A method for monitoring network bandwidth stability

Abstract

The present invention relates to the technical field of network monitoring, and specifically discloses a method for monitoring network bandwidth stability. The method comprises: S1, monitoring real-time bandwidth occupancy data, and taking corresponding active test strategies according to the bandwidth occupancy data; S2, sending data packets to a server according to the active test strategies, receiving return data packets from the server, evaluating network bandwidth stability according to the received data of the server and the received data of the sending end, and adjusting the channel selection strategy according to the evaluation result; the method monitors the real-time bandwidth occupancy data, and then takes corresponding active test strategies according to the bandwidth occupancy data, and then can adaptively select the applied test method according to the specific state of the network channel, thereby realizing accurate monitoring of the bandwidth stability of the channel, avoiding the influence of bandwidth instability on related services, and ensuring the normal operation of related services.

Description

Technical Field

[0001] The present invention relates to the technical field of network monitoring, and in particular to a method for monitoring network bandwidth stability. Background Art

[0002] With the popularization and application of the Internet, the normal operation of many industries needs to rely on the Internet, and the stability of network bandwidth will affect the normal operation of many industries, so it is necessary to ensure the stability of network bandwidth; in order to avoid the impact of fluctuations in single-channel network conditions, the existing network deployment method will adopt a multi-channel approach to network deployment. When the current network condition is detected to be poor, the connection channel is switched to ensure the smooth operation of the network and avoid various operational risks caused by poor network signals.

[0003] In the process of monitoring the network status, there are two methods: active monitoring and passive monitoring. Among them, active monitoring can more accurately determine the bandwidth stability status of the current channel through the process of active communication between the user end and the server.

[0004] However, at the same time, active monitoring will also occupy a certain amount of bandwidth, and there is a risk of affecting the normal use of the network. Therefore, it is necessary to ensure that the bandwidth stability status is accurately monitored without affecting normal network communications. Summary of the invention

[0005] The purpose of the present invention is to provide a network bandwidth stability monitoring method to solve the following technical problems:

[0006] How to accurately monitor the bandwidth stability status without affecting normal network communications.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for monitoring network bandwidth stability, the method comprising:

[0009] S1. Monitor real-time bandwidth occupancy data and adopt corresponding active testing strategies based on the bandwidth occupancy data;

[0010] S2. Send data packets to the server according to the active test strategy, and receive the return data packets from the server. Evaluate the stability of the network bandwidth based on the received data of the server and the received data of the sender, and adjust the channel selection strategy based on the evaluation results.

[0011] In one embodiment, the process of step S1 is:

[0012] S11. Get t 0 The real-time data transmission rate of the network during the period of t~t is used to fit the data transmission rate over time curve vB (t);

[0013] By formula Calculate the network occupancy coefficient D opy ;

[0014] Among them, n(v' B (t)=0) is v B (t) The number of points where the derivative is 0; n 0 is the preset reference value; p is the first conversion function; max(v B (t)) is t 0 ~t period v B (t) maximum value; t 0 ~t period v B (t) mean; R is the parameter function; BW is the standard bandwidth value, f is the second conversion function; x 1 、x 2 is the preset coefficient;

[0015] S12, based on the real-time network occupancy coefficient D opy Compared with the preset interval set, according to D opy and the interval in which it is located to select the corresponding active testing strategy.

[0016] In one embodiment, the active testing strategy is:

[0017] The sender sends a preset initial number of data packets to the server, and the value n corresponding to different active test strategies is add Increase the number of data packets step by step. When the number of data packets sent simultaneously reaches the maximum value n corresponding to the active test strategy, max Stop when.

[0018] In one embodiment, n add and n max The acquisition process is:

[0019] By formula Calculate to obtain n add ;

[0020] By formula Calculate to obtain n max ;

[0021] Among them, n add0 (D opy ) is D opy The interval corresponds to the preset value of the number of packets to be increased; n max0 (D opy ) is D opyThe preset maximum value of the corresponding quantity in the interval; min(s(D opy ) is D opy The minimum value of the interval; max(s(D opy )) is D opy The maximum value in the interval.

[0022] In one embodiment, the process of evaluating the network bandwidth is:

[0023] In the active test strategy, the server receives data sever , the sender sends data send And the sender receives data Data receive ;

[0024] Data sever 、Data send and Data receive They include the number of packets and the corresponding time points respectively;

[0025] By Data sever 、Data send and Data receive The network bandwidth is evaluated based on the number of data packets in the network and the corresponding time point.

[0026] In one embodiment, the process of evaluating the network bandwidth is:

[0027] By formula S BW =S up *S down Calculate the bandwidth stability coefficient S BW ;

[0028] Among them, the upward stability coefficient Calculate the uplink stability coefficient S up ;

[0029] Downward stability coefficient Calculate the downlink stability coefficient S down ;

[0030] Among them, m loss1 The difference between the number of packets received by the server and the number of packets sent by the sender; m loss2 is the difference between the data packet sent by the sender and the data packet received by the server; k is the first preset adjustment function, and k is an increasing function; M is the number of data packets received by the server, i∈[1,M]; delay i is the delay time of the ith data packet; Δt, m 0 is the reference value; H is the number of packets received by the sender, j∈[1,H]; delay jis the delay time of the jth data packet; α is the weight function, and α is an increasing function; m os1 The number of mismatches between the order of received data packets and the order of sent data packets during the sending process; m os2 is the number of mismatches between the order of received data packets and the order of sent data packets during the server sending process; G is a second preset adjustment function, and G is an increasing function;

[0031] Through the bandwidth stability factor S BW Evaluate network bandwidth.

[0032] In one embodiment, according to the bandwidth stability coefficient S BW The process of evaluating network bandwidth is as follows:

[0033] The bandwidth stability factor S BW With the preset interval [S 1 , S 2 ] for comparison:

[0034] If S BW <S 1 , then the bandwidth stability is judged to be excellent;

[0035] If S BW ∈[S 1 , S 2 ], the bandwidth stability is judged to be normal;

[0036] If S BW >S 2 , then it is judged that the bandwidth stability is abnormal.

[0037] In one embodiment, the channel selection strategy is adjusted as follows:

[0038] Get channels with excellent bandwidth stability and normal bandwidth stability;

[0039] Bandwidth stability coefficient S corresponding to the channel BW Sort from small to large;

[0040] Select a channel according to the priority of the sorting results.

[0041] Beneficial effects of the present invention:

[0042] (1) The present invention monitors real-time bandwidth occupancy data, and then adopts a corresponding active test strategy based on the bandwidth occupancy data, and can adaptively select the application test method according to the specific status of the network channel, thereby accurately monitoring the bandwidth stability of the channel without affecting normal network communication, and then adjusting the channel selection strategy in time or in advance, thereby avoiding the impact of bandwidth instability on related services and ensuring the normal operation of related services. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 is a flow chart of the steps of the network bandwidth stability monitoring method of the present invention;

[0045] Figure 2 It is a flow chart of step S1 of the network bandwidth stability monitoring method of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 As shown, in one embodiment, a method for monitoring network bandwidth stability is provided, the method comprising:

[0048] S1. Monitor real-time bandwidth occupancy data and adopt corresponding active testing strategies based on the bandwidth occupancy data;

[0049] S2. Send data packets to the server according to the active test strategy, and receive the return data packets from the server. Evaluate the stability of the network bandwidth based on the received data of the server and the received data of the sender, and adjust the channel selection strategy based on the evaluation results.

[0050] Through the above technical scheme, the present application provides a method for monitoring the stability of network bandwidth, by monitoring the real-time bandwidth occupancy data, and then taking the corresponding active testing strategy according to the broadband occupancy data, so as to adaptively select the applied testing method according to the specific state of the network channel, thereby accurately monitoring the bandwidth stability of the channel while avoiding affecting the normal network communication, and then timely or in advance adjusting the channel selection strategy, thereby avoiding the impact of bandwidth instability on related services and ensuring the normal operation of related services.

[0051] As an embodiment of the present invention, please refer to Figure 2 As shown, the process of step S1 is:

[0052] S11. Get t 0 The real-time data transmission rate of the network during the period of t~t is used to fit the data transmission rate over time curve v B (t);

[0053] By formula Calculate the network occupancy coefficient D opy ;

[0054] Among them, n(v' B (t)=0) is v B (t) The number of points where the derivative is 0; n 0 is the preset reference value; p is the first conversion function; max(v B (t)) is t 0 ~t period v B (t) maximum value; t 0 ~t period v B (t) mean; R is the parameter function; BW is the standard bandwidth value, f is the second conversion function; x 1 、x 2 is the preset coefficient;

[0055] S12, based on the real-time network occupancy coefficient D opy Compared with the preset interval set, according to D opy and the interval in which it is located to select the corresponding active testing strategy.

[0056] Through the above technical solution, this embodiment provides a method for determining the network status in real time, specifically by obtaining the network occupancy coefficient D opy By the formula Calculate the network occupancy coefficient D opy ,in, It indicates t 0 The fluctuation of network occupancy during the period of t~t. Obviously, when v' B The more values ​​of (t)=0, the more frequent the fluctuations. It indicates t 0 The overall proportion of network bandwidth in the period of t~t, f(BW) is the corresponding standard value obtained by the second conversion function of the current standard bandwidth value BW, so the network occupancy coefficient D opy The acquisition process, and then according to the real-time network occupancy coefficient D opy Compared with the preset interval set, according to D opy and the interval in which it is located to select the corresponding active test strategy, and then achieve adaptability to meet the specific status of the network channel to select the application test method.

[0057] It should be noted that the preset reference value n in the above technical solution is 0 and parameter function R are selected and set according to empirical data, which reflects the average state of the corresponding values; the first conversion function p, the second conversion function f and the preset coefficient x1 、x 2 They are all obtained after fitting based on massive test data and will not be further described here.

[0058] As an implementation mode of the present invention, the active testing strategy is:

[0059] The sender sends a preset initial number of data packets to the server, and the value n corresponding to different active test strategies is add Increase the number of data packets step by step. When the number of data packets sent simultaneously reaches the maximum value n corresponding to the active test strategy, max Stop when.

[0060] Through the above technical solution, the active test strategy in this embodiment sends a preset initial number of data packets to the server through the sending end, and then according to the value n corresponding to different active test strategies, add Increase the number of data packets step by step. When the number of data packets sent simultaneously reaches the maximum value n corresponding to the active test strategy, max When the network bandwidth is occupied, the number of data packets sent can be increased appropriately to improve the accuracy of monitoring the current bandwidth status and stability.

[0061] As an embodiment of the present invention, n add and n max The acquisition process is:

[0062] By formula Calculate to obtain n add ;

[0063] By formula Calculate to obtain n max ;

[0064] Among them, n add0 (D opy ) is D opy The interval corresponds to the preset value of the number of packets to be increased; n max0 (D opy ) is D opy The preset maximum value of the corresponding quantity in the interval; min(s(D opy ) is D opy The minimum value of the interval; max(s(D opy )) is D opy The maximum value in the interval.

[0065] Through the above technical solution, this embodiment uses the formula Calculate to obtain n add; Through the formula Calculate to obtain n max ; where n add0 (D opy ) and n max0 (D opy ) is set based on empirical data, so by n add and n max The calculation process can adaptably meet the needs of active monitoring of the current bandwidth status.

[0066] As an implementation mode of the present invention, the process of evaluating the network bandwidth is as follows:

[0067] In the active test strategy, the server receives data sever , the sender sends data send And the sender receives data Data receive ;

[0068] Data sever 、Data send and Data recive They include the number of packets and the corresponding time points respectively;

[0069] By Data sever 、Data send and Data receive The number of packets in the network and the corresponding time point are used to evaluate the network bandwidth;

[0070] The process of evaluating network bandwidth is as follows:

[0071] By formula S BW =S up *S down Calculate the bandwidth stability coefficient S BW ;

[0072] Among them, the upward stability coefficient Calculate the uplink stability coefficient S up ;

[0073] Downward stability coefficient Calculate the downlink stability coefficient S down ;

[0074] Among them, m loss1 The difference between the number of packets received by the server and the number of packets sent by the sender; m loss2 is the difference between the data packet sent by the sender and the data packet received by the server; k is the first preset adjustment function, and k is an increasing function; M is the number of data packets received by the server, i∈[1,M]; delay iis the delay time of the ith data packet; Δt, m 0 is the reference value; H is the number of packets received by the sender, j∈[1,H]; delay j is the delay time of the jth data packet; α is the weight function, and α is an increasing function; m os1 The number of mismatches between the order of received data packets and the order of sent data packets during the sending process; m os2 is the number of mismatches between the order of received data packets and the order of sent data packets during the server sending process; G is a second preset adjustment function, and G is an increasing function;

[0075] Through the bandwidth stability factor S BW Evaluate network bandwidth;

[0076] According to the bandwidth stability factor S BW The process of evaluating network bandwidth is as follows:

[0077] The bandwidth stability factor S BW With the preset interval [S 1 , S 2 ] for comparison:

[0078] If S BW <S 1 , then the bandwidth stability is judged to be excellent;

[0079] If S BW ∈[S 1 , S 2 ], the bandwidth stability is judged to be normal;

[0080] If S BW >S 2 , then it is judged that the bandwidth stability is abnormal.

[0081] Through the above technical solution, this embodiment receives data Data through the server in the active test strategy sever , the sender sends data send And the sender receives data Data receive To evaluate the bandwidth network data, specifically, through the formula S BW =S up *S down Calculate the bandwidth stability coefficient S BW , where the uplink stability coefficient Calculate the uplink stability coefficient S up ; Downward stability coefficient Calculate the downlink stability coefficient S down ; Then, by taking the bandwidth stability coefficient S BW Preset interval [S1 , S 2 ] to compare, when S BW <S 1 When S BW ∈[S 1 , S 2 ], the bandwidth stability is normal. BW >S 2 , then it is judged that the bandwidth stability is abnormal, and the judgment result can provide specific reference for the subsequent channel selection strategy.

[0082] It should be noted that in the above technical solution, the first preset adjustment function k, the second preset adjustment function G and the reference values ​​Δt and m 0 The settings are all selected based on empirical data, and the weight function α is set according to the interval of the delay time. The longer the delay time, the larger the corresponding value of α.

[0083] As an implementation mode of the present invention, the adjustment process of the channel selection strategy is as follows:

[0084] Get channels with excellent bandwidth stability and normal bandwidth stability;

[0085] Bandwidth stability coefficient S corresponding to the channel BW Sort from small to large;

[0086] A channel is selected according to the priority of the sorting results.

[0087] Through the above technical solution, this embodiment obtains channels with excellent bandwidth stability and normal bandwidth stability; according to the bandwidth stability coefficient S corresponding to the channel BW Sort from small to large; select channels according to the priority of the sorting results, thereby realizing the process of channel adaptive selection.

[0088] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for monitoring network bandwidth stability, characterized in that: The method comprises: S1. Monitor real-time bandwidth usage data and adopt corresponding active testing strategies based on the bandwidth usage data; S2. Send data packets to the server according to the active test strategy, and receive the return data packets from the server. Evaluate the stability of the network bandwidth according to the received data of the server and the received data of the sender, and adjust the channel selection strategy according to the evaluation results. The process of step S1 is: S11, obtain the network real-time data transmission rate during the period t0 to t, and fit the data transmission rate versus time curve v according to the network real-time data transmission rate B (t); By formula x2) / f(BW) to obtain the network occupancy factor D opy ; Among them, n(v′ B (t)=0) is v B (t) is the number of zero points for which the derivative is obtained; n0 is the preset reference value; p is the first conversion function; max(v B (t)) is the period from t0 to t B (t) maximum value; v is the period from t0 to t B (t) mean; R is the parameter function; BW is the standard bandwidth value, f is the second conversion function; x1 and x2 are preset coefficients; S12, based on the real-time network occupancy coefficient D opy Compared with the preset interval set, according to D opy and the interval in which it is located to select the corresponding active testing strategy; The active testing strategy is: The sender sends a preset initial number of data packets to the server, and the value n corresponding to different active test strategies is add Increase the number of data packets step by step. When the number of data packets sent simultaneously reaches the maximum value n corresponding to the active test strategy, max Stop when n add and n max The acquisition process is: By formula Calculate to obtain n add ; By formula Calculate to obtain n max ; Among them, n add0 (D opy ) is D opy The interval corresponds to the preset value of the number of packets to be increased; n max0 (D opy ) is D opy The preset maximum value of the corresponding quantity in the interval; min(s(D opy ) is D opy The minimum value of the interval; max(s(D opy )) is D opy The maximum value of the interval; The process of evaluating network bandwidth is as follows: In the active test strategy, the server receives data sever , the sender sends data send And the sender receives data Data receive ; Data sever 、Data send and Data receive They include the number of packets and the corresponding time points respectively; By Data sever 、Data send and Data receive The number of packets in the network and the corresponding time point are used to evaluate the network bandwidth; The process of evaluating network bandwidth is as follows: By formula S BW =S up *S down Calculate the bandwidth stability coefficient S BW ; Among them, the upward stability coefficient Calculate the uplink stability coefficient S up ; Downward stability coefficient Calculate the downlink stability coefficient S down ; Among them, m loss1 The difference between the number of packets received by the server and the number of packets sent by the sender; m loss2 is the difference between the data packets received by the sender and the data packets sent by the server; k is the first preset adjustment function, and k is an increasing function; M is the number of data packets received by the server, i∈[1,M]; dealy i is the delay time of the ith data packet; Δt, m0 are reference values; H is the number of data packets received by the sender, j∈[1,H]; delay j is the delay time of the jth data packet; α is the weight function, and α is an increasing function; m os1 The number of mismatches between the order of received data packets and the order of sent data packets during the sending process; m os2 is the number of mismatches between the order of received data packets and the order of sent data packets during the server sending process; G is a second preset adjustment function, and G is an increasing function; Through the bandwidth stability factor S BW Evaluate network bandwidth.

2. A network bandwidth stability monitoring method according to claim 1, characterized in that: According to the bandwidth stability factor S BW The process of evaluating network bandwidth is as follows: The bandwidth stability factor S BW Compare with the preset interval [S1, S2]: If S BW <S1, the bandwidth stability is judged to be excellent; If S BW ∈[S1, S2], then the bandwidth stability is judged to be normal; If S BW >S2, it is judged that the bandwidth stability is abnormal.

3. A method for monitoring network bandwidth stability according to claim 2, characterized in that: The adjustment process of the channel selection strategy is as follows: Get channels with excellent bandwidth stability and normal bandwidth stability; Bandwidth stability coefficient S corresponding to the channel BW Sort from small to large; A channel is selected according to the priority of the sorting results.

Images