KR102463075B1 - Methods of lossless traffic forwarding using distributed delay offset metching, and apparatuses performing the same - Google Patents

Abstract

Disclosed are a traffic lossless delivery method using distributed delay offset matching and apparatuses for performing the same. A lossless packet forwarding method according to an embodiment includes calculating a delay offset between a first forwarding path and a second forwarding path between a transmitting node and a receiving node, and the delay to delay packets transmitted on the first forwarding path. and controlling the buffer resource by the offset.

Description

Traffic lossless delivery method using distributed delay offset matching and devices for performing the same

The following embodiments are a kind of network protection switching technology, and relate to a lossless transmission method capable of seamlessly transmitting traffic when a failure occurs or is restored in a traffic transmission path.

Recently, in the field of network technology, research and development on an industrial convergence network technology that can accommodate time-sensitive traffic such as general management traffic and real-time remote control traffic at the same time in a single network is in progress. These include Time-Sensitive Networking (TSN) of IEEE 802.1 and Deterministic Networking (DetNet) of IETF.

One of the main functions provided by networking technology is a lossless forwarding function that can seamlessly forward traffic even when a failure occurs or is restored in a traffic forwarding path on a network. This lossless transfer function is defined in IEEE Std 802.1CBTM-2017 FRER (Frame Replication and Elimination for Reliability) in TSN, and is called PREF (Packet Replication and Elimination Function) in DetNet. Their basic operation method is the same as IEC 62439-3 High-availability Seamless Redundancy (HSR) and is as follows.

At least two traffic transmission paths (traffic transmission paths or traffic forwarding paths) are established between the sending node, through which traffic is received (or incoming) to the network, and the receiving node, which outputs (or egresses) traffic out of the network. At this time, the forwarding paths are separated from each other so that they are not disconnected at the same time in the event of a single failure in the network. The transmitting node inserts a sequence number into the packet overhead in the order in which it is received in every packet of traffic and transmits it through a plurality of forwarding paths, and the receiving node checks the sequence numbers of packets received from the plurality of forwarding paths and receives them before Only packets with a sequence number that have never been sent are sent out of the network, and packets that have already been received are determined as duplicate packets and deleted. Through such packet duplication and deletion operations, even if a network failure occurs, packet loss does not occur if at least one of the plurality of forwarding paths is normal.

However, the above technique causes problems because delay times of a plurality of transmission paths established between the transmitting node and the receiving node are different from each other.

Embodiments may provide a distributed delay polarization matching technique for efficiently matching packet delivery delay times of a plurality of delivery paths set for lossless delivery by utilizing buffer resources of network nodes on the delivery path.

In addition, embodiments may provide a technique for controlling/managing the distributed delay polarization matching technique based on Software-Defined Networking (SDN).

A lossless packet forwarding method according to an embodiment includes calculating a delay offset between a first forwarding path and a second forwarding path between a transmitting node and a receiving node, and the delay to delay packets transmitted on the first forwarding path. and controlling the buffer resource by the offset.

The calculating may include calculating a propagation delay time of the first delivery path, calculating a propagation delay time of the second delivery path, and a propagation delay time of the first delivery path and the second delivery path and calculating the delay offset based on a propagation delay time of .

The delay offset may be a propagation delay time difference between the first transfer path and the second transfer path.

The buffer resource may be located in at least one of nodes located on the first transfer path.

The nodes may include intermediate nodes located between the transmitting node and the receiving node and the receiving node.

The controlling may include receiving information on the size of the buffer resource from a node in which the buffer resource is located, and generating delay time information for delaying a packet through the buffer resource based on the size information. can

The controlling may further include transmitting the delay time information to a node in which the buffer resource is located.

The information on the size of the buffer resource may be information on the available size of the buffer resource.

In the generating of the delay time information, when the node in which the buffer resource is located is an intermediate node located between the transmitting node and the receiving node, generating delay time information for the intermediate node as a value in units of a traffic transmission period and, when the node in which the buffer resource is located is the receiving node, generating a difference between the delay offset and the delay time information for the intermediate node as delay time information for the receiving node. .

A control apparatus according to an embodiment includes a communication module communicating with a transmitting node and a receiving node, calculating a delay offset between a first transmission path and a second transmission path between the transmitting node and the receiving node, and the first and a controller controlling the buffer resource by the delay offset in order to delay packets transmitted on the forwarding path.

wherein the controller calculates a propagation delay time of the first delivery path, calculates a propagation delay time of the second delivery path, based on a propagation delay time of the first delivery path and a propagation delay time of the second delivery path Thus, the delay offset can be calculated.

The delay offset may be a propagation delay time difference between the first transfer path and the second transfer path.

The buffer resource may be located in at least one of nodes located on the first transfer path.

The nodes may include intermediate nodes located between the transmitting node and the receiving node and the receiving node.

The controller may receive information on the size of the buffer resource from a node in which the buffer resource is located through the communication module, and generate delay time information for delaying a packet through the buffer resource based on the size information.

The controller may transmit the delay time information to a node in which the buffer resource is located.

The information on the size of the buffer resource may be information on the available size of the buffer resource.

When the node in which the buffer resource is located is an intermediate node located between the transmitting node and the receiving node, the controller generates delay time information for the intermediate node as a value in units of traffic transmission period, and the buffer resource is When the located node is the receiving node, the difference between the delay offset and the delay time information for the intermediate node may be generated as the delay time information for the receiving node.

1 is a diagram for explaining traffic transmission in a network.
FIG. 2 is a diagram for explaining the concept of a traffic lossless transmission method using distributed delay offset matching according to an embodiment.
3 shows a network system using distributed delay offset matching according to an embodiment.
FIG. 4 is a diagram for explaining an example of a traffic lossless transmission method using distributed delay offset matching in the network system shown in FIG. 3 .
5 shows an example implementation of a delay matching buffer.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Terms such as first or second may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one element from another element, for example, without departing from the scope of rights according to the concept of the embodiment, a first element may be named as a second element, and similarly The second component may also be referred to as the first component.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are assigned the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In the description of the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

1 is a diagram for explaining traffic transmission in a network.

In FIG. 1, for convenience of description, it is assumed that two forwarding paths are established between the transmitting node and the receiving node. If two forwarding paths are physically separated from each other so as not to be simultaneously affected by a single failure on the network, the propagation delay time of each forwarding path may be different.

The two delivery paths consist of a first delivery route and a second delivery route. The first transfer path may be a path having a short propagation delay time. The second transfer path may be a path having a long propagation delay time.

In FIG. 1 , if it is assumed that the transmission delay times of the first forwarding path and the second forwarding path differ by the time it takes for 10 packets to be transmitted, the receiving node transmits packets 1 to 11 through the first forwarding path first. is received, and thereafter, packet No. 1 is received through the second forwarding path. As shown in FIG. 1 , the receiving node determines that packets 1 to 16 received through the first forwarding path are valid packets and accepts them, and packets 1 to 5 received through the second forwarding path are regarded as duplicate packets. Delete. If a failure occurs in the first forwarding path immediately after the receiving node receives the 16th packet through the first forwarding path, the receiving node determines that the 17th packet received through the second forwarding path is valid and accepts it. have.

Although the above-described operation is a lossless packet forwarding function, a packet can be transmitted without loss when the first forwarding path fails, but the packet is received by the receiving node for a time corresponding to the difference in the forwarding delay time between the first forwarding path and the second forwarding path. doesn't happen In particular, when the difference in delivery delay time between the first delivery path and the second delivery path is very large, as in a large-scale ring network, the session managed by the two terminal devices connected to the network expires and the connection between the terminal devices is temporarily cut off. can cause

Further, more serious problems may arise when the failure of the first delivery pathway is restored. As shown in FIG. 1 , when the failure of the first forwarding path is recovered immediately after receiving up to the 21st packet from the second forwarding path, the receiving node transmits packets after 32nd from the first forwarding path and 22nd from the second forwarding path. packets are received at the same time. At this time, the receiving node receives packet 32 from the second forwarding path for a certain period of time, that is, until the duplicate packet deletion function operates on both paths (for example, the first forwarding path and the second forwarding path). All packets are accepted as valid packets.

That is, when the first forwarding path is restored from a failure, the order of packets output (or outgoing, forwarded) from the receiving node to the outside of the network is mixed during a time corresponding to the difference in the transmission delay time between the first forwarding path and the second forwarding path. This causes a mis-ordering problem. This problem can be solved by correcting the sequence error at the application end of the terminal device if the terminal device connected to the receiving node has sufficient data processing performance, but low-cost sensors or actuators used in industrial IoT cannot correct the sequence error. It doesn't have that level of processor performance.

In addition, a situation in which packets are simultaneously received from both paths for a predetermined time when the first forwarding path is restored from failure causes a more serious problem in a time-deterministic packet network such as TSN or DetNet. The time-determined packet forwarding function, which guarantees the maximum packet forwarding delay time to be less than or equal to a specified value, can operate normally only when the traffic input to the network node follows a predetermined protocol. However, if the receiving node accepts all packets received from both paths and outputs them out of the network, traffic increases twice as much as the protocol for a certain period of time. type packet forwarding function itself becomes impossible.

Hereinafter, descriptions of the embodiments are based on a Time Sensitive Network (TSN), which is an Ethernet-based time-deterministic packet network, for convenience of description, and a packet delivery delay time for lossless delivery. It is assumed that different first and second transfer paths are set. Although the delivery delay time of each delivery path may be variously different, for convenience of description, it is assumed that the delivery delay deviation between the first delivery path and the second delivery path exists as much as the time it takes to deliver 10 packets.

Embodiments are TSN's FRER (Frame Replication and Elimination for Reliability), DetNet, which replicates a packet at a transmitting node, transmits it through two or more multiple forwarding paths, and deletes duplicate packets through sequence number verification at a receiving node. It is applicable to all kinds of lossless transfer technology such as PREF (Packet Replication and Elimination Function) or PREOF (Packet Replication, Elimination, and Ordering Function).

In addition, the embodiments may be applicable not only to packet networks but also to the case of implementing lossless transmission techniques based on frame duplication and deletion in circuit transport networks such as Synchronous Digital Hierarchy (SDH) and Optical Transport Network (OTN).

FIG. 2 is a diagram for explaining the concept of a traffic lossless transmission method using distributed delay offset matching according to an embodiment.

The traffic lossless delivery method may use a delay matching buffer. The delay matching buffer may be located on the first transfer path. Also, the delay matching buffer may be located in the receiving node of the first forwarding path. That is, the delay matching buffer may be implemented at any point in the first transfer path.

The delay matching buffer may buffer a packet transmitted through the first transmission path by a delay offset. A delay offset may refer to a delay variation. For example, the delay offset may mean a delay variation and may be a difference in propagation delay time between the first propagation path and the second propagation path. That is, the delay matching buffer may store the packet by the difference in the transfer delay time between the first transfer path and the second transfer path and then transfer the packet.

For example, as shown in FIG. 2, the delay matching buffer applies a timer to the traffic received through the first forwarding path to delay packets by a delay offset (where the delay offset is the time required to receive 10 packets). It can be saved and then forwarded. Through this, the block for the duplicate packet deletion function of the receiving node can always receive packets having the same sequence number from the first forwarding path and the second forwarding path.

The delay matching buffer may offset a delay deviation between the first transmission path and the second transmission path by buffering and forwarding packets as much as a delay offset on the first transmission path. As shown in FIG. 2 , if the delivery delay times of the first delivery path and the second delivery path match, packets with the same sequence number are always continuously received from the first delivery path and the second delivery path, so that a path failure may occur or be restored. When the above problems can be solved.

The method using the above-described delay matching buffer may delay the transfer delay time of the first transfer path by the second transfer path. Terminal device applications that require lossless transfer characteristics, such as real-time remote control, implement a control program based on the transfer delay time of the second transfer path in consideration of the worst-case packet transfer delay time, so the delay on the first transfer path is not a problem

The delay matching buffer may be implemented in the receiving node, but the delay matching buffer may be implemented in one or more nodes on the first forwarding path, and it is possible to efficiently compensate for the delay deviation by utilizing buffer resources provided by each node. A method in which the delay matching buffer is distributed to each node on the first transmission path to match the delay deviation may be referred to as a distributed delay deviation matching method. Considering that the delay matching buffer can be positioned anywhere on the network, it can be more cost effective than correcting all delay deviations at the receiving node.

The distributed delay deviation matching method can efficiently compensate for the delay deviation by utilizing buffer resources that can be provided by each node on the first delivery path including the receiving node. The distributed delay deviation matching method may be controlled/managed by a centralized control/management device such as an SDN controller.

3 shows a network system using distributed delay offset matching according to an embodiment.

The network system 300 may include a control device 310 , a transmitting node 320 , a receiving node 330 , and intermediate nodes 340 and 350 . The intermediate nodes 340 are nodes located in the first forwarding path, and the intermediate nodes 350 are nodes located in the second forwarding path. The delay matching buffer 360 may be located in at least one of the intermediate nodes 340 on the first forwarding path and/or in the receiving node 330 .

The control device 310 may be an SDN controller for controlling the overall operation of the network system 300 . The control device 310 may control distributed delay offset matching using the delay matching buffer 360 . The control device 310 may include a controller 313 and a communication module 315 . The controller 313 may communicate with each node 320 to 350 through the communication module 315 .

A series of packets that require (or request, guarantee) lossless delivery (or lossless delivery function) may be defined as a flow. The controller 313 collects node information and link information from the intermediate nodes 340 and 350 constituting the first delivery path and the second delivery path for each flow, and based on the collected node information and link information, two routes We can calculate the propagation delay offset of .

The propagation delay time may be calculated as the sum of the node delay times and all link delay times on the propagation path between the transmitting node 320 and the receiving node 330 .

Link latency may be proportional to the physical length of the link. For example, in the case of a typical optical cable, there is a delay of about 5 μs per 1 km. Link delay time can be calculated by measuring the cable length, or it can be measured using a separate delay time measurement method at both nodes connected to the link.

The node delay time may vary depending on the packet processing operation characteristic of the node. For example, in the case of a bridge system defined by TSN, the node delay time may be calculated as the sum of dependent delay x the packet size of time-sensitive traffic and independent delay. Here, the dependent delay is the time it takes for one packet to be stored in the memory in the node and then delivered to the output queue, and the time it takes for one packet received as a serial bit string through the input port to be stored in the memory is It can be determined by link speed and packet size. In addition, the non-dependent delay is a delay time independent of the packet length, and may mean a time required for packet processing such as packet overhead lookup and forwarding decision within a node.

If the node uses IEEE Std 802.1QbvTM-2015 TAS (Time-Aware Shaper) or IEEE Std 802.1QchTM-2017 CQF (Cyclic Queuing and Forwarding), which are time-determined packet forwarding methods defined in TSN, different from the above In this way, the propagation delay time of the path can be calculated. Since the above-described methods perform the operation of opening or closing the gate in units of the traffic transmission cycle for each traffic class queue at the output port, the node propagation delay time at one node on the path is equal to the delay time from the sending node to the node and the gate opening time. It may be changed in units of traffic transmission period due to the difference in time points.

The propagation delay time of the path in the above-described methods is determined by the flow attribute (traffic transmission period, the number of packets per transmission period, the maximum packet size) in the controller 313, the number of intermediate nodes on the path, the link delay time, and the number of nodes used by each node. It may be calculated using information such as a packet forwarding method.

The controller 313 may calculate a delay offset based on a propagation delay time of the first delivery path and a propagation delay time of the second delivery path. The controller 313 may control the delay matching buffer 360 on the first forwarding path based on the delay offset, thereby delaying packets transmitted on the first forwarding path by the delay offset.

The controller 313 may control the delay matching buffer 360 using the following parameters.

- B(k): the size of the delay matching buffer 360 that the node k can provide for delay offset matching (information provided by the node k to the control device 310)

Corresponding parameter information may be included in node information and transmitted to the controller 313 .

- Delay(k,i): delay time of a packet belonging to flow i in the delay matching buffer 360 of node k (information provided by the control device 310 to node k)

The corresponding parameter information may be included in the control signal of the controller 313 and transmitted to the node k.

As described above, the controller 313 distributes and delays packets by appropriately using the delay matching buffer 360 in consideration of the packet forwarding method in the intermediate nodes 340 and the receiving node 330 on the first forwarding path. The delivery delay times of the first delivery path and the second delivery path may be matched.

FIG. 4 is a diagram for explaining an example of a traffic lossless transmission method using distributed delay offset matching in the network system shown in FIG. 3 .

In FIG. 4 , the control device 310 , the transmitting node 320 , the receiving node 330 , and the intermediate nodes 340 on the first forwarding path are properties of flow i, for example, traffic transmission period, packet per transmission period. It is assumed that the number and maximum packet size are known.

The control device 310 may calculate a delivery delay time of the first delivery path. The control device 310 may calculate a propagation delay time of the second transfer path. The control device 310 may calculate a delay offset Delay based on a propagation delay time of the first delivery path and a propagation delay time of the second delivery path. The control device 310 may perform distributed delay offset matching based on the delay offset as follows.

First, the intermediate nodes 340 and the receiving node 330 on the first transmission path may transmit size information B(k) of the available delay matching buffer 360 to the control device 310 . The control device 310 may convert the value of the size information B(k) into a delay time value in consideration of the attribute of the flow i. For example, if B(k) = 640Byte and the property of flow i is stipulated to transmit one 64 byte packet per 100 μs of traffic transmission period, the converted delay time becomes 640 Byte/64 Byte x 100 μs = 1,000 μs. The control device 310 transmits the delay time information (Delay(k,i)) for the flow i within the delay time range that each node 330 and 340 can provide to each node 330 and 340 by the following rule. 340) can be provided.

Delay(k,i) of intermediate node = value in unit of traffic transmission period

(Receiving node's Delay(k,i) = ΔDelay - ∑Intermediate node's Delay(k,i)

When buffering is performed at the intermediate nodes 340 and the receiving node 330 on the first delivery path in the above-described manner, the propagation delay time of the first delivery path coincides with the propagation delay time of the second delivery path.

The reason that the intermediate node 340 delays the packet in units of the traffic transmission period is that even if the delay matching buffer 360 delays the packet by an arbitrary value, the output port using the time-confirmed packet forwarding method is transmitted in units of the traffic transmission period. This is because the node propagation delay time may be different from the value specified by the control device 310 because the gate is controlled.

In FIG. 4, as an operation example of the distributed delay deviation matching method for flow i, which transmits one 64-byte packet every 100 μs, there are five intermediate nodes 340 on the first transmission path, and the intermediate nodes 340 are It is assumed that the receiving node 330 has an available delay matching buffer 360 of 1,280 bytes and that the difference in the transmission delay time between the first transmission path and the second transmission path is 1,050 μs.

Each of the nodes 330 and 340 reports a B(k) parameter value of 1,280 to the control device 310 . The control device 310 converts the B(k) parameter value into a delay time for flow i, so that each node 330 and 340 can know that a delay of 2,000 μs (1,280 Byte/64 Byte x 100 μs) is possible. In order to compensate for the delay offset between the first transmission path and the second transmission path by 1,050 μs, the control device 310 performs various distribution methods between the intermediate nodes 340 and the receiving node 330 under the condition that satisfies the above-mentioned rule. delay time can be set.

In FIG. 4 , the control device 310 provides, as a Delay (k,i) parameter, 200 μs, which is a delay time corresponding to twice the traffic transmission period, to all intermediate nodes 340 , and the remaining 50 μs to the receiving node 330 . is provided as a Delay(k,i) parameter to match the propagation delay times of the first propagation path and the second propagation path s.

5 shows an example implementation of a delay matching buffer.

The delay matching buffer 360 may be configured in various forms depending on implementation. For example, in the bridge function model defined in IEEE 802.1, the function of the delay matching buffer 360 may be located between the stream filter performing the flow classification function and the stream gate responsible for the queuing function as shown in FIG. 5 .

As described above, in a network that requires lossless delivery of traffic, the delay times of different delivery paths are distributed through SDN-based centralized control/management and matched appropriately through buffering to each node. This can solve the problems in which packet delivery is interrupted or when the route is restored, the delivery order is temporarily changed, and packets are delivered twice as high as the set protocol.

Accordingly, the embodiments may provide a remarkably stable lossless transmission function, enable more efficient network resource utilization, and enable lossless transmission of citizen traffic.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (18)

A lossless packet transmission method of a control device, comprising:
calculating, by the control device, a delay offset between a first forwarding path and a second forwarding path between a transmitting node and a receiving node; and
controlling, by the control device, a buffer resource by the delay offset to delay packets transmitted on the first forwarding path;
including,
The controlling step is
receiving information on the size of the buffer resource from a node in which the buffer resource is located; and
generating delay time information for delaying a packet through the buffer resource based on the size information
Including, lossless packet delivery method.
According to claim 1,
The calculating step is
calculating a propagation delay time of the first propagation path;
calculating a propagation delay time of the second propagation path; and
calculating the delay offset based on a propagation delay time of the first propagation path and a propagation delay time of the second propagation path;
A lossless packet delivery method comprising a.
According to claim 1,
The delay offset is
A lossless packet delivery method that is a difference in delivery delay time between the first delivery path and the second delivery path.
According to claim 1,
The buffer resource is
A lossless packet forwarding method located in at least one of the nodes located on the first forwarding path.
5. The method of claim 4,
The nodes are
and intermediate nodes located between the transmitting node and the receiving node and the receiving node.
delete According to claim 1,
The controlling step is
Transmitting the delay time information to a node in which the buffer resource is located
A lossless packet forwarding method further comprising a.
According to claim 1,
The size information of the buffer resource,
A lossless packet delivery method which is information on the available size of the buffer resource.
According to claim 1,
The step of generating the delay time information comprises:
generating delay time information on the intermediate node as a value in units of a traffic transmission period when the node in which the buffer resource is located is an intermediate node located between the transmitting node and the receiving node; and
When the node in which the buffer resource is located is the receiving node, generating a difference between the delay offset and the delay time information for the intermediate node as delay time information for the receiving node
A lossless packet delivery method comprising a.
a communication module for performing communication with the transmitting node and the receiving node; and
A controller for calculating a delay offset between a first forwarding path and a second forwarding path between the transmitting node and the receiving node, and controlling a buffer resource by the delay offset to delay packets transmitted on the first forwarding path
including,
The controller is
Receives size information of the buffer resource from a node in which the buffer resource is located through the communication module, and generates delay time information for delaying a packet through the buffer resource based on the size information.
11. The method of claim 10,
The controller is
calculate a propagation delay time of the first delivery path, calculate a propagation delay time of the second delivery path, and calculate the delay based on a propagation delay time of the first delivery path and a propagation delay time of the second delivery path A control unit that calculates the offset.
11. The method of claim 10,
The delay offset is
a control device that is a difference in propagation delay time between the first transfer path and the second transfer path.
11. The method of claim 10,
The buffer resource is
A control device located in at least one of the nodes located on the first forwarding path.
14. The method of claim 13,
The nodes are
and intermediate nodes located between the transmitting node and the receiving node and the receiving node.
delete 11. The method of claim 10,
The controller is
A control device for transmitting the delay time information to a node in which the buffer resource is located.
11. The method of claim 10,
The size information of the buffer resource,
A control device that is information on the available size of the buffer resource.
11. The method of claim 10,
The controller is
When the node in which the buffer resource is located is an intermediate node located between the transmitting node and the receiving node, generating delay time information for the intermediate node as a value in units of traffic transmission period,
When the node in which the buffer resource is located is the receiving node, a control apparatus for generating a difference between the delay offset and delay time information for the intermediate node as delay time information for the receiving node.

Images