An active early warning campus network monitoring system

Abstract

The present invention discloses an active early warning type park network monitoring system, which relates to the field of network monitoring technology, and includes: an acquisition module, an image analysis module, an early warning module and a management module; the acquisition module acquires network data of each device in the park, acquires network conditions, and converts the acquired network data into a line graph for display; the image analysis module is electrically connected to the acquisition module, and the image analysis module analyzes the acquired line graph, proposes park network characteristics, analyzes the network conditions of park equipment based on a trend analysis method, and predicts the network conditions of park equipment in the future. When the present invention predicts that a failure of the park network may occur in the future, the early warning module will immediately issue an alarm, and timely early warning allows network management personnel to take action before the failure occurs, greatly reducing the impact of the failure on the park network, timely discovering hidden dangers, and reducing losses.

Description

Technical Field

[0001] The present invention relates to the technical field of network monitoring, and in particular to an active early warning type park network monitoring system. Background Art

[0002] The network monitoring system is an important tool for monitoring and managing campus networks. It plays a key role in ensuring stable network operation and efficient service. The network monitoring system is usually composed of multiple key parts. The first is the data acquisition module, which uses various advanced sensors and monitoring tools to collect various data in the campus network in real time, including network traffic, device status, and connection performance. These data are like the "eyes" of the system, providing basic materials for subsequent analysis and decision-making. With the rapid development of information technology, campus networks play a vital role in modern enterprises, scientific research institutions, industrial parks and other types of parks. The campus network not only carries the internal office automation, production management, and data of the enterprise, but also carries the information of the campus network, the campus network also plays a key role in ensuring stable network operation and efficient service. However, with the continuous expansion of the scale of the park, the increasing number of network devices and the increasing complexity of network applications, the management and maintenance of the park network are facing more and more severe challenges. At present, most park network monitoring systems adopt passive monitoring mode, that is, they will only issue an alarm when the network fails or the performance degrades. This method often leads to untimely discovery of problems, which has a serious impact on the normal operation of the park. For example, when network congestion causes delays in the transmission of important business data, it may have caused irreparable losses to the production process or business decision-making. In this regard, we propose an active early warning park network monitoring system. Summary of the invention

[0003] In order to solve the above technical problems, an active early warning campus network monitoring system is provided. This technical solution solves the problem of losses caused by the above passive monitoring.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: an active early warning type campus network monitoring system, including: a collection module, an image analysis module, an early warning module and a management module; The collection module obtains network data from each device in the park, collects network conditions, and converts the collected network data into a line graph for display; The image analysis module is electrically connected to the acquisition module. The image analysis module analyzes the obtained line graph, proposes the characteristics of the park network, analyzes the network status of the park equipment based on the trend analysis method, and predicts the network status of the park equipment in the future. The early warning module is electrically connected to the image analysis module. Based on the prediction results, the early warning module warns of future faults in the campus network by using sound and light alarms. The management module is electrically connected to the early warning module. The management module manages and configures the campus network, makes timely adjustments to future fault conditions, and provides a user interface for management personnel to manage and operate.

[0005] Preferably, the collection module includes a collection unit, a conversion unit and a visualization display unit, wherein the collection unit acquires network data of each device in the park in real time, including but not limited to network traffic, delay and packet loss rate, and the collection module monitors and collects data from the park network based on network monitoring tools; the conversion unit pre-processes the acquired data, draws it into a fluctuating line graph, processes and analyzes the collected network data, extracts key indicators, and converts them into a data format for visualization; the visualization display unit displays the processed network data in the form of a line graph, which reflects the changing trend of the network data and helps network managers quickly understand the network situation.

[0006] Preferably, the image analysis module analyzes the line graph, including the trend, fluctuation amplitude, peak and valley characteristics of the line, analyzes the characteristics, extracts the campus network characteristics, conducts in-depth analysis on the network status of the campus equipment based on the trend analysis method, and predicts the future network status of the campus equipment based on the analysis results, taking into account the changing patterns of historical data, the current network trends and external factors that may affect the network status, to predict the future network status of the campus equipment.

[0007] Preferably, the trend analysis method assumes that the network monitoring point sequence is V1, V2, ... V n , the moving average window size is m, then the moving average of the i-th data point is: ; Among them, MA i is the moving average of the i-th data point, and the trend of the network status is observed through the formula.

[0008] Preferably, based on the analysis results, the network status of the future campus equipment is predicted, and the network status of the future campus equipment is predicted by considering the changing rules of historical data, the current network trend and the external factors that may affect the network status. The analysis is performed based on the trend extrapolation prediction formula, which is: ; Where y is the predicted network index value, a and b are weights, and the predicted value y in the future park is obtained. The predicted value is analyzed by adding external factors. The analysis formula is: ; Where N w is the network status of the future campus equipment, Tc is the influencing factor of the network trend, and wi Weight, F i The specific value of the external factor is used to predict the future network status of the park equipment through the formula.

[0009] Preferably, the calculation of the network trend influencing factor Tc includes the quantification of the change rate and the fluctuation situation, determining the network status values ​​at two time points in the current time period, assuming that the network delay at the initial time point is D1, the network delay at the end time point is D2, the time interval is △t, and the change rate R=(D2-D1) / △t, mapping the calculated change rate to the interval of (0, 1), assuming that the normal change rate range is (R min , R max ), then the standardized rate of change is R b =(RR min ) / (R max -R min ); To quantify the fluctuation, assume that the normal range of the standard deviation is (c min , c max ), the standardized fluctuation is: c z =(cc min ) / (c max -c min ); Conduct a comprehensive evaluation, Tc=α*R b +βc z , where α and β are weight coefficients, and the value of the network trend influence factor Tc is calculated by the formula.

[0010] Preferably, the early warning module warns of future failures in the campus network based on the prediction results of the future campus equipment network status. When the prediction results show that there is a potential failure risk in the campus network, the early warning module uses sound and light alarms to attract the attention of relevant personnel at the first time. In terms of sound alarms, the early warning module emits a loud and rapid alarm sound, and the early warning module uses flashing lights to further enhance the early warning effect.

[0011] Preferably, the early warning module obtains a threshold of a safety network, and compares the predicted result with the safety threshold. If it is greater than the safety threshold, the early warning module issues an early warning, and if it is less than the safety threshold, monitoring continues.

[0012] Preferably, the management module conducts comprehensive management and fine configuration of the campus network. According to the prediction results of the early warning module, the management module conducts adjustment management, analyzes the type, scope of impact and severity of potential faults, and formulates targeted adjustment plans. For network congestion problems, the management module alleviates the pressure by optimizing network traffic distribution and adjusting data transmission paths.

[0013] Preferably, the management module provides managers with an intuitive and convenient user interface with good interactivity and ease of use, allowing them to view various parameters and operating indicators of the campus network in real time and understand the current status and historical trends of the network.

[0014] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention conducts in-depth analysis on the obtained line graph, and the image analysis module can extract the key features of the campus network. Based on the trend analysis method, the network status of the campus equipment is analyzed, and the future network status of the campus equipment can be predicted according to the changing trend of historical data. This forward-looking analysis can allow network management personnel to prepare in advance and take corresponding measures to deal with possible problems. When it is predicted that the campus network may fail in the future, the early warning module will immediately issue an alarm. Timely early warning can allow network management personnel to take action before the failure occurs, which greatly reduces the impact of the failure on the campus network, discovers hidden dangers in time, and reduces losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a framework diagram of the network monitoring system of the present invention. DETAILED DESCRIPTION

[0016] 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 described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1 As shown, an active early warning type campus network monitoring system includes: a collection module, an image analysis module, an early warning module and a management module; The collection module obtains network data from each device in the park, collects network conditions, and converts the collected network data into a line graph for display; The image analysis module is electrically connected to the acquisition module. The image analysis module analyzes the obtained line graph, proposes the characteristics of the park network, analyzes the network status of the park equipment based on the trend analysis method, and predicts the network status of the park equipment in the future. The early warning module is electrically connected to the image analysis module. Based on the prediction results, the early warning module warns of future faults in the campus network by using sound and light alarms. The management module is electrically connected to the early warning module. The management module manages and configures the campus network, makes timely adjustments to future fault conditions, and provides a user interface for management personnel to manage and operate.

[0018] The present invention analyzes the network status of the campus equipment based on the trend analysis method and can predict the network status of the campus equipment in the future, so that the management personnel can prepare in advance and take preventive measures to avoid the impact of potential network failures on the campus business. The early warning module is electrically connected to the image analysis module and can warn of future failures of the campus network based on the prediction results. Through the sound and light alarm mode, it can quickly attract attention even in a noisy environment or when the management personnel are not paying attention, ensuring that the fault information can be communicated in time. Timely warning allows the management personnel to take measures before the failure occurs, such as adjusting the network configuration and increasing resource allocation, thereby reducing the possibility and impact of the failure and reducing It reduces economic losses and business interruption time caused by network failures, provides a user interface for management and operation, and makes network management more convenient. Management personnel can view network status, set parameters, and perform management tasks through an intuitive interface. They can easily manage the network without professional technical knowledge. Various modules cooperate with each other to form a complete campus network monitoring and management system. From data collection to analysis, early warning and management, each link plays an important role, and together they provide strong guarantees for the stable operation and efficient service of the campus network. It improves the efficiency and accuracy of network management, reduces the risk of network failures, and creates a more reliable network environment for enterprises and users in the park.

[0019] The collection module includes a collection unit, a conversion unit and a visualization unit. The collection unit acquires the network data of each device in the park in real time, including but not limited to network traffic, delay and packet loss rate. The collection module monitors and collects the park network based on the network monitoring tool; the conversion unit pre-processes the acquired data and draws it into a fluctuating line graph, processes and analyzes the collected network data, extracts key indicators, and converts them into a data format for visualization; the visualization unit displays the processed network data in the form of a line graph, which reflects the changing trend of the network data and helps network managers quickly understand the network situation.

[0020] The present invention adopts network monitoring tools to monitor and collect data in the park network, which can ensure the accuracy and reliability of data. Professional network monitoring tools usually have efficient data collection algorithms and stable performance, and can accurately obtain various network data in complex network environments. At the same time, these tools can also adapt to different types of network equipment to ensure that all equipment in the park can be fully covered, thereby improving the integrity of data collection.

[0021] The image analysis module analyzes the line graph, including the trend, fluctuation amplitude, peak and valley characteristics of the line, analyzes the characteristics, extracts the campus network characteristics, conducts in-depth analysis of the network status of campus equipment based on the trend analysis method, and predicts the future network status of campus equipment based on the analysis results, taking into account the changing patterns of historical data, current network trends and external factors that may affect the network status, to predict the future network status of campus equipment.

[0022] The present invention conducts an in-depth analysis of the network status of campus equipment based on the trend analysis method, and can predict the network status of campus equipment in the future. By considering the changing rules of historical data, the development trend of the network can be discovered, such as whether the network traffic shows a periodic increase or decrease. Combined with the current network trend, the latest changes in the network status can be captured in time, such as the recent increase in network delay or the increase in packet loss rate. At the same time, external factors that may affect the network status, such as the access of new equipment in the campus and the risk of network attacks, can be considered to improve the accuracy and reliability of the prediction.

[0023] Trend analysis method: Assume that the network monitoring point sequence is V1, V2, ... V n , the moving average window size is m, then the moving average of the i-th data point is: ; Among them, MA i is the moving average of the i-th data point, and the trend of the network status is observed through the formula.

[0024] The trend analysis method in the present invention is mainly based on the following assumptions: past trends will continue to a certain extent into the future. It collects and analyzes a series of time series data and observes how the data changes over time to find out potential trends. These data can be quantitative values, such as sales, output, and price, or qualitative indicators, such as market share and user satisfaction. By analyzing historical data, the trend analysis method can predict future development trends and provide forward-looking information for decision-making. The analysis is based on objective historical data, which reduces the influence of subjective factors and improves the scientificity and accuracy of decision-making. By observing changes in trends, potential problems and opportunities can be discovered in a timely manner, and corresponding measures can be taken to deal with them.

[0025] Based on the analysis results, the network status of the future campus equipment is predicted. Considering the changing rules of historical data, the current network trends and external factors that may affect the network status, the network status of the future campus equipment is predicted. The analysis is based on the trend extrapolation prediction formula, which is: ; Where y is the predicted network index value, a and b are weights, and the predicted value y in the future park is obtained. The predicted value is analyzed by adding external factors. The analysis formula is: ; Where N w is the network status of the future campus equipment, Tc is the influencing factor of the network trend, and w i Weight, F i The specific value of the external factor is used to predict the future network status of the park equipment through the formula.

[0026] The calculation of the network trend influencing factor Tc includes the quantification of the change rate and the fluctuation situation. The network status values ​​at two time points in the current time period are determined. The network delay at the initial time point is set to D1, the network delay at the end time point is set to D2, the time interval is △t, and the change rate R= (D2-D1) / △t. The calculated change rate is mapped to the interval of (0, 1). The normal change rate range is set to (R min , R max ), then the standardized rate of change is R b =(RR min ) / (R max -R min ); To quantify the fluctuation, assume that the normal range of the standard deviation is (c min , c max ), the standardized fluctuation is: c z =(cc min ) / (c max -c min ); Conduct a comprehensive evaluation, Tc=α*R b +βc z , where α and β are weight coefficients, and the value of the network trend influence factor Tc is calculated by the formula.

[0027] The network trend influencing factors in the present invention include the network traffic growth trend: the change in network traffic is one of the important indicators of network trends. If the network traffic continues to grow, it may mean that business activities in the park increase or new applications and devices are connected to the network. For example, as the business of the enterprise expands, the demand for data transmission increases, and the network traffic may show an upward trend; Delay and packet loss rate changes: Delay and packet loss rate changes reflect the stability and reliability of the network. If the delay increases or the packet loss rate rises, it may indicate network congestion or failure. On the contrary, stable or declining delay and packet loss rate indicate good network performance; Changes in bandwidth utilization: Bandwidth utilization reflects the use of network resources. If bandwidth utilization continues to increase, you may need to consider expanding the network bandwidth to meet future demand.

[0028] The early warning module warns of future failures in the campus network based on the prediction results of the future campus equipment network status. When the prediction results show that there is a potential risk of failure in the campus network, the early warning module uses sound and light alarms to attract the attention of relevant personnel at the first time. In terms of sound alarms, the early warning module emits a loud and rapid alarm sound, and the early warning module uses flashing lights to further enhance the early warning effect.

[0029] The present invention provides early warning based on the predicted results of the future network status of campus equipment, and can give relevant personnel enough time to take countermeasures before potential failures actually occur. This can greatly reduce the economic losses, time costs and impact on business caused by network failures. For example, in the production environment of an enterprise, timely early warning can avoid production line stagnation caused by network failures, and reduce the risk of product loss and delayed delivery.

[0030] The early warning module obtains a threshold of a safe network and compares the predicted result with the safety threshold. If it is greater than the safety threshold, the early warning module will issue an early warning. If it is less than the safety threshold, monitoring will continue.

[0031] The present invention can more accurately determine whether there is a risk in the network status by obtaining the safety network threshold and comparing the prediction result with it. The safety threshold is determined based on the normal operating parameters of the network and historical experience, and can be used as a clear standard to measure the safety of the current network status. If the prediction result is greater than the safety threshold, it means that the network may face potential failures or safety problems. The early warning module will issue an alarm in time to avoid false positives or omissions caused by inaccurate subjective judgments.

[0032] The management module conducts comprehensive management and detailed configuration of the campus network. Based on the prediction results of the early warning module, the management module conducts adjustment management, analyzes the type, scope of impact and severity of potential faults, and formulates targeted adjustment plans. For network congestion problems, the management module alleviates the pressure by optimizing network traffic distribution and adjusting data transmission paths.

[0033] The present invention performs adjustment management according to the prediction results of the early warning module, and can take measures before potential failures occur to achieve early prevention. By analyzing the type, impact range and severity of potential failures, the management module can formulate targeted adjustment plans to avoid the occurrence of failures or reduce the impact of failures.

[0034] The management module provides managers with an intuitive and convenient user interface with good interactivity and ease of use, allowing them to view various parameters and operating indicators of the campus network in real time and understand the current status and historical trends of the network.

[0035] The managers of the present invention can quickly view various parameters and operating indicators of the campus network through an intuitive user interface without spending a lot of time searching and interpreting complex data tables or reports, which greatly improves the speed of information acquisition. For example, in an emergency, the key parameters of the network fault point can be quickly understood so as to make timely decisions.

[0036] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. An active early warning campus network monitoring system, characterized in that: include: Acquisition module, image analysis module, early warning module and management module; The collection module obtains network data from each device in the park, collects network conditions, and converts the collected network data into a line graph for display; The image analysis module is electrically connected to the acquisition module. The image analysis module analyzes the obtained line graph, proposes the characteristics of the park network, analyzes the network status of the park equipment based on the trend analysis method, and predicts the network status of the park equipment in the future. The early warning module is electrically connected to the image analysis module. Based on the prediction results, the early warning module warns of future faults in the campus network by using sound and light alarms. The management module is electrically connected to the early warning module. The management module manages and configures the campus network, makes timely adjustments to future fault conditions, and provides a user interface for management personnel to manage and operate.

2. The active early warning campus network monitoring system according to claim 1 is characterized in that: The collection module includes a collection unit, a conversion unit and a visualization unit. The collection unit acquires network data of each device in the park in real time, including but not limited to network traffic, delay and packet loss rate. The collection module monitors and collects park networks based on network monitoring tools. The conversion unit pre-processes the acquired data and draws it into a fluctuating line graph. It processes and analyzes the collected network data, extracts key indicators, and converts them into a data format for visualization. The visualization display unit displays the processed network data in the form of a line graph, which reflects the changing trend of the network data and helps network managers quickly understand the network status.

3. The active early warning campus network monitoring system according to claim 1 is characterized in that: The image analysis module analyzes the line graph, including the trend, fluctuation amplitude, peak and valley characteristics of the line, analyzes the characteristics, extracts the campus network characteristics, conducts in-depth analysis of the network status of campus equipment based on the trend analysis method, and predicts the future network status of campus equipment based on the analysis results, taking into account the changing patterns of historical data, current network trends and external factors that may affect the network status, to predict the future network status of campus equipment.

4. The active early warning campus network monitoring system according to claim 3 is characterized in that: Trend analysis method: Assume that the network monitoring point sequence is V1, V2, ... V n , the moving average window size is m, then the moving average of the i-th data point is: ； Among them, MA i is the moving average of the i-th data point, and the trend of the network status is observed through the formula.

5. The active early warning campus network monitoring system according to claim 3 is characterized in that: Based on the analysis results, the network status of the future campus equipment is predicted. Considering the changing rules of historical data, the current network trends and external factors that may affect the network status, the network status of the future campus equipment is predicted. The analysis is based on the trend extrapolation prediction formula, which is: ； Where y is the predicted network index value, a and b are weights, and the predicted value y in the future park is obtained. The predicted value is analyzed by adding external factors. The analysis formula is: ； Where N w is the network status of the future campus equipment, Tc is the influencing factor of the network trend, and w i Weight, F i The specific value of the external factor is used to predict the future network status of the park equipment through the formula.

6. The active early warning campus network monitoring system according to claim 5, characterized in that: The calculation of the network trend influencing factor Tc includes the quantification of the change rate and the fluctuation situation. The network status values ​​at two time points in the current time period are determined. The network delay at the initial time point is set to D1, the network delay at the end time point is set to D2, the time interval is △t, and the change rate R= (D2-D1) / △t. The calculated change rate is mapped to the interval of (0, 1). The normal change rate range is set to (R min , R max ), then the standardized rate of change is R b =(RR min ) / (R max -R min ); To quantify the fluctuation, assume that the normal range of the standard deviation is (c min , c max ), the standardized fluctuation is: c z =(cc min ) / (c max -c min ); Conduct a comprehensive evaluation, Tc=α*R b +βc z , where α and β are weight coefficients, and the value of the network trend influence factor Tc is calculated by the formula.

7. The active early warning campus network monitoring system according to claim 1 is characterized in that: The early warning module warns of future failures in the campus network based on the prediction results of the future campus equipment network status. When the prediction results show that there is a potential risk of failure in the campus network, the early warning module uses sound and light alarms to attract the attention of relevant personnel at the first time. In terms of sound alarms, the early warning module emits a loud and rapid alarm sound, and the early warning module uses flashing lights to further enhance the early warning effect.

8. The active early warning campus network monitoring system according to claim 7, characterized in that: The early warning module obtains a threshold of a safe network and compares the predicted result with the safety threshold. If it is greater than the safety threshold, the early warning module will issue an early warning. If it is less than the safety threshold, monitoring will continue.

9. The active early warning campus network monitoring system according to claim 1, characterized in that: The management module conducts comprehensive management and detailed configuration of the campus network. Based on the prediction results of the early warning module, the management module conducts adjustment management, analyzes the type, scope of impact and severity of potential faults, and formulates targeted adjustment plans. For network congestion problems, the management module alleviates the pressure by optimizing network traffic distribution and adjusting data transmission paths.

10. The active early warning campus network monitoring system according to claim 9, characterized in that: The management module provides managers with an intuitive and convenient user interface with good interactivity and ease of use, allowing them to view various parameters and operating indicators of the campus network in real time and understand the current status and historical trends of the network.

Images