WO2016172958A1

WO2016172958A1 - Dynamic traffic control method, device and home gateway, and hybrid access aggregation point

Info

Publication number: WO2016172958A1
Application number: PCT/CN2015/078086
Authority: WO
Inventors: 刘德
Original assignee: 华为技术有限公司
Priority date: 2015-04-30
Filing date: 2015-04-30
Publication date: 2016-11-03
Also published as: CN106464567B; CN106464567A

Abstract

Provided in embodiments of the present invention are a dynamic traffic control method and device for addressing the problem in the prior art in which traffic in a first tunnel can never overflow to another tunnel. The method comprises: receiving, by a first device, a data stream; establishing, by the first device according to stored connection information of establishing a TCP connection with a second device, N TCP connection channels with the second device, N being a positive integer greater than or equal to 2; and transmitting, by the first device according to traffic overflow thresholds corresponding to L in the N TCP connection channels, the data stream to the second device via at least one of the N TCP connection channels, wherein the traffic overflow threshold corresponding to each of the N TCP connection channels is pre-determined for each TCP connection channel according to statistics of round trip delays and a data drop rate of data packets transmitted in the TCP connection channel in a preset time period, and L is a positive integer less than N.

Description

Traffic dynamic control method, device and gateway, and fusion access convergence point

Technical field

The present invention relates to the field of communications technologies, and in particular, to a traffic dynamic control method, a device, a gateway, and a convergence access convergence point.

Background technique

The convergence of network broadband access has been a trend, including various fixed network and cable: x Digital Subscriber Line/Very High Rate Digital Subscriber Line (xDSL/VDSL), cable TV cable (Cable), Fiber, Wirless Fidelity (WiFi), Ethernet, third-generation mobile communication technology (the 3rd-generation, referred to as: 3G), fourth-generation mobile communication technology (the 4th-generation, referred to as: 4G) To maximize the coverage of the network. Through these converged access methods, data messages can be concurrently transmitted, providing users with access to the Internet, providing personalized interactive TV (Interactive Personality TV, IPTV for short), IP-based voice calls (Voice over) IP, referred to as: VoIP) Voice call and other aspects of the business experience.

In the networking of Digital Subscriber Line (DSL) and Long Term Evolution (LTE), terminals and core networks supporting both DSL and LTE access are used as two convergence points of the network. . As shown in FIG. 1 , the LTE link includes a Home Gateway (HG) evolved Node B (eNodeB), an Evolved Packet Core (EPC) device, and a converged access. Hybrid Access Aggregation Point (HAAP). The DSL link includes an HG, a Digital Subscriber Line Access Multiplexer (DSLAM), a Broadband Network Gateway (BNG), and a HAAP. Two common routing encapsulation (GRE) tunnels are established between the two points through the LTE and DSL links, and the two tunnels are bound to complete the data packets in the two tunnels. Forward.

In data processing, the two tunnels are superimposed and bound, that is, the total bandwidth of the system is the sum of the bandwidths of the two links. The Internet Protocol (IP) address of the data connection is redistributed in the bound tunnel. The outer address of the tunnel is only responsible for the connection and transmission of the links of the two tunnels. The inner address of the tunnel is user data. The package address is used to communicate with the Internet.

In the prior art, during data transmission, the traffic is filled on the DSL tunnel according to a statically configured threshold. After the actual data packet reaches the threshold, the data flow overflows to the LTE tunnel. At the other end of the two tunnels, the received data packets are sorted and integrated to complete the binding of the entire data.

The egress bandwidth of the core network is generally allocated based on the proportion of each user. However, when the number of users is large and concurrently concurrent, the egress bandwidth of the network of the core network becomes a bottleneck, and the end user activation or core network device allocation cannot be achieved. Bandwidth. Therefore, traffic on the first tunnel cannot always overflow to the second tunnel for transmission.

Summary of the invention

The embodiment of the invention provides a method, a device, a gateway, and a convergence access aggregation point for solving the problem that the traffic on the first tunnel cannot overflow to another tunnel in the prior art.

In a first aspect, an embodiment of the present invention provides a traffic dynamic control method, including:

The first device receives the data stream;

The first device establishes N encapsulated TCP connection channels with the second device according to the stored connection information of the Transmission Control Protocol (TCP) connection with the second device, where N is greater than or equal to 2. Positive integer

Transmitting, by the first device, the data flow to the at least one TCP connection channel of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels Second device

The traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is a pin. For each TCP connection channel, according to the TCP connection channel, the loopback delay and the packet loss rate of the data packet are determined in advance according to the preset duration; L is a positive integer smaller than N.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the acquiring, by the first device, the connection information of the TCP connection with the second device includes:

The first GRE protocol control signaling sent by the first device to the second interface of the second device by using the first interface, where the first GRE protocol control signaling carries the Internet Protocol IP address of the first interface a GRE tunnel is configured between the first interface and the second interface, and the second device records the IP address of the first interface as being between the first interface and the second interface. Destination IP address of the TCP connection channel;

Receiving, by the first device, the first GRE protocol control signaling reply signaling sent by the second device by using the second interface, where the first GRE protocol control signaling is carried in the signaling The IP address of the second interface;

The first device records an IP address of the second interface as a destination IP address of a TCP connection channel between the first interface and the second interface.

With reference to the first aspect or the first possible implementation manner of the first aspect, in the second possible implementation manner of the first aspect, for each TCP connection channel, according to the TCP connection channel, the preset is respectively The loopback delay and packet loss rate of the data packets measured in the duration determine the traffic overflow threshold, including:

The first device performs separately for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset length of the TCP connection channel are respectively counted. The loopback delay of the data packet and the packet loss rate are used to determine the TCP connection channel. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.

With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow threshold corresponding to the TCP connection channel, include:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the TCP The traffic overflow threshold corresponding to the connection channel, where 0<X<1; or

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, the comparison period is equal to M The preset duration, M is a positive integer.

With reference to the second or third possible implementation manner of the first aspect, in a fourth possible implementation manner of the foregoing aspect, the data packet loopback delay and the packet loss ratio are determined according to statistics The channel capability value of the TCP connection channel, including:

Determine the channel capability value of the TCP connection channel according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the data packet transmission congestion window, the MSS indicates the maximum fragmented packet size, P indicates the packet loss rate, and the RTT indicates the data packet ring. Back delay, min means take the minimum value.

With reference to the first aspect, and any one of the first to fourth possible implementation manners of the first aspect, in a fifth possible implementation manner of the first aspect, the method further includes:

After receiving the data stream, the first device performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is based on the arrival of each data packet. The order is determined.

With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the first device, according to the traffic corresponding to the L TCP connection channels in the N TCP connection channels And the overflowing the threshold, the data stream is sent to the second device by using at least one of the N TCP connection channels, including:

If the first device establishes two TCP connection channels, confirm that the first TCP connection channel is the default transmission channel;

When the number of the data packets of the data stream reaches the traffic overflow threshold corresponding to the first TCP connection channel, the first device adds an identifier to the head of each data packet of the data stream, where the identifier is The number is used to identify the link corresponding to each TCP connection channel;

The first device sends each data packet to the second device by using a TCP connection channel corresponding to the identifier number in each data packet.

With reference to the fifth possible implementation manner of the first aspect, in a seventh possible implementation manner of the first aspect, the first device, according to the traffic corresponding to the L TCP connection channels in the N TCP connection channels And the overflowing the threshold, the data stream is sent to the second device by using at least one of the N TCP connection channels, including:

If the first device establishes at least three TCP connection channels, determining a priority of the established TCP connection channel;

The first device adds an identification number to each data packet header according to a priority of each TCP connection channel and a traffic overflow threshold corresponding to each TCP connection channel; the identification number is used to identify each TCP connection channel. link;

In conjunction with the sixth or seventh possible implementation of the first aspect, in an eighth possible implementation manner of the first aspect, the identifier of the added TCP connection channel is located before the data field of each data packet. .

With reference to the first aspect, and any one of the first to the eighth possible implementation manners of the first aspect, in the ninth possible implementation manner of the first aspect, the first device is an HG, The second device is HAAP.

In a second aspect, an embodiment of the present invention further provides a traffic dynamic control method, including:

The second device receives the data stream;

The second device sends the data flow to the first one through the at least one TCP connection channel of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. device;

The N TCP connection channels are TCP connection channels between the second device and the first device that are established; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each TCP. Connection channel, according to the TCP connection channel, for a preset duration The internal data packet loopback delay and the packet loss rate are predetermined; L is a positive integer smaller than N.

With reference to the second aspect, in a first possible implementation manner of the second aspect, for each of the TCP connection channels, the loopback delay of the data packet that is counted in the preset duration is respectively determined according to the TCP connection channel. The packet loss rate determines the traffic overflow threshold, including:

The second device performs for each TCP connection channel:

With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow threshold corresponding to the TCP connection channel ,include:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow threshold, where 0<X<1;

With reference to the first or second possible implementation manner of the second aspect, in a third possible implementation manner of the second aspect, the data packet loopback delay and the packet loss ratio are determined according to statistics The channel capability value of the TCP connection channel, including:

Combining the second aspect with any one of the first to third possible implementations of the second aspect In a fourth possible implementation manner of the second aspect, the method further includes:

After receiving the data stream, the second device performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is based on the arrival of each data packet. The order is determined.

With reference to the fourth possible implementation manner of the second aspect, in a fifth possible implementation manner of the second aspect, the second device, according to the traffic corresponding to the L TCP connection channels in the N TCP connection channels And the overflowing threshold, the data stream is sent to the first device by using at least one of the N TCP connection channels, including:

If the second device establishes two TCP connection channels, confirm that the first TCP connection channel is the default transmission channel;

When the number of the data packets of the data stream reaches the traffic overflow threshold corresponding to the first TCP connection channel, the second device adds an identifier to the head of each data packet of the data stream, where the identifier is The number is used to identify the link corresponding to each TCP connection channel;

The second device sends each data packet to the first device by using a TCP connection channel corresponding to the identifier number in each data packet.

With the fourth possible implementation of the second aspect, in a sixth possible implementation manner of the second aspect, the second device, according to a traffic overflow threshold corresponding to the at least two TCP connection channels, is configured to Transmitting to the first device by using at least one of the at least two TCP connection channels, including:

If the second device establishes at least three TCP connection channels, determining a priority of the established TCP connection channel;

The second device adds an identification number to each data packet header according to a priority of each TCP connection channel and a traffic overflow threshold corresponding to each TCP connection channel; the identifier number is used to identify each TCP connection channel. link;

In combination with the fifth or sixth possible implementation of the second aspect, the seventh aspect of the second aspect In a possible implementation manner, the identifier of the added TCP connection channel is located before the data field of each data packet.

With reference to the second aspect, and any one of the first to seventh possible implementation manners of the second aspect, in the eighth possible implementation manner of the second aspect, the first device is an HG, The second device is HAAP.

A third aspect of the present invention provides a traffic dynamic control device, including:

a receiving module, configured to receive a data stream;

a storage module, configured to store connection information for performing TCP connection with the peer device corresponding to the device where the storage module is located;

a processing module, configured to establish, according to the connection information that the storage module performs a TCP connection with the peer device, establish N TCP connection channels with the peer device, where N is a positive integer greater than or equal to 2;

a sending module, configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels established by the processing module The connection channel is sent to the peer device;

The traffic overflow threshold corresponding to each of the TCP connection channels of the N TCP connection channels is a loopback delay of the data packets that are counted within the preset duration according to the TCP connection channel for each of the TCP connection channels. The packet loss rate is predetermined; L is a positive integer less than N.

With reference to the third aspect, in a first possible implementation manner of the third aspect, the sending module is further configured to send, by using the first interface, the first GRE protocol control signaling to the second interface of the peer device The first GRE protocol control signaling carries the Internet Protocol IP address of the first interface, and the GRE tunnel is configured between the first interface and the second interface; The IP address of the first interface is recorded as the destination IP address of the TCP connection channel between the first interface and the second interface;

The receiving module is further configured to receive, by using the first interface, a first GRE protocol control signaling reply signaling sent by the peer device by using a second interface, where the first GRE protocol control signaling reply signaling Carrying the IP address of the second interface;

The storage module is configured to store an IP address of the second interface as the first interface and the The destination IP address of the TCP connection channel between the second interfaces.

In combination with the third aspect or the first possible implementation manner of the third aspect, the processing module is further configured to perform separately for each TCP connection channel:

With reference to the second possible implementation manner of the third aspect, in a third possible implementation manner of the third aspect, determining, according to the determined channel capability value of the TCP connection channel, the traffic overflow gate corresponding to the TCP connection channel The processing module is specifically configured to use the value of the determined channel capability value of the TCP connection channel multiplied by X as a traffic overflow threshold, where 0<X<1; or

With reference to the second or third possible implementation manner of the third aspect, in a fourth possible implementation manner of the third aspect, determining, according to the statistics, the data packet loopback delay and the packet loss ratio The processing module is specifically configured to determine a channel capability value of the TCP connection channel according to the following formula:

In combination with the third aspect and any one of the first to fourth possible implementation manners of the third aspect, in a fifth possible implementation manner of the third aspect, the processing module is further configured to After receiving the data stream, the receiving module performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is arrived according to each data packet. The order of the determination is determined.

With reference to the fifth possible implementation manner of the third aspect, in a sixth possible implementation manner of the third aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, The data stream is sent to the peer device by using at least one of the N TCP connection channels, and the processing module is specifically configured to:

If the established TCP connection channel is two, it is confirmed that the first TCP connection channel is the default transmission channel; when it is determined that the number of data packets of the data flow reaches the traffic overflow threshold corresponding to the first TCP connection channel, Adding an identification number to the header of each data packet of the data stream, where the identifier number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to:

The data packets are sent to the peer device through the TCP connection channel corresponding to the identifier in each data packet.

With reference to the fifth possible implementation manner of the third aspect, in a seventh possible implementation manner of the third aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, When the data stream is sent to the peer device through the at least one of the N TCP connection channels, the processing module is specifically configured to:

If the established TCP connection channel is at least three, the priority of the established TCP connection channel is determined; and each data packet header is determined according to the priority of each TCP connection channel and the traffic overflow threshold corresponding to each TCP connection channel. Add an identification number; the identification number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to send each data packet to the peer device by using a TCP connection channel corresponding to the identifier number in each data packet.

In conjunction with the sixth or seventh possible implementation of the third aspect, in an eighth possible implementation manner of the third aspect, the processing module adds the identifier of the TCP connection channel to the data of each data packet. Before the field.

With reference to the third aspect, and any one of the first to the eighth possible implementation manners of the third aspect, in the ninth possible implementation manner of the third aspect, the device where the storage module is located is an HG, The peer device is a HAAP.

In a fourth aspect, the embodiment of the present invention further provides a traffic dynamic control device, including:

a receiving module, configured to receive a data stream;

a sending module, configured to send the data flow to the sending module by using at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels The peer device corresponding to the device;

The N TCP connection channels are TCP connection channels between the established peer device and the device where the sending module is located; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is For each TCP connection channel, according to the TCP connection channel, the loopback delay and the packet loss rate of the data packet are determined in advance according to the preset duration; L is a positive integer smaller than N.

With reference to the fourth aspect, in a first possible implementation manner of the fourth aspect, the method further includes:

Processing module for performing separately for each TCP connection channel:

With reference to the first possible implementation manner of the fourth aspect, in a second possible implementation manner of the fourth aspect, determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow corresponding to the TCP connection channel Threshold, the processing module is specifically used to:

In conjunction with the first or second possible implementation of the fourth aspect, in a third possible implementation manner of the fourth aspect, the data packet loopback delay and the packet loss rate according to statistics are obtained. Indeed The channel capability value of the TCP connection channel is determined, and the processing module is specifically configured to:

With reference to the fourth aspect, and any one of the first to the third possible implementation manners of the fourth aspect, in a fourth possible implementation manner of the fourth aspect, the processing module is further used in After receiving the data stream, the receiving module performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is based on the arrival of each data packet. The order is determined.

With reference to the fourth possible implementation manner of the fourth aspect, in a fifth possible implementation manner of the fourth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, When the data stream is sent to the peer device through the at least one of the N TCP connection channels, the processing module is specifically configured to:

The sending module is specifically configured to:

With reference to the fourth possible implementation manner of the fourth aspect, in a sixth possible implementation manner of the fourth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, When the data stream is sent to the peer device through the at least one of the N TCP connection channels, the processing module is specifically configured to:

The sending module is specifically configured to:

In conjunction with the fifth or sixth possible implementation of the fourth aspect, in a seventh possible implementation manner of the fourth aspect, the processing module is specifically configured to add an identifier of a TCP connection channel to each data. Before the data field of the message.

With reference to the fourth aspect, and any one of the first to seventh possible implementation manners of the fourth aspect, in the eighth possible implementation manner of the fourth aspect, the device where the sending module is located is a HAAP, The peer device is an HG.

In a fifth aspect, the embodiment of the present invention further provides a gateway, including:

a transceiver, a memory, and a processor;

The transceiver is configured to receive a data stream;

The memory is configured to store connection information for performing a TCP connection with the HAAP;

a processor, configured to establish N TCP connection channels with the HAAP according to the connection information that is stored in the memory and perform a TCP connection with the HAAP, where N is a positive integer greater than or equal to 2;

The transceiver is further configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels of the N TCP connection channels stored in the memory a connection channel is sent to the HAAP;

With reference to the fifth aspect, in a first possible implementation manner of the fifth aspect, the transceiver is further configured to: send, by using a first interface, a first GRE protocol to a second interface of the converged access convergence point Controlling the signaling, the first GRE protocol control signaling carries the IP address of the first interface, and the GRE tunnel is configured between the first interface and the second interface; Recording, by the first interface, the IP address of the first interface is the destination IP address of the TCP connection channel between the first interface and the second interface; The first GRE protocol control signaling reply signaling, where the first GRE protocol control signaling reply signaling carries the IP address of the second interface;

The memory is configured to store an IP address of the second interface as a destination IP address of a TCP connection channel between the first interface and the second interface.

In combination with the fifth aspect or the first possible implementation manner of the fifth aspect, the processor is further configured to perform separately for each TCP connection channel:

With reference to the second possible implementation manner of the fifth aspect, in a third possible implementation manner of the fifth aspect, determining, according to the determined channel capability value of the TCP connection channel, the traffic overflow gate corresponding to the TCP connection channel The processor is specifically configured to multiply the determined channel capability value of the TCP connection channel by the value of X as a traffic overflow threshold, where 0<X<1;

With reference to the second or third possible implementation manner of the fifth aspect, in a fourth possible implementation manner of the third aspect, determining, according to the statistics, the data packet loopback delay and the packet loss ratio The processor is specifically configured to determine a channel capability value of the TCP connection channel according to the following formula:

With reference to the fifth aspect and any one of the first to fourth possible implementation manners of the fifth aspect, in a fifth possible implementation manner of the fifth aspect, after the transceiver receives the data stream, The processor is further configured to perform TCP encapsulation on each data packet corresponding to the data stream, and add a sequence number to each data packet header; the sequence number is based on a sequence of arrival of each data packet. definite.

With reference to the fifth possible implementation manner of the fifth aspect, in a sixth possible implementation manner of the fifth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, The data stream is sent to the HAAP through at least one of the N TCP connection channels, where the processor is specifically configured to:

The transceiver is configured to send each data packet to the HAAP through a TCP connection channel corresponding to the identification number in each data packet.

With reference to the fifth possible implementation manner of the fifth aspect, in a seventh possible implementation manner of the fifth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, When the data stream is sent to the HAAP through at least one of the N TCP connection channels, the processor is specifically configured to:

The sending module is specifically configured to:

Each data packet is sent to the converged access convergence point through a TCP connection channel corresponding to the identification number in each data packet.

With reference to the sixth or the seventh possible implementation manner of the fifth aspect, in the eighth possible implementation manner of the fifth aspect, the processing module adds the identifier of the TCP connection channel to the data of each data packet Before the field.

In a sixth aspect, the embodiment of the present invention further provides a convergence access convergence point, including:

a transceiver for receiving a data stream;

a memory for storing a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels;

The transceiver is further configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels stored in the memory. Sent to the gateway;

The N TCP connection channels are TCP connection channels between the established gateway and the converged access convergence point; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each The TCP connection channel is determined according to the loopback delay and the packet loss rate of the data packet in the preset duration, and L is a positive integer smaller than N.

In conjunction with the sixth aspect, in a first possible implementation manner of the sixth aspect, the processor is further configured to perform separately for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the TCP connection channel are measured, and the channel capability value of the TCP connection channel is determined according to the statistics of the loopback delay and the packet loss rate of the data packet. The traffic overflow threshold corresponding to the TCP connection channel is determined according to the determined channel capability value of the TCP connection channel.

With reference to the first possible implementation manner of the sixth aspect, in a second possible implementation manner of the sixth aspect, determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow corresponding to the TCP connection channel Threshold, the processor is specifically used to:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow gate Limit, where 0<X<1; or

With reference to the first or second possible implementation manner of the sixth aspect, in a third possible implementation manner of the sixth aspect, the data packet loopback delay and the packet loss rate according to statistics are performed. Determining a channel capability value of the TCP connection channel, the processor is specifically configured to:

With reference to the sixth aspect and any one of the first to third possible implementation manners of the sixth aspect, in a fourth possible implementation manner of the sixth aspect, after the transceiver receives the data stream The processor is further configured to perform TCP encapsulation on each data packet corresponding to the data stream, and add a sequence number to each data packet header; the sequence number is based on a sequence of arrival of each data packet. definite.

With reference to the fourth possible implementation manner of the sixth aspect, in a fifth possible implementation manner of the sixth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, The data stream is sent to the gateway by using at least one of the N TCP connection channels, where the processor is specifically configured to:

The sending module is specifically configured to:

Sending each data packet to the gateway through a TCP connection channel corresponding to the identification number in each data packet.

With reference to the fourth possible implementation manner of the sixth aspect, in a sixth possible implementation manner of the sixth aspect, the traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels, The data stream is sent to the gateway by using at least one of the N TCP connection channels, where the processor is specifically configured to:

The transceiver is configured to send each data packet to the gateway through a TCP connection channel corresponding to the identification number in each data packet.

With reference to the fifth or the sixth possible implementation manner of the sixth aspect, in a seventh possible implementation manner of the sixth aspect, the processor is specifically configured to add an identifier of a TCP connection channel to each datagram. Before the data field of the text.

In a seventh aspect, an embodiment of the present invention further provides a computer readable storage medium storing one or more programs, the one or more programs including instructions executed by an electronic device including a plurality of applications The method of causing the electronic device to perform the method of any one of the first to eighth possible implementations of the first aspect and the first aspect.

In an eighth aspect, an embodiment of the present invention further provides a computer readable storage medium storing one or more programs, where the one or more programs include instructions that are executed by an electronic device that includes a plurality of applications. The method of causing the electronic device to perform the method of any one of the first to seventh possible implementations of the second aspect and the second aspect.

According to the solution provided by the embodiment of the present invention, the traffic overflow threshold is determined by the real-time statistics of the loopback delay and the packet loss rate of the data packet, and then the traffic is dynamically controlled according to the dynamically changing traffic overflow threshold, so that the data can overflow in one channel. Go to another channel.

DRAWINGS

Figure 1 is a schematic diagram of a GRE tunnel;

2 is a flowchart of a method for dynamically controlling traffic according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for dynamically controlling traffic according to an embodiment of the present invention;

4 is a schematic diagram of a traffic dynamic control device according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of another flow dynamic control device according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a gateway according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a convergence access convergence point according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a flow dynamic control system according to an embodiment of the present invention; FIG.

FIG. 9 is a schematic diagram of a method for learning LTE link parameters according to an embodiment of the present invention;

FIG. 10 is a schematic diagram of a DSL link parameter learning method according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of a method for a gateway to route the data packet to a binding virtual interface for TCP processing according to an embodiment of the present invention.

detailed description

The present invention will be further described in detail with reference to the accompanying drawings, in which FIG. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The embodiment of the invention provides a method, a device, a gateway, and a convergence access aggregation point for solving the problem that the traffic on the first tunnel cannot reach the other tunnel after the threshold is reached in the prior art. In the embodiment of the present invention, the data bearer is separated from the existing mode, and the data transmission and the signaling interaction use different bearer protocols, and the data bearer channel is upgraded from the current GRE tunnel to the TCP protocol. The dynamic statistics determine the loopback delay of the data packet and the packet loss rate within the preset duration to determine which TCP connection channel to transmit data. among them, The method and the device are based on the same inventive concept. Since the principles of the method and the device for solving the problem are similar, the implementation of the device and the method can be referred to each other, and the repeated description is not repeated.

The embodiment of the invention provides a dynamic flow control method, as shown in FIG. 2, the method includes:

Step 201: The first device receives the data stream.

Step 202: The first device establishes N TCP connection channels with the second device according to the stored connection information of the TCP connection with the second device, where N is a positive integer greater than or equal to 2.

The number of established TCP connection channels is related to the connection information.

The connection information includes the IP addresses of the interfaces at both ends of the established TCP connection channel. Therefore the number of connected channels is related to the number of interfaces.

The stored connection information for performing a TCP connection with the second device is stored in advance and acquired.

Step 203: The first device sends the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. Giving the second device.

The traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each TCP connection channel, and according to the TCP connection channel, the loopback delay of the data packet is counted according to the preset duration. And the packet loss rate is predetermined; L is a positive integer less than N.

A TCP connection channel corresponds to a traffic overflow threshold, and the traffic overflow threshold is determined on the TCP connection channel, and the data packet loopback delay and the packet loss rate are determined in a preset duration.

The first device may be a gateway, and the second device may be a convergence access convergence point.

Specifically, the first device obtains connection information for performing a TCP connection with the second device, and may be implemented by:

The first GRE protocol control signaling sent by the first device to the second interface of the second device by using the first interface, where the first GRE protocol control signaling carries the Internet protocol of the first interface An IP address is configured, a GRE tunnel is configured between the first interface and the second interface, and the second device records the IP address of the first interface as the first interface and the second interface. The destination IP address between the TCP connection channels;

Optionally, the first GRE protocol control signaling may further carry a port number of the first interface when carrying the Internet Protocol IP address of the first interface. Similarly, when the IP address of the second interface is carried in the first GRE protocol control signaling reply signaling, the port number of the second interface may also be carried.

For example, in the networking of DSL and LTE, the gateway and HAAP supporting both DSL and LTE access are used as two convergence points of the network. Two GRE tunnels are established between the two points through the links of LTE and DSL respectively. The DSL interface and the LTE interface are included in the gateway, and only one interface is included on the HAAP, which is called T3.

On the LTE interface of the LTE link, the gateway sends the GRE protocol control signaling to the HAAP, and the GRE protocol control signaling carries the IP address of the LTE interface. You can also carry a port number.

After receiving the GRE protocol control signaling, the HAAP records the IP address and port number of the LTE interface, and serves as the destination IP address and destination port number of the TCP connection channel between the TAP interface of the HAAP and the LTE interface of the gateway. .

The HAAP then sends the GRE protocol control signaling reply signaling to the gateway, and carries the IP address and port number of the TAP interface of the HAAP in the GRE protocol control signaling reply signaling. Therefore, after receiving the GRE protocol control signaling reply signaling, the gateway records the IP address of the T3 interface, and serves as the destination IP address and destination port of the TCP connection channel between the LTE interface of the gateway and the T3 interface of the HAAP. number.

On the DSL interface of the DSL link, the gateway sends GRE protocol control signaling to the HAAP. The GRE protocol control signaling carries the IP address of the DSL interface. It can also carry the port number of the DSL interface.

After receiving the GRE protocol control signaling through the T3 interface, the HAAP records the IP address of the DSL interface and serves as the destination IP address of the TCP connection channel between the TAP interface of the HAAP and the DSL interface of the gateway.

The HAAP then sends the GRE protocol control signaling reply signaling to the DSL interface of the gateway through the T3 interface, and carries the IP address of the TAP interface of the HAAP in the GRE protocol control signaling reply signaling. Therefore, after receiving the GRE protocol control signaling reply signaling, the gateway records the IP address of the T3 interface, and serves as the destination IP address of the TCP connection channel between the DSL interface of the gateway and the T3 interface of the HAAP.

Optionally, after receiving the data flow, the first device performs TCP encapsulation on each data packet corresponding to the data flow, and adds a sequence number to each data packet header; the serial number is according to each datagram. The order in which the text arrives is determined.

The traffic overflow threshold is determined according to the loopback delay and the packet loss rate of the data packet in the preset duration, and can be implemented in the following manner:

The first device performs for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset duration are measured, and the TCP connection channel is determined according to the statistics of the loopback delay of the data packet and the packet loss rate. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.

Specifically, since the serial number is added to the header of each data packet, the ACK of the data packet of the same sequence number received by the data packet on the TCP connection channel within the preset duration may be counted. The time difference of the feedback is obtained, and then the average value of the time difference between the sending and receiving of each data message is obtained as the RTT value within the preset duration. The packet loss rate of the TCP connection channel within the preset duration may be determined by whether each data packet receives the ACK feedback. After the data packet with the sequence number is sent, the sequence number of the data packet is continuous, so each sequence number in the ACK feedback of the data packet can be counted, so the packet loss rate can be determined.

Further, determining the traffic overflow threshold of the TCP connection channel according to the determined channel capability value of the TCP connection channel may be implemented as follows:

The first way to achieve:

The determined channel capability value of the TCP connection channel is multiplied by the value of X as the traffic overflow threshold, where 0<X<1.

The second way to achieve:

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, and adjusting the adjusted flow rate The overflow threshold is used as the traffic overflow threshold for this comparison period. The comparison period is equal to M preset durations, and M is a positive integer. A preset duration can also be referred to as a time window, and a time concept is represented in the embodiment of the present invention.

First, each TCP connection channel is executed separately: when the predetermined initial traffic overflow threshold is the first time window (a time window is equal to a preset duration), the TCP connection channel data message is looped back. The delay and packet loss rate are determined by multiplying the channel capability value of the TCP connection channel by a percentage (for example, 50%). Then, the loopback delay and the packet loss rate of the data packet in each subsequent time window are determined, and the channel capability value of the TCP connection channel is determined, and the determined channel capability value and the initial traffic overflow threshold are performed. For comparison, the comparison result is obtained, and the comparison result is saved, the flow threshold is adjusted according to the comparison result in the comparison period, and the adjusted flow threshold is saved. A comparison period is equal to M time windows.

For example, if the channel capability value determined in three consecutive time windows (one comparison period) is greater than the currently saved traffic overflow threshold, the flow overflow threshold is increased by 5%. If the channel capacity value determined in the three consecutive time windows is less than the currently saved traffic overflow threshold, the flow overflow threshold is lowered by 5%. In other cases, the flow overflow threshold is unchanged. Then, the adjusted flow overflow threshold is used as the flow overflow threshold of the dynamic control of the next comparative cycle of the comparison cycle. Therefore, the flow overflow threshold can be dynamically and real-time adjusted to ensure the superposition of the dual channel bandwidth.

Further, determining the channel capability value of the TCP connection channel according to the loopback delay and the packet loss rate of the statistical data packet can be implemented by using the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the data packet transmission congestion window, the MSS indicates the maximum fragmented packet size, P indicates the packet loss rate, and the RTT indicates the data packet ring. Back delay. Min means to take the minimum value. Min(A, B) represents the minimum value of the values of A and B, for example, min(5, 4)=4.

Among them, BW is the activation bandwidth of the connection channel, which is predetermined, and once it is determined, it generally does not change. The CWND and the MSS are obtained by TCP negotiation and are also fixed values. Therefore, the RTT and P in the above formula are dynamically changed, and real-time statistics are required.

The preset duration is T, that is, the period length. Then, the RTT value may be a data packet loopback delay that is counted in the previous time period. P can be the packet loss rate of the data packet counted in the previous time period. Therefore, the overflow traffic threshold is dynamically changed in real time. The gateway and HAAP periodically calculate the RTT and P values, and determine the overflow traffic threshold for the period, and save it in real time.

Specifically, each data packet corresponding to the data stream is encapsulated by TCP, that is, each data packet corresponding to the data stream is used as a payload of the TCP packet.

Further, the first device sends the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. Giving the second device includes:

Wherein, the TCP connection channel corresponds to the TCP link, and the identification number can be used to identify the TCP link. Of course, it can be said that the identification number is used to identify the TCP connection channel.

When it is determined that the number of data packets of the data stream reaches a traffic overflow threshold corresponding to the first TCP connection channel, an identifier is added to a header of each data packet of the data flow, where the identifier is added to identify the first TCP. The number of data packets connected to the channel is equal to the traffic overflow threshold. After determining that the number of data packets of the data flow reaches the traffic overflow threshold corresponding to the first TCP connection channel, the data packet may be evenly distributed and transmitted on the two TCP connection channels.

Optionally, if the first device establishes at least three TCP connection channels, the priority of the established TCP connection channel may be determined;

The first device adds an identification number to each data packet header according to a priority of each TCP connection channel and a traffic overflow threshold corresponding to each TCP connection channel;

For example, if there are 3 TCP connection channels established, they are TCP1, TCP2, and TCP3. The priority of TCP1 is greater than the priority of TCP2, and the priority of TCP2 is greater than the priority of TCP3.

The first device may add the identifier of the TCP1 to the header of the data packet whose sequence number does not reach the traffic overflow threshold corresponding to the TCP1, and reduce the sequence number of the data packet whose serial number reaches the traffic overflow threshold corresponding to the TCP1. After the traffic overflow threshold corresponding to TCP1 is received, the identifier of the TCP2 is added to the header of the data packet whose sequence number value does not reach the traffic overflow threshold corresponding to TCP2. The identifier of TCP3 is added to the header of the remaining data packet.

The first device may also add an identification number to the header of each data packet of the data stream when determining that the number of data packets of the data stream reaches the sum of the traffic overflow threshold of TCP1 and the traffic overflow threshold of TCP2. The number of added data packets identifying the identification number of TCP1 is less than or equal to the traffic overflow threshold of TCP1. The number of added data packets that identify the identifier of TCP2 is less than or equal to the traffic overflow threshold of TCP2.

When the first device determines that the number of data packets of the data flow reaches the traffic overflow threshold of TCP1, but does not reach the sum of the traffic overflow threshold of TCP1 and the traffic overflow threshold of TCP2, Data messages can be transmitted only through TCP1 and TCP2.

Further, the identification number of the added TCP connection channel is located before the data field of each data packet. As shown in Table 1.

Table 1

The embodiment of the invention provides a dynamic flow control method, as shown in FIG. 3, the method includes:

Step 301: The second device receives the data stream.

Step 302: The second device sends the data flow to at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. Said first device;

The N TCP connection channels are TCP connection channels between the second device and the first device that are established; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each TCP. The connection channel is determined according to the loopback delay and the packet loss rate of the data packet that are counted within the preset duration according to the TCP connection channel; L is a positive integer smaller than N.

The first device has established a TCP connection channel between the first device and the second device when sending the data packet to the second device.

The second device may be a converged access aggregation point, and other network devices that can be used to implement the convergent aggregation function are applicable to the present invention, and the first device may be a gateway.

Optionally, for each of the TCP connection channels, the traffic overflow threshold is determined according to the loopback delay and the packet loss rate of the data packet in the preset duration.

The second device performs for each TCP connection channel:

Specifically, since the sequence number is added to the header of each data packet, the ACK feedback of the data packet of the same sequence number received by the data packet on the TCP connection channel can be counted within the preset duration. The time difference is then obtained as an average of the time difference between the transmission and reception of each data message as the RTT value within the preset duration. The packet loss rate of the TCP connection channel within the preset duration may be determined by whether each data packet receives the ACK feedback. After the data packet with the sequence number is sent, the sequence number of the data packet is continuous, so each sequence number in the ACK feedback of the data packet can be counted, so the packet loss rate can be determined.

Further, determining the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel may be implemented by:

The first way to achieve:

The second way to achieve:

Optionally, determining the channel capability value of the TCP connection channel according to the statistics data packet loopback delay and the packet loss rate can be implemented by using the following formula:

Further, if N is equal to 2, the second device passes the data flow through the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. At least one TCP connection channel is sent to the first device, which can be implemented by:

The TCP connection channel corresponds to the TCP link, and the identification number can be used to identify the TCP link. Of course, the identification number is used to identify the TCP connection channel.

If N is a positive integer greater than or equal to 3, the second device is configured according to the N TCP connection channels. The traffic overflow threshold corresponding to the L TCP connection channels in the medium, and the data flow is sent to the first device by using at least one of the N TCP connection channels, which can be implemented by:

When the first device determines that the number of data packets of the data stream reaches the traffic overflow threshold of TCP1, but fails to reach the sum of the traffic overflow threshold of TCP1 and the traffic overflow threshold of TCP2, the data packet can pass only TCP1 and TCP2 transmission.

Further, the identification number of the added TCP connection channel is located in data of each data packet. Before the field.

The embodiment of the present invention further provides a traffic dynamic control device, which may be an HG. As shown in FIG. 4, the device includes:

a receiving module 401, configured to receive a data stream;

The storage module 402 is configured to store connection information for performing TCP connection with the peer device corresponding to the device where the storage module 402 is located.

The processing module 403 is configured to establish, according to the connection information that the storage module 402 stores the TCP connection with the corresponding peer device, establish N TCP connection channels with the peer device, where N is a positive integer greater than or equal to 2;

The sending module 404 is configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels established by the processing module 403. Sending a TCP connection channel to the peer device;

Optionally, the sending module 404 is further configured to send, by using the first interface, the first GRE protocol control signaling to the second interface of the peer device, where the first GRE protocol control signaling carries the a network protocol IP address of the first interface, a GRE tunnel is configured between the first interface and the second interface, and the peer device records the IP address of the first interface as the first interface a destination IP address of the TCP connection channel between the second interfaces;

The receiving module 401 is further configured to receive, by using the first interface, a first GRE protocol control signaling reply signaling sent by the peer device by using the second interface, where the first GRE protocol control signaling reply The IP address of the second interface is carried in the order;

The storage module 402 is configured to store an IP address of the second interface as the first interface. The destination IP address of the TCP connection channel with the second interface.

Optionally, the processing module 403 is further configured to perform separately for each TCP connection channel:

Further, when the flow overflow threshold corresponding to the TCP connection channel is determined according to the determined channel capability value of the TCP connection channel, the processing module 403 is specifically configured to determine the channel capability value of the TCP connection channel. Multiply the value after X as the traffic overflow threshold, where 0<X<1; or

When the channel capability value of the TCP connection channel is determined according to the statistics of the data packet loopback delay and the packet loss rate, the processing module 403 is specifically configured to determine the channel capability value of the TCP connection channel according to the following formula:

Optionally, the processing module 403 is further configured to: after the receiving module receives the data stream, perform TCP encapsulation on each data packet corresponding to the data stream, and add a serial number in each data packet header. The serial number is determined according to the order in which the individual data messages arrive.

Further, the data stream is sent to the pair through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. The processing module 403 is specifically configured to:

The sending module 404 is specifically configured to:

And when the data stream is sent to the peer device by using at least one of the N TCP connection channels, according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. The processing module 403 is specifically configured to:

When the processing module 403 adds the identification number of the TCP connection channel to the header of the data packet, specifically, the identification number of the TCP connection channel is added before the data field of each data packet.

The embodiment of the present invention further provides a traffic dynamic control device, which may be a HAAP. As shown in FIG. 5, the device includes:

The receiving module 501 is configured to receive a data stream.

The sending module 502 is configured to send the data flow to the sending by using at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. The peer device corresponding to the device where the module is located;

The N TCP connection channels are TCP connection channels between the established peer device and the device where the sending module is located; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is For each TCP connection channel, according to the TCP connection The loopback delay and the packet loss rate of the data packet counted in the preset duration are predetermined; L is a positive integer smaller than N.

Optionally, the device further includes:

Processing module for performing separately for each TCP connection channel:

Determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow threshold corresponding to the TCP connection channel, where the processing module is specifically configured to:

The channel capability value of the TCP connection channel is determined according to the statistics data packet loopback delay and the packet loss rate, and the processing module is specifically configured to:

Optionally, the processing module is further configured to: after the receiving module 501 receives the data stream, And performing a TCP encapsulation on each data packet corresponding to the data stream, and adding a sequence number to each data packet header; the sequence number is determined according to a sequence in which each data packet arrives.

The data stream is sent to the peer end by using at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. The device, the processing module is specifically configured to:

The sending module 502 is specifically configured to:

The data stream is sent to the peer end by using at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. The device is specifically configured to:

The sending module is specifically configured to:

The processing module is specifically configured to add an identification number of the TCP connection channel before the data field of each data packet.

A gateway is also provided in the embodiment of the present invention. As shown in FIG. 6, the gateway includes:

The transceiver 601, the memory 602, and the processor 603;

The transceiver 601, the processor 602, and the memory 603 are connected to each other. Not limited in the embodiment of the present invention Determine the specific connection medium between the above components. In the embodiment of the present invention, the memory 603, the processor 602, and the transceiver are connected by a bus 604 in FIG. 6. The bus is indicated by a thick line in FIG. 6, and the connection manner between other components is only schematically illustrated. Not limited to limits. The bus 604 can be a peripheral component interconnect standard (English: peripheral component interconnect, PCI for short) or an extended industry standard architecture (English: extended industry standard architecture, EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 6, but it does not mean that there is only one bus or one type of bus.

In the embodiment of the present invention, the memory 603 is configured to store the program code executed by the processor 602, and may be a read-only memory (English: read-only memory, abbreviated as: ROM), and a random access memory (English: random-access memory, referred to as :RAM), can also be Electrically Erasable Programmable Read-Only Memory (EEPROM), disk storage media or other magnetic storage devices, or can be used to carry or store instructions or The desired program code in the form of a data structure and any other medium that can be accessed by a computer, but is not limited thereto, for example, the memory 603 may be a combination of the above-described memories.

The processor 602 in the embodiment of the present invention may be a general central processing unit (English: central processing unit, CPU for short).

The transceiver 601 can include, but is not limited to, an antenna, and a transceiver device for implementing the function of transmitting and receiving data messages is suitable for use in the present invention.

The transceiver 601 is configured to receive a data stream.

The storage 603 is configured to store connection information for performing a TCP connection with the fused access aggregation point;

The processor 602 is configured to establish, according to the connection information that is stored in the memory 603 by using the TCP connection with the converged access aggregation point, to establish N TCP connection channels with the converged access aggregation point, where N is greater than or equal to 2. Integer

The transceiver 601 is further configured to: pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels of the N TCP connection channels stored by the memory. Sending, by the TCP connection channel, the converged access convergence point;

The first GRE protocol control signaling sent by the transceiver 601 to the second interface of the fused access aggregation point by using the first interface, where the first GRE protocol control signaling carries the Internet protocol of the first interface An IP address, a GRE tunnel is configured between the first interface and the second interface, and the fused access aggregation point records the IP address of the first interface as the first interface and the second The destination IP address of the TCP connection channel between the interfaces;

Receiving, by the first interface, the first GRE protocol control signaling reply signaling sent by the fused access aggregation point by using the second interface, where the first GRE protocol control signaling reply signaling carries the second The IP address of the interface; the memory 603 stores the IP address of the second interface as the destination IP address of the TCP connection channel between the first interface and the second interface.

The processor 602 performs separately for each TCP connection channel:

When determining the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel, the processor 602 multiplies the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow. Threshold, where 0<X<1; or the processor 602 compares the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusts the current current period according to the obtained comparison result. Comparing the periodic overflow threshold, the comparison period is equal to M preset durations, and M is a positive integer.

When determining the channel capability value of the TCP connection channel according to the statistical data packet loopback delay and the packet loss rate, the processor 602 determines the channel capability value of the TCP connection channel according to the following formula:

After the transceiver 601 receives the data stream, the processor 602 performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the serial number is based on each datagram. The order in which the text arrives is determined.

Transmitting the data stream to the converged access aggregation by using at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. Point, the processor 602 determines that if the established TCP connection channel is two, confirm that the first TCP connection channel is the default transmission channel; and determine that the number of data packets of the data stream reaches the first TCP connection channel. When the traffic overflow threshold, an identifier is added to the header of each data packet of the data stream, where the identifier is used to identify a link corresponding to each TCP connection channel; the transceiver 601 passes each data packet through each datagram. The TCP connection channel corresponding to the identification number in the text is sent to the HAAP.

And when the data stream is sent to the fused access aggregation point through at least one of the at least two TCP connection channels according to a traffic overflow threshold corresponding to the at least two TCP connection channels, the processor 602. Determine, if the established TCP connection channel is at least three, determine a priority of the established TCP connection channel; and use the datagram according to a priority of each TCP connection channel and a traffic overflow threshold corresponding to each TCP connection channel. The identifier is used to identify the link corresponding to each TCP connection channel; the transceiver 601 sends each data packet to the HAAP through the TCP connection channel corresponding to the identification number in each data packet. .

The processor 602 adds the identification number of the TCP connection channel before the data field of each data message.

The embodiment of the invention further provides a converged access aggregation point, as shown in FIG. 7, the converged access Convergence points include:

The transceiver 701, the processor 702, and the memory 703.

The transceiver 701, the processor 702, and the memory 703 are connected to each other. The specific connecting medium between the above components is not limited in the embodiment of the present invention. In the embodiment of the present invention, the memory 703, the processor 702, and the transceiver are connected by a bus 704 in FIG. 6. The bus is indicated by a thick line in FIG. 6, and the connection manner between other components is only schematically illustrated. Not limited to limits. The bus 704 can be a peripheral component interconnect standard (English: peripheral component interconnect, PCI for short) or an extended industry standard architecture (English: extended industry standard architecture, EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 6, but it does not mean that there is only one bus or one type of bus.

In the embodiment of the present invention, the memory 703 is used to store the program code executed by the processor 702, and may be a read-only memory (English: read-only memory, abbreviated as: ROM), and a random access memory (English: random-access memory, referred to as :RAM), can also be Electrically Erasable Programmable Read-Only Memory (EEPROM), disk storage media or other magnetic storage devices, or can be used to carry or store instructions or The desired program code in the form of a data structure and any other medium that can be accessed by a computer, but is not limited thereto, for example, the memory 703 may be a combination of the above-described memories.

The processor 702 in the embodiment of the present invention may be a general central processing unit (English: central processing unit, CPU for short).

The transceiver 701 can include, but is not limited to, an antenna, and a transceiver device for implementing the function of transmitting and receiving data messages is suitable for use in the present invention.

The memory 703 also stores a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels;

After receiving the data stream, the transceiver 701 passes the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels stored in the memory 703. A TCP connection channel is sent to the gateway;

Optionally, the processor 702 performs separately for each TCP connection channel:

Determining, according to the determined channel capability value of the TCP connection channel, a traffic overflow threshold corresponding to the TCP connection channel, the processor 702 multiplying the determined channel capability value of the TCP connection channel by a value of X as a traffic The overflow threshold, where 0<X<1; or the processor 702 compares the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusts according to the obtained comparison result in the current comparison period. The current overflow period threshold of the comparison period, the comparison period is equal to M preset durations, and M is a positive integer.

The channel capability value of the TCP connection channel is determined according to the statistics data packet loopback delay and the packet loss rate, and the processor 702 determines the channel capability value of the TCP connection channel according to the following formula:

After the transceiver 701 receives the data stream, the processor 702 performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the serial number is based on each datagram. The order in which the text arrives is determined.

Wherein the flow corresponding to the L TCP connection channels in the N TCP connection channels The overflow threshold is sent to the gateway by using at least one of the N TCP connection channels, and the processor 702 determines that if the established TCP connection channel is two, the first one is confirmed. The TCP connection channel is the default transmission channel; the identification number of the first TCP connection channel is added to the header of the data packet whose sequence number does not reach the traffic overflow threshold corresponding to the first TCP connection channel; and the data packet of the data stream is determined. When the number of the data reaches the traffic overflow threshold corresponding to the first TCP connection channel, an identifier is added to the header of each data packet of the data stream, where the identifier is used to identify the link corresponding to each TCP connection channel; The 701 sends the data packet to the gateway through a TCP connection channel corresponding to the identification number in each data packet.

The data flow is sent to the gateway through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels. If the processor 702 determines that the established TCP connection channel is at least three, determining the priority of the established TCP connection channel; according to the priority of each TCP connection channel and the traffic overflow threshold corresponding to each TCP connection channel, Adding an identification number to each data packet header; the identifier number is used to identify a link corresponding to each TCP connection channel; then the transceiver 701 sends each data packet through a TCP connection channel corresponding to the identification number in each data packet. Give the first device.

The processor adds the identification number of the TCP connection channel before the data field of each data packet.

Embodiments of the present invention also provide a computer readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by an electronic device including a plurality of applications, cause the The electronic device performs the flow dynamic control method in any of the embodiments corresponding to FIG. 2 described above.

Embodiments of the present invention also provide a computer readable storage medium storing one or more programs, the one or more programs including instructions, when the instructions are electronic including multiple applications When the device is executed, the electronic device is configured to execute the flow dynamic control method in any one of the embodiments corresponding to FIG. 3 above.

The embodiments of the present invention are specifically described below in conjunction with specific application scenarios.

The traffic dynamic control system, as shown in FIG. 8, includes: a gateway, a Hybrid Access Aggregation Point (HAAP), and a broadband network gateway device (abbreviation: BNG) and a packet core network device (abbreviation: EPC) ).

The gateway's LAN address supports both IPv4 addresses (or A4 addresses) and IPv6 addresses (or A6 addresses). And the gateway allocates an IPv4 or IPv6 address to the terminal device through the PHCP.

The gateway includes two interfaces for the DSL interface and the LTE interface, and the HAAP includes one interface for the Tx/Rx interface.

The address D of the DSL interface is obtained by the gateway from the BNG device through the DSL link, and the address E of the LTE interface is obtained by the gateway through the EPC device.

T3 is the address of the Tx/Rx interface that is connected between the HAAP and the gateway.

Before the data stream is transmitted, two TCP connection channels need to be established between the DSL interface and the Tx/Rx interface, the LTE interface, and the Tx/Rx interface. Parameters such as the address of the two TCP connection channels need to be acquired and saved for subsequent use by GRE protocol control signaling. The specific acquisition methods are as follows:

As shown in Figure 9, on the LTE interface:

P1: The gateway sends the GRE protocol control signaling to the HAAP, where the GRE protocol control signaling carries the IP address (E) and the port number of the LTE interface. After receiving the GRE protocol control signaling, the HAAP records the IP address of the LTE interface and serves as the destination IP address of the TCP connection channel between the Tx/Rx interface of the HAAP and the LTE interface of the gateway.

P2: The HAAP sends a GRE protocol control signaling reply signaling to the gateway, and carries the IP address of the TAP/Rx interface of the HAAP in the GRE protocol control signaling reply signaling. Therefore, after receiving the GRE protocol control signaling reply signaling, the gateway records the IP address of the Tx/Rx interface, and serves as the destination IP address of the TCP connection channel between the LTE interface of the gateway and the Tx/Rx interface of the HAAP. address.

As shown in Figure 10, on the DSL interface:

S1: The gateway sends GRE protocol control signaling to the HAAP, where the GRE protocol control signaling carries the IP address and port number of the DSL interface. Then, after receiving the GRE protocol control signaling through the Tx/Rx interface, the HAAP records the IP address and port number of the DSL interface, and serves as a TCP connection channel between the Tx/Rx interface of the HAAP and the DSL interface of the gateway. The destination IP address is used as the connection information.

S2: The HAAP sends the GRE protocol control signaling reply signaling to the DSL interface of the gateway through the Tx/Rx interface, and carries the IP address of the Tx/Rx interface of the HAAP in the GRE protocol control signaling reply signaling. Therefore, after receiving the GRE protocol control signaling reply signaling, the gateway records the IP address of the Tx/Rx interface, and serves as the destination IP address of the TCP connection channel between the DSL interface of the gateway and the Tx/Rx interface of the HAAP. The address is the connection information.

Through the two interaction processes described above in FIG. 9 and FIG. 10, the learning of the address parameters at both ends of the completed TCP connection channel is performed.

The gateway receives the data packet sent by the terminal, and the data packet carries the IP address of the terminal. The IP address of the terminal can be an A4 address or an A6 address. If the address is an A4 address, the gateway routes the data packet to the binding virtual interface for TCP processing, and then passes the A4 address to the NAT, and the NAT is the T1 address. It is then sent to HAAP through a DSL interface or an LTE interface. If the A6 address is used, the gateway routes the data packet to the bound virtual interface for TCP processing, and then sends the data packet to the HAAP through the DSL interface or the LTE interface. Because the A4 address is used as the private network address on the network side, the data packet carrying the A4 address cannot be transmitted on the Internet. If the data packet needs to be converted to a public network address, the T1 address is a preset public network. address. The A6 address is itself a public network address on the network side, so no further conversion is required.

The gateway routes the data packet to the bound virtual interface for TCP processing, as shown in Figure 11.

Step 1101: The gateway establishes two TCP connection channels with the HAAP according to the stored connection information of the TCP connection with the HAAP. Specifically, it is a first TCP connection channel between the DSL interface and the Tx/Rx interface, and a second TCP connection channel between the LTE interface and the Tx/Rx interface.

Step 1102: The gateway encapsulates the data packet by TCP and adds it to the header of each data packet. Add the serial number.

The data packet is encapsulated by TCP, that is, the data packet is added to the header of the TCP packet, as shown in Table 2.

Table 2

Step 1103, when the gateway determines that the number of the data packets of the data flow reaches the traffic overflow threshold corresponding to the first TCP connection channel, the gateway adds an identification number to the head of each data packet of the data flow. The identification number is used to identify the link corresponding to each TCP connection channel.

Step 1104: The gateway sends each data packet to the HAAP through a TCP connection channel corresponding to the identification number in each data packet.

Specifically, the gateway counts the loopback delay and the packet loss rate of the data packet in a time window, and then determines the channel capability of the first TCP connection channel. The channel capability value of the first TCP connection channel can be determined according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the data packet transmission congestion window, the MSS indicates the maximum fragmented packet size, P indicates the packet loss rate, and the RTT indicates the data packet ring. Back delay.

The traffic overflow threshold is then determined based on the channel capability of the first TCP connection channel. Specifically, the channel capability can be multiplied by an expected percentage (such as 50%) as the initial flow overflow threshold. E.g:

Where R is the flow overflow threshold, 0 < X < 1.

Currently, the channel capability of the first TCP connection channel (corresponding to the DSL link) determined in each time window may be saved, and the determined channel capability value of the first TCP connection channel is compared with the traffic overflow threshold. The comparison result is saved. When the channel capability value of the first TCP connection channel is greater than the flow overflow threshold value in the continuous M time window, the flow overflow threshold is adjusted. When it is confirmed that the channel capacity value of the first TCP connection channel is less than the flow overflow threshold within consecutive M time windows, the flow overflow threshold is lowered.

The RTT can be determined according to the time difference between each data message sent and received by the DSL connection channel. Since each data message adds a sequence number, the RTT is determined according to the time difference between the serial number corresponding to the data message sent and the ACK feedback received. The change in RTT reflects the change in the delay of the connection channel. Then, according to the ACK feedback condition of the message corresponding to each sequence number, the packet loss rate in the time window can be determined.

Specifically, after receiving the data packet sent by the gateway, the HAAP sorts and sorts the data packet according to the serial number, and performs timeout retransmission for the unreceived data packet in the time window, and does not receive the predetermined time. When the data packet arrives, it considers that the packet is lost, and sends an ACK feedback to the gateway for the received data packet. Then, the received data packet is sent out of the TCP packet header.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It should be understood that the flow chart can be implemented by computer program instructions And/or a combination of the processes and/or blocks in the block diagrams, and the flowcharts and/or blocks in the flowcharts. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing module to produce a machine for generating instructions for execution by a processor of a computer or other programmable data processing module. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing module to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing module to perform a series of operational steps on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

While the preferred embodiment of the invention has been described, it will be understood that Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and the modifications and

It is apparent that those skilled in the art can make various modifications and variations to the embodiments of the invention without departing from the spirit and scope of the embodiments of the invention. Thus, it is intended that the present invention cover the modifications and modifications of the embodiments of the invention.

Claims

A flow control method, comprising:

The first device receives the data stream;

The first device establishes N TCP connection channels with the second device according to the stored connection information of the TCP connection with the second device, where N is a positive integer greater than or equal to 2;

Transmitting, by the first device, the data flow to the at least one TCP connection channel of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels Second device

The traffic overflow threshold corresponding to each of the N TCP connection channels is for each TCP connection channel, and the data packets are counted back within the preset duration according to the TCP connection channel. The delay and the packet loss rate are predetermined; L is a positive integer less than N.
The method of claim 1, wherein the first device acquires connection information for performing a TCP connection with the second device, including:

Transmitting, by the first device, the first GRE protocol control signaling to the second interface of the second device by using the first interface, where the first GRE protocol control signaling carries an Internet Protocol IP address of the first interface, Configuring a GRE tunnel between the first interface and the second interface; and causing the second device to record the IP address of the first interface as the TCP between the first interface and the second interface The destination IP address of the connection channel;

Receiving, by the first device, the first GRE protocol control signaling reply signaling sent by the second device by using the second interface, where the first GRE protocol control signaling is carried in the signaling The IP address of the second interface;

The first device records an IP address of the second interface as a destination IP address of a TCP connection channel between the first interface and the second interface.
The method according to claim 1 or 2, wherein, for each TCP connection channel, determining a loopback delay and a packet loss rate of the data packet that are counted within the preset duration according to the TCP connection channel Traffic overflow thresholds, including:

The first device performs separately for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset length of the TCP connection channel are respectively counted. The loopback delay of the data packet and the packet loss rate are used to determine the TCP connection channel. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.
The method of claim 3, wherein determining a traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel comprises:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow threshold corresponding to the TCP connection channel, where 0<X<1;

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, the comparison period is equal to M The preset duration, M is a positive integer.
The method according to claim 3 or 4, wherein the determining the channel capability value of the TCP connection channel according to the statistical data packet loopback delay and the packet loss rate comprises:

Determine the channel capability value of the TCP connection channel according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the data packet transmission congestion window, the MSS indicates the maximum fragmented packet size, P indicates the packet loss rate, and the RTT indicates the data packet ring. Back delay, min means take the minimum value.
The method according to any one of claims 1 to 5, further comprising:

After receiving the data stream, the first device performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is based on the arrival of each data packet. The order is determined.
The method according to claim 6, wherein the first device passes the data flow through the N TCPs according to a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels. Transmitting at least one TCP connection channel in the connection channel to the second device, include:

If the first device establishes two TCP connection channels, confirm that the first TCP connection channel is the default transmission channel;

When the number of the data packets of the data stream reaches the traffic overflow threshold corresponding to the first TCP connection channel, the first device adds an identifier to the head of each data packet of the data stream, where the identifier is The number is used to identify the link corresponding to each TCP connection channel;

The first device sends each data packet to the second device by using a TCP connection channel corresponding to the identifier number in each data packet.
The method according to claim 6, wherein the first device passes the data flow through the N TCPs according to a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels. Sending, to the second device, at least one TCP connection channel in the connection channel, including:

If the first device establishes at least three TCP connection channels, determining a priority of the established TCP connection channel;

The first device adds an identification number to each data packet header according to the priority of each TCP connection channel and the traffic overflow threshold corresponding to each TCP connection channel; the identifier number is used to identify each TCP connection channel. link;

The first device sends each data packet to the second device by using a TCP connection channel corresponding to the identifier number in each data packet.
The method according to claim 7 or 8, wherein the identification number of the added TCP connection channel is located before the data field of each data message.
The method according to any one of claims 1 to 9, wherein the first device is a home gateway HG, and the second device is a converged access aggregation point HAAP.
A flow dynamic control method, comprising:

The second device receives the data stream;

The second device passes the traffic overflow threshold corresponding to the L TCP connection channels in the TCP connection channel of the N transmission control protocols, and passes the data flow through the N TCP connection channels to Sending less than one TCP connection channel to the first device;

The N TCP connection channels are TCP connection channels between the second device and the first device that are established; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each TCP. The connection channel is determined according to the loopback delay and the packet loss rate of the data packet that are counted within the preset duration according to the TCP connection channel; L is a positive integer smaller than N.
The method according to claim 11, wherein for each TCP connection channel, the traffic overflow is determined according to the loopback delay and the packet loss rate of the data packet counted within the preset duration for the TCP connection channel. Thresholds, including:

The second device performs for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset length of the TCP connection channel are respectively counted. The loopback delay of the data packet and the packet loss rate are used to determine the TCP connection channel. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.
The method of claim 12, wherein the traffic overflow threshold corresponding to the TCP connection channel is determined according to the determined channel capability value of the TCP connection channel, including:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow threshold, where 0<X<1;

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, the comparison period is equal to M The preset duration, M is a positive integer.
The method according to claim 12 or 13, wherein the channel capability value of the TCP connection channel is determined according to the statistics data packet loopback delay and the packet loss rate, including:

Determine the channel capability value of the TCP connection channel according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the congestion packet for the data packet, the MSS indicates the size of the largest fragmented packet, and P indicates the lost bandwidth. Packet rate, RTT indicates the loopback delay of the data packet, and min indicates the minimum value.
The method of any of claims 11 to 14, further comprising:

After receiving the data stream, the second device performs TCP encapsulation on each data packet corresponding to the data stream, and adds a sequence number to each data packet header; the sequence number is based on the arrival of each data packet. The order is determined.
The method according to claim 15, wherein the second device passes the data stream through the N TCPs according to a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels. Sending, to the first device, at least one TCP connection channel in the connection channel, including:

If the second device establishes two TCP connection channels, confirm that the first TCP connection channel is the default transmission channel;

When the number of the data packets of the data stream reaches the traffic overflow threshold corresponding to the first TCP connection channel, the second device adds an identifier to the head of each data packet of the data stream, where the identifier is The number is used to identify the link corresponding to each TCP connection channel;

The second device sends each data packet to the first device by using a TCP connection channel corresponding to the identifier number in each data packet.
The method according to claim 15, wherein the second device passes the data stream through at least one of the at least two TCP connection channels according to a traffic overflow threshold corresponding to at least two TCP connection channels. The connection channel is sent to the first device, including:

If the second device establishes at least three TCP connection channels, determining a priority of the established TCP connection channel;

The second device adds an identification number to each data packet header according to a priority of each TCP connection channel and a traffic overflow threshold corresponding to each TCP connection channel; the identifier number is used to identify each TCP connection channel. link;

The second device sends each data packet to the first device by using a TCP connection channel corresponding to the identifier number in each data packet.
A method according to claim 16 or 17, wherein said added TCP connection The identification number of the connected channel is located before the data field of each data packet.
The method according to any one of claims 11 to 18, wherein the first device is a home gateway HG, and the second device is a converged access convergence point.
A flow dynamic control device, comprising:

a receiving module, configured to receive a data stream;

a storage module, configured to store connection information of a transmission control protocol TCP connection of the peer device corresponding to the device where the storage module is located;

a processing module, configured to establish, according to the connection information that the storage module performs a TCP connection with the peer device, establish N TCP connection channels with the peer device, where N is a positive integer greater than or equal to 2;

a sending module, configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels established by the processing module The connection channel is sent to the peer device;

The traffic overflow threshold corresponding to each of the TCP connection channels of the N TCP connection channels is a loopback delay of the data packets that are counted within the preset duration according to the TCP connection channel for each of the TCP connection channels. The packet loss rate is predetermined; L is a positive integer less than N.
The device according to claim 20, wherein the sending module is further configured to encapsulate GRE protocol control signaling by using a first interface to the first universal route sent by the second interface of the peer device, The first GRE protocol control signaling carries the Internet Protocol IP address of the first interface, and the GRE tunnel is configured between the first interface and the second interface, so that the peer device sets the first interface The IP address is recorded as the destination IP address of the TCP connection channel between the first interface and the second interface;

The receiving module is further configured to receive, by using the first interface, a first GRE protocol control signaling reply signaling sent by the peer device by using a second interface, where the first GRE protocol control signaling reply signaling Carrying the IP address of the second interface;

The storage module is configured to store an IP address of the second interface as a destination IP address of the TCP connection channel between the first interface and the second interface.
The device according to claim 20 or 21, wherein said processing module further Used to execute separately for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset length of the TCP connection channel are respectively counted. The loopback delay of the data packet and the packet loss rate are used to determine the TCP connection channel. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.
The device according to claim 22, wherein the processing module is specifically configured to determine the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel. The value of the channel capability of the TCP connection channel is multiplied by the value of X as the traffic overflow threshold, where 0<X<1;

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, the comparison period is equal to M The preset duration, M is a positive integer.
The device according to claim 22 or 23, wherein, when determining the channel capability value of the TCP connection channel according to the statistical data packet loopback delay and the packet loss rate, the processing module is specific Used to determine the channel capability value of the TCP connection channel according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the data packet transmission congestion window, the MSS indicates the maximum fragmented packet size, P indicates the packet loss rate, and the RTT indicates the data packet ring. Back delay, min means take the minimum value.
The device according to any one of claims 20 to 25, wherein the processing module is further configured to perform TCP encapsulation on each data packet corresponding to the data stream after the receiving module receives the data stream. And adding a sequence number in each data packet header; the sequence number is determined according to the order in which the data packets arrive.
The device according to claim 25, wherein said data stream is passed through said N TCP connection channels according to a traffic overflow threshold corresponding to L of said N TCP connection channels Sending at least one TCP connection channel to the peer device, where The management module is specifically used to:

If the established TCP connection channel is two, it is confirmed that the first TCP connection channel is the default transmission channel; when it is determined that the number of data packets of the data flow reaches the traffic overflow threshold corresponding to the first TCP connection channel, Adding an identification number to the header of each data packet of the data stream, where the identifier number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to:

The data packets are sent to the peer device through the TCP connection channel corresponding to the identifier in each data packet.
The device according to claim 25, wherein said data stream is passed through said N TCP connection channels according to a traffic overflow threshold corresponding to L of said N TCP connection channels When the at least one TCP connection channel is sent to the peer device, the processing module is specifically configured to:

If the established TCP connection channel is at least three, the priority of the established TCP connection channel is determined; and each data packet header is determined according to the priority of each TCP connection channel and the traffic overflow threshold corresponding to each TCP connection channel. Add an identification number; the identification number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to send each data packet to the peer device by using a TCP connection channel corresponding to the identifier number in each data packet.
The device according to claim 26 or 27, wherein the processing module adds the identification number of the TCP connection channel before the data field of each data message.
The device according to any one of claims 20 to 28, wherein the device in which the storage module is located is a home gateway HG, and the peer device is a converged access aggregation point HAAP.
A flow dynamic control device, comprising:

a receiving module, configured to receive a data stream;

a sending module, configured to send, according to a traffic overflow threshold corresponding to the L TCP connection channels in the TCP connection channel of the N transmission control protocols, the data flow to the at least one TCP connection channel of the N TCP connection channels The peer device corresponding to the device where the sending module is located;

The N TCP connection channels are TCP connection channels between the established peer device and the device where the sending module is located; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is For each TCP connection channel, according to the TCP connection channel, the loopback delay and the packet loss rate of the data packet are determined in advance according to the preset duration; L is a positive integer smaller than N.
The device of claim 30, further comprising:

Processing module for performing separately for each TCP connection channel:

The loopback delay and the packet loss ratio of the data packet in the preset length of the TCP connection channel are respectively counted. The loopback delay of the data packet and the packet loss rate are used to determine the TCP connection channel. The channel capability value determines the traffic overflow threshold corresponding to the TCP connection channel according to the determined channel capability value of the TCP connection channel.
The device according to claim 31, wherein the traffic overflow threshold corresponding to the TCP connection channel is determined according to the determined channel capability value of the TCP connection channel, and the processing module is specifically configured to:

Multiplying the determined channel capability value of the TCP connection channel by the value of X as the traffic overflow threshold, where 0<X<1;

Comparing the determined channel capability value of the TCP connection channel with the flow overflow threshold determined by the previous comparison period, and adjusting the flow overflow threshold of the current comparison period in the current comparison period according to the obtained comparison result, the comparison period is equal to M The preset duration, M is a positive integer.
The device according to claim 31 or 32, wherein the channel capability value of the TCP connection channel is determined according to the statistical data packet loopback delay and the packet loss rate, and the processing module is specifically used. to:

Determine the channel capability value of the TCP connection channel according to the following formula:

The outbound indicates the channel capability value, the BW indicates the active bandwidth of the connected channel, the CWND indicates the size of the congestion packet for the data packet, the MSS indicates the size of the largest fragmented packet, and P indicates the lost bandwidth. Packet rate, RTT indicates the loopback delay of the data packet, and min indicates the minimum value.
The device according to any one of claims 30 to 33, wherein the processing module is further configured to perform TCP on each data packet corresponding to the data stream after the receiving module receives the data stream. Encapsulating, and adding a serial number in each data packet header; the serial number is determined according to the order in which each data packet arrives.
The device according to claim 34, wherein the data stream is passed through the N TCP connection channels according to a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels. When the at least one TCP connection channel is sent to the peer device, the processing module is specifically configured to:

If the established TCP connection channel is two, it is confirmed that the first TCP connection channel is the default transmission channel; when it is determined that the number of data packets of the data flow reaches the traffic overflow threshold corresponding to the first TCP connection channel, Adding an identification number to the header of each data packet of the data stream, where the identifier number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to:

The data packets are sent to the peer device through the TCP connection channel corresponding to the identifier in each data packet.
The device according to claim 34, wherein the data stream is passed through the N TCP connection channels according to a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels. When the at least one TCP connection channel is sent to the peer device, the processing module is specifically configured to:

If the established TCP connection channel is at least three, the priority of the established TCP connection channel is determined; and each data packet header is determined according to the priority of each TCP connection channel and the traffic overflow threshold corresponding to each TCP connection channel. Add an identification number; the identification number is used to identify a link corresponding to each TCP connection channel;

The sending module is specifically configured to:

The data packets are sent to the peer device through the TCP connection channel corresponding to the identifier in each data packet.
The device according to claim 35 or claim 36, wherein the processing module is specifically configured to add an identification number of the TCP connection channel before the data field of each data packet.
The device according to any one of claims 30 to 37, wherein the device in which the sending module is located is a converged access aggregation point HAAP, and the peer device is a home gateway HG.
A gateway, comprising:

a transceiver, a memory, and a processor;

The transceiver is configured to receive a data stream;

The memory is configured to store connection information that is connected to the convergence access point HAAP for a transmission control protocol TCP connection;

a processor, configured to establish N TCP connection channels with the HAAP according to the connection information that is stored in the memory and perform a TCP connection with the HAAP, where N is a positive integer greater than or equal to 2;

The transceiver is further configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels of the N TCP connection channels stored in the memory a connection channel is sent to the HAAP;

The traffic overflow threshold corresponding to each of the TCP connection channels of the N TCP connection channels is a loopback delay of the data packets that are counted within the preset duration according to the TCP connection channel for each of the TCP connection channels. The packet loss rate is predetermined; L is a positive integer less than N.
A converged access convergence point characterized by comprising:

a transceiver for receiving a data stream;

a memory for storing a traffic overflow threshold corresponding to L TCP connection channels in the N TCP connection channels;

The transceiver is further configured to pass the data flow through at least one of the N TCP connection channels according to a traffic overflow threshold corresponding to the L TCP connection channels in the N TCP connection channels stored in the memory. Sent to the gateway;

The N TCP connection channels are TCP connection channels between the established gateway and the converged access convergence point; the traffic overflow threshold corresponding to each TCP connection channel in the N TCP connection channels is for each The TCP connection channel is respectively based on the TCP connection channel Set the loopback delay and packet loss rate of the data packet in the duration to be predetermined; L is a positive integer less than N.
A computer readable storage medium storing one or more programs, wherein the one or more programs include instructions that, when executed by an electronic device comprising a plurality of applications, cause the electronic device to execute A method according to any one of claims 1 to 9.
A computer readable storage medium storing one or more programs, wherein the one or more programs include instructions that, when executed by an electronic device comprising a plurality of applications, cause the electronic device to execute A method according to any one of claims 11 to 18.