CN114785716B - Available bandwidth measurement method based on self-induced congestion and unidirectional delay - Google Patents
Available bandwidth measurement method based on self-induced congestion and unidirectional delay Download PDFInfo
- Publication number
- CN114785716B CN114785716B CN202210277722.6A CN202210277722A CN114785716B CN 114785716 B CN114785716 B CN 114785716B CN 202210277722 A CN202210277722 A CN 202210277722A CN 114785716 B CN114785716 B CN 114785716B
- Authority
- CN
- China
- Prior art keywords
- queue
- packet
- time
- parameter
- self
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
- H04L43/0858—One way delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0882—Utilisation of link capacity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/12—Network monitoring probes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Abstract
The invention discloses an available bandwidth measurement method based on self-induced congestion and unidirectional delay, and a method for recovering a time predicted value, which comprises the following steps: acquiring a first parameter of a self-induced congestion load queue and a second parameter of a congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; the method comprises the steps that a round of timing transmission is carried out on a detection queue through a packet transmitter, the receiving time of the detection queue after the round of timing transmission is measured through a packet receiver, and then a unidirectional delay array is obtained according to the receiving time and the transmitting time during the timing transmission; and positioning and denoising the unidirectional delay array based on a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet. The method of the invention can efficiently and accurately measure the available bandwidth of the network in the multi-hop modern network with high bandwidth rate and rapid change.
Description
Technical Field
The invention relates to the technical field of the next generation of Internet, in particular to an available bandwidth measurement method based on self-induced congestion and unidirectional delay.
Background
Network measurements are a very important part of network research and can be used for congestion control, routing algorithms, etc. Its performance and behavior has a significant impact on network research.
The traditional active available bandwidth measurement methods currently existing include two types: a probe interval model method and a probe rate model method. The packet interval model method transmits a probe packet queue, observes its reception interval, and calculates the available bandwidth according to the relation between the available bandwidth and the packet interval variation. The method has the advantages of high measurement speed and low cost, namely, the method can finish one measurement by sending one round of queue; its disadvantage is lack of versatility, and as the number of hops of the network path increases, the measurement error increases. The packet rate model method sends a detection packet queue to cause path congestion, tries to adjust the queue rate, and searches for the critical rate of congestion just occurring/not occurring, wherein the critical rate is the available bandwidth. The method has the advantages of strong universality, and the measurement result always converges to the actual available bandwidth no matter how many path hops are; its disadvantage is slow measurement speed, i.e. multiple rounds of queues and constant rate adjustment are required to complete a measurement.
With the development of the internet in recent years, network devices and technologies have undergone rapid revolution. The network card is developed from an electrical interface to a high-speed optical interface; the bandwidth rate of the main backbone network increases above 10 Gbps. In large data centers, there is an increasing demand for high-speed 40Gbps and 100Gbps transmission rates. The traditional active available bandwidth measurement method is difficult to adapt to the problem of low efficiency and accuracy of a high-speed and fast-changing network.
Accordingly, there is a need for improvement and development in the art.
Disclosure of Invention
The invention aims to solve the technical problems that the available bandwidth measuring method based on self-induced congestion and unidirectional delay is difficult to be applied to a network with high speed and rapid change and has low efficiency and accuracy.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect, an embodiment of the present invention provides a method for measuring available bandwidth based on self-induced congestion and unidirectional delay, where the method includes:
acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
Carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission; and positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
In one implementation, the self-induced congestion load queue is a constant rate queue with constant inclusion.
In one implementation, the congestion-recovering check queue includes a first check queue and a second check queue; wherein the first check queue consists of a plurality of data packets which are unevenly distributed; the second check queue is composed of a plurality of data packets which are uniformly distributed.
In one implementation, the first parameter includes: the number of packets of the self-induced congestion load queue, the inclusion of the self-induced congestion load queue and the sending rate of the self-induced congestion load queue.
In one implementation, the second parameter includes: the packet capacity of the check queue, the packet number of the first check queue, the upper and lower packet interval limits of the first check queue, the packet number of the second check queue, the packet interval of the second check queue, the upper and lower available bandwidth limits.
In one implementation, the generating the probe queue based on the preset algorithm according to the first parameter and the second parameter includes:
acquiring the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on the first parameter and the second parameter;
and generating a detection queue according to the first parameter, the second parameter, the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on a preset recursion function.
In one implementation manner, the generating the probe queue based on the preset recursive function according to the first parameter, the second parameter, the time of the current data packet relative to the start time, and the time of the last data packet relative to the start time includes:
adding the number of the packets of the self-induced congestion load queue in the first parameter to the number of the packets of the first check queue in the second parameter to obtain a first tundish number;
Subtracting 1 from the first tundish number to obtain a second tundish number;
multiplying the packet number of the self-induced congestion load queue in the first parameter by the packet capacity of the self-induced congestion load queue in the first parameter to obtain a first flow;
inputting the first flow, the packet number of the self-induced congestion load queue in the first parameter, the second tundish number, the upper limit of the available bandwidth and the lower limit of the available bandwidth, the time of the current data packet relative to the starting time, the time of the last data packet relative to the starting time, the upper limit of the packet interval of the first check queue and the lower limit of the packet interval into a preset recursion function to obtain the sending time of a plurality of data packets; wherein, the sending time takes the time of the first data packet as a reference;
and forming a detection queue by a plurality of data packets at the sending time.
In one implementation, the acquiring the unidirectional delay array according to the receiving time and the sending time when the sending is timed includes:
subtracting the sending time of timing sending from the receiving time to obtain a unidirectional delay array.
9. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 1, wherein after performing a round of timing transmission on the probe queue by a packet transmitter and measuring a reception time of the probe queue after a round of timing transmission by a packet receiver, and then acquiring a unidirectional delay array according to the reception time and a transmission time when timing transmission, the method comprises:
Acquiring a preset first threshold value, a preset second threshold value and the minimum detection packet quantity for recovering congestion;
and inputting the unidirectional delay array, the first threshold value, the second threshold value and the minimum detection packet quantity of the recovery congestion into a preset recovery evaluation algorithm to obtain a unidirectional delay recovery threshold value and a recovery measurement result.
In one implementation manner, the positioning and denoising the unidirectional delay array according to a preset restoration positioning algorithm and a preset denoising algorithm to obtain a restoration time predicted value and a subscript of a first restored packet, and calculating the available bandwidth of the network according to the restoration time predicted value and the subscript of the first restored packet includes:
removing noise in the network card interrupt merging and process switching process based on a preset denoising algorithm;
when the recovery measurement result is that the measurement is successful, inputting the unidirectional delay array, the unidirectional delay recovery threshold value and the transmission time of all data packets in the detection queue into a preset recovery positioning algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet;
multiplying the lower label of the first recovered packet by the packet capacity of the check queue to obtain a first product;
Multiplying the number of packets of the self-induced congestion load queue by the packet capacity of the self-induced congestion load queue to obtain a second product;
adding the second product to the first product to obtain a product sum;
dividing the product sum by the recovery time predicted value to obtain the available bandwidth of the network.
In a second aspect, an embodiment of the present invention further provides an apparatus for measuring available bandwidth based on self-induced congestion and unidirectional delay, where the apparatus includes: the detection queue generating module is used for acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
the unidirectional delay array acquisition module is used for carrying out one-round timing transmission on the detection queue through the packet transmitter, measuring the receiving time of the detection queue after one-round timing transmission through the packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission;
And the available bandwidth calculation module is used for carrying out positioning and denoising processing on the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
In a third aspect, an embodiment of the present invention further provides an intelligent terminal, including a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors, where the one or more programs include an available bandwidth measurement method based on self-induced congestion and unidirectional delay according to any one of the above.
In a fourth aspect, embodiments of the present invention also provide a non-transitory computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method of measuring available bandwidth based on self-induced congestion and unidirectional delay as described in any of the above.
The invention has the beneficial effects that: the method comprises the steps of firstly obtaining a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model; then, carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission; finally, according to a preset recovery positioning algorithm and a preset denoising algorithm, positioning and denoising the unidirectional delay array to obtain a recovery time predicted value and a subscript of a first recovered packet, and according to the recovery time predicted value and the subscript of the first recovered packet, calculating the available bandwidth of the network; therefore, the embodiment of the invention realizes one round of available bandwidth measurement by generating the expected self-induced congestion and congestion recovery of the detection queue, and can realize accurate available bandwidth measurement by recovering a positioning algorithm and a denoising algorithm.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
Fig. 1 is a schematic flow chart of a method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to an embodiment of the present invention.
Fig. 2 is a simplified network topology provided by an embodiment of the present invention.
Fig. 3 is a flowchart of a probe queue generating algorithm according to an embodiment of the present invention.
Fig. 4 is a flowchart of an arangefunc function algorithm provided in an embodiment of the present invention.
FIG. 5 is a flowchart of a recovery evaluation algorithm according to an embodiment of the present invention.
Fig. 6 is a flowchart of a denoising algorithm according to an embodiment of the present invention.
Fig. 7 is a flowchart of a recovery positioning algorithm according to an embodiment of the present invention.
Fig. 8 is a schematic diagram of a measurement environment according to an embodiment of the present invention.
Fig. 9 is a schematic block diagram of an apparatus for measuring available bandwidth based on self-induced congestion and unidirectional delay according to an embodiment of the present invention.
Fig. 10 is a schematic block diagram of an internal structure of an intelligent terminal according to an embodiment of the present invention.
Detailed Description
The invention discloses an available bandwidth measuring method based on self-induced congestion and unidirectional delay, which is used for making the purposes, technical schemes and effects of the invention clearer and more definite, and is further described in detail below by referring to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Because in the prior art, the active available bandwidth measurement method is difficult to be suitable for a high-speed and rapid-change network, the problems of low efficiency and low accuracy occur, and the system faces the following three challenges when the available bandwidth measurement is completed:
1. problems of the conventional methods: the detection interval model simplifies the network to be single-hop, so that the network does not perform well in a multi-hop scene; the probe rate model uses multiple rounds of queue probing and therefore the measurement speed is slower. Whichever conventional method fails to meet the actual demand.
2. Diversified noise sources: the performance of the active available bandwidth measurement method depends on the accuracy of the time stamp of the received and transmitted packets. And the accuracy of the receiving and transmitting packet receives various noise influences: the process switching of the operating system of the server for receiving and transmitting the package may cause delay of the package and delay of the package, thereby causing error of the time stamp; the interrupt delay of the router or the receiving network card is enabled, so that the packet is stored after reaching the network card, and is continuously processed after a period of delay.
3. Difficult to compare: in a real network, the real available bandwidth changes with time, and it is difficult to obtain a real value, which causes a certain trouble to the accuracy of the verification method.
In order to solve the problems in the prior art, the embodiment provides an available bandwidth measurement method based on self-induced congestion and unidirectional delay, which realizes one round of available bandwidth measurement by generating the self-induced congestion and congestion recovery of an expected detection queue, and can realize accurate available bandwidth measurement by recovering a positioning algorithm and a denoising algorithm. In the implementation, first, a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue are acquired, and a detection queue is generated according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model; then, carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission; and finally, positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
Exemplary method
The embodiment provides an available bandwidth measurement method based on self-induced congestion and one-way delay, which can be applied to intelligent terminals of the next generation of Internet. As shown in fig. 1, the method includes:
step S100, acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
in this embodiment, the theoretical basis of the burst buffer recovery model is as follows:
1. single route buffer length variation and available bandwidth relation
As shown in fig. 2, let i represent the i-th router, Δt i For the time that elapses from the arrival of the probe packet at the buffer to a certain point in time, and during which the router is operating at maximum link bandwidth,
for the average value of the background traffic arriving during the period, P is the sum of the probe packet traffic arriving at the buffer during the period, ΔQ i C for the difference in length between the buffer at the end of the period and the buffer at the beginning of the period i A represents the link bandwidth of the router egress i For the available bandwidth of the router during this period, the buffer length change has the following relationship with background traffic, probe traffic, and link bandwidth:
by definition, the relation between the buffer length change and the available bandwidth is obtained:
2. relation between multi-hop unidirectional delay and buffer length variation
Assuming that a fixed size packet starts at time t with a one-way delay D (t) from the start point to the destination point, it needs to undergo queuing when it passes through the ith route, assuming that the router buffer length is Q i (t) router link bandwidth C i The portion of the packet that is related to the buffer length that the packet experiences when arriving at the ith router is D i (t) the sum of the fixed transmission delays is denoted by β:
theorem: if T is assumed to represent a tight link, i.e. a link with minimum available bandwidth, consider time T 1 And t 2 . Let lambda set 1 ＝D(t 1 ) Beta, lambda set 2 ＝D(t 2 ) -beta. If DeltaQ T ＝Q T (t 2 )-Q T (t 1 ) then-C T ·λ 1 ≤AQ T ≤C T ·A 2
|AQ T |≤C T ·max(λ 1 ，λ 2 )
And (3) proving:
because of D T (t) is less than or equal to D (t) -beta and Q T (t)＝D T (t)·C T Therefore, it is
Q T (t)≤C T ·(D(t)-β)
Let t=t 1 And t=t 2 Substitution to obtain
Q T (t 1 )≤C T ·λ 1
Q T (t 2 )≤≤C T ·λ 2
Also known as Q T (t) is non-negative, so
-C T ·λ 1 ≤ΔQ T ≤C T ·λ 2
|ΔQ T |≤C T ·max(λ 1 ，λ 2 )
3. Theoretical relative error
It can be found that when lambda 1 And lambda (lambda) 2 All smaller, predicted value
And the true value->
Will be very close. Let the deviation be->
Assuming P > ΔQ T The relative error is:
when DeltaQ T When =0, η=0; when DeltaQ T When < 0, eta < 0; when DeltaQ T At > 0, η > 0.
if-C is used T ·λ 1 ≤Δ Q T≤C T ·λ 2 Substitution, can be obtained:
since each term in the above equation is known, the upper and lower limits of the theoretical relative error can be calculated.
Setting a first parameter of an auto-induction congestion load queue and a second parameter of a congestion recovery check queue according to the burst buffer recovery model, wherein the auto-induction congestion load queue is a constant-rate queue with constant inclusion; the congestion recovery check queue comprises a first check queue and a second check queue; wherein the first check queue consists of a plurality of data packets which are unevenly distributed; the second check queue consists of a plurality of data packets which are uniformly distributed; the first parameter includes: number of packets n of self-induced congestion load queue l Inclusion s of self-induced congestion load queues l And the sending rate r of the self-induced congestion load queue l . The second parameter includes: the inclusion s of the check queue i Number of packets n of first check queue a Upper limit g of packet interval of first check queue M And a lower packet interval limit g m Number of packets n of second check queue b Packet interval g of second check queue n Upper limit of available bandwidth a M And lower limit of available bandwidth a m . After the first parameter is obtained, a detection queue can be generated according to the first parameter and the second parameter based on a preset algorithm; correspondingly, the generating the detection queue based on the preset algorithm according to the first parameter and the second parameter comprises the following steps: acquiring the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on the first parameter and the second parameter; based on a preset recursion function, a detection queue is generated according to the first parameter, the second parameter, the time of the current data packet relative to the starting time and the time of the last data packet relative to the starting time, and the detection queue is designed by an engineer in advance, so that the expected detection queue is obtained.
Specifically, as shown in fig. 3, a time t [ n ] of the current data packet relative to the start time is obtained based on the first parameter and the second parameter l ]And the time t [ n ] of the last data packet relative to the start time a +n l -1]The method comprises the following steps: will be spentThe number of packets n of the self-induced congestion load queue in the first parameter l Multiplying the inclusion s of the self-induced congestion load queue in said first parameter l Obtaining a first flow rate P 1 The method comprises the steps of carrying out a first treatment on the surface of the Will have a first flow rate P 1 Divided by a M Obtaining the time t [ n ] of the current data packet relative to the initial time l ]I.e. t [ n ] l ]＝n l *s l /a M ＝P 1 /a M The method comprises the steps of carrying out a first treatment on the surface of the Second flow rate P 2 The calculation formula of (2) is as follows: p (P) 2 ＝P 1 +(n a -1)*s i T [ n ] a +n l -1]＝P 2 /a m And then, generating a detection queue according to the first parameter, the second parameter, the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on a preset recursion function.
In order to obtain a detection queue, the generating the detection queue based on the preset recursive function according to the first parameter, the second parameter, the time of the current data packet relative to the starting time and the time of the last data packet relative to the starting time includes the following steps: adding the number of the packets of the self-induced congestion load queue in the first parameter to the number of the packets of the first check queue in the second parameter to obtain a first tundish number; subtracting 1 from the first tundish number to obtain a second tundish number; multiplying the packet number of the self-induced congestion load queue in the first parameter by the packet capacity of the self-induced congestion load queue in the first parameter to obtain a first flow; inputting the first flow, the packet number of the self-induced congestion load queue in the first parameter, the second tundish number, the upper limit of the available bandwidth and the lower limit of the available bandwidth, the time of the current data packet relative to the starting time, the time of the last data packet relative to the starting time, the upper limit of the packet interval of the first check queue and the lower limit of the packet interval into a preset recursion function to obtain the sending time of a plurality of data packets; the sending time is an expected sending time stamp of the detection queue, and the time of the first data packet is taken as a reference; and forming a detection queue by a plurality of data packets at the sending time.
Specifically, the number of packets n of the self-induced congestion load queue in the first parameter l Adding the number of packets n of the first check queue in the second parameter a Obtaining a first number of tundish (n a +n l ) The method comprises the steps of carrying out a first treatment on the surface of the -comparing said first number of tundish (n a +n l ) Subtracting 1, a second number of tundish (n a +n l -1); the first flow rate P has been obtained 1 The method comprises the steps of carrying out a first treatment on the surface of the By passing the first flow rate P 1 Number of packets n of the self-induced congestion load queue in the first parameter l Said second number of tundish (n a +n l -1) said upper limit of available bandwidth a M And said lower limit of available bandwidth a m Time t [ n ] of current data packet relative to starting time l ]Time t [ n ] of last data packet relative to start time a +n l -1]Upper limit of packet interval a of first check queue M And a lower packet interval limit a m Inputting into preset recursion function to obtain the transmission time t of several data packets a The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the sending time takes the time of the first data packet as a reference; t is t a For detecting the scheduled transmission time of each packet of the queue relative to the first packet. And forming a detection queue by a plurality of data packets at the sending time. In the present embodiment, the recursive function is ArrF function, the ArrF function is calculated by the process shown in FIG. 4, and parameters of ArrF function are p, i l ,i r ,a l ,a r ,t l ,t r ,g m ,g M ,s i ,t a If i l +1 is greater than i r Return to (i) r -i l )/(i r -i l The result of +1) is assigned to q, q is a l +(1-q)*a r Assigned to a as a result of (c) temp P/a temp Is assigned to t temp If t temp Less than t l +g m Then t is l +g m Is assigned to t temp Otherwise, t is l +g M Is assigned to t temp Will t temp Assigning t to a [i l +1]Will p/t temp Assignment to a temp . Recall ArrF function and parametersp plus s i Substitution of p, i l Add 1 to replace i l Will a temp Replace al, let t temp Substitution t l 。
After the probe queue is obtained, the following steps may be performed as shown in fig. 1: s200, carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission;
specifically, the Linux system is used for calling, timing sending and receiving according to the expected time stamp, timing sending is performed on the detection queue for one round through the packet sender, and the receiving time of the detection queue after one round of timing sending is measured through the packet receiver, wherein the timing sending and the receiving time obtaining are in the prior art and are not repeated herein. And acquiring a unidirectional delay array according to the receiving time and the sending time when the timing sending is performed, namely subtracting the sending time when the timing sending is performed from the receiving time to obtain a unidirectional delay array d.
In one implementation, after obtaining the one-way delay array, the following steps may be performed: acquiring a preset first threshold value, a preset second threshold value and the minimum detection packet quantity for recovering congestion; and inputting the unidirectional delay array, the first threshold value, the second threshold value and the minimum detection packet quantity of the recovery congestion into a preset recovery evaluation algorithm to obtain a unidirectional delay recovery threshold value and a recovery measurement result.
Specifically, after the transmission and reception of the probe queue are completed, a one-way delay array d may be obtained, at which time a recovery evaluation algorithm needs to be used to evaluate the actual probe queue to confirm whether the measurement of the round of probe queue is successful. Recovery evaluation algorithm implementation as in fig. 5, recovery evaluation algorithm input parameters include: d, N, th a ，th b M, the output parameter is rec, th c D [ N-1 ]]-d[0]Assignment to v a If v a Greater than th a Assigning False to rec and 0 to th c Otherwise max (d [ i ]])-min(d[i]) Results of (2) are assigned to v b Wherein i is greater than N-m and less than N; if v b Greater than th b False is assigned to rec and 0 is assigned to th c Otherwise, true is assigned to rec, max (d [ i ]]) Assignment of values to th c . The algorithm finally returns rec, th c . Where d is the one-way delay array, N is the total number of packets, n=n l +n a +n b D represents an array of unidirectional delays of all probe packets in sequence; th (th) a A judgment threshold value representing one-way delay, and if the difference between the one-way delay at the end and the one-way delay at the beginning is larger than the judgment threshold value, the path congestion at the moment is considered to be unrecoverable; th (th) b Is a measurement threshold for path one-way delay stabilization, and if the one-way delay variation is greater than it, it is considered unstable; m represents the number of detection packets required for recovery, and if the number of packets in the recovery state at last is smaller than the number of detection packets, the path is considered to be not recovered; rec represents whether the measurement is successfully recovered or not, and when the measurement is successful, rec is True, otherwise False; th (th) c Represents a one-way delay recovery threshold and is considered recovered if the one-way delay is below it.
After obtaining the one-way delay array, the following steps may be performed as shown in fig. 1: and S300, positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
Step S300 includes the steps of:
S301, removing noise in the network card interrupt merging and process switching process based on a preset denoising algorithm;
s302, when the recovery measurement result is that measurement is successful, inputting a one-way delay array, a one-way delay recovery threshold value and the transmission time of all data packets in a detection queue into a preset recovery positioning algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet;
s303, multiplying the lower label of the first recovered packet by the packet capacity of the check queue to obtain a first product;
s304, multiplying the packet number of the self-induced congestion load queue by the packet capacity of the self-induced congestion load queue to obtain a second product;
s305, adding the second product to the first product to obtain a product sum;
s306, dividing the product sum by the recovery time predicted value to obtain the available bandwidth of the network.
In practice, when a single measurement packet is received on the device that has been turned on to interrupt the merge, it is stored by the hardware, waits for a period of time, and then triggers the interrupt to be forwarded to the operating system. The invention discovers that both mechanisms cause the probe packets to be received in an aggregated manner, i.e. a plurality of continuous packets are received at very small intervals, then waiting for a longer time, and then receiving the plurality of continuous packets; in this process, both process switching and interrupt coalescing can cause noise to be transmitted by packets clustered, requiring denoising of the clustered noise. The invention removes noise in the network card interrupt merging and process switching process based on the preset denoising algorithm, and the denoising algorithm of the invention can effectively reduce the denoising algorithm of the network card interrupt merging and the receiving and transmitting packet context switching. In this embodiment, the denoising algorithm is as shown in fig. 6, and the input parameter of the denoising algorithm is t in ，n in ，th d The output parameter is t out ，n out Will t out Assigning a value of null, n out Assigning a value of 0; using the for loop, 0 is assigned to i, which is self-incremented by 1 every time a subsequent operation is performed until i equals n out -1, subsequent operation as to let t in [i+1]-t in [i]Is assigned to g [ i ]]If g [ i ]]Greater than th d Then push back is called (t out ,t in [i]) And n is as follows out Self-accumulation 1 is performed, wherein push_back is a function in the prior art, and details are not described here. Final denoising algorithm output t out ，n out . Wherein t is in For noisy timestamp arrays, n in Th is the number of time stamps contained in the array d Representing our set anomaly threshold, when adjacent time stamp intervals are less than the threshold, determining that the time stamps are systematically delayed; when the interval between adjacent time stamps is greater than theAt the threshold value, it is accurate to determine the previous timestamp. t is t out To remove the noisy timestamp array, n out The number of time stamps contained in the time stamp array after noise removal. After denoising, the time series data may cancel noise from the process switching and interrupt combining. It should be noted that the noise removal algorithm is a separate process from the previous probe queue generation algorithm, the recovery evaluation algorithm, and the subsequent recovery localization algorithm. After completion of the recovery evaluation algorithm, if rec returned by it is False, discarding the measurement result; if it is True, the measurement result is the measurement success, the unidirectional delay array d and the unidirectional delay recovery threshold th are obtained c And detecting the transmission time t of all data packets in the queue b Inputting the number n of the packets of the self-induced congestion load queue in the first parameter into a preset restoration positioning algorithm l Also input into a preset recovery positioning algorithm to obtain a recovery time predicted value E and a subscript rec of the first recovered packet id . The recovery positioning algorithm is shown in fig. 7, and the input parameter of the recovery positioning algorithm is n l ,d,N,th c ,t b The output parameters are L, E, U, rec id In one for cycle, rec id The initial value of the R-C is N-1, when rec id Greater than or equal to n l The subsequent operations are performed, and rec will be executed once id The value of (1) is subtracted from 1 until rec id Less than n l The execution of the subsequent operations is stopped, the subsequent operations being if d rec id ]Greater than th c Then jump out. Will rec id A value of 1 is added to rec id Will t b [rec id -1]Assigning to L, t b [rec id ]Assigned to U, call XvalueF (x a ,y a ,x b ,y b Y), rec id Assigning pre to 1, assigning Xvalue F (t b [pre],d[pre],t b [rec id ],d[rec id ],th c ) The value of (2) is given to E, returns L, E, U, rec id Wherein, the XvalueF function is a function in the prior art, and will not be described herein. In addition, the following parameters can be obtained through the recovery positioning algorithm: the actual transmission time of all packets is consistentArray t of sequences b The lower bound L of the recovery time and the upper bound U of the recovery time.
To calculate the available bandwidth, the subscript rec of the first recovered packet is used id Multiplying the inclusion s of the inspection queue i Obtain a first product rec id *s i The method comprises the steps of carrying out a first treatment on the surface of the Number of packets n to queue self-induced congestion load l Multiplying the inclusion s of an auto-induced congestion load queue l Obtaining a second product n l *s l The method comprises the steps of carrying out a first treatment on the surface of the The first product rec id *s i Adding the second product n l *s l Obtain the product sum n l *s l +rec id *s i The method comprises the steps of carrying out a first treatment on the surface of the Sum the product of n l *s l +rec id *s i Dividing the recovery time predicted value E to obtain the available bandwidth of the network
In the theoretical model, A= (P-dQ)/dt, in the following calculation formula, because rec id Represents the number of packets that have been sent at recovery, so P-dq=n l *s l +rec id *s i ，dt＝n l *s l +rec id *s i So in the following calculation, a= (n l *s l +rec id *s i )/E。
In one implementation, the general measurement environment adopted by the present invention is shown in fig. 8, and the topology structure of the test platform is composed of 5 terminal nodes, namely a measurement node, a remote node and three side nodes. These 5 nodes are AMAX XP-4A201G servers, which are all equipped with Intel (R) Xeon (R) Silver4216CPU (@ 2.10 GHz) and two network cards: a tera network card of Intel 82599ES and an Intel X722 gigabit network card. Their operating systems are Ubuntu 18.04. The path includes three routers, in effect called S5731-S48T4X switches, providing 10Gbps SFP ports and 10/100/1000BASE-T electrical ports.
The platform of the present invention uses two tools to generate background traffic: iPorf 3, a tool that uses the Linux network stack to generate TCP, UDP traffic; tcpreplay, a tool to replay a packet-grabbing file to simulate real bursty traffic.
True value: the maximum transmission bandwidth without any background traffic is measured for each link first, we take it as the link bandwidth. And then, the side node sends background traffic with a specified rate, and the real value of the available bandwidth at the moment can be obtained by subtracting the background traffic rate from the link bandwidth.
By constructing the system, the conventional available bandwidth measurement tool and the latest tool can accurately perform comparative tests, thereby analyzing the respective inadequacies.
The main bright points of the invention include:
1. a new active available bandwidth measurement model, a buffer congestion recovery model, is presented. It relates the available bandwidth to the one-way delay based on the assumption that the network is multi-hop and the traffic is variable. The model overcomes the defects that the detection interval model is not universal and the detection rate model is slow to measure;
2. an active available bandwidth measurement tool is implemented based on a buffer congestion recovery model. The tool realizes technologies such as transmitting queues, receiving queues and the like under a high-speed network, comprises functions such as data processing and denoising, and improves the effect of measuring the available bandwidth;
3. A multi-hop test environment is built, and the method can adjust the background flow rate in the environment so as to acquire the real-time available bandwidth, thereby verifying the effect of the method.
Exemplary apparatus
As shown in fig. 9, an embodiment of the present invention provides an available bandwidth measurement apparatus based on self-induced congestion and unidirectional delay, which includes a probe queue generating module 401, a unidirectional delay array acquiring module 402, and an available bandwidth calculating module 403: the detection queue generating module 401 is configured to obtain a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generate a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
the unidirectional delay array acquisition module 402 is configured to perform one round of timing transmission on the detection queue through a packet transmitter, measure a receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquire a unidirectional delay array according to the receiving time and a transmitting time when the timing transmission is performed;
The available bandwidth calculating module 403 is configured to perform positioning and denoising processing on the unidirectional delay array according to a preset restoration positioning algorithm and a preset denoising algorithm, obtain a restoration time predicted value and a subscript of a first restored packet, and calculate an available bandwidth of the network according to the restoration time predicted value and the subscript of the first restored packet.
Based on the above embodiment, the present invention further provides an intelligent terminal, and a functional block diagram thereof may be shown in fig. 10. The intelligent terminal comprises a processor, a memory, a network interface, a display screen and a temperature sensor which are connected through a system bus. The processor of the intelligent terminal is used for providing computing and control capabilities. The memory of the intelligent terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the intelligent terminal is used for communicating with an external terminal through network connection. The computer program, when executed by a processor, implements a method of measuring available bandwidth based on self-induced congestion and one-way delay. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen, and a temperature sensor of the intelligent terminal is arranged in the intelligent terminal in advance and used for detecting the running temperature of internal equipment.
It will be appreciated by those skilled in the art that the schematic diagram in fig. 10 is merely a block diagram of a portion of the structure related to the present invention and is not limiting of the smart terminal to which the present invention is applied, and that a specific smart terminal may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.
In one embodiment, a smart terminal is provided that includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for: acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission;
And positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
In summary, the invention discloses a method for measuring available bandwidth based on self-induced congestion and unidirectional delay, which comprises the following steps: acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model; carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission; and positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet. The embodiment of the invention realizes one round of available bandwidth measurement by generating the expected self-induced congestion and congestion recovery of the detection queue, and can realize accurate available bandwidth measurement by recovering a positioning algorithm and a denoising algorithm.
Based on the above embodiments, the present invention discloses a method for measuring available bandwidth based on self-induced congestion and one-way delay, it should be understood that the application of the present invention is not limited to the above examples, and that modifications or variations can be made by those skilled in the art in light of the above description, and all such modifications and variations shall fall within the scope of the appended claims.
Claims (13)
1. A method for measuring available bandwidth based on self-induced congestion and one-way delay, the method comprising:
acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
carrying out one round of timing transmission on the detection queue through a packet transmitter, measuring the receiving time of the detection queue after one round of timing transmission through a packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission;
And positioning and denoising the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
2. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 1, wherein the self-induced congestion load queue is a constant rate queue with constant inclusion.
3. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 1, wherein the check queue for recovering from congestion comprises a first check queue and a second check queue; wherein the first check queue consists of a plurality of data packets which are unevenly distributed; the second check queue is composed of a plurality of data packets which are uniformly distributed.
4. The method for measuring available bandwidth based on self-induced congestion and one-way delay according to claim 1, wherein the first parameter comprises: the number of packets of the self-induced congestion load queue, the inclusion of the self-induced congestion load queue and the sending rate of the self-induced congestion load queue.
5. A method for measuring available bandwidth based on self-induced congestion and one-way delay according to claim 3, wherein the second parameter comprises: the packet capacity of the check queue, the packet number of the first check queue, the upper and lower packet interval limits of the first check queue, the packet number of the second check queue, the packet interval of the second check queue, the upper and lower available bandwidth limits.
6. The method of claim 1, wherein the generating a probe queue based on the first parameter and the second parameter based on a preset algorithm comprises:
acquiring the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on the first parameter and the second parameter;
and generating a detection queue according to the first parameter, the second parameter, the time of the current data packet relative to the starting moment and the time of the last data packet relative to the starting moment based on a preset recursion function.
7. The method of claim 6, wherein generating the probe queue based on the first parameter, the second parameter, the time of the current packet relative to the start time, and the time of the last packet relative to the start time according to a preset recursive function comprises:
Adding the number of the packets of the self-induced congestion load queue in the first parameter to the number of the packets of the first check queue in the second parameter to obtain a first tundish number;
subtracting 1 from the first tundish number to obtain a second tundish number;
multiplying the packet number of the self-induced congestion load queue in the first parameter by the packet capacity of the self-induced congestion load queue in the first parameter to obtain a first flow;
inputting the first flow, the packet number of the self-induced congestion load queue in the first parameter, the second tundish number, the upper limit of the available bandwidth and the lower limit of the available bandwidth, the time of the current data packet relative to the starting time, the time of the last data packet relative to the starting time, the upper limit of the packet interval of the first check queue and the lower limit of the packet interval into a preset recursion function to obtain the sending time of a plurality of data packets; wherein, the sending time takes the time of the first data packet as a reference;
and forming a detection queue by a plurality of data packets at the sending time.
8. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 1, wherein the acquiring the unidirectional delay array according to the reception time and the transmission time at the time of the timing transmission comprises:
Subtracting the sending time of timing sending from the receiving time to obtain a unidirectional delay array.
9. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 1, wherein after performing a round of timing transmission on the probe queue by a packet transmitter and measuring a reception time of the probe queue after a round of timing transmission by a packet receiver, and then acquiring a unidirectional delay array according to the reception time and a transmission time when timing transmission, the method comprises:
acquiring a preset first threshold value, a preset second threshold value and the minimum detection packet quantity for recovering congestion;
and inputting the unidirectional delay array, the first threshold value, the second threshold value and the minimum detection packet quantity of the recovery congestion into a preset recovery evaluation algorithm to obtain a unidirectional delay recovery threshold value and a recovery measurement result.
10. The method for measuring available bandwidth based on self-induced congestion and unidirectional delay according to claim 9, wherein the positioning and denoising the unidirectional delay array according to a preset restoration positioning algorithm and a preset denoising algorithm to obtain a restoration time predicted value and a subscript of a first restored packet, and calculating the available bandwidth of the network according to the restoration time predicted value and the subscript of the first restored packet comprises:
Removing noise in the network card interrupt merging and process switching process based on a preset denoising algorithm;
when the recovery measurement result is that the measurement is successful, inputting the unidirectional delay array, the unidirectional delay recovery threshold value and the transmission time of all data packets in the detection queue into a preset recovery positioning algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet;
multiplying the lower label of the first recovered packet by the packet capacity of the check queue to obtain a first product;
multiplying the number of packets of the self-induced congestion load queue by the packet capacity of the self-induced congestion load queue to obtain a second product;
adding the second product to the first product to obtain a product sum;
dividing the product sum by the recovery time predicted value to obtain the available bandwidth of the network.
11. An apparatus for measuring available bandwidth based on self-induced congestion and one-way delay, the apparatus comprising:
the detection queue generating module is used for acquiring a first parameter of a preset self-induced congestion load queue and a second parameter of a preset congestion recovery check queue, and generating a detection queue according to the first parameter and the second parameter based on a preset algorithm; wherein, the self-induced congestion load queue and the check queue for recovering congestion are set based on a burst buffer recovery model;
The unidirectional delay array acquisition module is used for carrying out one-round timing transmission on the detection queue through the packet transmitter, measuring the receiving time of the detection queue after one-round timing transmission through the packet receiver, and then acquiring a unidirectional delay array according to the receiving time and the transmitting time during timing transmission;
and the available bandwidth calculation module is used for carrying out positioning and denoising processing on the unidirectional delay array according to a preset recovery positioning algorithm and a preset denoising algorithm to obtain a recovery time predicted value and a subscript of a first recovered packet, and calculating the available bandwidth of the network according to the recovery time predicted value and the subscript of the first recovered packet.
12. An intelligent terminal comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for performing the method of any of claims 1-10.
13. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210277722.6A CN114785716B (en) | 2022-03-21 | 2022-03-21 | Available bandwidth measurement method based on self-induced congestion and unidirectional delay |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210277722.6A CN114785716B (en) | 2022-03-21 | 2022-03-21 | Available bandwidth measurement method based on self-induced congestion and unidirectional delay |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114785716A CN114785716A (en) | 2022-07-22 |
| CN114785716B true CN114785716B (en) | 2023-06-16 |
Family
ID=82425822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210277722.6A Active CN114785716B (en) | 2022-03-21 | 2022-03-21 | Available bandwidth measurement method based on self-induced congestion and unidirectional delay |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114785716B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584111B1 (en) * | 1998-11-04 | 2003-06-24 | Northern Telecom Limited | ABR flow control using single bit congestion indication and wavelet transform filtering |
| CN104618195A (en) * | 2015-02-16 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Bandwidth estimation method and device |
| CN105245399A (en) * | 2015-09-08 | 2016-01-13 | 海南大学 | Bottleneck link measurement method in end-to-end network communication path |
| CN112487880A (en) * | 2020-11-13 | 2021-03-12 | 河北省科学院应用数学研究所 | Median filter, device and system based on maximum error criterion |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080259813A1 (en) * | 2004-03-09 | 2008-10-23 | Johnny Mikhael Matta | Method and apparatus for quality of service determination |
-
2022
- 2022-03-21 CN CN202210277722.6A patent/CN114785716B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6584111B1 (en) * | 1998-11-04 | 2003-06-24 | Northern Telecom Limited | ABR flow control using single bit congestion indication and wavelet transform filtering |
| CN104618195A (en) * | 2015-02-16 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Bandwidth estimation method and device |
| CN105245399A (en) * | 2015-09-08 | 2016-01-13 | 海南大学 | Bottleneck link measurement method in end-to-end network communication path |
| CN112487880A (en) * | 2020-11-13 | 2021-03-12 | 河北省科学院应用数学研究所 | Median filter, device and system based on maximum error criterion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114785716A (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10623297B2 (en) | Methods, systems, and computer readable media for testing scheduling fidelity in a time sensitive network | |
| RU2439823C2 (en) | Using filtration and active probing to assess data transfer channel | |
| CN112217686B (en) | System, method and device for evaluating round trip delay | |
| US6996064B2 (en) | System and method for determining network throughput speed and streaming utilization | |
| EP2760182B1 (en) | Data communication apparatus, data transmission method, and computer system | |
| GB2422505A (en) | Sampling datagrams | |
| Gebert et al. | Performance modeling of softwarized network functions using discrete-time analysis | |
| US20220368606A1 (en) | Fault Detection Model Training Method, Apparatus, and System | |
| Chydzinski et al. | The single-server queue with the dropping function and infinite buffer | |
| Altukhov et al. | On real-time delay monitoring in software-defined networks | |
| Chertov et al. | A device-independent router model | |
| US20160285730A1 (en) | Apparatus and method for measuring a bandwidth for data transmission between communication devices | |
| CN114785716B (en) | Available bandwidth measurement method based on self-induced congestion and unidirectional delay | |
| Zangrilli et al. | Comparing passive network monitoring of grid application traffic with active probes | |
| US10263873B2 (en) | Method and system for determining short-timescale traffic rates from time-stamped packet data | |
| CN113179171B (en) | Fault detection method, device and system | |
| Ma et al. | Statistical analysis of TCP's retransmission timeout algorithm | |
| Min et al. | A new end-to-end measurement method for estimating available bandwidth | |
| CN112019443A (en) | Multi-path data transmission method and device | |
| US9882751B2 (en) | Communication system, communication controller, communication control method, and medium | |
| US20240113955A1 (en) | Measuring apparatus, method for measuring, and recorded program medium | |
| JP2020150359A (en) | Analysis program, analysis device, and analysis method | |
| Ozturk et al. | DIChirp: Direct injection bandwidth estimation | |
| Irey IV et al. | Techniques for LAN performance analysis in a real-time environment | |
| CN116264490A (en) | Message processing method, related device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |