CN115941557A - Self-adaptive congestion control method and device based on time delay - Google Patents
Self-adaptive congestion control method and device based on time delay Download PDFInfo
- Publication number
- CN115941557A CN115941557A CN202011250982.1A CN202011250982A CN115941557A CN 115941557 A CN115941557 A CN 115941557A CN 202011250982 A CN202011250982 A CN 202011250982A CN 115941557 A CN115941557 A CN 115941557A
- Authority
- CN
- China
- Prior art keywords
- time
- congestion control
- delay
- rate
- control system
- 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 33
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 230000000737 periodic effect Effects 0.000 claims abstract description 17
- 230000001133 acceleration Effects 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 4
- 230000003247 decreasing effect Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000033228 biological regulation Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 14
- 238000004088 simulation Methods 0.000 description 7
- 241000761389 Copa Species 0.000 description 6
- 230000001413 cellular effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The patent discloses a periodic congestion control method and equipment based on time delay, which are used for monitoring amplitude-frequency characteristics of network time delay in a detection period so as to judge whether a congestion control system is stable or not; when the congestion control system is stable, dynamically updating the detection period and the rate adjustment coefficient, continuously updating the acceleration factor, and finally, continuously and dynamically adjusting the current sending rate and the congestion window by integrating the target sending rate. The invention has the technical effects that whether the congestion control system enters a stable state with periodic change or not is judged through fast Fourier transform according to the behavior of network delay within a period of time, and the rate regulation mode is dynamically changed by deducing the current network environment in the stable state. The congestion control system can work within a preset range under different environments and presents expected behavior patterns.
Description
Technical Field
The present invention relates to the field of network congestion control, and in particular, to a method and an apparatus for controlling periodic congestion based on delay.
Background
In the Internet, the conventional mainstream congestion control protocol mainly performs congestion control according to packet loss information. However, when the network is not congested, the congestion control protocol based on packet loss may continue to increase the size of the congestion window until the buffer overflows where the data traffic is congested, i.e., at the network bottleneck. This makes the queuing queue at the bottleneck longer the larger the buffer, thereby increasing the transmission delay of the data packet. In order to avoid the problem, the existing congestion control method based on the delay judges whether the network is congested or not by using the delay information, and when the delay is overlarge, the network is judged to be congested, so that a congestion window is reduced before a buffer area overflows, and the increase of a queuing queue is avoided.
And the congestion control protocols Vegas and Copa based on time delay both combine queuing time delay and the size of a congestion window to judge whether the network is congested. After the Vegas judges the network congestion, the windows are adjusted in a static mode, and the adjustment amount of the windows in each RTT is only one packet. And when the window and queuing delay are in the desired position, the window size is kept constant. However, where the latency bandwidth product is large, vegas takes a long time to reach the desired size of the window. Meanwhile, as the windows are kept unchanged after Vegas reaches the expected position, the buffer area at the network bottleneck can keep a certain queue. This means that the newly arrived stream will have an erroneous estimated round trip link propagation delay, i.e. the measured RTTmin is larger than the real round trip link propagation delay.
Copa adopts a mechanism similar to Vegas to judge network congestion, and the difference is that the window adjusting amplitude of each RTT in Copa is determined by V & ltdelta & gt, wherein V is a dynamically adjusted parameter, delta is a preset parameter, and is not changed after the setting is finished, and is generally set as 2 in Copa. Copa associates the control target with the window adjustment amplitude by delta to periodically empty the queue, thereby solving the problem that Vegas cannot accurately measure RTTmin. However, like Vegas, the stable point queue length of Copa is linearly related to the number of data streams, and the low latency goal cannot be achieved in the scenario of multiple data streams or low bandwidth.
Disclosure of Invention
The problem that this patent will be solved is: the traditional congestion control algorithm cannot guarantee the expected performance of realizing high throughput and low delay in a network scene with wide variation, and the problem of performance collapse occurs in some scenes. In order to solve the problems, the invention provides a periodic congestion control method PDCC based on time delay.
In order to achieve the technical purpose, the technical scheme of the invention is that,
a periodic congestion control method based on time delay monitors amplitude-frequency characteristics of network time delay in a detection period to judge whether a congestion control system is stable; when the congestion control system is stable, the detection period and the rate adjustment coefficient are dynamically updated, the acceleration factor is continuously updated, and finally the target sending rate is synthesized to continuously and dynamically adjust the current sending rate and the congestion window.
The method according to claim 1, wherein the monitoring of amplitude-frequency characteristics to determine whether the congestion control system is stable comprises the following steps:
the sending end periodically detects the amplitude-frequency characteristic of the currently collected delay information and judges the state of the congestion control system; when the amplitude-frequency characteristic remains unchanged for a period of time, the congestion control system is considered stable, otherwise it is unstable.
The sending end periodically detects the amplitude-frequency characteristic of the currently collected delay information, and when the sending end receives an ACK packet, the sending time of the ACK packet is subtracted according to the receiving time of the ACK packet to obtain the instantaneous round-trip delay RTT, and all RTT information in the T time of the latest detection period is recorded; and then, performing fast Fourier transform on the RTT information in the latest T time to obtain corresponding amplitude-frequency characteristics.
The periodic congestion control method based on time delay judges the state of a congestion control system, and takes the frequency corresponding to the maximum amplitude value in the amplitude-frequency characteristics in a detection period as a dominant frequency fm; if fm in the time of two continuous detection periods T is close, the system is considered to be in a stable state, otherwise, the system is considered to be in a convergence state, namely:
wherein, fm pre Is the dominant frequency in the previous detection period T time, fm is the dominant frequency in the current detection period T time, and RTTmin is the minimum round-trip delay value measured in the latest preset time.
When the congestion control system is stable, the method dynamically updates the detection period and the rate adjustment coefficient, and comprises the following steps:
updating the detection period T by adopting the following formula:
T=5/fm
fm is the dominant frequency, namely the frequency corresponding to the maximum amplitude value in the amplitude-frequency characteristic in the detection period;
the rate adjustment factor λ is updated using the following equation:
wherein Q is ave And Q amp Respectively, the average value of the queuing delay and the jitter amplitude within T.
The periodic congestion control method based on the time delay continuously updates the acceleration factor, namely, the acceleration factor theta is updated according to the change condition of the sending rate CR when the sending end receives an ACK packet no matter whether the congestion control system is stable: when the transmission rate continues to increase, theta is increased, otherwise theta is set to 1.
In the method for controlling periodic congestion based on delay, the step of updating the acceleration factor θ includes: recording the increase or decrease of the CR when the sending end updates the sending rate CR every time; then the sending end counts the times of increasing and decreasing CR within the current RTT time, if the increased times are larger than the decreased times, the sending rate adjustment direction is recorded as positive at the sending end, otherwise, the sending rate adjustment direction is recorded as negative; and then judging whether the adjustment directions of the window within the last three continuous RTTs are positive or not, if so, doubling theta, and otherwise, resetting theta to be 1.
The periodic congestion control method based on time delay continuously and dynamically adjusts the current sending rate and the congestion window, namely, the sending rate CR and the congestion window cwnd are adjusted by the following symmetrical formula when the sending end receives an ACK packet no matter whether the congestion control system is stable or not:
cwnd=CR′*RTT
wherein, CR' is a new sending rate calculated according to the current sending rate CR, int is a time interval from the last ACK packet reception, RTT is an instantaneous round trip delay, TR is an independent target rate that dynamically changes with the delay, λ is a rate adjustment coefficient, and θ is an acceleration factor.
In the method for controlling the periodic congestion based on the time delay, the independent target rate TR which dynamically changes along with the time delay is calculated by the following formula:
the queuing delay Qd = srtt-RTTmin, srtt is an exponential weighted smooth value of the default round-trip delay in the TCP, RTTmin is a minimum round-trip delay value measured in the latest preset time, rc is a preset gain factor, and Bd is a preset maximum queuing delay.
An apparatus, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method as previously described.
The invention has the technical effects that whether the congestion control system enters a stable state with periodic change or not is judged through fast Fourier transform according to the behavior of network delay within a period of time, and the rate regulation mode is dynamically changed by deducing the current network environment in the stable state. Namely, 1) the rate adjustment coefficient lambda can reflect the current network environment by adjusting the oscillation amplitude of queuing delay, and guides the subsequent rate adjustment 2) the queue to be emptied periodically, so that the minimum RTT value can be measured accurately. The congestion control system can work within a preset range under different environments and presents expected behavior patterns. Simulation experiment results show that the method can achieve expected performance indexes of high throughput rate and low time delay under different environments. Compared with the traditional congestion control algorithm, the method has the advantages of lower time delay, higher environmental adaptability and more stable performance.
Drawings
Fig. 1 is a general block diagram of a PDCC, which is a method for delay-based periodic congestion control according to the present invention.
Fig. 2 is a comparison of performance of PDCC versus other mainstream congestion control algorithms in scenarios with widely varying delay-bandwidth products.
Fig. 3 is a comparison of performance of a simulated cellular network scenario using PDCC versus other mainstream congestion control algorithms.
Fig. 4 is a comparison of throughput rates in a weak network scenario with random packet loss using PDCC and other mainstream congestion control algorithms.
Fig. 5 shows the throughput rate of each flow as a function of time when a new flow arrives, using the PDCC algorithm.
Detailed Description
The following describes in further detail embodiments of the present invention with reference to the accompanying drawings.
Fig. 1 is a general framework diagram of a periodic congestion control method PDCC based on delay, a network environment determining a target behavior, and a network environment, an initial state, and an output result of a congestion control algorithm collectively determining a current behavior. Wherein the congestion control algorithm pushes the current behavior towards the target behavior by comparing the target behavior with the current state. When the target behavior is reached, the current network environment can be deduced, and then the coefficients of the congestion control algorithm are configured according to the network environment to realize the expected behavior, so that better performance is obtained. The operation comprises the following steps:
step one, judging whether the current behavior of the system is consistent with the target behavior, namely whether the system is in a stable state, and deducing the network environment and adjusting the congestion control coefficient according to the judgment: and when the sending end receives an ACK packet, performing fast Fourier transform on the delay information collected in the latest detection period T, wherein whether the dominant frequency fm in the transform result is stable directly reflects whether the current state of the congestion control system is stable. If the congestion control system is in a stable state at present, updating T and a rate adjustment coefficient lambda reflecting the current network environment; if not, then T and λ are kept unchanged.
And step two, whether the congestion control system is stable or not, continuously adjusting an acceleration factor theta, accelerating the acquisition of idle bandwidth and ensuring the network utilization rate: when a sending end receives an ACK packet, according to the change condition acceleration factor theta of a sending rate CR: increasing theta when the sending rate is continuously increased, and otherwise setting theta to be 1;
step three, similar to step two, no matter whether the congestion control system is stable or not, a symmetrical speed regulation mode is continuously adopted, so that the congestion control system presents more regular periodic behaviors: when a sending end receives an ACK packet, the sending rate CR and the congestion window cwnd are adjusted by the following symmetrical formula:
cwnd=CR′*RTT
wherein, CR' is a new sending rate calculated according to the current sending rate CR, int is a time interval from the last time when the ACK packet is received, RTT is an instant round-trip delay, and TR is an independent target rate which dynamically changes along with the delay.
In this embodiment, the first step specifically includes the following steps:
step A1, when a sending end receives an ACK packet, the sending time of the ACK packet is subtracted from the receiving time of the ACK packet to obtain the instant round-trip delay RTT, and all RTT information in the latest T time is recorded.
Step A2, judging the state of the current system through historical information: performing fast Fourier transform on RTT information in the latest T time to obtain the amplitude-frequency characteristic of the RTT information; and in the amplitude-frequency characteristic, the frequency corresponding to the maximum amplitude value is recorded as the dominant frequency fm. If fm in two continuous T is close, the system is in a stable state, and the system is in a convergence state. Wherein the determination of whether fm is approaching is by | fm pre -fm | is calculated, and if the result is less than 1/(4 × rttmin), then the current fm is considered stable, otherwise it is unstable. Wherein fm pre Is the dominant frequency in the previous detection period T time. fm is the dominant frequency in the current detection period T. RTTmin is the minimum round-trip delay value measured in the latest preset time, and since the RTTmin value generally does not change unless special conditions such as connection interruption occur, the preset time can be set to be relatively large, and in this embodiment, the preset time is set to be 10 seconds.
Step A3, deducing the current network environment, and adjusting the congestion control coefficient according to the current network environment to obtain better performance: when fm stabilizes, T is updated according to the following equation: t =5/fm; . When fm stabilizes, the rate adjustment factor λ is updated according to the following equation:the queuing delay oscillation amplitude is converged to the target queuing delay, so that the converged lambda value can reflect the current network environment. Wherein Q is ave And Q amp Respectively, the average value of the queuing delay and the jitter amplitude within T.
In this embodiment, the second step specifically includes the following steps:
step B1, when the sending end updates the sending rate CR each time, the changing direction of the sending end is recorded, namely the sending end is increased or decreased. Because the RTT is the time from the sending of the same ACK packet to the return of the same ACK packet, and the sending end actually continues to receive different ACK packets in this period, and meanwhile, the sending rate is adjusted every time an ACK packet is received in this embodiment, a situation of CR change occurs many times within one RTT. Then the sending end counts the times of CR increase and decrease in the current RTT, if the increased times are larger than the decrease times, the sending rate adjusting direction is recorded as positive at the sending end, otherwise, the sending rate adjusting direction is recorded as negative.
And B2, judging whether the window adjusting directions within the last three continuous RTTs are positive or not, if so, doubling theta, and otherwise, resetting theta to 1.
In this embodiment, in step three, in order to make the target behavior determined by the current network environment and further make the coefficient λ calculated when the target behavior is reached reflect the current network environment, the TR calculates the target rate TR dynamically changing with the queuing delay by using the following formula:
the queuing delay Qd = srtt-RTTmin, where srtt is an exponentially weighted smooth value of a default round-trip delay in TCP, RTTmin is a minimum round-trip delay value measured in the last 10 seconds, rc and Bd are preset parameters, bd is a maximum queuing delay setting according to a user requirement, rc is a gain factor, and in this embodiment, in an internet scene, rc and Bd are set to 30Mbps and 10ms by default.
The invention also provides equipment according to the embodiment of the invention.
The apparatus, comprising:
one or more processors;
a storage device to store one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the aforementioned method.
In specific use, the device serving as the sending end interacts with other servers or terminals serving as the same device based on the network to realize functions such as information transmission. The device can be various electronic devices provided with a display device and used based on a human-computer interface, including but not limited to a smart phone, a tablet computer, a notebook computer, a desktop computer and the like. The device may be installed with various specific operating systems, such as a Linux system, a Windows system, or other operating systems, as needed, and may also be installed with corresponding application software, including but not limited to web browser software, instant messaging software, social platform software, shopping software, and the like.
The server is a network server for providing various services, such as a background server for providing corresponding computing services for received data transmitted from the transmitting end, and for returning a final prediction result to the terminal device.
Fig. 2 shows the performance comparison with the current mainstream algorithm in the simulation link with wide variation of network delay bandwidth product (BDP) by adopting the PDCC method. The experimental environment adopts Mahimahi to establish a simulation link, the bandwidth of the link is 12 Mbps-1 Gbps, the round-trip link propagation delay RTTbase is 20 ms-400 ms, and the number of streams in the network is 10. Each stream was started from 0 seconds for a total run of 60 seconds.
Experimental results show that the PDCC can maintain low delay on the premise of ensuring high throughput rate, has minimum performance fluctuation under different environments and has strongest adaptability to the environment.
Fig. 3 shows the performance comparison with the current mainstream algorithm in the simulated cellular network link under different scenes by using the PDCC method. In the experimental environment, 4G network trace data when a bus, a taxi and a home walk are adopted to carry out cellular network link simulation, and the number of streams in the network is 10. Each stream was started from 0 seconds for a total run of 60 seconds.
Experimental results show that the PDCC can maintain low delay on the premise of ensuring high throughput rate, and the performance is almost free from fluctuation.
Fig. 4 shows the throughput rate comparison with the current mainstream algorithm in a simulated weak network link with random packet loss using the PDCC method. In the experimental environment, a simulation link is established by adopting Mahimahi, the bandwidth of the link is 100Mbps, the propagation delay RTTbase of a round-trip link is 20ms, and the number of streams in the network with the random packet loss rate of 1% -10% is 10. Each stream was started from 0 seconds for a total run of 60s.
Experimental results show that the PDCC is insensitive to random packet loss and can maintain high throughput rate in the environment with high packet loss rate.
Fig. 5 shows the throughput rate of each flow as a function of time when a new flow arrives using the PDCC algorithm. The simulation environment employs the topology shown in fig. 2. In the experimental environment, a simulation link is established by adopting Mahimahi, the bandwidth of the link is 100Mbps, and the propagation delay RTTbase of the round-trip link is 20ms. A total of 10 streams were run, 1 of which was started every 10s, each stream lasting 100s.
Experimental results show that the PDCC has good fairness.
Claims (10)
1. A periodic congestion control method based on time delay is characterized in that amplitude-frequency characteristic monitoring is carried out on network time delay in a detection period to judge whether a congestion control system is stable; when the congestion control system is stable, dynamically updating the detection period and the rate adjustment coefficient, continuously updating the acceleration factor, and finally, continuously and dynamically adjusting the current sending rate and the congestion window by integrating the target sending rate.
2. The method according to claim 1, wherein the monitoring amplitude-frequency characteristics to determine whether the congestion control system is stable comprises the following steps:
the sending end periodically detects the amplitude-frequency characteristic of the currently collected delay information and judges the state of the congestion control system; when the amplitude-frequency characteristic remains unchanged for a period of time, the congestion control system is considered stable, otherwise it is unstable.
3. The method for controlling the periodic congestion based on the time delay of the claim 2, characterized in that, the sending end periodically detects the amplitude-frequency characteristic of the currently collected time delay information, when the sending end receives an ACK packet, the sending time of the ACK packet is subtracted according to the receiving time of the ACK packet to obtain the instantaneous round-trip time RTT, and all RTT information in the latest detection period T time is recorded; and then, performing fast Fourier transform on the RTT information in the latest T time to obtain corresponding amplitude-frequency characteristics.
4. The method according to claim 2, wherein the state of the congestion control system is determined by taking a frequency corresponding to a maximum amplitude value in the amplitude-frequency characteristics in the detection period as a dominant frequency fm; if fm in the time of two continuous detection periods T is close, the system is considered to be in a stable state, otherwise, the system is considered to be in a convergence state, namely:
wherein, fm pre Is the dominant frequency in the previous detection period T time, fm is the dominant frequency in the current detection period T time, and RTTmin is the minimum round-trip delay value measured in the latest preset time.
5. The method of claim 1, wherein when the congestion control system is stable, the detection period and the rate adjustment factor are dynamically updated, comprising the steps of:
updating the detection period T by adopting the following formula:
T=5/fm
fm is the dominant frequency, namely the frequency corresponding to the maximum amplitude value in the amplitude-frequency characteristic in the detection period;
the rate adjustment coefficient λ is updated using the following equation:
wherein Q ave And Q amp Respectively, the average value of the queuing delay and the jitter amplitude within T.
6. The method according to claim 1, wherein the continuous updating of the acceleration factor is that, no matter whether the congestion control system is stable, when the sending end receives an ACK packet, the acceleration factor θ is updated according to the change of the sending rate CR: when the transmission rate continues to increase, theta is increased, otherwise theta is set to 1.
7. The method of claim 6, wherein the step of updating the acceleration factor θ comprises: recording the increase or decrease of the CR when the sending end updates the sending rate CR every time; then the sending end counts the times of increasing and decreasing CR within the current RTT time, if the increased times are larger than the decreased times, the sending rate adjustment direction is recorded as positive at the sending end, otherwise, the sending rate adjustment direction is recorded as negative; and then judging whether the adjustment directions of the window within the last three continuous RTTs are positive or not, if so, doubling theta, and otherwise, resetting theta to be 1.
8. The method according to claim 1, wherein the current sending rate and the congestion window are continuously and dynamically adjusted, and the sending rate CR and the congestion window cwnd are adjusted by the following symmetrical formula every time the sending end receives an ACK packet, regardless of whether the congestion control system is stable or not:
cwnd=CR′*RTT
wherein, CR' is a new sending rate calculated according to the current sending rate CR, int is a time interval from the last ACK packet reception, RTT is an instantaneous round trip delay, TR is an independent target rate that dynamically changes with the delay, λ is a rate adjustment coefficient, and θ is an acceleration factor.
9. A method for delay-based periodic congestion control according to claim 8, wherein the target rate TR, which is independent and dynamically varying with delay, is calculated by:
the queuing delay Qd = srtt-RTTmin, srtt is an exponential weighted smooth value of the default round-trip delay in the TCP, RTTmin is a minimum round-trip delay value measured in the latest preset time, rc is a preset gain factor, and Bd is a preset maximum queuing delay.
10. An apparatus, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011250982.1A CN115941557A (en) | 2020-11-10 | 2020-11-10 | Self-adaptive congestion control method and device based on time delay |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011250982.1A CN115941557A (en) | 2020-11-10 | 2020-11-10 | Self-adaptive congestion control method and device based on time delay |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115941557A true CN115941557A (en) | 2023-04-07 |
Family
ID=86654541
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011250982.1A Pending CN115941557A (en) | 2020-11-10 | 2020-11-10 | Self-adaptive congestion control method and device based on time delay |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115941557A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7248564B1 (en) * | 2001-04-30 | 2007-07-24 | Network Physics, Inc. | Method for determining network congestion and link capacities |
CN105915464A (en) * | 2016-06-21 | 2016-08-31 | 中南大学 | Rapid and simple quantitative congestion notification method |
US20170353386A1 (en) * | 2016-06-01 | 2017-12-07 | Sichuan University | Kind of congestion improvement method based on the quic protocol |
CN109391521A (en) * | 2017-08-10 | 2019-02-26 | 华为技术有限公司 | A kind of Network Traffic Monitoring method and the network equipment |
CN110620737A (en) * | 2019-09-09 | 2019-12-27 | 中南大学 | Self-adaptive congestion control method based on delay |
CN111371899A (en) * | 2020-03-13 | 2020-07-03 | 山东三电新能源技术有限公司 | Data acquisition method and system suitable for large-scale distributed photovoltaic |
-
2020
- 2020-11-10 CN CN202011250982.1A patent/CN115941557A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7248564B1 (en) * | 2001-04-30 | 2007-07-24 | Network Physics, Inc. | Method for determining network congestion and link capacities |
US20170353386A1 (en) * | 2016-06-01 | 2017-12-07 | Sichuan University | Kind of congestion improvement method based on the quic protocol |
CN105915464A (en) * | 2016-06-21 | 2016-08-31 | 中南大学 | Rapid and simple quantitative congestion notification method |
CN109391521A (en) * | 2017-08-10 | 2019-02-26 | 华为技术有限公司 | A kind of Network Traffic Monitoring method and the network equipment |
CN110620737A (en) * | 2019-09-09 | 2019-12-27 | 中南大学 | Self-adaptive congestion control method based on delay |
CN111371899A (en) * | 2020-03-13 | 2020-07-03 | 山东三电新能源技术有限公司 | Data acquisition method and system suitable for large-scale distributed photovoltaic |
Non-Patent Citations (1)
Title |
---|
魏蔚;董亚波;鲁东明;金光;: "低速率TCP拒绝服务攻击的检测响应机制", 浙江大学学报(工学版), no. 05, 15 May 2008 (2008-05-15) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2387837B1 (en) | Maximizing bandwidth utilization in networks with high latencies and packet drops using transmission control protocol | |
US8125910B2 (en) | Communication system | |
US8787378B2 (en) | Systems and methods to improve performance of TCP over large bandwidth-delay-product networks | |
EP1393508B1 (en) | Data transport acceleration and management within a network communication system | |
CN106301684B (en) | Media data transmission method and device | |
US6560243B1 (en) | System and method for receiver based allocation of network bandwidth | |
CN110620737B (en) | Self-adaptive congestion control method based on delay | |
CN110572333B (en) | Method for adjusting sending rate in bandwidth detection stage and method for realizing congestion control algorithm | |
WO2017000719A1 (en) | Congestion control method and device based on queue delay | |
CN104618258B (en) | A kind of control method of message transmission rate | |
KR20020038548A (en) | Network protocol | |
CN109698925B (en) | Real-time video congestion control method and device based on data driving | |
US20150003245A1 (en) | Systems and methods for initializing packet transfers | |
CN113242183A (en) | Data stream sending control method and device, intelligent terminal and storage medium | |
CN104579582B (en) | A kind of high-quality speech transmission method based on communication network | |
CN115941557A (en) | Self-adaptive congestion control method and device based on time delay | |
CN115714746A (en) | Congestion control method and system based on delay and packet loss | |
Al-Saadi et al. | Characterising LEDBAT performance through bottlenecks using PIE, FQ-CoDel and FQ-PIE active queue management | |
CN111130923B (en) | Network bandwidth determining method and device, electronic equipment and storage medium | |
CN113542215A (en) | Method for improving streaming media transmission performance and related device | |
Lu et al. | EQF: An explicit queue-length feedback for TCP congestion control in datacenter networks | |
CN117692396B (en) | TCP unilateral acceleration method and device in complex network environment | |
Lu et al. | Ts-tcp: Two-stage congestion control algorithm for high concurrency tcps in data center networks | |
TWI308012B (en) | Method for adaptive estimation of retransmission timeout in wireless communication systems | |
Chaponniere et al. | Effect of physical layer bandwidth variation on TCP performance in CDMA2000 |
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 |