing.

[0012] Preferably, the network recovery and repair process in step 6 includes: When equipment failure occurs, the type of failure is detected, and a repair plan is proposed through the network management duty robot. The repair plan includes reconfiguring or replacing the faulty equipment and adjusting the working status of other nodes according to the repair progress. If a major network failure occurs and the automatic repair solution cannot resolve the issue, a manual repair process will be initiated through manual intervention, providing on-duty personnel with detailed repair guidelines and spare parts management functions.

[0013] This invention also provides a cross-domain collaborative network management system for power ASON, implementing the deployment method of the cross-domain collaborative network management system for power ASON described in any one of the above, including: The network management duty robot module is used to automatically collect and analyze the operating status of each node in the power communication optical transmission network, and optimize the system through automated scripts. The data analysis module is used to analyze equipment performance, traffic fluctuations and failure risks based on real-time collected node data, and predict potential failures through data mining and machine learning algorithms. The fault prediction module is used to predict potential faults and generate automatic scheduling strategies based on threshold settings and traffic analysis results. The alarm module is used to automatically issue early warnings and optimize scheduling when a fault occurs, and to provide system status feedback and repair suggestions to the on-duty personnel.

[0014] The network management duty robot module also includes: The repair module is used to restore the equipment of the power communication network according to the fault type and repair priority, and to ensure that the network interruption time is minimized. The resource management module is used to manage device resources based on device load, health status, and cross-domain collaboration strategies, thereby achieving efficient allocation and optimized scheduling of device resources.

[0015] Compared with the prior art, the technical effects of the present invention are as follows: This invention enables real-time monitoring, fault early warning, automatic repair, and dynamic optimization of power communication optical transmission networks through an intelligent network management robot, significantly improving network stability, reliability, and efficiency. Through cross-domain collaborative optimization and resource scheduling, the system can efficiently configure bandwidth, load balancing, and routing, reducing the need for manual intervention, accelerating fault recovery, and ensuring that the network operates in the optimal state. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0017] 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, and 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.

[0018] This invention provides, for example Figure 1 The method for deploying a cross-domain collaborative network management system for power ASON, as shown, includes the following steps: Step 1: Deploy a network management robot within the power communication optical transmission network. This robot acquires real-time operational status information from each node device via system interfaces, ensuring it can connect to and obtain status data from all devices within the power communication network, including node performance, operational status, and health status. This provides a data foundation for subsequent network management, fault prediction, and optimization decisions, ensuring the network management system can comprehensively monitor the power communication network. The specific steps of step 1 include: Step 1.1: Connect to the optical transmission network via remote monitoring equipment and collect data from each node, including the device's bandwidth utilization, response time, and traffic load information. By connecting to the remote monitoring equipment, real-time data collection of each communication node is achieved. The collected data includes key performance indicators such as bandwidth utilization, response time, and traffic load. This data reflects the operating status and load of each node in the network. This information helps to assess the health of the network and promptly detect problems such as traffic overload or response delay. Step 1.2: Set up automated scripts to extract transmission performance data of each node from the network management system in real time, and obtain the health status information of each node in real time, including device temperature, power status, and device faults. By using automated scripts, the efficiency and accuracy of data collection can be improved, and the operating status of each node can be obtained in real time, including important health indicators such as device temperature, power status, and device faults. This enables the network management system to continuously monitor the physical status and health status of the devices, and detect potential fault risks early, reducing the possibility of device downtime. The automated scripts are developed using Python 3.8+ and utilize the Paramiko library to establish SSH connections to remote node devices. First, the host key is loaded and the device is connected using Paramiko's SSHClient class (e.g., using the connect method to specify the host IP, port 22, username, and key path). Second, remote commands such as 'show system status' or custom SNMP query commands are executed to obtain raw data. Then, the Pandas library is used to parse the collected data into a structured format (such as CSV or JSON) and perform real-time cleaning (removing invalid values ​​and standardizing units). Finally, the Logging library records operation logs, and timers (such as the schedule library, executing every 5 seconds) are set to achieve real-time monitoring. This process ensures the accuracy and low latency of data collection and is suitable for multi-node (n≥100) scenarios in power ASON networks. Example code snippet: import paramiko # Used for SSH connections import pandas as pd # Used for data processing import logging # Used for logging from datetime import datetime # Used for timestamps # Configuration Log logging.basicConfig(filename='network_monitor.log', level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') def collect_node_status(host, username, key_path, commands): """ Function: Collects health status information of remote nodes parameter: - host: Node IP address (str) - username: SSH username (str) - key_path: Path to the private key file (str) - commands: A list of commands to execute, such as ['show temperature', 'show power-status']. Returns: Node state data in DataFrame format """ try: # Create an SSH client client = paramiko.SSHClient() client.set_missing_host_key_policy(paramiko.AutoAddPolicy()) # Automatically add a key for an unknown host. private_key = paramiko.RSAKey.from_private_key_file(key_path) # Load the RSA private key client.connect(hostname=host, username=username, pkey=private_key, port=22, timeout=10) data = [] # Store collected data for cmd in commands: stdin, stdout, stderr = client.exec_command(cmd) # Execute a remote command output = stdout.read().decode('utf-8').strip() # Read the output error = stderr.read().decode('utf-8').strip() # Check for errors if error: logging.error(f"Command {cmd} execution error: {error}") continue # Parse the output (assuming the output is in key-value pair format; you can customize the parsing logic according to the device) parsed = dict(line.split(':') for line inoutput.splitlines() if ':' in line) parsed['timestamp'] = datetime.now().isoformat() # Add timestamp data.append(parsed) # Use Pandas to convert to a DataFrame and clean it df = pd.DataFrame(data) df = df.dropna() # Remove null values logging.info(f"Data collection successful for node {host}: {df.to_dict()}") client.close() # Close the connection return df except Exception as e: logging.error(f"Failed to connect to node {host}: {str(e)}") return pd.DataFrame() # Return an empty DataFrame in case of failure # Example call (in the main script) if __name__ == "__main__": host = '192.168.1.100' # Example node IP username = 'admin' # Example username key_path = ' / path / to / private_key.pem' # Private key path commands = ['show temperature', 'show power-status', 'showfaults'] # Example commands, adjust according to the device status_df = collect_node_status(host, username, key_path,commands) if status_df.empty: status_df.to_csv('node_status.csv', index=False) # Save as a CSV file for later analysis; This code demonstrates how to use Paramiko to connect to a remote device and obtain its health status information, assuming that the node device supports SSH access and standard commands (such as on a Cisco or similar router). Step 1.3: Transmit the collected equipment information to the network management duty robot system for data cleaning and formatting for subsequent analysis and decision-making. This ensures that the collected equipment data can be transmitted to the network management duty robot system and cleaned and formatted, making the data suitable for further analysis and decision-making. The data cleaning and formatting process removes noise and redundant information, improves data quality, and ensures that subsequent analysis is based on accurate and consistent input, thereby supporting efficient fault diagnosis, performance optimization, and resource scheduling.

[0019] Step 2: Based on the operational status information, establish the topology diagram of the power communication network, and use a network management robot to monitor the status of each communication node, obtaining detailed performance indicators for each node, such as bandwidth utilization, transmission delay, and failure rate. This ensures that the network topology diagram of the power communication network can be updated in a timely manner based on the status data of each node, and that the network management robot enables real-time monitoring of each node. By monitoring key indicators such as bandwidth utilization, transmission delay, and failure rate, the overall operational status of the power communication network can be clearly understood, facilitating rapid problem location and response when anomalies occur. Step 2 includes the following specific steps: Step 2.1: Based on the IP addresses, locations, and connection information of the node devices, construct the topology of the power communication network and establish connections with each node device through the network management system. Constructing the topology diagram of the power communication network using the IP addresses, locations, and connection information of the node devices ensures that the actual network structure is accurately mapped. After establishing connections with each node, the network management robot can monitor the operating status of each node in real time, ensuring that the status of each device in the network is tracked and managed in real time. This step provides a basic framework and real-time data source for network status analysis and fault location. Step 2.2: Based on the real-time status information obtained by the network management duty robot, update the topology map to ensure that the status information of the power communication network is synchronized with the actual network topology. This ensures that the topology map of the power communication network can reflect the changing status of devices in the network in real time. For example, when a node fails or changes its connection status, the topology map will be updated in real time to reflect the changes in the device. This ensures that the network management system can always have an accurate network view, which helps to troubleshoot, optimize traffic and dynamically allocate network resources, and avoid management errors caused by inaccurate topology. Step 2.3: Perform performance tests on all nodes within the power communication network, including bandwidth, latency, and equipment health status. Monitor the operating status of each node in real time and respond to any abnormal conditions. By conducting performance tests on each node and monitoring key indicators such as bandwidth, latency, and equipment health status in real time, we can help evaluate the operating quality of the nodes. Through testing and monitoring, we can promptly identify performance bottlenecks, latency anomalies, or equipment failures, provide early warnings, and take measures to optimize the system. For example, if the bandwidth utilization of a certain node is too high, it may lead to network congestion. Timely response can prevent the system from overloading and ensure stable network operation.

[0020] Step 3: Based on node status data, automatically identify potential anomalies in the network and analyze their impact on the entire network service through algorithms to generate fault warnings and repair suggestions; By analyzing node status data and combining intelligent algorithms to identify potential anomalies, the network management system can provide early warnings before problems occur, greatly improving fault prevention capabilities. By assessing the impact of these anomalies on the entire network service, the system can intelligently generate repair suggestions, providing efficient support for subsequent fault handling and recovery. Step 3 includes the following specific steps: Step 3.1: Collect real-time traffic data for each communication node and use data mining techniques to identify abnormal traffic fluctuations and predict potential fault risks. The judgment of abnormal traffic fluctuations is based on the following formula: △F(t) = F(t) - F avg (t); Where ΔF(t) represents the flow fluctuation of a node at time t, and F(t) represents the real-time flow of that node. avg (t) represents the average traffic of the node during this time period. If ΔF(t) exceeds the set threshold, it is considered that a traffic anomaly has occurred. When the traffic fluctuation exceeds the preset threshold, abnormal traffic in the network can be identified in a timely manner, and potential bandwidth bottlenecks, network congestion or other traffic-related problems can be predicted. This can provide early warning and prevent these problems from developing into serious failures, thus ensuring the stability of the network. Step 3.2: Based on the characteristics of abnormal traffic, set multiple thresholds and trigger an early warning mechanism when the thresholds are exceeded, initiating automatic repair or manual intervention measures. The specific threshold settings are based on the device operating mode and historical fault data to ensure timely response to network fluctuations. When abnormal traffic exceeds the set threshold, the system will automatically trigger an early warning and initiate corresponding repair measures. Automatic repair or manual intervention can be selected. The threshold settings are dynamically adjusted based on the device operating mode and historical fault data to ensure that abnormal fluctuations under different devices and network environments can be addressed. This process can quickly respond to traffic fluctuations and reduce the impact of potential faults on the overall network service. Step 3.3: Based on the real-time collected equipment health data, assess the overall health index of the power communication network and identify weak links in the network. The formula for calculating the health index is as follows: ; Where H represents the health index, and W... i R represents the importance weight of the i-th node. iThe health score is given for the i-th node, and n is the number of nodes. The health index comprehensively considers factors such as the health status and importance weight of each node, and can objectively assess the overall health status of the network. At the same time, through this index, the system can identify the weakest link in the network, helping operation and maintenance personnel to focus on optimizing and maintaining key nodes and avoid potential network failures in advance.

[0021] Step 4: Generate corresponding deployment strategies based on the analysis results. Use the network management robot to schedule, configure, and optimize network devices, including but not limited to bandwidth adjustment, load balancing, and routing. The goal is to improve network operating efficiency and performance. Through this automated scheduling and optimization, the network management robot can ensure that network devices operate in the best way, thereby achieving efficient resource utilization and reducing network congestion and potential failures. In step 4, device scheduling and routing selection are performed according to the following formula: ; Among them, C opt Cost(i) represents the total cost of optimized device scheduling and routing, where Cost(i) is the device maintenance cost of the i-th node and Distance(i) is the distance between the i-th node and the target device. This formula selects the optimal scheduling path and routing configuration by calculating the device scheduling cost and the distance between devices. By calculating the maintenance cost of each node and the distance between nodes, the system can select the best path that minimizes costs while ensuring smooth data transmission. This optimization process can improve network efficiency, reduce energy consumption, avoid unnecessary resource waste, and improve network stability and response speed.

[0022] Step 5: During network deployment, dynamically adjust device configuration and routing selection, and optimize network management deployment based on cross-domain collaboration strategies. By dynamically adjusting device configuration and routing strategies in the network, ensure that network resources are fully optimized, improve the overall efficiency and stability of the network, and the dynamically adjusted strategy can adaptively adjust according to network load, device performance and cross-domain collaboration requirements, thereby ensuring that network resources can be optimally allocated under different operating environments and avoiding overload or resource waste. The dynamic adjustment process in step 5 includes: By monitoring real-time operating status data of equipment, machine learning algorithms are used to predict the performance of cross-domain equipment, predict potential equipment failure points, and take measures in advance to reduce the risk of network interruption. Machine learning algorithms can analyze historical and real-time data, predict potential equipment failure points, and trigger automated repair or resource scheduling, thereby effectively avoiding network interruption before failure occurs and improving network reliability and continuity. The machine learning algorithm is the Long Short-Term Memory (LSTM) network model algorithm, which predicts the performance of cross-domain devices. The algorithm trains the model based on historical operating status data (such as bandwidth utilization, latency and fault records). The input vector includes multi-dimensional features (such as temperature and flow rate), and the output is the probability of device failure risk. The training environment can use Python's TensorFlow or PyTorch framework. The model parameters include 128 hidden layer units and a learning rate of 0.001, and iterative training is performed using the Adam optimizer. The performance prediction process includes: The real-time status data of the equipment (such as temperature, flow, bandwidth, latency, fault records, etc.) is transmitted through the network management system. Then, features are extracted from the real-time data to generate input vectors. Machine learning models are then used to infer and predict the real-time data, outputting the probability of possible equipment failure risks or performance degradation.

[0023] Based on network load and device performance, the device's operating mode is dynamically adjusted, and bandwidth allocation and traffic management strategies are changed to ensure that the device can operate efficiently under different working conditions, avoiding network congestion and bandwidth bottlenecks. Real-time adjustment of bandwidth and traffic can effectively alleviate network pressure, improve network throughput, and ensure the priority of critical applications and services. At the same time, traffic management strategies can dynamically allocate resources, avoid overload, and optimize network performance.

[0024] The cross-domain collaboration strategy in step 5 specifically includes: Based on the configuration requirements of different domains in the network, the network management strategy is dynamically adjusted to ensure efficient collaboration between domains. The specific process includes selecting the optimal cross-domain resource configuration scheme to maximize the utilization efficiency of cross-domain devices; avoiding uneven or redundant resource allocation; and optimizing cross-domain resources to maximize the utilization efficiency of devices in each domain, improve the working efficiency of the entire power communication network, and reduce resource waste and redundant expenditures. Intelligent algorithms are used to evaluate device performance and network load, and dynamic adjustments are made to cross-domain resources based on the evaluation results. Specifically, this includes cross-domain collaborative optimization through network topology adjustment, traffic allocation optimization, and bandwidth balancing. Based on the evaluation results, the system can automatically adjust cross-domain resources, optimize traffic allocation and bandwidth balancing, and ensure that the synergy between various network domains is maximized. Dynamic adjustments can respond to changes in the needs of different domains in a timely manner, effectively avoiding overloading of a certain domain or node, thereby improving the overall load balancing and performance of the network.

[0025] Step 6: After a device failure occurs, perform network recovery and repair; The network recovery and repair process in step 6 includes: When a device malfunctions, the system detects the type of malfunction and proposes a repair plan via a network management robot. The repair plan includes reconfiguring or replacing the faulty device and adjusting the working status of other nodes according to the repair progress. During the repair process, the system can also dynamically adjust the working status of other nodes according to the repair progress to ensure that the repair process does not affect the operation of other devices and avoid further aggravating the impact of the malfunction. For example, when repairing a certain device, the network management robot can ensure network stability through load balancing, traffic adjustment, and other methods. If a major network failure occurs and the automatic repair solution cannot resolve the issue, a manual repair process will be initiated through manual intervention. Detailed repair guidelines and spare parts management functions will be provided to on-duty personnel to ensure they can quickly obtain the necessary spare parts, further reducing repair time. The initiation of the manual intervention process provides the system with flexibility and fault tolerance, ensuring that equipment functionality can be restored through manual operation in extreme cases, thus avoiding prolonged impacts of equipment failures on network services.

[0026] This invention also provides a cross-domain collaborative network management system for power ASON, and a deployment method for a cross-domain collaborative network management system for power ASON that implements any one of the above, comprising: The network management duty robot module is used to automatically collect and analyze the operating status of each node in the power communication optical transmission network, and optimize the system through automated scripts. The data analysis module is used to analyze equipment performance, traffic fluctuations, and failure risks based on real-time collected node data, and to predict potential failures through data mining and machine learning algorithms. The fault prediction module is used to predict potential faults and generate automatic scheduling strategies based on threshold settings and traffic analysis results. The alarm module is used to automatically issue early warnings and optimize scheduling when a fault occurs, providing system status feedback and repair suggestions to on-duty personnel.

[0027] The network management duty robot module also includes: The repair module is used to restore the equipment of the power communication network according to the fault type and repair priority, and to ensure that the network interruption time is minimized. The resource management module is used to manage device resources based on device load, health status, and cross-domain collaboration strategies, thereby achieving efficient allocation and optimized scheduling of device resources.

[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for deploying a cross-domain collaborative network management system for power ASON, characterized in that, Includes the following steps: Step 1: Deploy a network management robot within the power communication optical transmission network to obtain real-time operating status information of each node device through the system interface; Step 2: Based on the operating status information, establish the topology diagram of the power communication network, and use the network management duty robot to monitor the status of each communication node and obtain detailed performance indicators of each node; Step 3: Based on node status data, automatically identify possible anomalies in the network, analyze their impact on the entire network service through algorithms, and generate fault warnings and repair suggestions; Step 4: Generate corresponding deployment strategies based on the analysis results, and use the network management robot to schedule, configure and optimize network devices; Step 5: During network deployment, dynamically adjust equipment configuration and routing selection, and optimize network management deployment effectiveness based on cross-domain collaboration strategies; Step 6: After a device failure occurs, perform network recovery and repair.

2. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The specific steps of step 1 include: Step 1.1: Connect to the optical transmission network via remote monitoring equipment and collect data from each node, including the device's bandwidth utilization, device response time, and traffic load information. Step 1.2: Set up an automated script to extract transmission performance data of each node from the network management system in real time and obtain the health status information of each node in real time, including device temperature, power status, and device faults. Step 1.3: Transmit the collected device information to the network management duty robot system for data cleaning and formatting processing for subsequent analysis and decision-making.

3. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The specific steps of step 2 include: Step 2.1: Based on the IP address, location, and connection information of the node devices, construct the topology of the power communication network and establish connections with each node device through the network management system; Step 2.2: Based on the real-time status information obtained by the network management duty robot, update the topology map to ensure that the status information of the power communication network is synchronized with the actual network topology. Step 2.3: Perform performance tests on all nodes in the power communication network, including bandwidth, latency, and equipment health status. Monitor the operating status of each node in real time and respond to abnormal conditions.

4. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The specific steps of step 3 include: Step 3.1: Collect real-time traffic data for each communication node and use data mining techniques to identify abnormal traffic fluctuations and predict potential fault risks. The judgment of abnormal traffic fluctuations is based on the following formula: △F(t)=F(t)-F avg (t); Where ΔF(t) represents the flow fluctuation of a node at time t, and F(t) represents the real-time flow of that node. avg (t) represents the average flow rate of the node during this time period. If ΔF(t) exceeds the set threshold, it is considered that an abnormal flow rate has occurred. Step 3.2: Based on the characteristics of abnormal traffic, set multiple thresholds, and trigger an early warning mechanism when the thresholds are exceeded, and start automatic repair or manual intervention measures. The specific threshold settings are based on the equipment operating mode and historical fault data to ensure timely response to network fluctuations. Step 3.3: Based on the real-time collected equipment health data, assess the overall health index of the power communication network and identify weak links in the network. The formula for calculating the health index is as follows: ； Where H represents the health index, and W... i R represents the importance weight of the i-th node. i Let n be the health score of the i-th node, and n be the number of nodes.

5. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The device scheduling and routing selection in step 4 are performed according to the following formula: ； Among them, C opt Cost(i) represents the total cost of optimized device scheduling and routing, where Cost(i) is the device maintenance cost of the i-th node and Distance(i) is the distance between the i-th node and the target device. This formula selects the optimal scheduling path and routing configuration by calculating the device scheduling cost and the distance between devices.

6. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The dynamic adjustment process in step 5 includes: By monitoring the real-time operating status data of the equipment, machine learning algorithms are used to predict the performance of cross-domain equipment, predict potential equipment failure points, and take measures in advance to reduce the risk of network interruption. Based on network load and device performance, dynamically adjust the device's operating mode, change bandwidth allocation and traffic management strategies, and ensure that the device can operate efficiently under different working conditions, avoiding network congestion and bandwidth bottlenecks.

7. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The cross-domain collaboration strategy in step 5 specifically includes: Based on the configuration requirements of different domains in the network, the network management policy is dynamically adjusted to ensure efficient collaboration between domains. The specific process includes selecting the optimal cross-domain resource configuration scheme to maximize the utilization efficiency of cross-domain devices. Intelligent algorithms are used to evaluate device performance and network load, and dynamic adjustments are made to cross-domain resources based on the evaluation results. Specifically, this includes cross-domain collaborative optimization through network topology adjustment, traffic allocation optimization, and bandwidth balancing.

8. The method for deploying a cross-domain collaborative network management system for power ASON according to claim 1, characterized in that, The network recovery and repair process in step 6 includes: When equipment failure occurs, the type of failure is detected, and a repair plan is proposed through the network management duty robot. The repair plan includes reconfiguring or replacing the faulty equipment and adjusting the working status of other nodes according to the repair progress. If a major network failure occurs and the automatic repair solution cannot resolve the issue, a manual repair process will be initiated through manual intervention, providing on-duty personnel with detailed repair guidelines and spare parts management functions.

9. A cross-domain collaborative network management system for power ASON, implementing the deployment method of a cross-domain collaborative network management system for power ASON as described in any one of claims 1-8, characterized in that, include: The network management duty robot module is used to automatically collect and analyze the operating status of each node in the power communication optical transmission network, and optimize the system through automated scripts. The data analysis module is used to analyze equipment performance, traffic fluctuations and failure risks based on real-time collected node data, and predict potential failures through data mining and machine learning algorithms. The fault prediction module is used to predict potential faults and generate automatic scheduling strategies based on threshold settings and traffic analysis results. The alarm module is used to automatically issue early warnings and optimize scheduling when a fault occurs, and to provide system status feedback and repair suggestions to the on-duty personnel.

10. A cross-domain collaborative network management system for power ASON, characterized in that, The network management duty robot module also includes: The repair module is used to restore the equipment of the power communication network according to the fault type and repair priority, and to ensure that the network interruption time is minimized. The resource management module is used to manage device resources based on device load, health status, and cross-domain collaboration strategies, thereby achieving efficient allocation and optimized scheduling of device resources.

Images