CN113839880A - Congestion control method in named data network - Google Patents
Congestion control method in named data network Download PDFInfo
- Publication number
- CN113839880A CN113839880A CN202111059129.6A CN202111059129A CN113839880A CN 113839880 A CN113839880 A CN 113839880A CN 202111059129 A CN202111059129 A CN 202111059129A CN 113839880 A CN113839880 A CN 113839880A
- Authority
- CN
- China
- Prior art keywords
- data packet
- attribute
- congestion
- congestion degree
- cwnd
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 abstract description 9
- 230000008713 feedback mechanism Effects 0.000 abstract description 5
- 208000027744 congestion Diseases 0.000 description 69
- 238000011160 research Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a congestion control method in a named data network, which comprises the following steps: the explicit feedback mechanism is characterized in that fields are expanded in a data packet, the network congestion state is recorded by counting information capable of expressing the network congestion state in the data packet sending process, the congestion information is fed back to a receiving end by using the data packet, and the receiving end adjusts the sending rate of an interest packet according to the congestion information. The method of the active queue management mechanism is to calculate the time delay of a data packet in a buffer queue, and if the queuing time of the data packet exceeds a set target value within a continuous time period, a buffer control field of the data packet is marked until the queuing time of the data packet in the queue is less than the target value. The invention utilizes the data packet to feed back the congestion information to the receiving end, and uses an active queue management mechanism, and the method is to calculate the time delay of the data packet in the buffer queue, regulate and control the buffer so as to keep the buffer queue length of the buffered data packet at a reasonable value, thereby solving the problem of buffer expansion.
Description
Technical Field
The invention relates to a network congestion control method, in particular to a named data network congestion control method based on an explicit feedback mechanism and an active queue management mechanism, and belongs to the technical field of network information transmission and communication.
Background
The traditional TCP/IP network is designed primarily for realizing communication between two hosts, and its purpose is to realize sharing of hardware resources such as disk and super computer. However, through the rapid development of more than half a century, the internet has undergone tremendous changes in scale and application, the amount of users and information in the network has increased dramatically, people have entered the big data era, and the main application mode of the network has also been shifted from text communication to information access and distribution, users have an increasing demand for content, and people are more concerned about how to acquire the content itself rather than the source and location of the content. This trend has strongly promoted the research of next-generation network technologies, and since 2006, various next-generation network architectures have been proposed by the foreign academics, including Data-Oriented network architecture (DONA), Publish/Subscribe Internet Routing Paradigm (PSIRP), and content-centric network (CCN). These projects adopt a content-centric concept, in which Named Data Networking (NDN) is more representative, and is gradually becoming a research hotspot for researching next-generation network architecture, and is considered as one of the most classical content-centric networks. The NDN architecture is used as one of content and data-oriented network architecture research projects, a content block is introduced at a thin waist part on the basis of keeping an hourglass model of the original Internet, an IP layer of a TCP/IP architecture is replaced, a data message transmitted by the network is uniquely identified in a naming prefix mode, the concerned point of the network is changed from 'where' to 'what', the current trend that the content demand of the Internet is continuously increased is adapted, and the NDN architecture has great research value and significance for the development and evolution of the future network.
Network congestion, as a network state with continuous overload, may reduce the transmission performance of the network, cause an increase in network transmission delay and an increase in packet loss, and affect network user experience. Because the content data volume is huge and the number of access devices is large in the current network, the congestion control capability of the network is very important, and the current network is not exceptional in NDN. The quality of the design of the network congestion control mechanism directly affects the throughput, the time delay, the resource utilization rate and other network performances of the NDN architecture. Although the research on the network congestion control mechanism in the conventional network based on the TCP/IP architecture is more complete, if the existing research is simply and roughly transplanted into the NDN architecture, the efficiency of the congestion control mechanism is not only reduced due to the difference between the TCP/IP architecture and the NDN architecture, but also the characteristics and advantages of the NDN architecture cannot be fully utilized due to the fact that the characteristics of the NDN architecture are not fully understood and utilized. Therefore, corresponding research is carried out aiming at NDN congestion control, which plays a crucial role and influence on the future development of an NDN system architecture, the research in the NDN field is still in the starting stage at present, and the existing congestion control method of the named data network has various defects.
Disclosure of Invention
In order to overcome the defects of the existing named data network congestion control method, the invention provides a named data network congestion control method based on an explicit feedback mechanism and an active queue manager, which comprises the following contents: the explicit feedback mechanism is characterized in that fields are expanded in a data packet, the network congestion state is recorded by counting information capable of expressing the network congestion state in the data packet sending process, the congestion information is fed back to a receiving end by using the data packet, and the receiving end adjusts the sending rate of an interest packet according to the congestion information. The method of the active queue management mechanism is to calculate the time delay of a data packet in a buffer queue, and if the queuing time of the data packet exceeds a set target value within a continuous time period, a buffer control field of the data packet is marked until the queuing time of the data packet in the queue is less than the target value. The invention comprises the following steps:
step 1: the data packet structure in the named data network is modified, and a congestion degree attribute, an arrival time attribute and a cache control tag attribute are added to the data packet structure.
Step 2: based on the congestion degree attribute added in step 1, in order to set the congestion degree attribute in the data packet, the average queue length of the data packet forwarding interface of the node is calculated at the routing node.
The specific process of the step 2 is as follows:
step 2-1: the average queue length is recorded as avgQ, and the initial queue length is set to 0.
Step 2-2: and after sampling the length of the data packet queue of the current data packet forwarding interface every 200 milliseconds, updating the value of the avgQ according to an update formula of the avgQ. The update formula of avgQ is:
avgQ＝(1-Wq)*avgQ+Wq*q
wherein, Wq is a weighting factor, and q is the actual queue length during sampling.
And step 3: based on the average queue length of the forwarding interface calculated in step 2, when the data packet reaches the intermediate node, the congestion degree attribute added in step 1 of the data packet is updated, and meanwhile, the arrival time attribute added in step 1 of the data packet is modified.
The specific flow of the step 3 is as follows:
step 3-1: and when the current data packet arrives at the routing node, reading the avgQ stored in the routing node, and modifying the arrival time attribute of the data packet into the time of the data packet reaching the routing node.
Step 3-2: MAXth and MINth are two thresholds related to packet queue length. Comparing avgQ with MAXth and MINTH, if avgQ > is MAXth, setting the attribute value of the congestion degree of the data packet to 2 to represent that the current network is in a congestion state, if MINth < avgQ < MAXth, setting the attribute value of the congestion degree of the data packet to 1 to represent that the current network has moderate load, and if MINth < avgQ, setting the attribute value of the congestion degree of the data packet to 0 to represent that the current network is in an idle state. Furthermore, an important principle of setting the congestion degree attribute is that an NDN routing node cannot set the congestion degree attribute to a value lower than the congestion degree attribute value set by the previous routing node. If the congestion degree attribute value in the packet arriving at the current routing node is "2" (set by the last routing node), even if the calculation result of the router is "1", it cannot be changed to "1".
And 4, step 4: based on the packet arrival time recorded in step 3, when the packet leaves the routing node, the packet queuing delay is calculated, and the calculation formula is as follows:
QueueDelay＝NowTime-ArrivalTime
where QueueDelay is queuing delay, NowTime is current time, and ArrivalTime is arrival time of the data packet. And then setting the attribute of the cache control mark added in the step 1 according to the calculated queuing time.
And 5: based on the congestion degree attribute set in step 3 and the cache control flag attribute set in step 4, the receiving end maintains an interest packet sending window, which represents the number of interest packets allowed to be sent at the current time, after receiving the data packets, the receiving end recalculates the window value according to the congestion degree attribute and the cache control flag attribute in the received data packets, and all the overtime data packets are not used as a calculation element.
The specific process of step 5 is as follows:
step 5-1: and after receiving the new data packet, the receiving end reads the congestion degree attribute and the cache control mark attribute.
Step 5-2: and (3) judging based on the attribute of the cache control mark read in the step (5-1), if the attribute of the cache control mark is True, indicating that the number of data packets in the current cache is too much, updating the value of cwnd, wherein an updating formula is as follows:
cwnd＝cwnd-1
and then, judging based on the congestion degree attribute read in the step 5-1, if the congestion degree attribute is 0, executing the step 5-3, if the congestion degree attribute is 1, executing the step 5-4, and if the congestion degree attribute is 2, executing the step 5-5.
Step 5-3: at this time, the current network is in an idle state, and the cwnd value is updated, wherein the updating formula is as follows:
cwnd＝cwnd*(1+γ).
step 5-4: at this time, the load of the current network is moderate, the cwnd value is updated, and the updating formula is as follows:
cwnd＝cwnd+α.
step 5-5: at this time, the current network is in a congestion state, and the cwnd value is updated according to the following formula:
cwnd＝cwnd/β.
compared with the prior art, the invention has the following technical advantages:
(1) in NDN, an implicit congestion control method based on RTO timeout may not accurately reflect the degree of network congestion, and may perform congestion control only after a timeout event indicating congestion occurs. This is due to the multi-sourced nature of NDNs, where the location of the content provider is constantly changing for end node requests, and thus the timeout value as a congestion signal tends to be inefficient in reacting to congestion. Aiming at the defect, the invention provides a congestion control method based on an explicit feedback mechanism. The method is that a receiving end adjusts the sending rate of the interest packet according to the explicit congestion information fed back by the router, specifically, a field is expanded in a data packet, and the network congestion state is recorded by counting the information capable of expressing the network congestion state in the data packet sending process. The congestion information is fed back to a receiving end by using a data packet, the receiving end adjusts the sending rate of the interest packet according to the congestion information, the congestion information is obtained by the method through the middle routing node and recorded in the data packet, then the congestion information is accumulated hop by hop through the middle node, the network global information can be reflected, and the feedback of the congestion information uses a data packet 'piggybacking' method, so that excessive extra load cannot be increased.
(2) The buffer expansion problem is a phenomenon that when a transmission window of a data packet is too large, network delay caused by blocking of the data packet more than the link capacity in a buffer is increased, and the phenomenon is increasingly serious along with the increase of the buffer size of a routing device in recent years. The existing NDN congestion control method is not researched for solving the problem of buffer expansion. The invention uses an active queue management mechanism, and the method is to calculate the time delay of the data packet in the buffer queue, if the queuing time of the data packet exceeds the set target value in a continuous time period, the buffer control field of the data packet is marked until the queuing time of the data packet in the queue is less than the target value, thereby regulating and controlling the buffer to keep the length of the buffer data packet queue at a reasonable value, and solving the problem of buffer expansion
Drawings
Fig. 1 is a diagram illustrating a packet structure of a named data network before modification in the present invention.
Fig. 2 is a diagram illustrating the structure of a named data network packet modified in the present invention.
Fig. 3 is a flow chart of the process of setting the congestion attribute of the data packet in the present invention.
Fig. 4 is a flowchart of a process of setting a cache control flag attribute according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. The invention is described in further detail below with reference to the attached drawing figures:
step 1: as shown in fig. 1 and fig. 2, a data packet structure in a named data network is modified, and a congestion degree attribute, an arrival time attribute and a cache control flag attribute are added to the data packet structure, where the congestion degree attribute is used to indicate a congestion state of a current network, the attribute is calculated by a routing node and recorded in a data packet, the arrival time attribute is used to record a time when the data packet arrives at the routing node, and the cache control flag attribute is used to trigger an active queue management mechanism. Wherein the structure of the data packet before modification is shown in fig. 1 and the structure of the data packet after modification is shown in fig. 2.
Step 2: based on the congestion degree attribute added in step 1, in order to set the congestion degree attribute in the data packet, the average queue length of the data packet forwarding interface of the node is calculated at the routing node. The specific process of the step 2 is as follows:
step 2-1: the average queue length is recorded as avgQ, and the initial queue length is set to 0.
Step 2-2: and updating the value of the avgQ according to an update formula of the avgQ after sampling the length of the data packet queue of the current data packet forwarding interface every 200 milliseconds. The update formula of avgQ is:
avgQ＝(1-Wq)*avgQ+Wq*q
wherein, Wq is a weighting factor, and q is the actual queue length during sampling. When the average queue length avgQ is calculated, a method similar to a Low-pass filter (Low-pass filter) with a weight value is adopted. Therefore, the average queue length will not change obviously due to the sudden nature of the network flow or the temporary increase of the actual queue length caused by the transient congestion, so that the short-term queue length change is 'filtered' and the long-term congestion change is reflected as much as possible. In the formula for calculating the average queue length, the weight Wq is equivalent to the time constant of the low-pass filter, which determines the degree of response of the router to changes in the incoming traffic. Therefore, the choice of Wq is very important, and if Wq is too large, avgQ cannot effectively filter out transient congestion; if Wq is too small, avgQ will react too slowly to changes in the actual queue length to reasonably reflect the congestion condition, in which case the router will not be able to effectively detect early congestion. The value of Wq should be preset according to different situations, and is generally determined by the size and duration of the burst traffic allowed to occur by the router.
And step 3: based on the average queue length calculated in step 2, whenever a data packet arrives at the intermediate node, the congestion degree attribute added in step 1 of the data packet is updated according to the average queue length of the forwarding interface calculated by the intermediate node, and meanwhile, the arrival time attribute added in step 1 of the data packet is modified.
The specific flow of step 3 is shown in fig. 3, and comprises the following steps:
step 3-1: and when the current data packet arrives at the routing node, reading the avgQ stored by the routing node.
Step 3-2: MAXth and MINth are two thresholds related to packet queue length. Comparing avgQ with MAXth and MINTH, if avgQ is less than MINth and the attribute value of the degree of congestion in the current data packet is not more than 0, executing step 3-3, if MINth is not less than avgQ and not more than MAXth and the attribute value of the degree of congestion in the current data packet is not more than 1, executing step 3-4, and if avgQ is greater than MAXth, executing step 3-5.
Step 3-3: and setting the attribute value of the congestion degree of the data packet to be 0, and indicating that the current network is in an idle state.
Step 3-4: and setting the attribute value of the congestion degree of the data packet to be 1, which indicates that the load of the current network is moderate.
Step 3-5: and setting the attribute value of the congestion degree of the data packet to be 2, and indicating that the current network is in a congestion state.
And 4, step 4: based on the arrival time of the data packet recorded in the step 3, when the data packet leaves the routing node, the queuing delay of the data packet is calculated, and the calculation formula is as follows:
QueueDelay＝NowTime-ArrivalTime
where QueueDelay is queuing delay, NowTime is current time, and ArrivalTime is arrival time of the data packet. Then, a buffer control flag is set for the data packet according to the calculated queuing delay, and the specific flow is shown in fig. 4, which will now be described in detail:
based on the calculated queuing delay, if the queuing delay of the data packet is detected to be larger than a set target value (target), firstly judging whether the data packet has entered into an alert state, if the starting time (StartTime) is equal to 0, indicating that the data packet is not in the alert state currently, setting the starting time as the current time, namely the starting time of the alert state, if the data packet has entered into the alert state currently, judging whether the duration of the alert state is larger than a set duration threshold, if the threshold is exceeded, setting the cache control mark of the data packet to True, otherwise, designing as False. If the queue time is less than the target value, the buffer control flag is set to False and the armed state duration is reset to 0.
And 5: based on the congestion degree attribute set in step 3 and the cache control flag attribute set in step 4, the receiving end maintains an interest packet sending window, which represents the number of interest packets allowed to be sent at the current time, after receiving the data packets, the receiving end recalculates the window value according to the congestion degree attribute and the cache control flag attribute in the received data packets, and all the overtime data packets are not used as a calculation element. .
The specific process of step 5 is as follows:
step 5-1: and after receiving the new data packet, the receiving end reads the congestion degree attribute and the cache control mark attribute.
Step 5-2: and (3) judging based on the attribute of the cache control mark read in the step (5-1), if the attribute of the cache control mark is True, indicating that the number of data packets in the current cache is too much, updating the value of cwnd, wherein an updating formula is as follows:
cwnd＝cwnd-1
and then, judging based on the congestion degree attribute read in the step 5-1, if the congestion degree attribute is 0, executing the step 5-3, if the congestion degree attribute is 1, executing the step 5-4, and if the congestion degree attribute is 2, executing the step 5-5.
Step 5-3: at this point, indicating that the current network is idle, the window is increased using the MI (multiplicative growth) algorithm to reach the value of the network maximum bandwidth update cwnd as soon as possible, with the update formula as follows, where 0< γ < 1: cwnd ═ cwnd [ (+ 1+ ])
Step 5-4: at this time, the load of the current network is moderate, and in order to fully utilize network bandwidth resources and accelerate convergence of a congestion window, an AI algorithm (sum-type growth) is adopted for congestion window adjustment. Updating the value of cwnd by the following formula, where α > 0: cwnd ═ cwnd + alpha
Step 5-5: at the moment, the current network is in a congestion state, and the sending rate of the interest packet is quickly reduced by using an MD (multiplicative reduction) algorithm to effectively avoid congestion. Updating the value of cwnd, the update formula is as follows, where 1< β < 2: cwnd ═ cwnd/beta.
Claims (4)
1. A congestion control method in a named data network is characterized in that: the method comprises the following steps:
step 1: modifying the data packet structure in the named data network, and adding a congestion degree attribute, an arrival time attribute and a cache control mark attribute for the data packet structure;
step 2: based on the attribute of congestion degree added in step 1, calculating the average queue length of the data packet forwarding interface of the node at the routing node in order to set the attribute of congestion degree in the data packet;
and step 3: based on the average queue length of the forwarding interface calculated in the step 2, when the data packet reaches the intermediate node, updating the congestion degree attribute added in the step 1 of the data packet, and simultaneously modifying the arrival time attribute added in the step 1 of the data packet;
and 4, step 4: based on the packet arrival time recorded in step 3, when the packet leaves the routing node, the packet queuing delay is calculated, and the calculation formula is as follows:
QueueDelay＝NowTime-ArrivalTime
wherein, QueueDelay is queuing delay, NowTime is current time, ArrivalTime is arrival time of the data packet; then setting the attribute of the cache control mark added in the step 1 according to the calculated queuing time;
and 5: based on the congestion degree attribute set in step 3 and the cache control flag attribute set in step 4, the receiving end maintains an interest packet sending window, which represents the number of interest packets allowed to be sent at the current time, after receiving the data packets, the receiving end recalculates the window value according to the congestion degree attribute and the cache control flag attribute in the received data packets, and all the overtime data packets are not used as a calculation element.
2. A method for congestion control in a named data network according to claim 1, characterized in that: the specific process of the step 2 is as follows:
step 2-1: recording the average queue length as avgQ, and setting the initial queue length as 0;
step 2-2: after sampling the data packet queue length of the current data packet forwarding interface every 200 milliseconds, updating the value of the avgQ according to the update formula of the avgQ; the update formula of avgQ is:
avgQ＝(1-Wq)*avgQ+Wq*q
wherein, Wq is a weighting factor, and q is the actual queue length during sampling.
3. A method for congestion control in a named data network according to claim 1, characterized in that: the specific flow of the step 3 is as follows:
step 3-1: when the current data packet reaches the routing node, reading the avgQ stored by the routing node, and modifying the arrival time attribute of the data packet into the time of the data packet reaching the routing node;
step 3-2: MAXth and MINth are two thresholds related to packet queue length; comparing avgQ with MAXth and MINTH, if avgQ > is MAXth, setting the attribute value of the congestion degree of the data packet to be 2, indicating that the current network is in a congestion state, if MINth < avgQ < MAXth, setting the attribute value of the congestion degree of the data packet to be 1, indicating that the load of the current network is moderate, and if MINth ═ < avgQ, setting the attribute value of the congestion degree of the data packet to be 0, indicating that the current network is in an idle state; in addition, an important principle of setting the congestion degree attribute is that one NDN routing node cannot set the congestion degree attribute to a value lower than the congestion degree attribute value set by the previous routing node; if the value of the attribute of the degree of congestion in a packet arriving at the current routing node is "2", even if the calculation result of the router is "1", it cannot be changed to "1".
4. A method for congestion control in a named data network according to claim 1, characterized in that: the specific process of step 5 is as follows:
step 5-1: after receiving a new data packet, a receiving end reads the attribute of congestion degree and the attribute of cache control mark;
step 5-2: and (3) judging based on the attribute of the cache control mark read in the step (5-1), if the attribute of the cache control mark is True, indicating that the number of data packets in the current cache is too much, updating the value of cwnd, wherein an updating formula is as follows: cwnd ═ cwnd-1
Then, judging based on the congestion degree attribute read in the step 5-1, if the congestion degree attribute is 0, executing the step 5-3, if the congestion degree attribute is 1, executing the step 5-4, and if the congestion degree attribute is 2, executing the step 5-5;
step 5-3: at this time, the current network is in an idle state, and the cwnd value is updated, wherein the updating formula is as follows:
cwnd＝cwnd*(1+γ)；
step 5-4: at this time, the load of the current network is moderate, the cwnd value is updated, and the updating formula is as follows:
cwnd＝cwnd+α；
step 5-5: at this time, the current network is in a congestion state, and the cwnd value is updated according to the following formula:
cwnd＝cwnd/β。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111059129.6A CN113839880A (en) | 2021-09-10 | 2021-09-10 | Congestion control method in named data network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111059129.6A CN113839880A (en) | 2021-09-10 | 2021-09-10 | Congestion control method in named data network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113839880A true CN113839880A (en) | 2021-12-24 |
Family
ID=78958821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111059129.6A Pending CN113839880A (en) | 2021-09-10 | 2021-09-10 | Congestion control method in named data network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113839880A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114828081A (en) * | 2022-03-30 | 2022-07-29 | 天津大学 | Cooperative hybrid congestion control method based on path recovery |
| CN114915595A (en) * | 2022-03-11 | 2022-08-16 | 北京邮电大学 | Burst packet matching method and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060045008A1 (en) * | 2004-08-27 | 2006-03-02 | City University Of Hong Kong | Queue-based active queue management process |
| WO2018225039A1 (en) * | 2017-06-09 | 2018-12-13 | Telefonaktiebolaget Lm Ericsson (Publ) | Method for congestion control in a network |
| CN110943927A (en) * | 2019-12-06 | 2020-03-31 | 湖南大学 | Named data network transmission control method, device and equipment based on time delay management |
| CN113098783A (en) * | 2021-03-26 | 2021-07-09 | 辽宁大学 | Named data network congestion control method based on link bandwidth and time delay |
-
2021
- 2021-09-10 CN CN202111059129.6A patent/CN113839880A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060045008A1 (en) * | 2004-08-27 | 2006-03-02 | City University Of Hong Kong | Queue-based active queue management process |
| WO2018225039A1 (en) * | 2017-06-09 | 2018-12-13 | Telefonaktiebolaget Lm Ericsson (Publ) | Method for congestion control in a network |
| CN110943927A (en) * | 2019-12-06 | 2020-03-31 | 湖南大学 | Named data network transmission control method, device and equipment based on time delay management |
| CN113098783A (en) * | 2021-03-26 | 2021-07-09 | 辽宁大学 | Named data network congestion control method based on link bandwidth and time delay |
Non-Patent Citations (2)
| Title |
|---|
| 沈越欣;王兴伟;李洁;曾荣飞;: "基于多源的NDN端节点拥塞控制算法", 网络空间安全, no. 08, 25 August 2019 (2019-08-25) * |
| 王文静;雒江涛;: "命名数据网络中的一种主动拥塞控制策略", 计算机工程与应用, no. 10, 16 May 2017 (2017-05-16) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114915595A (en) * | 2022-03-11 | 2022-08-16 | 北京邮电大学 | Burst packet matching method and electronic equipment |
| CN114915595B (en) * | 2022-03-11 | 2023-08-01 | 北京邮电大学 | Burst packaging method and electronic equipment |
| CN114828081A (en) * | 2022-03-30 | 2022-07-29 | 天津大学 | Cooperative hybrid congestion control method based on path recovery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7142508B2 (en) | System and method for controlling data transfer rates on a network | |
| CN111683393A (en) | Adaptive congestion control method for dynamically adjusting gain coefficient | |
| CN113839880A (en) | Congestion control method in named data network | |
| CN104994031B (en) | A kind of active queue adaptive management method ASRED | |
| Abbasov et al. | Effective RED: An algorithm to improve RED's performance by reducing packet loss rate | |
| CN113746748B (en) | Explicit congestion control method in named data network | |
| WO2010101650A1 (en) | Method and system for i/o driven rate adaptation | |
| CN113141315B (en) | Congestion control method and equipment | |
| CN113098783B (en) | Named data network congestion control method based on link bandwidth and time delay | |
| CN110730469B (en) | Method for predicting bandwidth based on extended Kalman wireless network and congestion control thereof | |
| CN113141314B (en) | Congestion control method and equipment | |
| Tahiliani et al. | CARED: cautious adaptive RED gateways for TCP/IP networks | |
| CN112995048A (en) | Blocking control and scheduling fusion method for data center network and terminal equipment | |
| Huang et al. | A more refined mobile edge cache replacement scheme for adaptive video streaming with mutual cooperation in multi-mec servers | |
| CN110266606B (en) | Active queue management optimization method and device in edge network | |
| Ye et al. | PTP: Path-specified transport protocol for concurrent multipath transmission in named data networks | |
| Zala et al. | Comparative analysis of RED queue variants for data traffic reduction over wireless network | |
| WO2022242170A1 (en) | Data processing method and related device | |
| CN116980342B (en) | Method and system for transmitting data in multi-link aggregation mode | |
| CN112787942A (en) | TCP congestion control method, device, terminal and readable storage medium | |
| CN114500394A (en) | Congestion control method for differentiated services | |
| Mahawish et al. | Survey on: A variety of aqm algorithm schemas and intelligent techniques developed for congestion control | |
| CN116827867A (en) | Low-delay congestion flow identification method based on data center network | |
| CN110943927B (en) | Named data network transmission control method, device and equipment based on time delay management | |
| Sharma et al. | A Survey on Active Queue Management Techniques |
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 |