CN111865635B - Method and device for determining out-of-limit time of ring network capacity - Google Patents

Abstract

The embodiment of the invention discloses a method and a device for determining the out-of-limit time of looped network capacity, wherein the method comprises the steps of carrying out cluster training on the peak value change coefficient of looped network flow in unit time in a preset historical time period based on two classifications to obtain a flow mutation screening model, wherein the two classifications comprise a normal value and a mutation value; correcting a network looped network flow peak value per unit time in a historical investigation period based on a flow mutation screening model; determining a unit time increase coefficient of the network ring network flow peak value based on the corrected unit time network ring network flow peak value in the historical investigation period; and determining a time point when the network ring network flow peak value reaches a preset capacity threshold value based on the current network ring network flow peak value in unit time and the unit time increase coefficient of the network ring network flow peak value. The embodiment of the invention solves the problem that the capacity expansion time cannot be accurately obtained in the prior art.

Description

Method and device for determining limit time of ring network capacity

technical field

The embodiments of the present invention relate to the field of communication technologies, and in particular, to a method and device for determining the time when the capacity of a ring network exceeds a limit.

Background technique

At present, the prediction of transmission PTN ring network capacity is generally determined based on manual checks. Therefore, the prediction results are inaccurate and time-consuming. At the same time, some existing network management prediction schemes cannot accurately inform the specific expansion time point, but can only inform the current Therefore, it is impossible to predict the specific date when the capacity of the ring network will be 100%, which leads to a delay in the expansion of the transmission PTN network. Generally, the expansion is not arranged until the load of the ring network is very high, and it is impossible to prepare for the expansion in advance. Therefore, the development of 4G mobile Internet access services will be adversely affected.

Contents of the invention

Embodiments of the present invention provide a method and device for determining the time when the capacity of the ring network exceeds the limit, so as to solve the problem in the prior art that the time for capacity expansion cannot be accurately determined.

In order to solve the problems of the technologies described above, the present invention is achieved in that:

In the first aspect, a method for determining the limit time of the ring network capacity is provided, including:

Carrying out cluster training on the peak variation coefficient of the network ring network traffic per unit time in the predetermined historical time period based on the binary classification, to obtain a traffic mutation screening model, the binary classification includes normal values and sudden changes;

Based on the flow mutation screening model, the mutation value in the network ring network flow peak value per unit time in the historical investigation period is corrected;

Determine the unit time growth factor of the network ring network traffic peak value based on the corrected historical survey period in the unit time network ring network traffic peak value;

Based on the current network ring network traffic peak value per unit time and the unit time growth coefficient of the network ring network traffic peak value, the time point at which the network ring network traffic peak value reaches a preset capacity threshold is determined.

In the second aspect, a device for determining the limit time of the ring network capacity is provided, including:

The model acquisition unit is used to perform clustering training on the peak variation coefficient of network ring network traffic per unit time within a predetermined historical time period based on two classifications, the two classifications include normal values and mutation values, to obtain a traffic mutation screening model;

The traffic peak correction unit is used to correct the mutation value in the network ring network traffic peak value per unit time in the historical investigation period based on the traffic mutation screening model;

A growth coefficient determination unit, used to determine the growth coefficient per unit time of the network ring network traffic peak value per unit time based on the corrected historical investigation period in the network ring network traffic peak value per unit time;

The time determination unit is configured to determine the time point when the network ring network traffic peak value reaches a preset capacity threshold based on the current unit time network ring network traffic peak value and the unit time growth coefficient of the network ring network traffic peak value.

In the third aspect, there is also provided a terminal device, which includes a processor, a memory, and a computer program stored on the memory and operable on the processor. When the computer program is executed by the processor, the following The steps of the method described in the first aspect.

In a fourth aspect, a computer-readable storage medium is further provided, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method according to the first aspect are implemented.

In the embodiment of the present invention, the method for determining the time when the capacity of the ring network exceeds the limit uses the traffic mutation screening model obtained by performing cluster training on the peak change coefficient of the network ring network traffic per unit time within a predetermined historical time period according to the binary classification, and corrects the history The network ring network traffic peak value per unit time in the investigation period, and according to the revised historical network ring network traffic peak value per unit time in the historical investigation period, determine the unit time growth coefficient of the ring network traffic peak value, so that according to the current network ring network traffic per unit time The traffic peak value and the unit time growth coefficient of the ring network traffic peak value determine the time point when the ring network traffic peak value reaches the preset capacity threshold. In this way, the unit time growth coefficient of the ring network traffic peak value can be determined according to the corrected historical survey period of the network ring network traffic peak value in the unit time period according to the traffic mutation screening model, so as to accurately determine that the network ring network traffic peak value reaches the preset capacity threshold The time point can not only solve the problem that the expansion time cannot be accurately obtained in the prior art, but also solve the time-consuming and inaccurate problem of predicting the capacity of the ring network through manual checking in the prior art.

Description of drawings

Fig. 1 is a schematic flow chart of a method for determining a ring network capacity overrun time according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a method for determining a ring network capacity overrun time according to another embodiment of the present invention;

3 is a schematic flow chart of a method for determining a ring network capacity overrun time according to another embodiment of the present invention;

4 is a schematic flow chart of a method for determining a ring network capacity overrun time according to another embodiment of the present invention;

Fig. 5 is a schematic flowchart of a method for determining a ring network capacity exceeding time limit according to a specific embodiment of the present invention;

FIG. 6 is a schematic schematic diagram of a method for determining a ring network capacity overrun time according to an embodiment of the present invention;

Fig. 7 is a schematic structural block diagram of an apparatus for determining the time when the capacity of the ring network exceeds the limit according to an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The technical solutions provided by various embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

Fig. 1 is a schematic flow chart of a method for determining the limit time of the ring network capacity according to an embodiment of the present invention, so as to solve the problem that the capacity expansion time cannot be accurately obtained in the prior art. The method can include:

Step 102. Perform clustering training on the peak variation coefficient of network ring network traffic per unit time within a predetermined historical time period based on binary classification to obtain a traffic mutation screening model. The binary classification includes normal values and sudden changes. Wherein, the peak variation coefficient is used to characterize the peak variation range, for example, the peak variation coefficient is determined based on the flow peak variation of two days before and after the current day.

Specifically, it can collect the PTN network ring network traffic data in the last two years, and calculate the daily peak changes in the past two years based on the network ring network traffic data, and then perform clustering training through the artificial intelligence K-means algorithm, and train out The traffic mutation screening model of the current ring network. Wherein, when collecting the PTN ring network traffic numbers in the past two years, the unit time may correspond to every hour, or even every minute, etc., and the operation may be performed according to specific operation requirements, and is not limited to the method described in the embodiment of the present invention.

Step 104. Based on the traffic mutation screening model, correct the mutation value in the network ring network traffic peak value per unit time in the historical investigation period.

Among them, as shown in Figure 2, the operation of correcting the sudden change value in the network ring network traffic peak value per unit time in the historical investigation period may include:

Step 202. Based on the traffic mutation threshold output by the traffic mutation screening model, determine the mutation value in the network ring network traffic peak value per unit time in the historical investigation period.

Step 204. Delete the mutation value to correct the peak value of network ring network traffic per unit time in the historical investigation period.

After the traffic mutation screening model is obtained, the mutation value in the network ring network traffic peak value per unit time in the historical investigation period can be determined and deleted according to the traffic mutation threshold value output by it, so as to correct the network ring network traffic peak value in unit time in the historical investigation period , that is to say, the data that cannot be referenced in the network ring network traffic peak per unit time in the historical investigation period can be removed through the traffic mutation screening model, so as to obtain a relatively smooth traffic peak growth curve, so as to determine the network ring network in the subsequent steps Growth coefficient per unit time of flow peak.

Step 106 . Based on the corrected peak value of network ring network traffic per unit time in the historical investigation period, determine the unit time growth coefficient of the network ring network traffic peak value. Among them, the unit time can correspond to each day, and the daily average peak traffic growth coefficient formula is:

Among them, t represents the current day, t-1 represents the previous day, N _t represents the traffic peak value on the t-th day, N _t-1 represents the traffic peak value on the t-1 day, and ΔN represents the daily average growth coefficient (that is, the unit time growth factor).

The value range of t can represent the historical investigation period, for example, the current day is pushed forward by 20 days, and the maximum does not exceed 30 days. Wherein, the number of days for collecting the traffic peaks of each PTN ring network on the OMC network management system may be the number of days defined in the historical investigation period.

It is understandable that the network ring network traffic peaks collected in the historical investigation period are imported into the artificial intelligence module, and the traffic mutation screening model is started to perform data smoothing, so as to remove the mutation value in the collected ring network traffic peaks, and smooth the The data are summed, and the ratio of the summed result to the time period (such as 20) of the investigation period after removing the mutation value can be the unit time growth coefficient ΔN of the PTN ring network in the historical investigation period. Among them, the method of evaluating the smoothed data by weighted average or mean square error can also be used to obtain the growth coefficient ΔN per unit time in the historical investigation period, and the specific implementation process will not be elaborated here.

In this way, according to the formula (1), the growth coefficient ΔN per unit time of all PTN ring networks to be investigated in the historical investigation period can be obtained, so that the historical growth rate of bandwidth per unit time of each ring network in each region can be calculated. Therefore, in the subsequent steps, the growth rate per unit time obtained according to the historical growth rate per unit time, and the final bandwidth utilization rate that the ring network can achieve.

Step 108. Based on the current peak network ring network traffic per unit time and the growth factor per unit time of the network ring network traffic peak value, determine the time point when the network ring network traffic peak value reaches a preset capacity threshold.

Among them, as shown in Figure 3, based on the current peak value of the network ring network traffic per unit time and the unit time growth coefficient of the network ring network traffic peak value, the time point at which the network ring network traffic peak value reaches the preset capacity threshold is determined, including:

Step 302 . Based on the current network ring network traffic peak value per unit time, the unit time growth coefficient of the network ring network traffic peak value, and the holiday peak traffic compensation coefficient, determine the network ring network traffic peak value per unit time.

The formula for calculating the peak value of network ring network traffic per unit time is:

A _t1 =N _t1-1 +ΔN+ΔM (2)

Among them, t ₁ represents a certain day in the historical investigation cycle, A _t1 represents the peak flow rate on the t _1st day in the historical investigation cycle, N _t1-1 represents the flow peak value on the t ₁ -1th day in the historical investigation cycle, and ΔN is The unit time growth coefficient in the historical investigation period, ΔM is the holiday compensation coefficient.

Specifically, the ΔN of the PTN ring network calculated by the formula (1) is substituted into the formula (2), and the traffic peak value A ₁ of the first day in the future is calculated first. Then, the calculated A ₁ is substituted into the formula (2) again, and the value is substituted for the term N _t1-1 to calculate A ₂ . By analogy, until all A's in the historical investigation period are calculated, the sequence N ₀ ={A ₁ , A ₂ , A ₃ ,...A _t1 } is formed. In the process of calculating A _t1 , the system will judge whether the future investigation date covers holidays, and if it covers holidays, it will extract the traffic growth coefficient corresponding to the same holidays in the history of the PTN ring network for compensation.

Therefore, by substituting the result obtained from formula (1) into formula (2), the traffic peak value of a certain PTN ring network in the future investigation period (that is, the investigation period after the current moment) is calculated, presented in the system, and then Statistics can be made on the specific number of days when each ring network exceeds a certain utilization rate, and the operation and maintenance personnel can filter out the high-frequency occupied ring network information for key attention and analysis.

Step 304 . Based on the peak value of network ring network traffic per unit time, determine the time point when the peak value of network ring network traffic reaches a preset capacity threshold.

The calculation formula for the time point when the ring network traffic peak reaches the preset capacity threshold in the future investigation period is shown in formula (3):

T=max{N ₀ }≥W×70% (3)

Among them, T represents the exceeding limit date (the date of capacity expansion completion, that is, the time point when the preset capacity threshold is reached), w represents the static capacity, and the static capacity of the PTN ring network to be investigated can be obtained through the interface of the ring network in the network management system, Wx70 % can be expressed as the early warning value of the upper limit of capacity.

By obtaining the maximum value of A ₁ , A ₂ ... in N ₀ , the system substitutes the obtained maximum value into formula (3) to judge whether the formula condition of max{N ₀ }≥W×70% is established.

If the traffic peak value that makes the formula (3) established is obtained, the ring network is taken out, and the time corresponding to the traffic peak value is determined as the time point when the preset capacity threshold is reached. Of course, if the traffic peak value for formula (3) is not obtained, it means that the PTN ring network will not exceed the capacity expansion threshold (preset capacity threshold) in the future investigation period. After executing the above logic for all ring networks, the PTN ring network that needs to be expanded is formed, and the expansion date and countdown countdown calculated from the current day are presented to the operation and maintenance personnel, which is convenient for visually observing the expansion date and expansion countdown, thus facilitating operation and maintenance The personnel formulate scientific expansion strategies in a timely manner.

In the embodiment of the present invention, the method for determining the time when the capacity of the ring network exceeds the limit uses the traffic mutation screening model obtained by performing cluster training on the peak change coefficient of the network ring network traffic per unit time within a predetermined historical time period according to the binary classification, and corrects the history The network ring network traffic peak value per unit time in the investigation period, and according to the revised historical network ring network traffic peak value per unit time in the historical investigation period, determine the unit time growth coefficient of the ring network traffic peak value, so that according to the current network ring network traffic per unit time The traffic peak value and the unit time growth coefficient of the ring network traffic peak value determine the time point when the ring network traffic peak value reaches the preset capacity threshold. In this way, the unit time growth coefficient of the ring network traffic peak value can be determined according to the corrected historical investigation period of the network ring network traffic peak value per unit time in the historical investigation period, so as to accurately determine the time when the ring network traffic peak value reaches the preset capacity threshold It can not only solve the problem that the expansion time cannot be accurately obtained in the prior art, but also solve the time-consuming and inaccurate problem of predicting the capacity of the ring network through manual checking in the prior art.

In the above-mentioned further embodiment, as shown in Figure 4, the method for determining the limit time of the ring network capacity also includes:

Step 402. When the target difference exceeds the preset capacity expansion time deviation threshold, adjust the traffic mutation screening model. The target difference is the time point when the ring network traffic peak value reaches the preset capacity threshold and the current unit time network ring network traffic peak value reaches the predetermined value. The difference between the time points when the capacity threshold is set;

Step 404. Based on the adjusted traffic mutation screening model, re-correct the peak value of the network ring network traffic per unit time in the historical investigation period, so as to correct the network ring network traffic peak value per unit time in the historical investigation period based on the re-correction. The unit time growth factor of the network traffic peak value;

Step 406 . Based on the current peak network ring network traffic per unit time and the corrected growth factor per unit time of the network ring network traffic peak value, correct the time point when the network ring network traffic peak value reaches the preset capacity threshold.

Among them, the operation of adjusting the flow mutation screening model may include:

If the time point when the network ring network traffic peak value reaches the preset capacity threshold per unit time is earlier than the time point when the network ring network traffic peak value reaches the preset capacity threshold value, increase the traffic mutation threshold value output by the traffic mutation screening model;

If the time point at which the network ring network traffic peak value reaches the preset capacity threshold per unit time is later than the time point at which the network ring network traffic peak value reaches the preset capacity threshold value, the traffic sudden change threshold output by the traffic sudden change screening model is reduced.

It is understandable that when the system determines the expansion date of a certain PTN ring network (that is, the time point when the network ring network traffic peak reaches the preset capacity threshold), the system will collect the occupancy of the ring network per unit time, and Judging the occupancy status, when it is determined to reach 100%, that is, when the peak value of the network ring network traffic reaches the preset capacity threshold, the time point when the current unit time network ring network traffic peak value reaches the preset capacity threshold and the expansion date determined by the system For comparison, if the compared difference exceeds the preset expansion time deviation threshold, at this time, the artificial intelligence learning module can be triggered to adjust the traffic mutation screening model to change the traffic mutation threshold output by the traffic mutation screening model, thereby according to Re-output the sudden change threshold of the traffic, re-determine and delete the sudden change value of the network ring network traffic peak value per unit time in the historical investigation period, and correct the unit time growth coefficient of the ring network traffic peak value, so that the corrected ring network traffic peak value reaches the expected value. The purpose of setting the time point of the capacity threshold closer to the actual expansion date.

Among them, according to the traffic mutation threshold output after adjusting the traffic mutation screening model, when re-determining the sudden change value of the network ring network traffic peak value per unit time in the historical investigation period, because the previously determined sudden change value is not adjusted after the traffic mutation screening model When re-judging, it is likely that it is no longer a mutation value, so the previously determined mutation value needs to be re-judged.

In any one of the above embodiments, the method for determining the time when the capacity of the ring network exceeds the limit further includes: displaying to the user the time point when the peak value of the ring network traffic reaches the preset capacity threshold. That is, after performing the method described in any one of the above-mentioned embodiments on all ring networks, the PTN ring network to be expanded is formed, and the expansion date and the countdown countdown calculated from the current day are presented to the operation and maintenance personnel, which can be intuitively Observe the expansion date and expansion countdown, so that the operation and maintenance personnel can formulate scientific expansion strategies in a timely manner.

5 and 6 for illustration, the implementation process of the method for determining the ring network capacity overrun time in the embodiment of the present invention can be as follows:

First, collect the PTN ring network traffic data in the last two years, calculate the daily traffic peak change coefficient, and then perform clustering training through the K-means algorithm in the artificial intelligence module to train a traffic mutation screening model.

Second, during the historical investigation period, collect the daily traffic peak value of the PTN ring network, and then use the K traffic mutation screening model to remove the sudden change value in the daily traffic peak value of the ring network during the historical investigation period.

Third, after screening out the mutation value, calculate the daily growth coefficient of the ring network traffic peak value in the historical investigation period.

Fourth, calculate the daily peak traffic of the ring network according to the daily growth coefficient of the peak traffic of the ring network in the historical investigation period and the compensation coefficient of holidays.

Fifth, according to the manual setting of the ring network occupancy rate of 70% of the threshold value w (red and yellow cards can be set for early warning, 45-70% is a yellow card, and more than 70% is a red card), the calculated peak value of the ring network traffic on the target day When the occupancy rate of the ring network reaches 70% of the inspection threshold w, the target date is the expansion date.

Sixth, by comparing the calculated expansion date with the expansion date determined by the actual ring network proportion, when their difference exceeds the preset expansion time deviation threshold, the traffic mutation screening model is corrected through the self-learning adjustment module to change the output The traffic mutation threshold, and return to the first step to continue execution, so as to correct the unit time growth coefficient of the ring network traffic peak value, so that the corrected time point of the ring network traffic peak value reaching the preset capacity threshold is closer to the actual expansion date Purpose.

Among them, as shown in Figure 6, the data processed by the artificial intelligence function module is sent to the database for storage, and is retrieved by algorithms 1, 2, and 3. After retrieval, the ring network that needs to be expanded is calculated and stored in In the storage table of the ultra-tolerance ring network details, the data integration and call presentation are performed by the front-end web interface.

It can be seen that the method of the embodiment of the present invention uses the K-means algorithm to perform clustering training on the collected historical data, establishes a traffic mutation screening model, and uses the traffic mutation screening model to screen out the traffic mutation value, that is, it cannot refer to the situation After the data is collected, the full load date of the PTN ring network is calculated and displayed through the front-end BS architecture, so that the PTN network manager can prepare and plan in advance.

Moreover, the K-means algorithm has the ability of artificial intelligence learning. When the full load date is displayed, the actual traffic occupancy of the PTN ring network collected by the system is compared and calculated with the full load date of the PTN ring network when the current day is full load. On the current full-load date, when the difference threshold is exceeded, the machine self-learning is started to dynamically adjust the interval, and the traffic mutation screening model is changed to change the traffic mutation threshold output by the model, so that the daily growth coefficient is automatically changed, so that through continuous dynamic Adjustment, so that the calculated full-load date of the PTN ring network is closer to the actual situation, so as to solve the problem that the expansion time cannot be accurately obtained in the prior art, and it can also solve the problem caused by the prediction of the ring network capacity through manual checking in the prior art. Time-consuming and inaccurate problem.

The embodiment of the present invention also provides a device for determining the limit time of the ring network capacity, as shown in FIG. The traffic peak variation coefficient is clustered and trained to obtain a traffic mutation screening model, and the two classifications include normal values and mutation values; the traffic peak correction unit 704 is used to correct the unit time network in the historical investigation period based on the traffic mutation screening model Ring network traffic peak value; growth coefficient determination unit 706, for determining the unit time growth coefficient of network ring network traffic peak value in the unit time network ring network traffic peak value in the historical investigation period based on the correction; Time determination unit 708, for based on The current peak value of the network ring network traffic per unit time and the unit time growth coefficient of the network ring network traffic peak value determine the time point when the network ring network traffic peak value reaches the preset capacity threshold.

The device for determining the limit time of the ring network capacity in the embodiment of the present invention is obtained by performing cluster training on the network ring network traffic peak change coefficient per unit time within a predetermined historical time period according to the model acquisition unit 702 based on the binary classification by the traffic peak correction unit 704 The traffic mutation screening model corrects the peak value of the network ring network traffic per unit time in the historical investigation period, and determines the network ring network traffic peak value according to the corrected network ring network traffic peak value per unit time in the historical investigation period through the growth coefficient determination unit 706 The unit time growth coefficient of the passing time determination unit 708 determines the time point when the network ring network traffic peak value reaches the preset capacity threshold according to the current unit time network ring network traffic peak value and the unit time growth coefficient of the network ring network traffic peak value. In this way, the unit time growth coefficient of the ring network traffic peak value can be determined according to the corrected historical investigation period of the network ring network traffic peak value per unit time in the historical investigation period, so as to accurately determine the time when the ring network traffic peak value reaches the preset capacity threshold It can not only solve the problem that the expansion time cannot be accurately obtained in the prior art, but also solve the time-consuming and inaccurate problem of predicting the capacity of the ring network through manual checking in the prior art.

In the above-mentioned embodiment, the device for determining the limit time of the ring network capacity further includes: a sudden change value determination unit 710, which is used to determine the network ring network traffic per unit time in the historical investigation period based on the traffic sudden change threshold output by the traffic sudden change screening model The abrupt value in the peak value; the traffic peak correction unit 704 is used to delete the abrupt value, so as to correct the peak value of network ring network traffic per unit time in the historical investigation period.

After the traffic mutation screening model is obtained, the mutation value in the network ring network traffic peak value per unit time in the historical investigation period can be determined and deleted according to the traffic mutation threshold value output by it, so as to correct the network ring network traffic peak value in unit time in the historical investigation period , that is to say, the data that cannot be referenced in the network ring network traffic peak per unit time in the historical investigation period can be removed through the traffic mutation screening model, so as to obtain a relatively smooth traffic peak growth curve, so as to determine the network ring network in the subsequent steps Growth coefficient per unit time of flow peak.

In the further embodiment above, it also includes: an adjustment unit 712, which is used to adjust the traffic mutation screening model when the target difference exceeds the preset expansion time deviation threshold, and the target difference is that the peak value of the network ring network traffic reaches the preset capacity The difference between the time point of the threshold and the time point at which the network traffic peak value of the network ring network per unit time reaches the preset capacity threshold; the traffic peak correction unit 704 is used to re-correct the historical investigation period based on the adjusted traffic mutation screening model The network ring network traffic peak value per unit time is based on the network ring network traffic peak value per unit time in the historical investigation period after the re-correction, and the unit time growth coefficient of the network ring network traffic peak value is corrected; the time correction unit 714 is used for based on the current unit time The unit time growth coefficient of the network ring network traffic peak value and the corrected network ring network traffic peak value, and correct the time point when the network ring network traffic peak value reaches the preset capacity threshold.

Wherein, the adjustment unit 712 is also used for: if the time point when the network ring network traffic peak value reaches the preset capacity threshold per unit time is earlier than the time point when the network ring network traffic peak value reaches the preset capacity threshold value, increase the traffic mutation screening model The output traffic mutation threshold; if the time point when the network ring network traffic peak value reaches the preset capacity threshold per unit time is later than the time point when the network ring network traffic peak value reaches the preset capacity threshold value, reduce the traffic output by the traffic mutation screening model mutation threshold.

It is understandable that when the system determines the expansion date of a certain PTN ring network (that is, the time point when the network ring network traffic peak reaches the preset capacity threshold), the system will collect the occupancy of the ring network per unit time, and Judging the occupancy status, when it is determined to reach 100%, that is, when the network ring network traffic peak value reaches the preset capacity threshold, the time point when the current unit time ring network traffic peak value reaches the preset capacity threshold value is compared with the expansion date determined by the system , if the compared difference exceeds the preset expansion time deviation threshold, at this time, the artificial intelligence learning module can be triggered to adjust the traffic mutation screening model to change the traffic mutation threshold output by the traffic mutation screening model, so that according to the re-output Redefine and delete the mutation value in the peak value of the network ring network traffic per unit time in the historical investigation period, and correct the growth coefficient of the network ring network traffic peak value per unit time. In this way, the corrected network ring network traffic peak value reaches the expected value. The purpose of setting the time point of the capacity threshold closer to the actual expansion date.

In any of the above-mentioned embodiments, the determining device may further include a traffic peak determination unit 716, configured to be based on the current network ring network traffic peak value per unit time, the unit time growth coefficient of the network ring network traffic peak value, and the holiday traffic peak compensation coefficient, Determine the peak value of the network ring network traffic per unit time; the time determining unit 708 is used to determine the time point when the network ring network traffic peak value reaches the preset capacity threshold based on the network ring network traffic peak value per unit time. A display unit 718 may also be included, configured to display to the user the point in time when the network ring network traffic peak value reaches the preset capacity threshold.

That is to say, calculate the network ring network traffic peak value per unit time according to the current network ring network traffic peak value per unit time and the unit time growth coefficient of the network ring network traffic peak value, and reach the preset capacity threshold according to the calculated network ring network traffic peak value The time corresponding to the time is determined as the expansion date. After executing the above logic for all ring networks, the PTN ring network to be expanded is formed, and the expansion date and the countdown countdown calculated from the current day are presented to the operation and maintenance personnel, which is convenient for intuitive Observe the expansion date and expansion countdown, so that the operation and maintenance personnel can formulate scientific expansion strategies in a timely manner.

An embodiment of the present invention also provides a terminal device, which may include a processor, a memory, and a computer program stored on the memory and operable on the processor. When the computer program is executed by the processor, the above-mentioned Figure 1 to Figure 1 are implemented. Each process of the method embodiment shown in 5 can achieve the same technical effect, and will not be repeated here to avoid repetition.

An embodiment of the present invention also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the method shown in FIGS. 1 to 5 above is implemented, and can To achieve the same technical effect, in order to avoid repetition, no more details are given here. Wherein, the computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The above descriptions are only examples of the present invention, and are not intended to limit the present invention. Various modifications and variations of the present invention will occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims (7)

1. A method for determining the limit time of ring network capacity, comprising: Carrying out cluster training on the peak variation coefficient of the network ring network traffic per unit time in the predetermined historical time period based on the binary classification, to obtain a traffic mutation screening model, the binary classification includes normal values and sudden changes; Based on the flow mutation screening model, the mutation value in the network ring network traffic peak value per unit time in the historical investigation period is corrected; Determine the unit time growth factor of the network ring network traffic peak value based on the corrected historical survey cycle peak value of the network ring network traffic per unit time; Determine the time point when the network ring network traffic peak reaches the preset capacity threshold based on the current network ring network traffic peak value per unit time and the unit time growth coefficient of the network ring network traffic peak value; Correct the abrupt value of the network ring traffic peak value per unit time during the historical investigation period, including: Based on the flow mutation threshold output by the flow mutation screening model, determine the mutation value in the peak value of the network ring network traffic per unit time in the historical investigation period; Delete the mutation value to correct the peak value of the network ring network traffic per unit time in the historical investigation period; Based on the current network ring network traffic peak value per unit time and the unit time growth coefficient of the ring network traffic peak value, determine the time point when the network ring network traffic peak value reaches the preset capacity threshold, including: Determine the network ring network traffic peak per unit time based on the current network ring network traffic peak value per unit time, the unit time growth coefficient of the ring network traffic peak value, and the holiday traffic peak compensation coefficient; Based on the network ring network traffic peak value per unit time, determine the time point when the network ring network traffic peak value reaches the preset capacity threshold. 2. The method of claim 1, further comprising: When the target difference exceeds the preset expansion time deviation threshold, adjust the traffic mutation screening model, and the target difference is the time point when the network ring network traffic peak reaches the preset capacity threshold and the current unit time network ring network traffic peak value The difference between the time points when the preset capacity threshold is reached; wherein, the time point when the current network ring network traffic peak value reaches the preset capacity threshold per unit time refers to the time when the occupancy of the ring network reaches 100% per unit time point in time; Based on the adjusted traffic mutation screening model, re-correct the peak value of the network ring network traffic per unit time in the historical investigation period, so as to correct the peak value of the network ring network traffic based on the re-corrected historical investigation period The network ring network traffic peak value per unit time The unit time growth coefficient of ; Based on the current network ring network traffic peak value per unit time and the corrected growth factor per unit time of the network ring network traffic peak value, the time point at which the network ring network traffic peak value reaches the preset capacity threshold is corrected. 3. The method according to claim 2, characterized in that, adjusting the flow mutation screening model comprises: If the time point when the network ring network traffic peak value reaches the preset capacity threshold per unit time is earlier than the time point when the network ring network traffic peak value reaches the preset capacity threshold value, then increase the traffic mutation threshold output by the traffic mutation screening model ; If the time point when the network ring network traffic peak value reaches the preset capacity threshold per unit time is later than the time point when the network ring network traffic peak value reaches the preset capacity threshold value, then reduce the traffic mutation threshold output by the traffic mutation screening model . 4. The method of claim 1, further comprising: Display the time point when the network ring network traffic peak reaches the preset capacity threshold to the user. 5. A device for determining the limit time of ring network capacity, comprising: The model acquisition unit is used to perform clustering training on the peak variation coefficient of network ring network traffic per unit time within a predetermined historical time period based on two classifications, the two classifications include normal values and mutation values, to obtain a traffic mutation screening model; The traffic peak correction unit is used for correcting the mutation value in the network ring network traffic peak value per unit time in the historical investigation period based on the traffic mutation screening model; A growth coefficient determination unit, configured to determine the growth coefficient per unit time of the network ring network traffic peak value per unit time based on the corrected historical survey cycle peak value of the network ring network traffic; The time determination unit is used to determine the time point when the network ring network traffic peak value reaches the preset capacity threshold based on the current unit time network ring network traffic peak value and the unit time growth coefficient of the network ring network traffic peak value; Also includes: A sudden change value determination unit, configured to determine the sudden change value in the peak value of the network ring network traffic per unit time in the historical investigation period based on the traffic sudden change threshold output by the traffic sudden change screening model; The traffic peak correction unit is used to delete the sudden change value, so as to correct the network ring network traffic peak value per unit time in the historical investigation period; The determination device also includes a traffic peak determination unit, the traffic peak determination unit is used to determine the unit based on the current network ring network traffic peak value per unit time, the unit time growth coefficient of the network ring network traffic peak value, and the holiday traffic peak compensation coefficient. Time network ring network traffic peak value; The time determination unit is configured to determine the time point when the network ring network traffic peak value reaches a preset capacity threshold based on the network ring network traffic peak value per unit time. 6. The device of claim 5, further comprising: An adjustment unit, configured to adjust the traffic mutation screening model when the target difference exceeds the preset expansion time deviation threshold, and the target difference is the time point when the network ring network traffic peak value reaches the preset capacity threshold and the current unit time The difference between the time points when the network ring network traffic peak value reaches the preset capacity threshold; wherein, the time point when the current unit time network ring network traffic peak value reaches the preset capacity threshold value refers to the time point when the current unit time network ring network traffic peak value reaches the preset capacity threshold. The point in time when the occupancy reaches 100%; The traffic peak correction unit is used to re-correct the network ring network traffic peak value per unit time in the historical investigation period based on the adjusted traffic mutation screening model, so as to re-correct the network ring network traffic per unit time in the historical investigation period after the re-correction. Peak value, correcting the growth factor per unit time of the peak value of the network ring network traffic; The time correction unit is configured to correct the time point when the network ring network traffic peak value reaches the preset capacity threshold based on the current network ring network traffic peak value per unit time and the corrected network ring network traffic peak value unit time growth coefficient. 7. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented A step of.

Images