Smart park communication network fusion control method, system and device

Abstract

The invention discloses a smart park communication network fusion management and control method, system and device, and relates to the technical field of communication network management and control, and the method comprises the steps: collecting and managing network data of different subnetworks through a management and control platform, and forming a global resource pool; different network protocols are analyzed in a unified manner through the protocol conversion gateway, so that data intercommunication among the sub-networks is realized; performing anomaly detection and early warning on the acquired network data based on a machine learning algorithm, and monitoring the network state in real time; network resource allocation is automatically optimized through a dynamic resource scheduling algorithm; and providing a visual terminal interface for displaying the state, the abnormal information and the dynamic scheduling strategy of each subnet. Network resource allocation is optimized through a dynamic resource scheduling algorithm, bandwidth and resource utilization efficiency is improved, network stability is guaranteed through anomaly detection and early warning based on machine learning, network load balancing is guaranteed through a load balancing technology, a network management process is simplified through a management and control platform integration module, and efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of communication network management and control, and particularly to a method, system, and device for integrated management and control of communication networks in smart campuses. Background Art

[0002] With the construction and development of smart campuses, the communication networks within the campuses have become increasingly complex, involving multiple subnets and different network protocols. These subnets include enterprise local area networks, Internet of Things networks, wireless networks, etc., which often use different communication protocols, leading to many challenges in data exchange and resource management. In order to efficiently manage these complex network resources, improve network bandwidth utilization, optimize network resource allocation, achieve cross-subnet data interconnection and real-time monitoring, the integrated management and control technology for communication networks in smart campuses has emerged. Currently, traditional communication network management and control methods face the following problems: uneven allocation of network resources among different subnets, resulting in overloaded resources in some subnets and idle resources in some subnets, affecting network performance; different communication protocols used by different subnets, resulting in unconnected data exchange and affecting the collaborative work of the system; when network anomalies occur, the detection and response speed of traditional methods is slow, and potential problems cannot be identified in a timely manner; when the network load changes, the network resources cannot be automatically adjusted, affecting network stability and user experience.

[0003] To solve these problems, the integrated management and control method for communication networks in smart campuses, based on the latest communication technologies and algorithms, proposes an integrated, automated, and intelligent management solution that can collect, analyze, and schedule network resources in real time, improving network reliability and efficiency. Summary of the Invention

[0004] To solve the above technical problems, there are provided a method, system, and device for integrated management and control of communication networks in smart campuses, and the present technical solution solves the above problems.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows: An integrated management and control method for communication networks in smart campuses, comprising: Collecting and managing network data of different subnets through a management and control platform to form a global resource pool; Performing unified parsing on different network protocols through a protocol conversion gateway to enable data interconnection between subnets; Performing anomaly detection and early warning on the collected network data based on machine learning algorithms to monitor the network status in real time; Automatically optimizing network resource allocation through a dynamic resource scheduling algorithm to improve the utilization efficiency of bandwidth and other network resources; providing a visual terminal interface for displaying the status, anomaly information, and dynamic scheduling strategies of each subnet.

[0006] Preferably, the collection and management of network data from different subnets by the control platform to form a global resource pool specifically includes: The control platform connects to the devices of each subnet through the southbound interface, and real-time collects the network data of each subnet, including network performance indicators such as traffic, bandwidth, latency, and packet loss rate; Preprocess the collected data. The preprocessing includes removing noise, outliers, and invalid data, formatting the data, unifying the data structure, and integrating data from different subnets; Classify and store the processed network data according to different network resource types to form a global resource pool. The resource pool adopts a distributed database method; Real-time synchronize the data of each subnet. During the data collection and update process, perform data verification and consistency check.

[0007] Preferably, the unified parsing of different network protocols through the protocol conversion gateway to enable data intercommunication between subnets specifically includes: The protocol conversion gateway identifies the network protocols used by different subnets and selects the corresponding parsing strategy according to the protocol type; Encapsulate the data of each protocol, parse the protocol-specific header information and data body, and through data encapsulation, convert the communication information of each subnet into JSON data format; The protocol conversion gateway converts the data received from different subnets, uses mapping rules to compare similar fields and attributes in different protocols, and processes the differences between protocols during the conversion process; Unify the data of different protocols into an API-oriented format, and through the standardized unified data format, enable data exchange between different subnets; The protocol conversion gateway forwards the parsed and unified formatted data. The data is transmitted from one subnet to another subnet. During the data forwarding process, the protocol conversion gateway can select the corresponding transmission protocol according to the requirements of the target subnet for data forwarding; According to the performance requirements and communication conditions of the subnet, the protocol conversion gateway automatically adapts and optimizes the transmission strategy of the protocol. After data intercommunication, cross-protocol data can be sent to the global resource pool.

[0008] Preferably, the abnormal detection and early warning of the collected network data based on machine learning algorithms and real-time monitoring of the network status specifically includes: Obtain the network data of each subnet from the control platform, including traffic data, latency, bandwidth usage, error rate, and network topology change information; Extract features from the preprocessed data using the principal component analysis method. Based on the extracted features, construct an anomaly detection model; train the selected algorithm using historical network data, and optimize the algorithm parameters according to the data characteristics and anomaly patterns of different subnets; Apply the trained model to the real-time data stream, continuously monitor the network status, and identify potential abnormal behaviors by comparing with the normal mode; When the network status is abnormal, the model automatically triggers the warning mechanism, and the system will generate warning messages at different levels according to the severity of the anomaly; Feed back the anomaly detection results to the operation and maintenance personnel through the management and control platform to provide anomaly information.

[0009] Preferably, the method of extracting features from the preprocessed data using the principal component analysis method and constructing an anomaly detection model based on the extracted features specifically includes: Among them, the formula of the anomaly detection model is: In the formula, is the final prediction result of the model for the input sample x, mv is to determine the final prediction based on the output results of all decision trees, T1(x), T2(x), …, T m (x) are the prediction functions of m decision trees in the random forest, x is the data point to be classified, and m is the number of trees in the random forest.

[0010] Preferably, the automatic optimization of network resource allocation and improvement of the utilization efficiency of bandwidth and other network resources through the dynamic resource scheduling algorithm specifically includes: Perform real-time analysis on the data in the resource pool, identify the trends and bottlenecks of resource usage in each subnet, and use time series analysis methods to predict the network traffic demand and load conditions in the future for a period of time; Based on the load assessment results, determine which subnet resources are overloaded, which resources are idle or redundant, and identify potential resource bottlenecks; dynamically adjust the resource allocation according to the real-time network traffic, predicted load information, and the requirements of each subnet; When the network load changes, the system automatically re-schedules resources according to the real-time monitoring results and optimization algorithm to ensure the balance of network load, and dynamically distributes traffic to each network node through load balancing technology.

[0011] Preferably, the method of performing real-time analysis on the data in the resource pool, identifying the trends and bottlenecks of resource usage in each subnet, and using time series analysis methods to predict the network traffic demand and load conditions in the future for a period of time specifically includes: Among them, the formula of the time series analysis method is: In the formula, is the predicted network traffic at the future k time steps, μ is a constant term representing the trend, is the autoregressive coefficient, ∈ t is the white noise error term.

[0012] Preferably, the dynamic adjustment of resource allocation according to real-time network traffic, predicted load information, and the requirements of each subnet specifically includes: Among them, the dynamic resource allocation formula is: In the formula, Z is the weighted sum of resource utilization minus the cost of the load, n is the number of subnets in the network, w i is the resource utilization weight of subnet i, R i is the resource usage efficiency of subnet i, c i is the load cost of subnet i, L i is the load of subnet i.

[0013] A smart campus communication network fusion control system includes: A control module for collecting, sorting, and managing network resource data of different subnets; A protocol conversion module for parsing network data of different protocols to ensure cross-platform interoperability of data; An intelligent analysis module integrating machine learning and big data analysis functions to monitor the network status in real time and perform anomaly detection; A visualization terminal module providing an operator-friendly interaction interface to support network monitoring and scheduling operations; A high-speed data bus module for efficient data transmission between modules.

[0014] A smart campus communication network fusion control device includes: A processor for executing computer instructions stored in a memory to complete network data collection, protocol parsing, analysis, and scheduling tasks; A memory for storing computer programs and network data to support efficient data storage and reading; A protocol conversion module for supporting data conversion of multiple network protocols to ensure network interoperability; An intelligent analysis module for analyzing the network status based on algorithms, identifying anomalies, and providing solutions.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes to optimize network resource allocation through a dynamic resource scheduling algorithm, improve bandwidth and resource utilization efficiency, use a protocol conversion gateway to achieve data interconnection between different subnets, avoid protocol difference problems, ensure network stability through anomaly detection and early warning based on machine learning, use load balancing technology to ensure network load balancing, provide a visualization management interface to support real-time monitoring and adjustment, improve network adaptability through the protocol conversion gateway, optimize data transmission strategies, and simplify the network management process through the integrated module of the control platform to improve efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart framework diagram of the steps of the present invention; Figure 2 It is a system framework diagram of the present invention; Figure 3 It is a schematic diagram of the device structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0018] Referring to Figure 1 as shown, the intelligent park communication network integration control method includes: Collect and manage network data of different subnets through the control platform to form a global resource pool; Use a protocol conversion gateway to uniformly parse different network protocols to enable data interconnection between subnets; Perform anomaly detection and early warning on the collected network data based on machine learning algorithms to monitor the network status in real time; Through a dynamic resource scheduling algorithm, automatically optimize network resource allocation, improve the usage efficiency of bandwidth and other network resources; provide a visualization terminal interface for displaying the status, anomaly information and dynamic scheduling strategies of each subnet.

[0019] Collecting and managing network data of different subnets through the control platform to form a global resource pool specifically includes: The control platform is connected to the devices of each subnet through a southbound interface to collect network data of each subnet in real time, including network performance indicators such as traffic, bandwidth, latency, and packet loss rate; Preprocess the collected data. The preprocessing includes removing noise, outliers and invalid data, formatting the data, unifying the data structure, and integrating data from different subnets; Classify and store the processed network data according to different network resource types to form a global resource pool. The resource pool uses a distributed database method; Real-time synchronize the data of each subnet, and perform data verification and consistency check during the data collection and update process; Through data collection, preprocessing, storage, and synchronization functions, this method solves the data quality problems caused by noise, outliers, and inconsistencies during the transmission of network data in each subnet. It uses a distributed database to store the global resource pool, enabling network management to share data in real time between different subnets and perform efficient analysis.

[0020] Unify the parsing of different network protocols through a protocol conversion gateway to enable data interoperability between each subnet, specifically including: The protocol conversion gateway identifies the network protocols used by different subnets and selects the corresponding parsing strategy according to the protocol type; Encapsulate the data of each protocol, parse the protocol-specific header information and data body, and through data encapsulation, convert the communication information of each subnet into the JSON data format; The protocol conversion gateway converts the data received from different subnets, uses mapping rules to compare similar fields and attributes in different protocols, and processes the differences between protocols during the conversion process; Unify the conversion of data in different protocols into an API-oriented format, and through a standardized unified data format, enable data exchange between different subnets; The protocol conversion gateway forwards the parsed and unified-formatted data. The data is transmitted from one subnet to another subnet. During the data forwarding process, the protocol conversion gateway can select the corresponding transmission protocol for data forwarding according to the requirements of the target subnet; According to the performance requirements and communication conditions of the subnet, the protocol conversion gateway automatically adapts and optimizes the transmission strategy of the protocol. After data interoperability, cross-protocol data can be sent to the global resource pool; The introduction of the protocol conversion gateway enables interoperability between different subnets in the presence of different network protocols. Through protocol encapsulation, parsing, and conversion, the originally heterogeneous network environment is standardized through a unified data format, improving the efficiency and accuracy of data exchange.

[0021] Perform anomaly detection and early warning on the collected network data based on machine learning algorithms, and monitor the network status in real time, specifically including: Obtain the network data of each subnet from the management and control platform, including traffic data, latency, bandwidth usage, error rate, and network topology change information; Extract features from the preprocessed data based on the principal component analysis method, and build an anomaly detection model based on the extracted features; use historical network data to train the selected algorithm, and optimize the algorithm parameters according to the data characteristics and anomaly patterns of different subnets; Apply the trained model to the real-time data stream, continuously monitor the network status, and identify potential abnormal behaviors by comparing with the normal mode; When the network status is abnormal, the model automatically triggers the warning mechanism, and according to the severity of the abnormality, the system will generate warning messages at different levels; Feed the abnormal detection results back to the operation and maintenance personnel through the management and control platform to provide abnormal information; Combined with machine learning algorithms and data preprocessing, real-time abnormal detection and warning of network status are realized. This solution is trained based on historical network data, combined with information such as network topology changes, and can intelligently identify potential abnormal behaviors, and trigger warnings in a timely manner according to the severity, avoiding the lag and error rate of traditional monitoring systems.

[0022] Extract features from the preprocessed data based on the principal component analysis method. Based on the extracted features, the construction of the abnormal detection model specifically includes: Among them, the formula of the abnormal detection model is: In the formula, is the final prediction result of the model for the input sample x, mv is to determine the final prediction based on the output results of all decision trees, T1(x), T2(x),..., T m (x) are the prediction functions of m decision trees in the random forest, x is the data point to be classified, and m is the number of trees in the random forest.

[0023] Through the dynamic resource scheduling algorithm, automatically optimize the network resource allocation and improve the usage efficiency of bandwidth and other network resources. Specifically include: Conduct real-time analysis on the data in the resource pool, identify the trends and bottlenecks of resource usage in each subnet, and use time series analysis methods to predict the network traffic demand and load conditions in the next period of time; Based on the load assessment results, judge which subnet resources are overloaded, which resources are idle or redundant, and identify potential resource bottlenecks; dynamically adjust the resource allocation according to the real-time network traffic, predicted load information and the requirements of each subnet; When the network load changes, the system automatically performs resource rescheduling according to the real-time monitoring results and optimization algorithms to ensure the balance of network load. Through load balancing technology, the traffic is dynamically distributed to each network node; The dynamic resource scheduling algorithm can automatically optimize the allocation of bandwidth and other network resources based on real-time network data and traffic prediction, improve the resource usage efficiency, avoid the waste of traditional static resource allocation, and through the application of load balancing technology, can effectively cope with network load fluctuations and ensure that the network can still operate efficiently and stably under high load.

[0024] Perform real-time analysis on the data in the resource pool, identify the trends and bottlenecks in resource usage in each subnet, and use time series analysis methods to predict the network traffic demand and load conditions in the next period. Specifically include: Among them, the formula of the time series analysis method is: In the formula, is the predicted network traffic at the next k time steps, μ is the constant term, representing the trend, is the autoregressive coefficient, ∈ t is the white noise error term.

[0025] Dynamically adjust resource allocation according to the real-time network traffic, predicted load information, and the requirements of each subnet. Specifically include: Among them, the formula for dynamic resource allocation is: In the formula, Z is the weighted sum of resource utilization minus the cost of the load, n is the number of subnets in the network, w i is the resource utilization weight of subnet i, R i is the resource usage efficiency of subnet i, c i is the load cost of subnet i, L i is the load of subnet i.

[0026] Refer to Figure 2 As shown, a fusion control and management system for a smart park communication network includes: A control module, used to collect, organize, and manage network resource data of different subnets; A protocol conversion module, used to parse network data of different protocols to ensure cross-platform interoperability of data; An intelligent analysis module, integrating machine learning and big data analysis functions, to monitor the network status in real time and perform anomaly detection; A visualization terminal module, providing an operator-friendly interaction interface to support network monitoring and scheduling operations; A high-speed data bus module, used for efficient data transmission between modules.

[0027] Refer to Figure 3 As shown, a fusion control and management device for a smart park communication network includes: A processor, used to execute computer instructions stored in the memory to complete network data collection, protocol parsing, analysis, and scheduling tasks; A memory, used to store computer programs and network data to support efficient data storage and reading; A protocol conversion module, used to support data conversion of multiple network protocols to ensure network interoperability; The intelligent analysis module analyzes the network status based on algorithms, identifies anomalies, and provides solutions.

[0028] In summary, the advantages of the present invention are as follows: Through the dynamic resource scheduling algorithm, it can analyze the data in the resource pool in real time, identify the trends and bottlenecks in resource usage in each subnet, automatically optimize resource allocation, and improve the usage efficiency of bandwidth and other network resources; The protocol conversion gateway uniformly parses the network protocols used by different subnets and converts them into a standardized data format, enabling efficient data intercommunication between different subnets and avoiding data compatibility problems caused by protocol differences; Based on the machine learning algorithm, the system can perform anomaly detection and early warning on the collected network data, monitor the network status in real time. Through the training of historical data, the system can automatically identify potential abnormal behaviors and trigger early warnings to ensure network stability; through the load balancing technology, the system can dynamically adjust resource allocation according to real-time network traffic, predicted load information, and the requirements of each subnet to ensure network load balancing and avoid overload or resource waste; The visual terminal interface provided by the system can display the status, anomaly information, and dynamic scheduling strategies of each subnet, enabling operation and maintenance personnel to grasp the network status in real time and take timely measures for adjustment; The protocol conversion gateway can automatically adapt and optimize the protocol transmission strategy according to the requirements of the target subnet to ensure efficient data transmission and intercommunication, enabling the network to better cope with the changing demands of different application scenarios; By integrating different functional modules through the management and control platform, uniformly collecting, managing, and analyzing network data, it simplifies the traditional network management process, reduces manual intervention, and improves network management efficiency.

[0029] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. Smart park communication network integration control method, characterized in that, It includes: Collect and manage the network data of different subnets through a control platform to form a global resource pool; Unify the parsing of different network protocols through a protocol conversion gateway to enable data intercommunication between subnets; Based on machine learning algorithms, perform anomaly detection and early warning on the collected network data, and monitor the network status in real time; Through a dynamic resource scheduling algorithm, automatically optimize network resource allocation and improve the usage efficiency of bandwidth and other network resources; Provide a visual terminal interface for displaying the status, anomaly information, and dynamic scheduling strategies of each subnet.

2. The intelligent park communication network fusion control method according to claim 1, wherein The specific steps of collecting and managing the network data of different subnets through the control platform to form a global resource pool include: The control platform connects to the devices of each subnet through a southbound interface, and collects the network data of each subnet in real time, including network performance indicators such as traffic, bandwidth, latency, and packet loss rate; Preprocess the collected data. The preprocessing includes removing noise, outliers, and invalid data, formatting the data, unifying the data structure, and integrating data from different subnets; Classify and store the processed network data according to different network resource types to form a global resource pool. The resource pool adopts a distributed database method; Synchronize the data of each subnet in real time, and perform data verification and consistency check during the data collection and update process.

3. The intelligent park communication network fusion control method according to claim 2, wherein The specific steps of unifying the parsing of different network protocols through the protocol conversion gateway to enable data intercommunication between subnets include: The protocol conversion gateway identifies the network protocols used by different subnets and selects the corresponding parsing strategy according to the protocol type; Encapsulate the data of each protocol, parse the protocol-specific header information and data body, and through data encapsulation, convert the communication information of each subnet into JSON data format; The protocol conversion gateway converts the data received from different subnets, uses mapping rules to compare similar fields and attributes in different protocols, and processes the differences between protocols during the conversion process; Unify the data of different protocols into an API-oriented format, and enable data exchange between different subnets through a standardized unified data format; The protocol conversion gateway forwards the parsed and unified formatted data. The data is transmitted from one subnet to another subnet. During the data forwarding process, the protocol conversion gateway can select the corresponding transmission protocol according to the requirements of the target subnet for data forwarding; According to the performance requirements and communication conditions of the subnet, the protocol conversion gateway automatically adapts and optimizes the transmission strategy of the protocol. After data intercommunication, cross-protocol data can be sent to the global resource pool.

4. The intelligent park communication network fusion control method according to claim 3, characterized in that, The specific steps of performing anomaly detection and early warning on the collected network data based on machine learning algorithms and monitoring the network status in real time include: Obtain the network data of each subnet from the control platform, including traffic data, latency, bandwidth usage, error rate, and network topology change information; Extract features from the preprocessed data based on the principal component analysis method, and build an anomaly detection model based on the extracted features; use historical network data to train the selected algorithm, and optimize the algorithm parameters according to the data characteristics and anomaly patterns of different subnets; Apply the trained model to the real-time data stream to continuously monitor the network status, and identify potential abnormal behaviors by comparing with the normal mode; When the network status is abnormal, the model automatically triggers the warning mechanism, and the system generates warning messages at different levels according to the severity of the abnormality; Feed back the anomaly detection results to the operation and maintenance personnel through the management and control platform to provide anomaly information.

5. The intelligent park communication network fusion control method according to claim 4, characterized in that, The method based on principal component analysis extracts features from the preprocessed data, and constructs an anomaly detection model specifically including: Among them, the anomaly detection model formula is: Wherein, is the final prediction result of the model for the input sample x, and mv determines the final prediction based on the output results of all decision trees. T1(x), T2(x), …, T m (x) are the prediction functions of m decision trees in the random forest, x is the data point to be classified, and m is the number of trees in the random forest.

6. The intelligent park communication network fusion control method according to claim 5, wherein The automatic optimization of network resource allocation through the dynamic resource scheduling algorithm to improve the utilization efficiency of bandwidth and other network resources specifically includes: Perform real-time analysis on the data in the resource pool, identify the trends and bottlenecks of resource usage in each subnet, and use time series analysis methods to predict the network traffic demand and load conditions in the next period of time; Based on the load assessment results, determine which subnet resources are overloaded, which resources are idle or redundant, and identify potential resource bottlenecks; dynamically adjust resource allocation according to the real-time network traffic, predicted load information, and the requirements of each subnet; When the network load changes, the system automatically re-schedules resources according to the real-time monitoring results and optimization algorithms to ensure the balance of network load, and dynamically distributes traffic to each network node through load balancing technology.

7. The intelligent park communication network fusion control method according to claim 6, wherein The real-time analysis of the data in the resource pool to identify the trends and bottlenecks of resource usage in each subnet, and use time series analysis methods to predict the network traffic demand and load conditions in the next period of time specifically including: Among them, the time series analysis method formula is: wherein, is the predicted network traffic at the next k time steps, μ is a constant term representing the trend, is the autoregressive coefficient, ∈ t is the white noise error term.

8. The intelligent park communication network fusion control method according to claim 7, wherein The dynamic adjustment of resource allocation according to the real-time network traffic, predicted load information, and the requirements of each subnet specifically including: Among them, the dynamic resource allocation formula is: where Z is the weighted sum of resource utilization minus the cost of the load, n is the number of subnets in the network, w i is the resource utilization weight of subnet i, R i is the resource utilization efficiency of subnet i, c i is the load cost of subnet i, L i is the load of subnet i.

9. A communication network integration control system for an intelligent park, characterized in that, including: A management and control module for collecting, sorting, and managing network resource data of different subnets; A protocol conversion module for parsing network data of different protocols to ensure cross-platform interoperability of data; An intelligent analysis module integrating machine learning and big data analysis functions to continuously monitor the network status and perform anomaly detection; A visualization terminal module providing an operator-friendly interaction interface to support network monitoring and scheduling operations; A high-speed data bus module for efficient data transmission between modules.

10. A communication network fusion control device for an intelligent park, characterized in that, including: A processor for executing computer instructions stored in the memory to complete network data collection, protocol parsing, analysis, and scheduling tasks; A memory for storing computer programs and network data to support efficient data storage and reading; A protocol conversion module for supporting data conversion of multiple network protocols to ensure network interoperability; An intelligent analysis module for analyzing the network status based on algorithms, identifying anomalies, and providing solutions.

Images