Campus network flow prediction method and system

Abstract

The invention discloses a campus network traffic prediction method and system, and relates to the technical field of traffic prediction.The campus network traffic prediction method comprises the first step of historical traffic analysis, the second step of traffic distribution and the third step of traffic scheduling. The method comprises the following steps: predicting the total demand quantity of campus traffic in the current period, analyzing to obtain the traffic priority and the traffic threshold value of each region in each time period, performing traffic distribution on each region based on the traffic priority of each region in each time period, and performing speed limit analysis on each region in each time period when the traffic threshold value is reached. Therefore, flow resources are dynamically adjusted through a refined network management strategy, the utilization rate of the network resources is improved to a great extent, and finally flow scheduling is performed on each region in each time period, so that on-demand distribution and dynamic optimization of campus flow are ensured.

Description

Technical Field

[0001] The present application relates to the technical field of traffic prediction, and in particular to a method and system for predicting campus network traffic. Background Art

[0002] Nowadays, campus networks have become a core tool for universities to support educational informatization. University network administrators need to comprehensively monitor network traffic status, promptly understand operational conditions, identify potential problems early, and take corrective measures. Therefore, accurate and effective network traffic prediction and adjustment are crucial for improving campus network management quality and service efficiency, maintaining campus network stability and reliability, and many other aspects. Therefore, this application proposes a campus network traffic prediction method and system.

[0003] The prior art, such as the invention application patent with announcement number: CN113055923B, discloses a mobile network traffic prediction method, device and equipment, which includes: obtaining historical mobile network data within a target time period; inputting the historical mobile network data into a traffic prediction model to obtain the output result of the traffic prediction model; determining the weights corresponding to each of the traffic prediction models; and calculating the traffic prediction result at the time to be predicted based on the output results of each of the traffic prediction models and the weights.

[0004] Regarding the above solution, there are the following technical problems: 1. The current technology only predicts the traffic at the predicted time based on historical mobile network data, and does not consider how to allocate and adjust the traffic in each predicted time period when the traffic data is insufficient. The current technology ignores this aspect, resulting in the lack of perfection and comprehensiveness of the current technology.

[0005] 2. Current technology does not consider how to distribute and adjust traffic data in each area when traffic data is insufficient, nor does it consider how to adjust traffic between areas when traffic data in a certain area exceeds the standard at a certain predicted time, so as to ensure the normal operation of each area. The current technology's neglect of this aspect may lead to network performance degradation in each area when traffic exceeds the standard, which in turn causes workload. Summary of the Invention

[0006] The purpose of this application is to provide a campus network traffic prediction method and system to solve the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present application adopts the following technical solutions: In the first aspect, the present application provides a campus network traffic prediction method, including: Step 1, historical traffic analysis: Obtain traffic usage information in the campus from the information and network center, and then predict the total traffic demand for the current preset period, and analyze to obtain the traffic priority of each area in each time period, and at the same time analyze to obtain the traffic threshold of each area in each time period.

[0008] Step 2: Traffic allocation: Allocate traffic to each area of ​​the current preset period according to the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, limit the traffic of each area in each time period based on the traffic type.

[0009] Step 3: Traffic scheduling: When traffic is insufficient, traffic scheduling is performed in each area at each time period.

[0010] In a second aspect, the present application provides a campus network traffic prediction system, comprising: a historical traffic analysis module, a traffic allocation module, and a traffic scheduling module.

[0011] Historical traffic analysis module: used to obtain traffic usage information on campus from the information and network center, and then predict the total traffic demand for the current preset period, and analyze the traffic priority of each area in each time period, and at the same time analyze the traffic thresholds of each area in each time period.

[0012] Traffic allocation module: used to allocate traffic to each area of ​​the current preset period according to the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, the traffic in each area in each time period is speed-limited based on the traffic type.

[0013] Traffic scheduling module: used to schedule traffic in different time periods and areas when traffic is insufficient.

[0014] The beneficial effects of the present application are: 1. The present application provides a campus network traffic prediction method and system, which analyzes the traffic information of each area in each time period in each historical preset period, and then predicts the total campus traffic demand in the current period. At the same time, the traffic priority and traffic threshold of each area in each time period are analyzed, and then the traffic is allocated to each area based on the traffic priority of each area in each time period. When the traffic threshold is reached, the speed limit analysis is performed on each area in each time period. Based on this, through refined network management strategies, traffic resources are dynamically adjusted, which greatly improves the utilization rate of network resources. Finally, traffic scheduling is performed on each area in each time period to ensure on-demand allocation and dynamic optimization of campus traffic.

[0015] 2. This application obtains traffic information for each historical preset period, providing a data basis for subsequent prediction of the total campus traffic demand in the current period, and also laying the foundation for traffic priority and traffic threshold analysis in each area in each time period.

[0016] 3. This application distributes traffic to each area according to the traffic priority of each area in each time period, establishes a refined network management strategy based on this, dynamically adjusts traffic resources, greatly improves network resource utilization, and limits the speed of each area in each time period when the traffic threshold is reached, thereby ensuring the stability of key businesses and avoiding system paralysis caused by traffic overload. Finally, traffic scheduling is performed in each area in each time period to ensure on-demand allocation and dynamic optimization of campus traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 This is a flowchart of the steps for implementing the application method.

[0019] Figure 2 This is a schematic diagram of the system structure connection for this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] Reference Figure 1 As shown, the present application provides a campus network traffic prediction method in the first aspect, comprising the following steps: Step 1, historical traffic analysis: obtaining traffic usage information in the campus from the information and network center, and then predicting the total traffic demand for the current preset period, and analyzing to obtain the traffic priority of each area in each time period, and at the same time analyzing to obtain the traffic threshold of each area in each time period.

[0022] It should be noted that the specific length of the preset period is set by the relevant staff and can be one day, one week, or one month. Specific restrictions are set here.

[0023] In a specific example, the traffic usage information includes the bandwidth threshold and total traffic usage for each area in each time period in each historical preset period, wherein the bandwidth threshold includes an upper limit value and a lower limit value of the bandwidth.

[0024] In a specific example, the total traffic demand for the current preset period is predicted, and the specific process is as follows: the traffic monitoring data of each area in each time period in each historical preset period is divided into a data set and a prediction set according to a preset ratio, a network traffic VMD-PSO-BiLSTM prediction model is constructed based on the data set, and the prediction set is input into the network traffic VMD-PSO-BiLSTM prediction model as a data source, and the total campus traffic demand for the current preset period is predicted by the network traffic VMD-PSO-BiLSTM prediction model.

[0025] It should be noted that the preset ratio is set by relevant staff and is not specifically limited here.

[0026] It should be noted that the method for constructing the network traffic VMD-PSO-BiLSTM prediction model and the traffic prediction based on the network traffic VMD-PSO-BiLSTM prediction model are both existing technologies and will not be described in detail.

[0027] In a specific example, the analysis obtains the traffic priority of each area in each time period. The specific analysis process is as follows: based on the traffic usage information on campus, the bandwidth threshold of each area in each time period in each historical preset period is obtained, and then the traffic rate demand assessment coefficient of each area in each time period is obtained by analysis. Where i represents the number of each time period, which is a positive integer; j represents the number of each area, which is a positive integer.

[0028] Based on the traffic usage information on campus, the total traffic usage of each area in each time period in each historical preset period is obtained, and then the traffic usage demand assessment coefficient of each area in each time period is obtained by analysis.

[0029] Input the traffic rate demand assessment coefficient and traffic usage demand assessment coefficient of each area in each time period into the traffic classification model. According to the traffic classification model expression: Output the flow demand characteristic value η of the area numbered j in the time period numbered i ij, where χ′ and χ″ are the lower and upper limits of the comprehensive flow demand assessment coefficient, respectively. An area in a certain time period with a flow demand characteristic value of 1 is recorded as a first-level flow priority area, an area in a certain time period with a flow demand characteristic value of 0 is recorded as a second-level flow priority area, and an area in a certain time period with a flow demand characteristic value of -1 is recorded as a third-level flow priority area. Based on this, the first-level flow priority areas, second-level flow priority areas, and third-level flow priority areas of each time period are obtained.

[0030] It should be noted that when the traffic demand characteristic value is 1, it indicates that the traffic demand is large; when the traffic demand characteristic value is 0, it indicates that the traffic demand is average; and when the traffic characteristic value is -1, it indicates that the traffic demand is low.

[0031] It should be noted that the lower limit and upper limit of the flow comprehensive demand assessment coefficient are set by relevant staff. For example, the lower limit of the flow comprehensive demand assessment coefficient can be set to 2, and the upper limit can be set to 5. When the flow comprehensive demand assessment coefficient is 3, 2<3<5, and the flow characteristic value is 0 at this time, and the corresponding area is the secondary flow priority area.

[0032] In a specific example, the traffic rate demand evaluation coefficient and traffic usage demand evaluation coefficient of each area in each time period are obtained by analysis. The specific analysis process is as follows: the bandwidth threshold of each area in each time period in each historical preset period is recorded as and in and They are the upper and lower bandwidth limits respectively, according to the calculation formula: Analyze and obtain the flow rate demand assessment coefficient of area numbered j in time period numbered i Wherein, E represents the total number of historical preset periods, and W′ represents the set bandwidth standard value.

[0033] It should be noted that the bandwidth standard value is obtained by the network operator according to different network package settings, such as 100Mbps and 500Mbps.

[0034] The total traffic usage in each area in each time period in each historical preset period is recorded as According to the calculation formula: Analyze and obtain the flow demand evaluation coefficient of area numbered j in time period numbered i where Q′ ij Indicates the set standard value of total flow usage.

[0035] It should be noted that the standard value of total traffic usage is set by the Information and Network Technology Center. For example, the average value of total traffic usage in each region in each time period corresponding to each historical period is recorded as the standard value of total traffic usage in each region in each time period.

[0036] In a specific example, the analysis obtains the traffic thresholds of each area in each time period. The specific analysis process is as follows: based on the traffic usage information on campus, the total traffic usage of each area in each time period in each historical preset period is obtained, and the total traffic usage of a certain area in a certain time period in each historical preset period is normally distributed. The middle value after the normal distribution is recorded as the secondary traffic threshold of the area in the time period, and the maximum value after the normal distribution is recorded as the primary traffic threshold of the area in the time period. Based on this, the primary traffic threshold and the secondary traffic threshold of each area in each time period are obtained.

[0037] Step 2: Traffic allocation: Allocate traffic to each area of ​​the current preset period according to the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, limit the traffic of each area in each time period based on the traffic type.

[0038] In a specific example, the flow allocation for each area of ​​the current preset period is performed according to the flow priority of each area in each time period. The specific process is as follows: the flow usage demand evaluation coefficient and the flow rate demand evaluation coefficient of each area in each time period are combined, and the calculation formula is:

[0039] The comprehensive traffic demand assessment coefficient of the jth area is obtained by analysis, where I is the total number of each time period. The ratio of the comprehensive traffic demand assessment coefficient of each area is then calculated. Based on the ratio of the comprehensive traffic assessment coefficient of each area, the current information and the traffic of the network center are distributed to obtain the matching traffic of each area in the current preset period.

[0040] Comprehensively consider the traffic usage demand assessment coefficient and traffic rate demand assessment coefficient for each area in each time period, according to the calculation formula: The comprehensive flow demand assessment coefficient of the jth area in the i-th time period is obtained through analysis, and then the ratio of the comprehensive flow demand assessment coefficient of each area in each time period is calculated. Based on the ratio of the comprehensive flow demand assessment coefficient of each area in each time period, the matching flow of each area is redistributed to obtain the matching flow of each area in each time period.

[0041] In a specific example, the speed limit processing of the traffic in each area in each time period is based on the traffic type. The specific process is as follows: the traffic usage in each area in each time period is monitored, and the traffic usage type and total traffic usage in each area in each time period are obtained based on the traffic usage monitoring results.

[0042] It should be noted that the traffic usage types include characteristic traffic for education and scientific research applications, characteristic traffic for high-bandwidth applications, and characteristic traffic for social and tool applications, among which characteristic traffic for high-bandwidth applications is used for various online games for video media, characteristic traffic for education and scientific research applications includes virtual simulation experiment platforms, online examination systems, remote collaboration tools, and file transfer, and characteristic traffic for social and tool applications includes social software, instant messaging, and email, etc.

[0043] When the total traffic usage of a certain area in a certain time period reaches the first-level traffic threshold of the area, the traffic priority of the area in the time period is obtained based on the traffic priority of each area in each time period, and the traffic usage type of the area in the time period is obtained based on the traffic usage type of each area in each time period. Based on the traffic usage type of the area in the time period, the characteristic traffic of education and scientific research applications, the characteristic traffic of high-bandwidth applications, and the characteristic traffic of social and tool applications are obtained. The characteristic traffic of education and scientific research applications is subject to first-level speed limit processing, and the characteristic traffic of high-bandwidth applications and the characteristic traffic of social and tool applications are subject to second-level speed limit processing.

[0044] When the traffic usage in a certain area during a certain time period reaches the secondary traffic threshold of that area, the characteristic traffic of education and scientific research applications will be subject to primary speed limit processing, the characteristic traffic of social and tool applications will be subject to secondary speed limit processing, and the characteristic traffic of high-bandwidth applications will be subject to tertiary speed limit processing.

[0045] The first-level speed limit processing is to not limit the speed, the third-level speed limit processing is to disconnect the traffic, and the second-level speed limit processing is to limit the speed to half of the original bandwidth.

[0046] Step 3: Traffic scheduling: When traffic is insufficient, traffic scheduling is performed in each area at each time period.

[0047] In a specific example, the traffic scheduling for each area and each time period is performed as follows: based on the traffic monitoring results of each area in each time period of the current preset cycle, the total traffic usage of each area in each time period as of the current time point is obtained; if the total traffic usage of a certain area in a certain time period as of the current time point reaches the matching traffic total of the area in the time period, the traffic priority of the area in the time period and the traffic priority of other areas in the time period are obtained, and then the areas with lower traffic priority than the area in the time period are obtained, recorded as matching areas, and the remaining traffic of each matching area as of the current time point is sorted in order from large to small, and then the traffic scheduling is performed on the area according to the sorting result, and the sorting result is updated in real time based on the scheduling result.

[0048] It should be noted that traffic scheduling is performed preferentially on matching areas with higher rankings.

[0049] Reference Figure 2As shown, the present application provides a campus network traffic prediction system in the second aspect, including the following modules: a historical traffic analysis module, a traffic allocation module and a traffic scheduling module.

[0050] Historical traffic analysis module: used to obtain traffic usage information on campus from the information and network center, and then predict the total traffic demand for the current preset period, and analyze the traffic priority of each area in each time period, and at the same time analyze the traffic thresholds of each area in each time period.

[0051] Traffic allocation module: used to allocate traffic to each area of ​​the current preset period according to the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, the traffic in each area in each time period is speed-limited based on the traffic type.

[0052] Traffic scheduling module: used to schedule traffic in different time periods and areas when traffic is insufficient.

[0053] The present application provides a campus network traffic prediction method and system, which predicts the total campus traffic demand in the current period by analyzing the traffic information of each area in each time period in each historical preset period, and at the same time obtains the traffic priority and traffic threshold of each area in each time period, and then allocates traffic to each area based on the traffic priority of each area in each time period, and performs speed limit analysis on each area in each time period when the traffic threshold is reached. Based on this, through refined network management strategies, traffic resources are dynamically adjusted, which greatly improves the utilization rate of network resources. Finally, traffic scheduling is performed on each area in each time period to ensure on-demand allocation and dynamic optimization of campus traffic.

[0054] The above content is merely an example and explanation of the concept of the present application. Technicians in this technical field may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they should all fall within the scope of protection of this application.

Claims

1. A campus network traffic prediction method, characterized in that: include: Step 1: Historical traffic analysis: Obtain campus traffic usage information from the Information and Network Center, and then predict the total traffic demand for the current preset period. Analyze and determine the traffic priority for each area in each time period, and also analyze and determine the traffic thresholds for each area in each time period. Step 2: Traffic allocation: Allocate traffic to each area in the current preset period based on the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, the traffic rate of each area in each time period is limited based on the traffic type. Step 3: Traffic scheduling: When traffic is insufficient, traffic scheduling is performed in each area at each time period.

2. A campus network traffic prediction method according to claim 1, characterized in that: The traffic usage information includes the bandwidth threshold and total traffic usage of each area in each time period in each historical preset period, wherein the bandwidth threshold includes the upper limit value and the lower limit value of the bandwidth.

3. A campus network traffic prediction method according to claim 2, characterized in that: The described prediction of the total traffic demand for the current preset period is carried out, and the specific process is as follows: the traffic monitoring data of each area in each time period in each historical preset period is divided into a data set and a prediction set according to a preset ratio, a network traffic VMD-PSO-BiLSTM prediction model is constructed based on the data set, and the prediction set is input into the network traffic VMD-PSO-BiLSTM prediction model as a data source, and the total campus traffic demand for the current preset period is predicted by the network traffic VMD-PSO-BiLSTM prediction model.

4. A campus network traffic prediction method according to claim 3, characterized in that: The analysis obtains the traffic priority of each area in each time period. The specific analysis process is as follows: Based on the traffic usage information on campus, the bandwidth threshold of each area in each time period in each historical preset period is obtained, and then the traffic rate demand assessment coefficient of each area in each time period is obtained by analysis. Where i represents the number of each time period, i is a positive integer, j represents the number of each area, j is a positive integer; Based on the traffic usage information on campus, the total traffic usage of each area in each time period in each historical preset period is obtained, and then the traffic usage demand assessment coefficient of each area in each time period is obtained by analysis. The flow rate demand assessment coefficient and flow usage demand assessment coefficient of each area in each time period are input into the flow classification model. According to the flow classification model expression: Output the flow demand characteristic value η of the area numbered j in the time period numbered i ij , where χ′ and χ″ are the lower and upper limits of the comprehensive flow demand assessment coefficient, respectively. An area in a certain time period with a flow demand characteristic value of 1 is recorded as a first-level flow priority area, an area in a certain time period with a flow demand characteristic value of 0 is recorded as a second-level flow priority area, and an area in a certain time period with a flow demand characteristic value of -1 is recorded as a third-level flow priority area. Based on this, the first-level flow priority areas, second-level flow priority areas, and third-level flow priority areas of each time period are obtained.

5. A campus network traffic prediction method according to claim 4, characterized in that: The analysis obtains the traffic rate demand evaluation coefficient and traffic usage demand evaluation coefficient of each area in each time period. The specific analysis process is as follows: the bandwidth threshold of each area in each time period in each historical preset period is recorded as and in and They are the upper and lower bandwidth limits respectively, according to the calculation formula: Analyze and obtain the flow rate demand assessment coefficient of area numbered j in time period numbered i Where E represents the total number of historical preset cycles, and W′ represents the set bandwidth standard value; The total traffic usage in each area in each time period in each historical preset period is recorded as According to the calculation formula: Analyze and obtain the flow demand evaluation coefficient of area numbered j in time period numbered i where Q′ ij Indicates the set standard value of total flow usage.

6. A campus network traffic prediction method according to claim 5, characterized in that: The analysis obtains the traffic thresholds of each area in each time period. The specific analysis process is as follows: based on the traffic usage information on campus, the total traffic usage of each area in each time period in each historical preset period is obtained, and the total traffic usage of a certain area in a certain time period in each historical preset period is normally distributed. The middle value after the normal distribution is recorded as the secondary traffic threshold of the area in the time period, and the maximum value after the normal distribution is recorded as the primary traffic threshold of the area in the time period. Based on this, the primary traffic threshold and the secondary traffic threshold of each area in each time period are obtained.

7. A campus network traffic prediction method according to claim 6, characterized in that: The flow allocation for each area of ​​the current preset period is performed according to the flow priority of each area in each time period. The specific process is as follows: the flow usage demand evaluation coefficient and the flow rate demand evaluation coefficient of each area in each time period are combined, and the calculation formula is: The comprehensive traffic demand assessment coefficient of the jth region is obtained by analysis, where I is the total number of each time period. The ratio of the comprehensive traffic demand assessment coefficients of each region is then calculated. Based on the ratio of the comprehensive traffic assessment coefficients of each region, the current information and network center traffic are allocated to obtain the matching traffic of each region in the current preset period. Comprehensively consider the traffic usage demand assessment coefficient and traffic rate demand assessment coefficient for each area in each time period, according to the calculation formula: The comprehensive flow demand assessment coefficient of the jth area in the i-th time period is obtained through analysis, and then the ratio of the comprehensive flow demand assessment coefficient of each area in each time period is calculated. Based on the ratio of the comprehensive flow demand assessment coefficient of each area in each time period, the matching flow of each area is redistributed to obtain the matching flow of each area in each time period.

8. A campus network traffic prediction method according to claim 7, characterized in that: The speed limit processing of the traffic in each area in each time period based on the traffic type is performed as follows: the traffic usage in each area in each time period is monitored, and the traffic usage type and total traffic usage in each area in each time period are obtained based on the traffic usage monitoring results; When the total traffic usage of a certain area in a certain time period reaches the first-level traffic threshold of the area, the traffic priority of the area in the time period is obtained based on the traffic priority of each area in each time period, and the traffic usage type of the area in the time period is obtained based on the traffic usage type of each area in each time period. Based on the traffic usage type of the area in the time period, the characteristic traffic of education and scientific research applications, the characteristic traffic of high-bandwidth applications, and the characteristic traffic of social and tool applications are obtained. The characteristic traffic of education and scientific research applications is subject to first-level speed limit processing, and the characteristic traffic of high-bandwidth applications and the characteristic traffic of social and tool applications are subject to second-level speed limit processing; When the traffic usage in a certain area during a certain time period reaches the secondary traffic threshold of that area, the characteristic traffic of education and scientific research applications will be subject to primary speed limit processing, the characteristic traffic of social and tool applications will be subject to secondary speed limit processing, and the characteristic traffic of high-bandwidth applications will be subject to tertiary speed limit processing. The first-level speed limit processing is to not limit the speed, the third-level speed limit processing is to disconnect the traffic, and the second-level speed limit processing is to limit the speed to half of the original bandwidth.

9. A campus network traffic prediction method according to claim 8, characterized in that: The specific process of performing traffic scheduling for each area and each time period is as follows: based on the traffic monitoring results of each area in each time period of the current preset cycle, the total traffic usage of each area in each time period as of the current time point is obtained; if the total traffic usage of a certain area in a certain time period as of the current time point reaches the matching traffic total of the area in the time period, the traffic priority of the area in the time period and the traffic priority of other areas in the time period are obtained, and then the areas with lower traffic priority than the area in the time period are obtained, recorded as matching areas, and the remaining traffic of each matching area as of the current time point is sorted in descending order, and then the traffic scheduling is performed on the area according to the sorting result, and the sorting result is updated in real time based on the scheduling result.

10. A campus network traffic prediction system for executing the campus network traffic prediction method according to any one of claims 1 to 9, characterized in that: include: Historical traffic analysis module: used to obtain campus traffic usage information from the information and network center, and then predict the total traffic demand for the current preset period, and analyze the traffic priority of each area in each time period, and at the same time, analyze and obtain the traffic thresholds of each area in each time period; Traffic allocation module: used to allocate traffic to each area of ​​the current preset period according to the traffic priority of each area in each time period, and monitor the traffic type of each area in each time period. When the traffic threshold is reached, the traffic rate of each area in each time period is limited based on the traffic type; Traffic scheduling module: used to schedule traffic in different time periods and areas when traffic is insufficient.

Images