CN102045219A - High-efficiency single-end available bandwidth measuring method - Google Patents
High-efficiency single-end available bandwidth measuring method Download PDFInfo
- Publication number
- CN102045219A CN102045219A CN 201010586725 CN201010586725A CN102045219A CN 102045219 A CN102045219 A CN 102045219A CN 201010586725 CN201010586725 CN 201010586725 CN 201010586725 A CN201010586725 A CN 201010586725A CN 102045219 A CN102045219 A CN 102045219A
- Authority
- CN
- China
- Prior art keywords
- bag
- reduction
- speed
- transmitting terminal
- available bandwidth
- 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.)
- Granted
Links
Images
Abstract
The invention relates to a high-efficiency single-end available bandwidth measuring method (pathpider) which comprises the following steps: a transmitting end transmits a specific probe packet train to a destination node; the transmitting end calculates a series of round trip time delay (RTT) values in accordance with a series of ICMP (Internet Control Message Protocol) packets returned by the destination node, and determines the time when the round trip time delay starts to remain constant; and the transmitting end calculates the average transmission rate of the packet train within the time period from the time when the packet train starts to be transmitted to the time when the round trip time delay starts to remain constant, and uses the average transmission rate as the measured value of the available bandwidth of the path. The invention can realize single-end available bandwidth measurement based on the novel probe packet train, and the available bandwidth value can be measured by only transmitting the probe packet train once. Thus, the invention has the advantages of high measurement accuracy, high convergence speed, low invasion degree and high robustness.
Description
Technical field
The present invention relates to a kind of single-ended efficiently availability bandwidth measurement method, belong to the network performance measurement field.
Background technology
Available bandwidth refers to exist under the situation of background stream, the maximum data transfer rate that link can also provide for other streams.The link of available bandwidth minimum is called the tight link (Tight Link) in this section path in each section link.The available bandwidth of tight link is the available bandwidth in this section path.Available bandwidth of end-to-end route is an important parameter of dynamically describing the network path transmittability, and it can effectively assess the actual bearer ability and the performance quality of a network path.Available bandwidth value has reacted the physical transport capacity of network, is the important references factor of monitoring network performance, diagnostic network operation conditions, optimization network performance.Available bandwidth measurement for congested control, Route Selection, Streaming Media use, the Dynamic Selection and service quality (QoS) checking of server wait application significant.
According to the difference of detection mode, present availability bandwidth measurement method can be divided into bag method, Bao Liefa are reached the availability bandwidth measurement method based on model.Bag utilizes bag that available bandwidth is estimated in the variation in the time interval in transmission course (Dispersion Time) to technology (Packet Pairs).Bag goes out a lot of algorithms and instrument to derives from technology, as Spruce, IGI, Delphi, LinkPPQ etc.It is the hypothesis of same link that bag needs based on tight link and narrow link the commercial measurement available bandwidth, and measure error may be very big when this hypothesis was false.Bag row technology obtains available bandwidth value by sending row or multiple row detection packet, and its principle is to send packet by the method from load to make path congestion, changes by the One Way Delay of detection packet in the analysis package row and estimates available bandwidth value.Adopt the typical method of bag row technology to have: Pathload, PathChirp, PTR,, YAZ, abget etc.The robustness and the stability of bag row commercial measurement available bandwidth are more intense, but sensing lead is often bigger.Method of measurement based on model also is an important directions in available bandwidth measurement field, basic thought is that the network of complexity is simplified modeling, estimate the path available bandwidth by combination model after sending a spot of detection flows collection routing information, this method is less to state of network own and background traffic influence, but when model can not accurately be portrayed traffic characteristic, certainty of measurement will be difficult to guarantee.
According to the difference of operational mode, the available bandwidth measurement system can be with being divided into unit/terminal system and two terminal system.The unit/terminal system only needs in network the instrument that installs and measures on the node just can measure the available bandwidth of this node to the path of other nodes.Two terminal systems except that needs transmitting terminal installs and measures instrument, also need install and measure instrument in destination node.The range of application of two terminal systems is very limited, its reason be the user often can only be on transmitting terminal install software, and the authority of install software on long-range machine not. in contrast, the unit/terminal system only needs just can measure at the transmitting terminal instrument that installs and measures the available bandwidth value of this node other node path to the network.
Unit/terminal available bandwidth measurement system the earliest is CProbe, and it has utilized the request-acknowledgement mechanism of ICMP agreement to send the IP bag that many groups are used to survey from transmitting terminal to receiving terminal; These IP bags have triggered the ICMP fault processing flow process of node, thereby the node on the path can send ICMP time-exceeded (TE) and destination-unreachable (DU) bag to transmitting terminal; After CProbe receives ICMP TE and DU bag, calculate that according to time of reception surveying IP wraps in transmission rate variations situation on every section link, and then the estimation available bandwidth.The method Pipechar of Chu Xianing also is based on the realization of ICMP agreement afterwards, had afterwards studies confirm that CProbe and Pipechar measured be not available bandwidth in fact, but be in the asymmetric dispersion rate (asymptotic dispersion rate) between available bandwidth and the bandwidth capacity.The characteristic of having utilized agreement based on the SProbe of TCP and http protocol exploitation to be obtaining the feedback of remote node, and excavates the interval variation rule and then the estimation available bandwidth of reply data bag.Follow-up single ended system has Abget, BFind and BNeck.Abget do not need the node unlatching ICMP function on the path just can realize single-ended measurement, but it is based on the algorithm thought of Pathload, need send repeatedly the detection packet row based on TCP and http protocol, and sensing lead is bigger.BFind causes network congestion by continuous transmission UDP message conductance, and the round-trip delay (RTT) of every the link that records from traceroute is estimated available bandwidth; BFind produces a large amount of load bags in the one-time positioning process, its invasion degree can not be ignored.BNeck calculates available bandwidth by obtaining to wrap the input rate and the output speed that are listed on every link, in calculating the available bandwidth process, need to know link capacity, BNeck adopts single packet technology measure link capacity, this need send more detection packet with lower speed just can obtain capacity value will more accurately, and the error of link capacity will directly influence the available bandwidth measurement precision.
In a word, there are problems in existing various availability bandwidth measurement method: 1) there is great limitation in the range of application of double ended system; 2) Measuring Time is long, and for example, have experiment to show: the required Measuring Time of option A bing is: 1.3-1.4 second; The required Measuring Time of scheme pathChirp is about: 5.4 seconds; The required Measuring Time of scheme Iperf is: 10.0-10.2 second; The required Measuring Time of scheme Spruce is: 10.9-11.2 second; The required Measuring Time of scheme Pathload is: 7.2-22.3 second, specifically can be referring to document: " Shriram A; Murray M; Hyun Y; Brownlee N; Broido A.Comparison of publicend-to-end bandwidth estimation tools on high-speed links., in Proc.Passive and Active Measurement Workshop, 2005.306-320 "; 3) sensing lead is excessive, cause the invasion degree of link bigger, for example, Abget, BFind and BNeck scheme all need to send repeatedly Bao Liecai finish measurement, therefore, it is significant to design the single-ended availability bandwidth measurement method of a kind of advantages of simplicity and high efficiency.
Summary of the invention
The purpose of this invention is to provide a kind of certainty of measurement height, fast convergence rate, low, the strong single-ended availability bandwidth measurement method of robustness of invasion degree.
For reaching above-mentioned purpose and other purposes, the single-ended availability bandwidth measurement method that provides of the present invention comprises step:
1) transmitting terminal is provided with the destination interface and the TTL territory of detection packet row;
2) transmitting terminal sends some load bags in back-to-back mode earlier, sends some reduction of speed bags to destination node with the speed of successively decreasing gradually again;
Be sent to the bag row of destination node, should be able to make destination node produce the icmp echo bag, for example, can be that unreachable port is realized by the destination interface that detection packet is set, also can equal transmitting terminal to the path of destination node by the TTL territory that detection packet is set and realize.The transmission rate of bag row can be that index successively decreases when sending the reduction of speed bag.
3) transmitting terminal receives the ICMP bag that returns from destination node, calculates a series of round-trip delay values
Round-trip delay refers to from sending this detection packet to receiving the time that icmp echo bag that this detection packet triggers is experienced, and promptly the time of reception of each ICMP bag deducts the value that the transmitting time of its corresponding detection packet obtains.
4) transmitting terminal determines to begin the pairing reduction of speed bag of round-trip delay that keeps constant according to a series of round-trip delays;
Because the send mode of bag row is to lean against earlier to send some load bags privately, these wrap in tight link and constantly pile up, and queuing delay constantly increases, and causes the queuing delay of the reduction of speed bag that sends later also will increase gradually, thereby round-trip delay also increases gradually.When the average transmission rate of bag row drops to a certain degree, the accumulation situation of packet is alleviated gradually in the buffering area at tight link place, the queuing delay of detection packet reduces gradually, thereby round-trip delay also reduces gradually, and round-trip delay will remain unchanged when being decreased to packet and no longer lining up in buffering area.
Bag column average transmission rate when 5) transmitting terminal calculates determined reduction of speed bag and is sent out, and with its measured value as available bandwidth.
Beneficial effect of the present invention is: realized single-ended available bandwidth measurement simply efficiently, only sent detection packet row and just can record available bandwidth value, and certainty of measurement height, measuring speed soon, the invasion degree is low, robustness is strong.
Description of drawings
Fig. 1 is an embodiment of the invention available bandwidth measurement flow chart.
Fig. 2 is the described bag row of embodiments of the invention organigrams.
Fig. 3 is an embodiment of the invention bag row round-trip delay variation diagram.
Fig. 4 is the embodiment of the invention one a constant background stream experiment topology.
Fig. 5 is the embodiment of the invention one a constant background stream experimental result.
Fig. 6 is the embodiment of the invention one a burst background stream experiment topology.
Fig. 7 is the embodiment of the invention one a burst background stream experimental result.
Embodiment
Describe preferred embodiment of the present invention in detail below in conjunction with accompanying drawing.
Embodiment one
See also Fig. 1, single-ended availability bandwidth measurement method of the present invention may further comprise the steps:
At first, transmitting terminal sends a plurality of load bags to destination node continuously in back-to-back mode, sends a plurality of reduction of speed bags to destination node continuously with the speed of progressively successively decreasing again subsequently, and wherein, each load bag and reduction of speed bag will arrive port and all be set to unreachable port.Please again referring to Fig. 2, it lists intention for transmitting terminal to the bag that destination node sends, be that transmitting terminal at first leans against and sends d load bag privately, send a plurality of reduction of speed bags subsequently, so that network path is carried out fully congested, the exponential form that can adopt transmitting terminal progressively reduces the average transmission rate of bag row, also can adopt other reduction of speed modes to send the reduction of speed bag.If the employing exponential form, the average transmission rate R of bag row when then transmitting terminal sends i reduction of speed bag
iBe the average transmission rate R of bag row when sending i+1 reduction of speed bag
I+1α (α＞1) doubly.
Then, after described each load bag and reduction of speed bag arrival destination node, because each load bag and reduction of speed bag will arrive port and be set to unreachable port, so described destination node receives load bag or reduction of speed bag at every turn, all can feed back to a corresponding ICMP destination-unreachable (DU) bag to transmitting terminal.
Then, transmitting terminal receives the ICMP bag that feeds back to from destination node, and according to the transmitting time of the time of reception of ICMP bag and the detection packet corresponding with it, calculates the round-trip delay value.For example, the time that transmitting terminal sends i reduction of speed bag is 08:20:00, and the time that receives the feedback information bag of i reduction of speed bag correspondence be 08:20:02, then to calculate round-trip delay be 2 seconds to transmitting terminal.
Then, transmitting terminal determines to begin the pairing reduction of speed bag of round-trip delay that keeps constant according to a series of round-trip delays.Because the send mode of bag row is to lean against earlier to send some load bags privately, these wrap in tight link and constantly pile up, queuing delay constantly increases, cause the queuing delay of the reduction of speed bag that sends later also will increase gradually, thereby make the reduction of speed bag arrive the time lengthening of destination node, and then the time of destination node transmission respective feedback packets of information is delayed, the time that further causes transmitting terminal to receive this feedback information bag delays, and just makes that also calculating round-trip delay increases.And when the average transmission rate of bag row drops to a certain degree, the accumulation situation of packet is alleviated gradually in the buffering area at tight link place, the queuing delay of reduction of speed bag reduces gradually, thereby round-trip delay also reduces gradually, constantly beginning round-trip delay to congested lucky elimination will remain unchanged, and round-trip delay changes as shown in Figure 3.
At last, the bag column average transmission rate when transmitting terminal calculates determined detection packet and is sent out is with its measured value as available bandwidth.Transmitting terminal is according to formula
K=1,2,3... calculate described detection packet column average transmission rate, wherein, S is the size (the load bag is identical with reduction of speed bag size) of bag, and d is the number of load bag, k is the sequence number of the pairing reduction of speed bag of round-trip delay that begins to keep constant, t is for from beginning to send the 1st load bag to sending k needed time of reduction of speed bag, the average transmission rate of R bag row when sending the 1st reduction of speed bag, and α is the decrement factor of bag row transmission rate decline.If the average transmission rate of bag row is R when sending i reduction of speed bag
i, the average transmission rate of bag row is R when sending i+1 reduction of speed bag
I+1, then α should be R
iWith R
I+1Ratio, and α＞1.
Experimental verification
For verifying the performance of availability bandwidth measurement method of the present invention, the NS2 that uses the network research field extensively to adopt carries out emulation experiment.Because the present invention is an end-to-end measurement instrument, therefore adopt the experiment topology of having only a linear trunk path, each router all adopts the scheduling strategy of first in first out in the topology, and buffering area adopts the tail drop strategy.All links are the link of bi-directional symmetrical in the topology, and capacity is 100Mbps.
1 constant background stream situation
Test topology as shown in Figure 4, transmitting terminal Snd passes through router n1, n2, n3 successively to the path P of destination node n9 ... n8, background stream 1,2,3 is and runs through n1, n2 ... the constant bit rate background stream of n8, size is respectively 10Mbps, 30Mbps, 70Mbps.Be respectively 10-40 second, 40 seconds-70 seconds, 70 seconds-100 seconds the running time of background stream 1,2,3.Measurement result such as Fig. 5, in whole measuring process, along with the variation of background stream, available bandwidth value is respective change also, and pathpider can accurately measure available bandwidth value always.The average measurement error is 0.011Mbps, and Mean Time Measurement is 0.193 second, and the average measurement load is 1.296Mb
2 burst background stream situations
The experiment topology as shown in Figure 6, background stream on every link meets stream that Pareto distributes by 10 and compiles and form, to simulate paroxysmal background stream, the bag size of Pareto stream is set to: the bag size is respectively 50%, 40%, 10% (to wrap size distribution in the realistic network of trying one's best) for packet shared ratio in load of 40/550/1500bytes, packet sending speed on every link is 20Mbps, Pareto distribution shape parameter alpha=1.9.This is because show the self similarity feature after the stream polymerization that the Pareto of a plurality of obedience parameter alpha＜2 distributes.Other has two CBR flow CBR1 and CBR2, and their size is 20Mbps, and CBR1 runs through n1, n2, and n3, n4, CBR2 runs through n3, n4, n5, n6.Be 0-15 second, 40-65 second the running time of CBR1, and be 40-100 second the running time of CBR2.The background of adding up on each bar link with the short time interval in measuring process flows the actual value that flow is determined available bandwidth.Measurement result as shown in Figure 7, the average measurement error is 0.077Mbps, Mean Time Measurement is 0.196 second, average load is 1.296Mb.Average measurement error ratio under the burst background is less to have illustrated that also the robustness of available bandwidth measurement of the present invention is more intense.
Embodiment two
Measure the path of transmitting terminal earlier to path, destination node place.Can send a row TTL territory since the 1 IP bag that increases gradually to destination node at transmitting terminal, under the situation that packet loss do not occur, transmitting terminal receives that the number of ICMP time-exceeded (TE) bag is path so.
The Bao Liezhong detection packet is the IP bag, and purpose IP is the IP address of destination node, and the TTL territory of bag is set to the path of transmitting terminal to path, destination node place.Detection packet is dropped owing to TTL is kept to 0 after arriving destination node like this, and destination node sends the TE bag to transmitting terminal.Transmitting terminal at first leans against and sends d detection packet privately (this d detection packet is called the load bag, the detection packet of Fa Songing is called the reduction of speed bag subsequently) network path is carried out fully congested, progressively reducing the average transmission rate of wrapping row with exponential form subsequently (need to prove, also can adopt other reduction of speed modes to send the reduction of speed bag), the average transmission rate R of bag row when sending i reduction of speed bag
iAverage transmission rate R for send i+1 reduction of speed bag time bag row
I+1α (α＞1) doubly.
Transmitting terminal goes out round-trip delay according to the Time Calculation that receives the TE bag.Because the send mode of bag row is to lean against earlier to send some load bags privately, these wrap in tight link and constantly pile up, and queuing delay constantly increases, and causes the queuing delay of the reduction of speed bag that sends later also will increase gradually, thereby round-trip delay also increases gradually.When the average transmission rate of bag row drops to a certain degree, the accumulation situation of packet is alleviated gradually in the buffering area at tight link place, the queuing delay of detection packet reduces gradually, thereby round-trip delay also reduces gradually, and constantly beginning round-trip delay to congested lucky elimination will remain unchanged.We only need find round-trip delay to begin that bag that keeps constant, and the moment that this bag arrives tight link is congested elimination constantly, and the average transmission rate of bag row was path to be measured available bandwidth value when this bag sent.Available bandwidth value avbw is calculated by following formula:
Wherein, S is the size of load bag or reduction of speed bag, d is the number of load bag, k is the sequence number of the pairing reduction of speed bag of round-trip delay that begins to keep constant, t is from beginning to send the 1st load bag to sending k needed time of reduction of speed bag, R is the average transmission rate of bag row when sending the 1st reduction of speed bag, and α is for wrapping the decrement factor that the row transmission rate descends.If the average transmission rate of bag row is R when sending i reduction of speed bag
i, the average transmission rate of bag row is R when sending i+1 reduction of speed bag
I+1, then α should be R
iWith R
I+1Ratio, and α＞1.
Above embodiment is the unrestricted technical scheme of the present invention in order to explanation only.Any modification or partial replacement that does not break away from spirit and scope of the invention all should be encompassed in the middle of the claim scope of the present invention.
Performance evaluation
Below will analyze the performance of single-ended availability bandwidth measurement method of the present invention:
1, certainty of measurement
Owing to show a series of ever-reduced discrete values in the transmission rate decline process of bag row, when available bandwidth value to be measured is between certain adjacent two value, will inevitably produce theoretical error.Theoretical error is influenced by decrement factor setting, and the more little theoretical error of decrement factor is more little.
In the actual measurement process, round-trip delay is influenced by the flow size on the reverse path, thereby according to judging that round-trip delay begins to keep constant and determines that available bandwidth may produce error, but because Measuring Time is very short, the possibility of the big micromutation of flow in very short time on the reverse path is very little, and therefore oppositely the background rheologyization is very little to the influence of certainty of measurement.As Fig. 5 and shown in Figure 7, average measurement error of the present invention is less than 0.1Mb, and certainty of measurement is very high.
2, Measuring Time
The time that the present invention finishes an available bandwidth measurement is to begin to send the time of bag row to receiving certain feedback information bag only to begin to be held constant at definite two-way time.Measuring Time is wrapped the influence of row transmission rate decrease speed and bag round-trip delay.Wherein wrapping row transmission rate decrease speed influenced by being provided with of initial fall off rate and decrement factor.Generally, just can finish measurement because the present invention sends once the bag row, Measuring Time is very short.As Fig. 5 and shown in Figure 7, Measuring Time of the present invention about 0.2 second, much smaller than the Measuring Time of several schemes described in the background technology, as: the required Measuring Time of option A bing is: 1.3-1.4 second; The required Measuring Time of scheme pathChirp is about: 5.4 seconds; The required Measuring Time of scheme Iperf is: 10.0-10.2 second; The required Measuring Time of scheme Spruce is: 10.9-11.2 second; The required Measuring Time of scheme Pathload is: 7.2-22.3 second.
3, sensing lead
Sensing lead refers to the load capacity that produced in the one-shot measurement process.One-shot measurement sends bag row, and the actual negative carrying capacity of these bag row is sensing lead.Sensing lead follows the number of the load bag that is sent, initial fall off rate, decrement factor and available bandwidth value to be measured relevant.By reasonable parameter is set, sensing lead of the present invention is controlled in the very little scope.Fig. 5 and Fig. 7 show that the sensing lead of pathpider is about 1.3Mb, and Abget, BFind and BNeck scheme all need to send repeatedly Bao Liecai finish measurement, and method of the present invention only need send single bag row and just can finish measurement, and load is starkly lower than existing other technical scheme.
4, robustness
As shown in Figure 3, the overall variation tendency of round-trip delay value be rises earlier afterwards drop to constant, in this process if the influence of the background stream that is subjected to happening suddenly can cause the variation of rising or downward trend.If background stream flow increases, then detection flows queuing aggravation, round-trip delay descends and slows down, and then the sequence number of the round-trip delay bag that begins to keep constant increases, and measured available bandwidth value reduces; Otherwise if background stream flow reduces, then the detection flows queuing slows down, and round-trip delay descends and accelerates, and then the round-trip delay sequence number that drops to the detection packet that begins to keep constant reduces, and measured available bandwidth value increases.This has just guaranteed to flow down in the burst background and has carried out available bandwidth measurement and have higher robustness.
In sum, beneficial effect of the present invention is: realized simple efficient single-ended available bandwidth measurement, only sent detection packet row and just can record available bandwidth value that certainty of measurement height, measuring speed are soon, the invasion degree is low, robustness is strong.
Claims (4)
1. a single-ended efficiently availability bandwidth measurement method is characterized in that comprising the steps:
1) transmitting terminal is provided with the destination interface and the TTL territory of detection packet row;
2) the load bag and the reduction of speed bag that are comprised of transmitting terminal detection packet row that setting is finished is sent to destination node, wherein, earlier each load bag sent in back-to-back mode, sends the reduction of speed bag with the speed of successively decreasing gradually again;
3) transmitting terminal receives a series of ICMP bags that return from destination node, calculate a series of round-trip delays, wherein, round-trip delay is to deduct time of reception that transmitting terminal receives ICMP when bag the corresponding load bag of this ICMP bag or the time difference that delivery time obtained of reduction of speed bag;
4) transmitting terminal determines to begin the pairing reduction of speed bag of round-trip delay that keeps constant according to a series of round-trip delays;
Bag column average transmission rate when 5) transmitting terminal calculates determined reduction of speed bag and is sent out is with its measured value as available bandwidth.
2. as right item 1 described method, it is characterized in that: transmitting terminal is provided with destination interface to be unreachable port or the TTL territory is set equals the path of transmitting terminal to destination node, so as each load bag and reduction of speed bag arrive destination node after destination node can produce the ICMP bag.
3. as right item 1 described method, it is characterized in that: the transmission rate of reduction of speed bag is successively decreased with exponential form.
4. as right item 3 described methods, it is characterized in that: available bandwidth value avbw is calculated by following formula:
Wherein, S is the size of each bag that transmitting terminal sent, d is the number of load bag, k begins the pairing reduction of speed bag of the round-trip delay sequence number that keeps constant, t is from beginning to send the 1st load bag to sending k needed time of reduction of speed bag, R is the average transmission rate of bag row when sending the 1st reduction of speed bag, and α is for wrapping the decrement factor that the row transmission rate descends; If the average transmission rate of bag row is R when sending i reduction of speed bag
i, the average transmission rate of bag row is R when sending i+1 reduction of speed bag
I+1, then α should be R
iWith R
I+1Ratio, and α＞1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105867255A CN102045219B (en) | 2010-12-14 | 2010-12-14 | High-efficiency single-end available bandwidth measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105867255A CN102045219B (en) | 2010-12-14 | 2010-12-14 | High-efficiency single-end available bandwidth measuring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102045219A true CN102045219A (en) | 2011-05-04 |
| CN102045219B CN102045219B (en) | 2012-07-25 |
Family
ID=43911031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105867255A Expired - Fee Related CN102045219B (en) | 2010-12-14 | 2010-12-14 | High-efficiency single-end available bandwidth measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102045219B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102594629A (en) * | 2012-03-29 | 2012-07-18 | 迈普通信技术股份有限公司 | Method and system for measuring subscriber line bandwidth |
| CN103095531A (en) * | 2013-01-28 | 2013-05-08 | 北京星网锐捷网络技术有限公司 | Method, device and gateway equipment for bandwidth measurement |
| CN103905263A (en) * | 2012-12-26 | 2014-07-02 | 中国移动通信集团公司 | Service bandwidth testing method and device |
| CN104113446A (en) * | 2014-07-03 | 2014-10-22 | 南京航空航天大学 | Method for measuring single-end available bandwidth in unexpected background flow environment |
| CN105490882A (en) * | 2015-12-11 | 2016-04-13 | 上海大学 | Network physical bandwidth measuring method capable of fending off expansion attacks |
| WO2016192478A1 (en) * | 2015-05-29 | 2016-12-08 | 腾讯科技（深圳）有限公司 | Data transmission method and apparatus |
| CN106411647A (en) * | 2016-10-13 | 2017-02-15 | 腾讯科技（深圳）有限公司 | Communication quality detection method and detection server |
| CN107171887A (en) * | 2017-05-19 | 2017-09-15 | 郑州云海信息技术有限公司 | A kind of network bandwidth test method, client and network bandwidth test system |
| CN107426048A (en) * | 2017-05-12 | 2017-12-01 | 腾讯科技（深圳）有限公司 | A kind of single-end available bandwidth measuring, device and transmitting terminal |
| EP3286979A4 (en) * | 2015-04-24 | 2019-03-06 | Intel IP Corporation | Apparatus, computer readable medium, and method for multi-user request-to-send for wide channel access in a high efficiency wireless local-area network |
| CN110098976A (en) * | 2019-04-08 | 2019-08-06 | 京信通信系统（中国）有限公司 | Measurement method, device, computer equipment and the storage medium of network parameter |
| US20200145311A1 (en) * | 2018-11-07 | 2020-05-07 | Palo Alto Research Center Incorporated | Network measurement in an enterprise environment |
| CN112583658A (en) * | 2020-11-20 | 2021-03-30 | 鹏城实验室 | Available bandwidth measuring method, storage medium and equipment |
| US11115305B2 (en) | 2017-02-27 | 2021-09-07 | Airmobile Ab | Mobile radio network node and method for estimating a capacity of a link in a radio communications network |
| CN116633791A (en) * | 2023-07-26 | 2023-08-22 | 常州楠菲微电子有限公司 | Bandwidth detection method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101895417A (en) * | 2010-07-06 | 2010-11-24 | 同济大学 | Positioning method for tight link based on available bandwidth of subpaths |
-
2010
- 2010-12-14 CN CN2010105867255A patent/CN102045219B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101895417A (en) * | 2010-07-06 | 2010-11-24 | 同济大学 | Positioning method for tight link based on available bandwidth of subpaths |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102594629A (en) * | 2012-03-29 | 2012-07-18 | 迈普通信技术股份有限公司 | Method and system for measuring subscriber line bandwidth |
| CN103905263B (en) * | 2012-12-26 | 2017-06-20 | 中国移动通信集团公司 | A kind of service bandwidth method of testing and device |
| CN103905263A (en) * | 2012-12-26 | 2014-07-02 | 中国移动通信集团公司 | Service bandwidth testing method and device |
| CN103095531A (en) * | 2013-01-28 | 2013-05-08 | 北京星网锐捷网络技术有限公司 | Method, device and gateway equipment for bandwidth measurement |
| CN103095531B (en) * | 2013-01-28 | 2015-05-20 | 北京星网锐捷网络技术有限公司 | Method, device and gateway equipment for bandwidth measurement |
| CN104113446A (en) * | 2014-07-03 | 2014-10-22 | 南京航空航天大学 | Method for measuring single-end available bandwidth in unexpected background flow environment |
| EP3286979A4 (en) * | 2015-04-24 | 2019-03-06 | Intel IP Corporation | Apparatus, computer readable medium, and method for multi-user request-to-send for wide channel access in a high efficiency wireless local-area network |
| CN106304203B (en) * | 2015-05-29 | 2020-02-21 | 腾讯科技（深圳）有限公司 | Data transmission method and device |
| WO2016192478A1 (en) * | 2015-05-29 | 2016-12-08 | 腾讯科技（深圳）有限公司 | Data transmission method and apparatus |
| CN106304203A (en) * | 2015-05-29 | 2017-01-04 | 腾讯科技（深圳）有限公司 | Data transmission method and device |
| CN110730105B (en) * | 2015-05-29 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Picture data transmission method, device, equipment and storage medium |
| CN110730105A (en) * | 2015-05-29 | 2020-01-24 | 腾讯科技（深圳）有限公司 | Picture data transmission method, device, equipment and storage medium |
| US10462707B2 (en) | 2015-05-29 | 2019-10-29 | Tencent Technology (Shenzhen) Company Limited | Data transmission method and apparatus |
| CN105490882B (en) * | 2015-12-11 | 2018-10-23 | 上海大学 | The network physical Bandwidth Measurement Method of expansion attack can be resisted |
| CN105490882A (en) * | 2015-12-11 | 2016-04-13 | 上海大学 | Network physical bandwidth measuring method capable of fending off expansion attacks |
| CN106411647A (en) * | 2016-10-13 | 2017-02-15 | 腾讯科技（深圳）有限公司 | Communication quality detection method and detection server |
| US11115305B2 (en) | 2017-02-27 | 2021-09-07 | Airmobile Ab | Mobile radio network node and method for estimating a capacity of a link in a radio communications network |
| CN107426048B (en) * | 2017-05-12 | 2018-11-09 | 腾讯科技（深圳）有限公司 | A kind of single-end available bandwidth measuring, device and transmitting terminal |
| CN107426048A (en) * | 2017-05-12 | 2017-12-01 | 腾讯科技（深圳）有限公司 | A kind of single-end available bandwidth measuring, device and transmitting terminal |
| CN107171887A (en) * | 2017-05-19 | 2017-09-15 | 郑州云海信息技术有限公司 | A kind of network bandwidth test method, client and network bandwidth test system |
| US20200145311A1 (en) * | 2018-11-07 | 2020-05-07 | Palo Alto Research Center Incorporated | Network measurement in an enterprise environment |
| US11956135B2 (en) * | 2018-11-07 | 2024-04-09 | Xerox Corporation | Network measurement in an enterprise environment |
| CN110098976A (en) * | 2019-04-08 | 2019-08-06 | 京信通信系统（中国）有限公司 | Measurement method, device, computer equipment and the storage medium of network parameter |
| CN112583658A (en) * | 2020-11-20 | 2021-03-30 | 鹏城实验室 | Available bandwidth measuring method, storage medium and equipment |
| CN116633791A (en) * | 2023-07-26 | 2023-08-22 | 常州楠菲微电子有限公司 | Bandwidth detection method and device |
| CN116633791B (en) * | 2023-07-26 | 2023-09-26 | 常州楠菲微电子有限公司 | Bandwidth detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102045219B (en) | 2012-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102045219B (en) | High-efficiency single-end available bandwidth measuring method | |
| Ribeiro et al. | pathchirp: Efficient available bandwidth estimation for network paths | |
| CN101026509B (en) | End-to-end low available bandwidth measuring method | |
| CN101272290B (en) | Measuring method, measuring apparatus for route congestion state in IP network | |
| CN100463422C (en) | A link, path, and network availability bandwidth measurement method | |
| CN101958811B (en) | Method and system for measuring end-to-end available bandwidth | |
| US20050232227A1 (en) | Method and apparatus for characterizing an end-to-end path of a packet-based network | |
| JP5029125B2 (en) | Available bandwidth estimation system, stream data distribution system, method, and program | |
| CN101895417B (en) | Positioning method for tight link based on available bandwidth of subpaths | |
| US10181994B2 (en) | Probing a network | |
| CN114747169B (en) | Round trip packet loss measurement in packet switched communication networks | |
| US20220191117A1 (en) | Enabling a round-trip packet loss measurement in a packet-switched communication network | |
| CN104113446A (en) | Method for measuring single-end available bandwidth in unexpected background flow environment | |
| CN102055628B (en) | Method of available bandwidth measurement and close link circuit positioning based on single pack column | |
| US10462032B2 (en) | Probing a network | |
| Abdelaziz et al. | Evaluation of the performance of the SLoPS: Available bandwidth estimation technique in IEEE 802.11 b wireless networks | |
| CN104539486A (en) | End-to-end available bandwidth estimating method based on TCP acknowledgement packet pair | |
| CN114553783A (en) | Load balancing method for self-adaptive rectifying cell granularity of data center network | |
| Sargento et al. | Capacity and cross-traffic estimation of all links in a path using ICMP Timestamps | |
| Mamatas et al. | BOTTLENECK-QUEUE BEHAVIOR: How much can TCP know about it? | |
| Tian et al. | ABuGET: Measuring the Non-Cooperative Available Bandwidth | |
| Kumar | EChirp: Measuring Available Bandwidth for the Internet Using Multiple Chirp Packet Trains | |
| Yuan et al. | Intelligent Probing Technique for Bandwidth Estimation in Wireless Network | |
| 社团法人 et al. | Using Active Probing | |
| Zaman et al. | Multimedia stream rate control over MANET based on router feedback |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120725 Termination date: 20141214 |
|
| EXPY | Termination of patent right or utility model |