CN116886622B - Network congestion control method, device, equipment and storage medium - Google Patents
Network congestion control method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116886622B CN116886622B CN202311155722.XA CN202311155722A CN116886622B CN 116886622 B CN116886622 B CN 116886622B CN 202311155722 A CN202311155722 A CN 202311155722A CN 116886622 B CN116886622 B CN 116886622B
- Authority
- CN
- China
- Prior art keywords
- congestion
- current
- network congestion
- network
- queue length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- 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
- H04L47/25—Flow control; Congestion control with rate being modified by the source upon detecting a change of network conditions
-
- 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
- H04L47/28—Flow control; Congestion control in relation to timing considerations
- H04L47/283—Flow control; Congestion control in relation to timing considerations in response to processing delays, e.g. caused by jitter or round trip time [RTT]
-
- 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
- H04L47/36—Flow control; Congestion control by determining packet size, e.g. maximum transfer unit [MTU]
- H04L47/365—Dynamic adaptation of the packet size
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a network congestion control method, a device, equipment and a storage medium, which belong to the technical field of communication, and are applied to a sending end, wherein the sending end monitors the current round trip delay of a sent data packet and the receiving state of a congestion notification message sent by a receiving end; the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion. Therefore, based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, the network congestion degree is determined, the change of the network congestion degree can be monitored more timely, and based on the network congestion degree, the control strategy of the current sending rate is determined, so that the current sending rate can be controlled more rapidly and more accurately according to different network congestion degrees.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, and a storage medium for controlling network congestion.
Background
Currently, it is relatively common to control network congestion based on an ECN (Explicit Congestion Notification ) related algorithm. Specifically, ECN defines a flow control and end-to-end congestion notification mechanism based on the IP layer and the transport layer, i.e. during data transmission. A congestion indicator may be embedded in the IP header or a congestion acknowledgement may be embedded in the TCP header; the ECN-compatible switch and router marks the data packet when congestion is detected, the ECN mark on the data packet, the data packet with the ECN mark is transmitted to the receiving end, and the receiving end sends a CNP message (Congestion Notification Packet, congestion notification message) to the sending end. Based on the congestion notification message, the terminal device adjusts the sending rate of the message, and congestion is avoided.
However, under the condition that the network is congested, the queue buffer area of the switch accumulates data packets, so that in the process of controlling the network congestion based on the related algorithm of the ECN, a certain time is required from the process of detecting the network congestion, marking the data packets, and sending the CNP message from the receiving end to the sending end and receiving the CNP message, and the sending end cannot control the network congestion at the first time. Resulting in less time-efficient control of network congestion and thus affecting the accuracy of the control of network congestion.
Accordingly, there is a problem in the related art that accuracy of controlling network congestion is low.
Disclosure of Invention
The application mainly aims to provide a network congestion control method, a device, equipment and a storage medium, which aim to solve the technical problem of low accuracy in controlling network congestion.
In order to achieve the above object, the present application provides a network congestion control method applied to a transmitting end, the network congestion control method comprising the steps of:
monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
determining a network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and determining a control strategy of the current sending rate based on the network congestion degree;
the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion.
In one possible implementation manner of the present application, the step of determining a network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and determining the control policy of the current sending rate based on the network congestion degree includes:
Calculating to obtain the predicted moderate congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth;
calculating the difference value between the predicted moderate congestion starting time length and the predicted advanced speed-down time length, and judging whether the current round trip delay is smaller than the difference value;
if not, and the congestion notification message is not received, determining that the current network congestion degree is light congestion;
and taking the current sending rate as a target sending rate, and reducing the target sending rate based on a preset fixed rate.
In a possible implementation manner of the present application, the step of calculating, based on the minimum congestion queue length and a preset bandwidth, a predicted moderate congestion start duration and a predicted advanced speed-down duration of the switch includes:
calculating to obtain the predicted moderate congestion starting time length of the switch based on the minimum congestion queue length, the preset reference round trip delay and the preset bandwidth;
and calculating the predicted advanced speed-reducing time length based on the minimum congestion queue length, a preset bandwidth and the number of the sending ends which simultaneously send the data packets to the receiving end.
In one possible embodiment of the present application, the predicted moderate congestion start duration calculation formula is:
wherein the saidFor said predicted moderate congestion start duration, said +.>For said minimum congestion queue length, said +.>For the preset reference round trip delay, theBWAnd the bandwidth is preset.
In a possible embodiment of the present application, after the step of determining whether the current round trip delay is less than the difference value, the method further includes:
if the current round trip delay is smaller than the difference value, determining that no network congestion exists currently;
the current sending rate is raised to the average value of the target sending rate and the current sending rate;
and on the basis of the current sending rate which is lifted to the average value, continuously lifting the current sending rate based on the preset fixed rate until the current round trip delay is greater than or equal to the difference value.
In one possible implementation manner of the present application, the step of determining a network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and determining the control policy of the current sending rate based on the network congestion degree includes:
Calculating the predicted severe congestion starting time length of the data packet based on the maximum congestion queue length, the preset reference round trip delay and the preset bandwidth;
judging whether the current round trip delay is smaller than the predicted severe congestion starting time length or not;
if the congestion degree is smaller than the preset congestion degree, starting to receive the congestion notification message, and determining the current network congestion degree as medium congestion;
and calculating a rate reduction ratio based on a preset rate adjustment factor and a preset adjustment coefficient, and reducing the current sending rate based on the rate reduction ratio, wherein the preset rate adjustment factor and the preset adjustment coefficient are determined based on the number of the currently received congestion notification messages.
In a possible embodiment of the present application, after the step of determining whether the current round trip delay is less than the predicted heavy congestion start duration, the method further includes:
and if the current round trip delay is not less than the predicted severe congestion starting time, determining that the current network congestion degree is severe congestion, and reducing the current sending rate by one half.
The application also provides a network congestion control device applied to the transmitting end, comprising:
The monitoring module is used for monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
the network congestion control module is used for determining the network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and the maximum congestion queue length in the switch, and determining the control strategy of the current sending rate based on the network congestion degree, wherein the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is slightly congested, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is severely congested.
The application also provides a network congestion control device, which comprises: a memory, a processor, and a network congestion control program stored on the memory and executable on the processor, the network congestion control program configured to implement the steps of the network congestion control method as set forth in any one of the preceding claims.
The present application also provides a storage medium having stored thereon a network congestion control program which, when executed by a processor, implements the steps of the network congestion control method as described in any of the preceding claims.
Compared with the prior art that in the process of controlling network congestion based on the ECN related algorithm, the network congestion control method provided by the application has the advantages that a certain time is required from the process of detecting network congestion, marking a data packet, and sending a CNP message by a receiving end to the process of receiving the CNP message by a sending end, and the sending end cannot control the network congestion in the first time.
The application is applied to a transmitting end, and the transmitting end monitors the current round trip delay of a sent data packet and the receiving state of a congestion notification message sent by a receiving end; specifically, in the process of controlling network congestion based on the related algorithm of the ECN, a certain time is required from the process of detecting network congestion, marking a data packet, and sending a CNP message from a receiving end to a sending end, and the RTT signal can directly respond to the time delay from the sending end to the receiving end caused by network queuing, so that compared with the related algorithm of the ECN, the congestion condition can be detected more sensitively and more in advance; and, the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion. Therefore, based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, the network congestion degree is determined, the change of the network congestion degree can be monitored more timely, and based on the network congestion degree, the control strategy of the current sending rate is determined, so that the current sending rate can be controlled more rapidly and more accurately according to different network congestion degrees.
Therefore, the application can improve the control accuracy of network congestion.
Drawings
Fig. 1 is a flowchart of a first embodiment of a network congestion control method according to the present application;
fig. 2 is a schematic structural diagram of a network congestion control device of a hardware running environment according to an embodiment of the present application;
fig. 3 is a schematic diagram of a network congestion control apparatus according to a first embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. Although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope herein.
An embodiment of the present application provides a network congestion control method, referring to fig. 1, in this embodiment, the network congestion control method includes:
Step S10: monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
step S20: and determining the network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and the preset maximum congestion queue length in the switch, and determining the control strategy of the current sending rate based on the network congestion degree, wherein the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is slightly congested, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is severely congested.
As an example, the network congestion control method is applied to a network congestion control apparatus which is subordinate to a network congestion control device, specifically, a transmission end, or a control device capable of controlling the transmission end, or the like, without limitation.
As an example, network congestion (network congestion) refers to a situation where when the number of data packets transmitted by a sender through a switch is too large, network transmission performance is degraded due to limited resources of the switch.
As an example, the network congestion level may be classified into light congestion, medium congestion, and heavy congestion, etc., based on the current network transmission performance, without limitation.
Currently, it is relatively common to control network congestion based on an ECN (Explicit Congestion Notification ) related algorithm. Specifically, ECN defines a flow control and end-to-end congestion notification mechanism based on the IP layer and the transport layer, i.e. during data transmission. A congestion indicator may be embedded in the IP header or a congestion acknowledgement may be embedded in the TCP header; the ECN-compliant switch and router will mark the packet when congestion is detected, and the packet with ECN mark is transmitted to the receiving end, and the receiving end sends CNP message (Congestion Notification Packet, congestion notification message) to the sending end. Based on the congestion notification message, the terminal device adjusts the sending rate of the message, and congestion is avoided.
However, under the condition that the network is congested, the queue buffer area of the switch accumulates data packets, so that in the process of controlling the network congestion based on the related algorithm of the ECN, a certain time is required from the process of detecting the network congestion, marking the data packets, and sending the CNP message from the receiving end to the sending end and receiving the CNP message, and the sending end cannot control the network congestion at the first time. Resulting in less time-efficient control of network congestion and thus affecting the accuracy of the control of network congestion.
The present embodiment aims at: because the current network Time delay (RTT) can directly respond to the end-to-end Time delay caused by network queuing, compared with the ECN related algorithm, the network congestion condition can be detected more quickly and timely. In order to more accurately and timely respond to network congestion, the network congestion degree is judged together based on the two modes, so that the network congestion is controlled more accurately and timely.
The method comprises the following specific steps:
step S10: monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
as an example, the sender monitors the current round trip delay of the sent data packet, specifically, the current round trip delay of the data packet is calculated by the sender from the time stamp of the start of sending the data packet to the time stamp of the acknowledgement received by the sender from the receiver (the acknowledgement is sent immediately after the receiver receives the data), and the total delay experienced by the obtained sending packet is calculated.
As an example, at present, a method for controlling network congestion based on the related algorithm of the ECN alone is: and prompting the receiving end to generate network congestion through ECN marks of the data packet head. The data packet carrying the ECN mark is transmitted to a receiving end, the receiving end creates a congestion notification message, and the congestion notification message is sent to a sending end corresponding to the data packet marked by the ECN. Therefore, the congestion notification message is sent to the sender by the receiver, and the receiving state of the congestion notification message refers to a state, such as whether the sender currently receives the congestion notification message, and/or whether the sender does not receive the congestion notification message, and/or whether the sender starts to receive the congestion notification message, and the like, which is not limited herein.
Step S20: and determining the network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and determining the control strategy of the current sending rate based on the network congestion degree.
In this embodiment, the minimum congestion queue length is used to represent a maximum queue length when the network congestion level is light congestion, and the maximum congestion queue length is used to represent a minimum queue length when the network congestion level is heavy congestion.
As an example, when the switch generally performs ECN marking according to a certain marking probability during network congestion, first, the sender cannot determine the manner in which the switch determines the network congestion, and cannot immediately and hundred percent receive the congestion notification message when the network congestion occurs.
Therefore, the application sets the minimum congestion queue length in the exchanger based on the historical experience dataAnd maximum congestion queue length +> ax。
As an example, if the current queue length of the switch is smaller than the minimum congestion queue length, the current network congestion degree is considered to be slightly congested, if the current queue length is greater than or equal to the maximum congestion queue length, the current network congestion degree is considered to be severely congested, and if the current queue length is greater than the minimum congestion queue length and smaller than the maximum congestion queue length, the current network congestion degree is considered to be moderately congested, so the network congestion degree can be determined based on the current queue length and the minimum congestion queue length and the maximum congestion queue length preset in the switch.
However, the sender cannot monitor the current queue length in the switch, and therefore, the current queue length in the switch can be indirectly reflected based on the current round trip delay and the receiving state of the congestion notification message.
Therefore, the network congestion degree is determined based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and the preset maximum congestion queue length in the switch, and the current network congestion degree can be accurately and timely judged.
As an example, a control policy for the current transmission rate is determined based on the above-obtained network congestion level. Specifically, the control policy of the current transmission rate may be to decrease the current transmission rate or increase the current transmission rate.
As an example, the current transmission rate may be decreased when the network congestion level is severe congestion, or the current transmission rate may be increased when the network congestion level is mild congestion, or the like, which is not limited herein.
Specifically, the current sending rate is the sending rate of the data packet sent by the sending end at present, and if the current sending rate is not adjusted, the current sending rate is the same as the sending rate of the data packet sent last time.
In this embodiment, the sending end monitors the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end; specifically, in the process of controlling network congestion based on the related algorithm of the ECN, a certain time is required from the process of detecting network congestion, marking a data packet, and sending a CNP message from a receiving end to a sending end, and the RTT signal can directly respond to the time delay from the sending end to the receiving end caused by network queuing, so that compared with the related algorithm of the ECN, the congestion condition can be detected more sensitively and more in advance; and, the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion. Therefore, based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, the network congestion degree is determined, the change of the network congestion degree can be monitored more timely, and based on the network congestion degree, the control strategy of the current sending rate is determined, so that the current sending rate can be controlled more rapidly and more accurately according to different network congestion degrees. The accuracy of control over network congestion can be improved.
Further, according to the above embodiment of the present application, there is provided another embodiment of the present application, in which the step of determining a network congestion level based on the current round trip delay, the receiving state of the congestion notification message, a minimum congestion queue length and a maximum congestion queue length preset in the switch, and determining a control policy of a current sending rate based on the network congestion level includes:
step A1: calculating to obtain the predicted moderate congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth;
as an example, network congestion needs to be controlled in advance because when the network congestion level is monitored, a control policy for the current sending rate is determined based on the network congestion level, or the current queue length in the switch cannot be completely avoided from increasing.
Specifically, the method for controlling network congestion in advance is to calculate the predicted medium congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth. Based on the current round trip delay, whether the current sending rate needs to be reduced in advance at the current moment is determined, so that the switch is prevented from being changed from light congestion to medium congestion at the next moment when the current sending rate is kept all the time.
In this embodiment, the step of calculating, based on the minimum congestion queue length and the preset bandwidth, a predicted moderate congestion start duration and a predicted advanced speed-down duration of the switch includes:
step B1: calculating to obtain the predicted moderate congestion starting time length of the switch based on the minimum congestion queue length, the preset reference round trip delay and the preset bandwidth;
as an example, the Bandwidth (BW) is the theoretical available bandwidth of the sender-to-receiver link.
As an example, based on historical experience data, the round trip delay of the first data packet sent by the first sender to the receiver through the switch is taken as the reference round trip delayTherefore, the preset reference round trip delay refers to the normal round trip delay of the data packet in the absence of network congestion.
In this embodiment, the calculation formula of the predicted moderate congestion start time length is:
wherein the saidFor said predicted moderate congestion start duration, said +.>For said minimum congestion queue length, said +.>For the preset reference round trip delay, theBWAnd the bandwidth is preset.
As an example, theAnd the method comprises the step of predicting the longest buffer time of the data packet in a buffer queue of a switch, and adding the longest buffer time to the normal round trip delay of the data packet under the condition that network congestion does not exist, so as to obtain the predicted moderate congestion starting time.
The preset reference round-trip delay is smaller than the current round-trip delay, and the current round-trip delay is smaller than the predicted moderate congestion starting time.
Step B2: and calculating the predicted advanced speed-reducing time length based on the minimum congestion queue length, a preset bandwidth and the number of the sending ends which simultaneously send the data packets to the receiving end.
In this embodiment, the predicted advanced speed-down duration is a time predicted before the predicted medium congestion start duration is reached, at which time the current sending rate needs to be slowed down in advance to prevent the current network congestion level from changing from light congestion to medium congestion when the predicted medium congestion start duration is reached.
As an example, the number of transmitting ends that simultaneously transmit data packets to the receiving endMay be 1, 2 or n and in a randomly varying state.
As an example, the predicted advance speed-down period is affected by the number of transmitting ends that simultaneously transmit data packets to the receiving end. Specifically, since the minimum congestion queue length and the preset bandwidth are both fixed, if the number of the transmitting ends that simultaneously transmit the data packet to the receiving end is increased, the current transmission rate needs to be reduced earlier, and if the number of the transmitting ends that simultaneously transmit the data packet to the receiving end is reduced, the current transmission rate needs to be reduced later, and so on.
Thus, the predicted advance downshift periodThe calculation formula of (2) is as follows:
wherein the saidFor said predictive advance speed-down period said +.>For the number of transmitting ends simultaneously transmitting data packets to said receiving end, said +.>For allowable time fluctuations determined based on historical empirical data.
Step A2: calculating the difference value between the predicted moderate congestion starting time length and the predicted advanced speed-down time length, and judging whether the current round trip delay is smaller than the difference value;
as an example, since the predicted medium congestion start time period and the predicted advanced speed-down time period have been calculated, it may be determined whether the current transmission rate needs to be reduced at the current time based on the difference between the predicted medium congestion start time period and the predicted advanced speed-down time period.
Specifically, it may be determined whether the current round trip delay is smaller than the difference, and if so, it is determined that the current transmission rate does not need to be reduced at the current time. That is, the network congestion level will not change from light congestion to medium congestion or heavy congestion at the next time without decreasing the current sending rate at the current time.
Step A3: if not, and the congestion notification message is not received, determining that the current network congestion degree is light congestion;
as an example, the current round trip delay is not less than (greater than or equal to) the difference, which can be expressed as:
as an example, if the current round trip delay is not less than (equal to or greater than) the difference, the current network congestion level may still be lightly congested or may already be moderately/severely congested. Therefore, it is also necessary to determine whether the congestion notification message is currently received, if the congestion notification message is not received, determine that the current network congestion level is still in light congestion, and if the congestion notification message is received (because the switch will send the congestion notification message after detecting network congestion), determine that the current network congestion level may be already in medium/serious congestion.
Therefore, if the current round trip delay is not less than (greater than or equal to) the difference value and the congestion notification message is not received, determining that the current network congestion degree is light congestion, that is, determining that the current sending rate needs to be reduced at the current moment. That is, the network congestion level may change from light congestion to medium congestion at the next time without decreasing the current transmission rate at the current time.
Step A4: and taking the current sending rate as a target sending rate, and reducing the target sending rate based on a preset fixed rate.
As an example, the current transmission rate is taken as the target transmission rate, because the current time is the time when the predicted network congestion level is about to be changed from light congestion to medium congestion, and the transmission rate at this time can be taken as a reference when network congestion control is performed subsequently.
As an example, the preset fixed rate is determined based on experimental data.
As an example, the target sending rate is reduced based on a preset fixed rate, and the target sending rate can be gradually reduced without affecting the throughput of the current network.
In this embodiment, after the step of determining whether the current round trip delay is less than the difference value, the method further includes:
Step A5: if the current round trip delay is smaller than the difference value, determining that no network congestion exists currently;
as an example, in the above process of reducing the target transmission rate based on the preset fixed rate, it is also required to monitor the change of the current round trip delay at all times. If the current round trip delay is smaller than the difference value, it is determined that there is no network congestion currently, that is, the current sending rate does not need to be reduced at the current moment, but in order to further ensure that the throughput of the current network is not affected in the process of reducing the target sending rate based on the preset fixed rate, it is required to avoid that the throughput of the network is reduced due to too much reduction of the current sending rate.
Step A6: the current sending rate is raised to the average value of the target sending rate and the current sending rate;
and if the current round trip delay is monitored to be smaller than the difference value, the current sending rate is increased to the average value of the target sending rate and the current sending rate, namely, the average value of the target sending rate and the current sending rate is calculated, and the current sending rate is increased to the average value. It is understood that the average value is smaller than the target transmission rate.
Since the target sending rate is the rate at which the first predicted network congestion level is about to change from light congestion to medium congestion, it can be referred to as the sending rate at which medium congestion starts, and thus, raising the current sending rate to the average value of the target sending rate and the current sending rate can quickly raise the current sending rate (quickly raise the throughput of the network) but does not exceed the target sending rate, that is, does not cause the network congestion level to change to medium congestion due to this quick raising.
Step A7: and on the basis of the current sending rate which is lifted to the average value, continuously lifting the current sending rate based on the preset fixed rate until the current round trip delay is greater than or equal to the difference value.
As an example, based on the preset fixed rate, the current transmission rate is continuously increased based on the current transmission rate increased to the average value, so that the throughput of the network can be gradually increased.
As an example, based on the preset fixed rate, continuing to increase the current transmission rate until the current round-trip delay is greater than or equal to the difference value, because, based on the preset fixed rate, continuing to increase the current transmission rate can gradually increase the throughput of the network, but cannot cause the network congestion degree to become moderate congestion in the process, therefore, in the process of continuing to increase the current transmission rate based on the preset fixed rate, determining whether the current round-trip delay is smaller than the difference value, if not, considering that the current transmission rate cannot be continuously increased, at this time, the increased transmission rate can be maintained, continuing to perform the calculation of the difference value between the predicted moderate congestion start time length and the predicted advanced slow down time length, and determining whether the current round-trip delay is smaller than the difference value, if not smaller than the difference value, and if the congestion notification message is not received, determining that the current network congestion degree is mild congestion, taking the current transmission rate as the target transmission rate, and reducing the target transmission rate based on the preset fixed rate.
In this embodiment, by monitoring the current round trip delay of the sent data packet, the switch buffer queue gradually decelerates based on the preset fixed rate when the switch buffer queue has not reached the preset minimum congestion queue length, and compared with the related algorithm of the traditional ECN, the response to the network congestion state is faster, and the delay increase caused by the subsequent switch buffer queue surge can be effectively prevented. And when the length of the switch buffer queue is reduced below the preset minimum congestion queue length again, and the current round trip delay is smaller than the difference value, the current sending rate is improved, so that the reduction of bandwidth utilization rate caused by too much speed reduction is avoided, the reduction of network throughput is avoided, and network congestion is also avoided.
Further, according to the above embodiment of the present application, there is provided another embodiment of the present application, in which the step of determining a network congestion level based on the current round trip delay, the receiving state of the congestion notification message, a minimum congestion queue length and a maximum congestion queue length preset in the switch, and determining a control policy of a current sending rate based on the network congestion level includes:
Step C1: calculating the predicted severe congestion starting time length of the data packet based on the maximum congestion queue length, the preset reference round trip delay and the preset bandwidth;
in this embodiment, the calculation formula of the predicted severe congestion start time is:
wherein the saidFor said predicted severe congestion start duration, said +.>For said maximum congestion queue length, said +.>For the preset reference round trip delay, theBWAnd the bandwidth is preset.
Step C2: judging whether the current round trip delay is smaller than the predicted severe congestion starting time length or not;
step C3: if the congestion degree is smaller than the preset congestion degree, starting to receive the congestion notification message, and determining the current network congestion degree as medium congestion;
as an example, for the same reasons as in the above embodiments, in order to determine the current network congestion level, it is necessary to determine whether the current round trip delay is smaller than the predicted severe congestion start duration.
As an example, if the current round trip delay is greater than or equal to the predicted heavy congestion start duration, then the current network congestion level may be determined to be heavy congestion; and if the current round trip delay is smaller than the predicted severe congestion start time, the current network congestion degree may be slightly congested or moderately congested. Therefore, it needs to determine whether the sender starts to receive the congestion notification message, and if the sender starts to receive the congestion notification message, it indicates that the switch has monitored network congestion, and therefore, the current network congestion level is unlikely to be slightly congested, but is moderately congested.
Step C4: and calculating a rate reduction ratio based on a preset rate adjustment factor and a preset adjustment coefficient, and reducing the current sending rate based on the rate reduction ratio, wherein the preset rate adjustment factor and the preset adjustment coefficient are determined based on the number of the currently received congestion notification messages.
In this embodiment, the preset rate adjustment factor and the preset adjustment coefficient are both determined based on the number of the currently received congestion notification messages. Specifically, the greater the number of currently received congestion notification messages, the higher the preset rate adjustment factor, and the lower the preset adjustment factor.
As an example, the rate reduction ratio is calculated based on a preset rate adjustment factor and a preset adjustment coefficientThe calculation formula of (2) is as follows:
wherein the saidThe preset adjustment coefficient is the preset adjustment coefficient;
wherein the saidThe calculation formula of (2) is as follows:
wherein the saidAnd adjusting a factor for the preset rate.
As an example, when the current network congestion level is detected to be in moderate congestion, the current sending rate is controlled in the above manner, so that the reduced proportion can be continuously adjusted according to the change of the network state, and the network congestion condition can be improved more quickly based on the current network state. And calculating a rate reduction ratio based on a preset rate adjustment factor and a preset adjustment coefficient, determining a network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and the preset maximum congestion queue length in the switch, and executing the corresponding control strategy based on the network congestion degree while reducing the current sending rate based on the rate reduction ratio.
In this embodiment, after the step of determining whether the current round trip delay is less than the predicted heavy congestion start duration, the method further includes:
step C5: and if the current round trip delay is not less than the predicted severe congestion starting time, determining that the current network congestion degree is severe congestion, and reducing the current sending rate by one half.
As an example, if the current round trip delay is not less than (greater than or equal to) the predicted severe congestion start duration, determining that the current network congestion degree is severe congestion, at this time, directly reducing the current sending rate to half, continuing to monitor the current round trip delay after reducing to half, and if the current round trip delay is still greater than or equal to the predicted severe congestion start duration, continuing to reduce the current sending rate after reducing to half. If the current round-trip delay is smaller than the predicted serious congestion starting time length, determining the network congestion degree continuously based on the current round-trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and executing the corresponding control strategy based on the network congestion degree.
In this embodiment, based on the current round trip delay of the data packet sent by the monitoring, the receiving state of the congestion notification packet sent by the receiving end and the judging conditions of different network congestion degrees, a corresponding control policy of the current sending rate is executed, so that network congestion can be relieved, network delay can be reduced, and throughput of the network can be ensured.
Referring to fig. 2, fig. 2 is a schematic device structure diagram of a hardware running environment according to an embodiment of the present application.
As shown in fig. 2, the network congestion control apparatus may include: a processor 1001, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to enable connected communication between the processor 1001 and the memory 1005.
Optionally, the network congestion control device may further include a user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, a WiFi module, and so on. The user interface may include a Display, an input sub-module such as a Keyboard (Keyboard), and the optional user interface may also include a standard wired interface, a wireless interface. The network interface may include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the network congestion control device structure shown in fig. 2 does not constitute a limitation of the network congestion control device, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 2, an operating system, a network communication module, and a network congestion control program may be included in the memory 1005 as one type of storage medium. The operating system is a program that manages and controls network congestion control device hardware and software resources, supporting the operation of network congestion control programs and other software and/or programs. The network communication module is used to enable communication between components within the memory 1005 and with other hardware and software in the network congestion control system.
In the network congestion control apparatus shown in fig. 2, a processor 1001 is configured to execute a network congestion control program stored in a memory 1005, and implement the steps of the network congestion control method described in any of the above.
The specific implementation manner of the network congestion control device of the present application is basically the same as that of each embodiment of the network congestion control method, and will not be described herein again.
The application also provides a network congestion control device, which is applied to a sending end, as shown in fig. 3, and comprises:
The monitoring module 10 is configured to monitor a current round trip delay of an sent data packet and a receiving state of a congestion notification packet sent by a receiving end;
the network congestion control module 20 is configured to determine a network congestion level based on the current round trip delay, the receiving state of the congestion notification packet, a minimum congestion queue length preset in the switch, and a maximum congestion queue length, and determine a control policy of a current sending rate based on the network congestion level, where the minimum congestion queue length is used to characterize a maximum queue length when the network congestion level is slightly congested, and the maximum congestion queue length is used to characterize a minimum queue length when the network congestion level is severely congested.
Optionally, in one possible embodiment of the present application, the network congestion control module 20 includes:
the first calculation sub-module is used for calculating and obtaining the predicted moderate congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth;
the second calculation sub-module is used for calculating the difference value between the predicted moderate congestion starting time length and the predicted advanced speed-down time length and judging whether the current round trip delay is smaller than the difference value;
The first determining submodule is used for determining that the current network congestion degree is slightly congested if the congestion notification message is not smaller than the first determining submodule and the congestion notification message is not received;
and the first rate reduction sub-module is used for taking the current sending rate as a target sending rate and reducing the target sending rate based on a preset fixed rate.
Optionally, in a possible embodiment of the present application, the first computing submodule includes:
a first calculating unit, configured to calculate, based on the minimum congestion queue length, a preset reference round trip delay and a preset bandwidth, a predicted moderate congestion start duration of the switch;
the second calculating unit is used for calculating the predicted advanced speed-down time length based on the minimum congestion queue length, the preset bandwidth and the number of the sending ends which send the data packets to the receiving end at the same time.
Optionally, in one possible embodiment of the present application, the predicted moderate congestion start duration calculation formula is:
wherein the saidFor said predicted moderate congestion start duration, said +.>For said minimum congestion queue length, said +.>For the preset reference round trip delay, theBWAnd the bandwidth is preset.
Optionally, in a possible implementation manner of the present application, after the step of determining whether the current round trip delay is smaller than the difference value, the apparatus further includes:
a determining module, configured to determine that there is no network congestion currently if the current round trip delay is less than the difference value;
the first rate lifting module is used for lifting the current sending rate to the average value of the target sending rate and the current sending rate;
and the second rate lifting module is used for continuously lifting the current sending rate based on the preset fixed rate on the basis of the current sending rate lifted to the average value until the current round trip delay is greater than or equal to the difference value.
Optionally, in one possible embodiment of the present application, the network congestion control module 20 includes:
a third calculation sub-module, configured to calculate, based on the maximum congestion queue length, a preset reference round trip delay, and a preset bandwidth, a predicted severe congestion start duration of the data packet;
a judging sub-module, configured to judge whether the current round trip delay is less than the predicted severe congestion start duration;
a third determining submodule, configured to determine that the current network congestion degree is moderate congestion if the third determining submodule is smaller than the third determining submodule and starts to receive the congestion notification message;
And the second rate reduction sub-module is used for calculating a rate reduction proportion based on a preset rate adjustment factor and a preset adjustment coefficient, and reducing the current sending rate based on the rate reduction proportion, wherein the preset rate adjustment factor and the preset adjustment coefficient are determined based on the number of the currently received congestion notification messages.
Optionally, in a possible implementation manner of the present application, after the step of determining whether the current round trip delay is less than the predicted severe congestion start duration, the apparatus further includes:
and the rate reduction module is used for determining that the current network congestion degree is serious congestion if the current round trip delay is not less than the predicted serious congestion starting time length, and reducing the current sending rate by one half.
The specific implementation manner of the network congestion control device of the present application is basically the same as the embodiments of the network congestion control method described above, and will not be described herein again.
The present application also provides a storage medium having stored thereon a network congestion control program which, when executed by a processor, implements the steps of the network congestion control method as described in any of the preceding claims.
The specific implementation manner of the storage medium of the present application is basically the same as that of each embodiment of the network congestion control method, and will not be repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The network congestion control method is characterized by being applied to a transmitting end, and comprises the following steps of:
monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
determining a network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch, and determining a control strategy of the current sending rate based on the network congestion degree;
the step of determining the network congestion degree based on the current round trip delay, the receiving state of the congestion notification message, the preset minimum congestion queue length and maximum congestion queue length in the switch includes:
calculating to obtain the predicted moderate congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth;
Calculating the difference value between the predicted moderate congestion starting time length and the predicted advanced speed-down time length, and judging whether the current round trip delay is smaller than the difference value;
if not, and the congestion notification message is not received, determining that the current network congestion degree is light congestion;
if the current round trip delay is smaller than the difference value, determining that no network congestion exists currently;
calculating the predicted severe congestion starting time length of the data packet based on the maximum congestion queue length, the preset reference round trip delay and the preset bandwidth;
judging whether the current round trip delay is smaller than the predicted severe congestion starting time length or not;
if the congestion degree is smaller than the preset congestion degree, starting to receive the congestion notification message, and determining the current network congestion degree as medium congestion;
if the current round trip delay is not less than the predicted severe congestion starting time, determining the current network congestion degree as severe congestion;
the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion.
2. The network congestion control method according to claim 1, wherein the step of determining a control policy for a current transmission rate based on the network congestion level comprises:
And if the current network congestion degree is light congestion, taking the current sending rate as a target sending rate, and reducing the target sending rate based on a preset fixed rate.
3. The network congestion control method according to claim 2, wherein the step of calculating a predicted moderate congestion start duration and a predicted advanced speed reduction duration of the switch based on the minimum congestion queue length and a preset bandwidth comprises:
calculating to obtain the predicted moderate congestion starting time length of the switch based on the minimum congestion queue length, the preset reference round trip delay and the preset bandwidth;
and calculating the predicted advanced speed-reducing time length based on the minimum congestion queue length, a preset bandwidth and the number of the sending ends which simultaneously send the data packets to the receiving end.
4. A network congestion control method according to claim 3, wherein the predicted moderate congestion start time length calculation formula is:
wherein the saidFor said predicted moderate congestion start duration, said +.>For said minimum congestion queue length, said +.>For the preset reference round trip delay, theBWAnd the bandwidth is preset.
5. The network congestion control method according to claim 2, wherein the step of determining the control policy of the current transmission rate based on the network congestion degree comprises:
If no network congestion exists currently, the current sending rate is raised to the average value of the target sending rate and the current sending rate;
and on the basis of the current sending rate which is lifted to the average value, continuously lifting the current sending rate based on the preset fixed rate until the current round trip delay is greater than or equal to the difference value.
6. The network congestion control method according to claim 1, wherein the step of determining a control policy for a current transmission rate based on the network congestion level comprises:
if the current network congestion degree is moderate congestion, calculating a rate reduction ratio based on a preset rate adjustment factor and a preset adjustment coefficient, and reducing the current sending rate based on the rate reduction ratio, wherein the preset rate adjustment factor and the preset adjustment coefficient are determined based on the number of the currently received congestion notification messages.
7. The network congestion control method of claim 6, wherein said step of determining a control policy for the current sending rate based on said network congestion level, the method further comprising:
if the current network congestion level is severe congestion, the current sending rate is reduced by one half.
8. A network congestion control apparatus, applied to a transmitting end, comprising:
the monitoring module is used for monitoring the current round trip delay of the sent data packet and the receiving state of the congestion notification message sent by the receiving end;
a network congestion control module, configured to determine a network congestion degree based on the current round trip delay, a receiving state of the congestion notification packet, a minimum congestion queue length and a maximum congestion queue length preset in the switch, and determine a control policy of a current sending rate based on the network congestion degree;
the network congestion control module includes:
the first calculation sub-module is used for calculating and obtaining the predicted moderate congestion starting time length and the predicted advanced speed-down time length of the switch based on the minimum congestion queue length and the preset bandwidth;
the second calculation sub-module is used for calculating the difference value between the predicted moderate congestion starting time length and the predicted advanced speed-down time length and judging whether the current round trip delay is smaller than the difference value;
the first determining submodule is used for determining that the current network congestion degree is slightly congested if the congestion notification message is not smaller than the first determining submodule and the congestion notification message is not received;
A determining module, configured to determine that there is no network congestion currently if the current round trip delay is less than the difference value;
a third calculation sub-module, configured to calculate, based on the maximum congestion queue length, a preset reference round trip delay, and a preset bandwidth, a predicted severe congestion start duration of the data packet;
a judging sub-module, configured to judge whether the current round trip delay is less than the predicted severe congestion start duration;
a third determining submodule, configured to determine that the current network congestion degree is moderate congestion if the third determining submodule is smaller than the third determining submodule and starts to receive the congestion notification message;
the rate reduction module is used for determining that the current network congestion degree is serious congestion if the current round trip delay is not less than the predicted serious congestion starting time length;
the minimum congestion queue length is used for representing the maximum queue length when the network congestion degree is light congestion, and the maximum congestion queue length is used for representing the minimum queue length when the network congestion degree is heavy congestion.
9. A network congestion control apparatus, the apparatus comprising: a memory, a processor and a network congestion control program stored on the memory and executable on the processor, the network congestion control program being configured to implement the steps of the network congestion control method of any of claims 1 to 7.
10. A storage medium having stored thereon a network congestion control program which, when executed by a processor, implements the steps of the network congestion control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311155722.XA CN116886622B (en) | 2023-09-08 | 2023-09-08 | Network congestion control method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311155722.XA CN116886622B (en) | 2023-09-08 | 2023-09-08 | Network congestion control method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116886622A CN116886622A (en) | 2023-10-13 |
| CN116886622B true CN116886622B (en) | 2023-11-24 |
Family
ID=88268478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311155722.XA Active CN116886622B (en) | 2023-09-08 | 2023-09-08 | Network congestion control method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116886622B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118869600A (en) * | 2024-05-29 | 2024-10-29 | 腾讯科技（深圳）有限公司 | Congestion control method, device, electronic device and medium |
| CN118555251B (en) * | 2024-07-26 | 2024-12-27 | 中国电信股份有限公司 | Congestion control method, device, equipment, medium and product |
| CN119402435A (en) * | 2024-12-30 | 2025-02-07 | 腾讯科技（深圳）有限公司 | Data congestion processing method, device, equipment, storage medium and program product |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7369498B1 (en) * | 1999-12-13 | 2008-05-06 | Nokia Corporation | Congestion control method for a packet-switched network |
| CN109347702A (en) * | 2018-11-13 | 2019-02-15 | 天津津航计算技术研究所 | Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC |
| WO2020143180A1 (en) * | 2019-01-11 | 2020-07-16 | 深圳市网心科技有限公司 | Network congestion detection-based intelligent speed limiting method and apparatus, and storage medium |
| CN111526096A (en) * | 2020-03-13 | 2020-08-11 | 北京交通大学 | Intelligent identification network state prediction and congestion control system |
| US10986027B1 (en) * | 2018-03-27 | 2021-04-20 | Akamai Technologies, Inc. | Efficient congestion control in a tunneled network |
| CN113411264A (en) * | 2021-06-30 | 2021-09-17 | 中国工商银行股份有限公司 | Network queue monitoring method and device, computer equipment and storage medium |
| CN113507420A (en) * | 2021-08-05 | 2021-10-15 | 清华大学 | Congestion control method and device |
| CN115460156A (en) * | 2022-09-21 | 2022-12-09 | 长沙理工大学 | A data center lossless network congestion control method, device, equipment and medium |
| CN116170380A (en) * | 2023-04-21 | 2023-05-26 | 中国科学技术大学 | ECN marking strategy and queue management method and system based on congestion prediction |
| CN116545933A (en) * | 2023-07-06 | 2023-08-04 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Network congestion control method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210036942A1 (en) * | 2019-08-02 | 2021-02-04 | Dell Products, Lp | Systems and methods for identifying persistently congested queues |
| CN112511325B (en) * | 2019-09-16 | 2022-03-11 | 华为技术有限公司 | Network congestion control method, node, system and storage medium |
-
2023
- 2023-09-08 CN CN202311155722.XA patent/CN116886622B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7369498B1 (en) * | 1999-12-13 | 2008-05-06 | Nokia Corporation | Congestion control method for a packet-switched network |
| US10986027B1 (en) * | 2018-03-27 | 2021-04-20 | Akamai Technologies, Inc. | Efficient congestion control in a tunneled network |
| CN109347702A (en) * | 2018-11-13 | 2019-02-15 | 天津津航计算技术研究所 | Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC |
| WO2020143180A1 (en) * | 2019-01-11 | 2020-07-16 | 深圳市网心科技有限公司 | Network congestion detection-based intelligent speed limiting method and apparatus, and storage medium |
| CN111526096A (en) * | 2020-03-13 | 2020-08-11 | 北京交通大学 | Intelligent identification network state prediction and congestion control system |
| CN113411264A (en) * | 2021-06-30 | 2021-09-17 | 中国工商银行股份有限公司 | Network queue monitoring method and device, computer equipment and storage medium |
| CN113507420A (en) * | 2021-08-05 | 2021-10-15 | 清华大学 | Congestion control method and device |
| CN115460156A (en) * | 2022-09-21 | 2022-12-09 | 长沙理工大学 | A data center lossless network congestion control method, device, equipment and medium |
| CN116170380A (en) * | 2023-04-21 | 2023-05-26 | 中国科学技术大学 | ECN marking strategy and queue management method and system based on congestion prediction |
| CN116545933A (en) * | 2023-07-06 | 2023-08-04 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Network congestion control method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 一种新的显式拥塞控制策略的研究;王一飞;高仲合;张伟伟;;电脑与信息技术(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116886622A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116886622B (en) | Network congestion control method, device, equipment and storage medium | |
| US7283814B2 (en) | Method and apparatus for scheduling transmissions in wireless data networks | |
| US11044290B2 (en) | TCP cross traffic rate control | |
| CN102468941B (en) | Network packet loss processing method and device | |
| US8902739B2 (en) | Backhaul congestion control for wireless communication networks | |
| CN109818874B (en) | Data transmission method, device and computer storage medium | |
| US20120163385A1 (en) | Systems and methods to improve performance of tcp over large bandwidth-delay-product networks | |
| GB2372172A (en) | Congestion handling in a packet data network | |
| CN109698797B (en) | TCP congestion control method and device | |
| KR20160144257A (en) | Method and apparatus for control transmission base on transmision control protocol in a communication system | |
| EP4156766A1 (en) | Data packet sending method and apparatus | |
| CN111314237B (en) | Method, device and equipment for adjusting data packet transmission rate and readable storage medium | |
| CN116545933B (en) | Network congestion control method, device, equipment and storage medium | |
| CN108667560B (en) | Method and device for adjusting data sending rate of terminal | |
| WO2009037152A1 (en) | Improved utilization of data links | |
| KR101818243B1 (en) | Method and Apparatus for Adaptive Buffer Management in Communication Systems | |
| JP4328794B2 (en) | COMMUNICATION SYSTEM, COMMUNICATION DEVICE, AND TRANSMISSION CONTROL METHOD | |
| US8279756B2 (en) | Communication terminal, communication control method, and communication control program | |
| US8693329B2 (en) | Congestion control in a wireless communication network | |
| JP4166602B2 (en) | Mobile device | |
| EP1648183A1 (en) | The adjusting method for the transmitting window of the radio link layer | |
| JP6897769B2 (en) | Data transmitters, methods and programs | |
| CN115714746B (en) | Congestion control method and system based on delay and packet loss | |
| JP2006340081A (en) | Multicast communication flow control method and apparatus | |
| CN110912831B (en) | TCP transmission method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |