JPH09181768A - Cell abort method in exchange node - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent an exchange node from being reduced in throughput by suppressing packets or cells transferred in waste to be a prescribed ratio or below so as to reduce invalid processing in the network. SOLUTION: A measurement device 2, a timer 7, a counter 5 are used to measure a ratio (fault ratio) of packets or cells transferred in waste for each unit time, and when the fault rate is larger than a predetermined threshold level, a threshold level decision device 6 decreases a threshold level of a buffer and when the fault rate is smaller than a predetermined threshold level, the threshold level decision device 6 increases the threshold level of the buffer. Thus, the threshold level is changed to a proper value and packets or cells transferred in waste are suppressed to be a prescribed ratio and invalid processing in the network is reduced to prevent throughput reduction of a node.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a cell discarding method at the time of congestion of a switching node constituting a data communication network, and more particularly to a cell discarding method capable of suppressing a decrease in throughput of the switching node.

[0002]

2. Description of the Related Art ATM (Asynchronous Transfer Mod)
e) A communication network is a high-speed packet switching in a broad sense. Instead of variable-length packets, data is divided into fixed-length cells and transferred in cell units. Is a promising communication network in the multimedia society of. In a cell transfer type data communication network based on such cell transfer, information indicating that the own cell is the last cell of the packet is written in advance in the last cell forming each packet, and the switching node The last cell is detected based on this information, and the break of each packet of the cell stream transferred by this is recognized. Also, the switching node has a buffer, and a plurality of cells to be transferred are temporarily stored in this buffer. However, when the switching node is congested, there are cells that cannot be stored in the buffer (overflow) because the buffer becomes full of cells. Cells overflowing such a buffer will be discarded.

FIG. 1 is a diagram for explaining how some cells are discarded when a plurality of packets disassembled into cells are transferred. In the figure, 11 is a transmitting terminal,
Reference numeral 12 is a receiving terminal, and from the transmitting terminal 11 to the receiving terminal 12
Consider that the packets A to D are transferred in this order. Each of the packets A to D is composed of a plurality of cells. All cells of packet A are transferred normally,
After that, the cell b forming the packet B is discarded due to overflow of the buffer. In this case, the discarded cell b among the cells forming the packet B
All cells transferred before (invalid cell a in FIG. 1) and discarded cells b (invalid cell c in FIG. 1) are invalid cells.

Conventionally, a method using an error correction coding technique is known as a data restoration method on the receiving side when an error occurs in a part of transfer data. However, this method is expensive because it requires an additional circuit such as a circuit for decoding an error correction code and a circuit for recovering an error, and it requires a certain condition (recovery) to enable error correction. There is a problem such as that there is a limit on the ratio of the amount of data that has an error to the amount of data that can be correctly received) and that an extra redundant code must be sent. The resending method of resending is generally widely adopted.

When such a resending method is applied to a communication network in which an incomplete packet (incomplete packet) in which some cells constituting the packet are lost due to discarding or the like is directly transferred, Eventually, all cells forming a complete packet will be retransmitted later, and therefore cells forming an incomplete packet transferred previously will be wastefully transferred. That is, in the case of FIG. 1, the cell transferred before the discarded cell b (invalid cell a) and the cell transferred after the discarded cell (invalid cell c) are the same as those at the time of the first transfer. This means that the transfer is performed twice at the retransmission transfer. As a result, the throughput of effective packets is reduced. Therefore, in order to improve the throughput by minimizing the cells that are wastefully transferred,
In addition to the discarded cells (corresponding to b in FIG. 1), it is also considered to discard other cells in the packet forming the discarded cells.

Generally, it is possible to identify a cell group forming one packet by reading the information (packet configuration information) written in the cell. For example,
In AAL3 / 4 in the ATM network, ST (segment type) is written in each cell for each packet, and the switching node can identify the cell group forming one packet by reading this ST. Further, in the AAL5 in the ATM network, the cell group forming one packet can be identified by reading the payload type indication written in the last cell of the cell group forming one packet. Therefore, even if each of the plurality of packets is divided into a plurality of cell groups and the plurality of cell groups are transferred in a timely manner, it is possible to identify which cell group the packet belongs to.

[0007] When such packet configuration information is written in a cell, a method for discarding another cell constituting a packet including the discarded cell in response to cell discard performed at the time of congestion As a conventional, Partial
Two methods have been proposed, called the Pocket Discard and the Early Pocket Discard.

The former method called Partial Packet Discard is such that when a buffer provided in the switching node overflows and a cell is discarded, all subsequent cells forming the same packet are not taken into the buffer. It is a method of discarding. The latter Early Pa
The method called cket Discard is such that a threshold for storing cells is predetermined in the buffer of the switching node, and when the number of cells stored in the buffer exceeds the predetermined threshold, the next packet In this method, the buffer is expected to overflow and the cells will be discarded. Then, when the cell at the beginning of the packet arrives, all cells constituting the packet are discarded without being taken into the buffer. That is, this method accepts the packet when the cell located at the head of the packet arrives and configures the packet only when the number of cells in the buffer of the switching node is below the predetermined threshold value. The subsequent cells are taken into the buffer. According to these methods, when a cell discard due to a buffer overflow (Partial Packet Discard) or a cell discard (Early Packet Discard) is expected, a cell forming a single packet including the cell is actively discarded. , It is possible to prevent the cells of other packets from being discarded.

[0009]

However, in the above-mentioned method called "Partial Packet Discard", cells are discarded at the switching node. Therefore, even if cells of a certain packet are determined to be discarded, the packet is determined to be discarded. The cells accepted by the time of transfer will be transferred in the network as incomplete packets, resulting in useless cell transfer for the entire network. Further, the cells of these incomplete packets wastefully use the buffer of the switching node, so that the throughput of the switching node decreases as the load increases.

Further, in the method called Early Packet Discard, cells are discarded in the switching node, and the threshold value of the buffer for deciding whether or not to discard cells is fixed in advance, so that the buffer overflows. Even if it is decided that the next packet will be accepted once, the buffer of the exchange node will overflow unexpectedly and the cell will be discarded if the load becomes high in the middle. Can occur (this happens when multiple packets are accepted in parallel at the same time). As a result, incomplete packets are transmitted in the network,
Useless cell transfer is performed for the entire network. In addition, the cells of these incomplete packets wastefully use the buffer of the switching node, so that the throughput of the switching node further decreases as the load increases.

This is because the threshold value of the buffer in the Early Packet Discard differs in an appropriate value depending on the number of cells constituting a packet as a traffic condition, the input speed, and the size of the load. Without taking this into account, the buffer threshold is fixed in advance,
And because it is fixed. The purpose of the present invention is to
By changing the threshold value of the buffer in the Packet Discard, the number of packets and cells transferred in vain as described above is suppressed below a certain ratio, and the invalid processing in the network is reduced.
This prevents the throughput of the switching node from decreasing.

[0012]

According to the present invention, in order to achieve the above object, the threshold value of a buffer of a switching node is made small when there are many unnecessary transfers and made large when there are few unnecessary transfers. By doing so, it is possible to suppress the decrease in throughput of the exchange node as much as possible. More specifically, (1) a threshold B is set in the buffer in the switching node, and when the cell storage amount of the buffer exceeds the threshold B of the buffer, the first cell of the newly arrived packet is accepted and A packet to which a cell belongs is identified, and all cells of the identified packet are discarded, so-called E
In the cell discard method called arly Packet Discard, measure the total number of packets Hp (the number of incomplete packets) Hp and the number of packets that were received (the number of incomplete packets) Hp, but the cells that make up the packets were discarded due to buffer overflow Then, at every unit time, failure rate =
Hp / Ap is calculated, and the failure rate and a predetermined threshold S
And the threshold value B of the buffer is decreased when the failure rate> the threshold value S, and the threshold value B of the buffer is increased when the failure rate <the threshold value S (first embodiment).

(2) A threshold B is set in the buffer in the switching node, and the cell storage amount of the buffer is the threshold B of the buffer.
If it exceeds, the first cell of the newly arrived packet is accepted and the packet to which the cell belongs is identified,
In a cell discarding method called so-called Early Packet Discard, in which all cells of the identified packet are discarded, the total number of cells that constitute the accepted packet but are discarded due to buffer overflow (incomplete cell Number) Hc and the total number of cells in the received packet (the number of received cells) Ac are measured, the failure rate = Hc / Ac is calculated for each unit time, and the failure rate is compared with a predetermined threshold value S. When the failure rate> threshold value S, the buffer threshold value B is decreased, and when the failure rate <threshold value S, the buffer threshold value B is increased (second embodiment).

(3) The threshold B is set in the buffer in the switching node, and the cell storage amount of the buffer is the threshold B of the buffer.
If it exceeds, the first cell of the newly arrived packet is accepted and the packet to which the cell belongs is identified,
In a cell discarding method called so-called Early Packet Discard, which discards all cells of the identified packet, the total number of packets Hp and the number of accepted packets in which cells constituting the packet are discarded due to buffer overflow The total Ap is measured, and every time the total number of received packets reaches a predetermined threshold Apo, the total number of packets Hp in which cells constituting the packet are discarded due to buffer overflow of the received packets is compared with a predetermined threshold Sp. Then, when Hp> threshold value Sp, the buffer threshold value B is decreased, and when Hp <threshold value Sp, the buffer threshold value B is increased (third embodiment).

(4) The threshold B is set in the buffer in the switching node, and the cell storage amount of the buffer is the threshold B of the buffer.
If it exceeds, the first cell of the newly arrived packet is accepted and the packet to which the cell belongs is identified,
In a cell discarding method called so-called Early Packet Discard, in which all cells of the identified packet are discarded, the total number of cells Hc that have been discarded due to a buffer overflow even though they are cells constituting the received packet are accepted. Total number of cells in a packet
Every time the total number of cells of the received packet reaches a predetermined value Aco, the total number of cells Hc that are cells constituting the received packet but are discarded due to buffer overflow is determined in advance. Compared with the threshold Sc, when Hc> threshold Sc, the buffer threshold B is reduced, and when Hc <threshold Sc, the buffer threshold B.
Is increased (fourth embodiment).

[0016]

BEST MODE FOR CARRYING OUT THE INVENTION In the present invention, the number of packets arriving at a buffer, the number of cells, the number of packets including discarded cells,
By counting the number of discarded cells, the ratio of packets and cells that are transferred in vain (failure rate) is calculated for each unit of time, and if the failure rate is greater than a predetermined threshold, the buffer threshold is set. If the failure rate is smaller than the predetermined threshold value, the buffer threshold value is increased. As a result, the threshold can be changed to an appropriate value, packets and cells that are wastefully transferred can be suppressed to a certain ratio or less, and invalid processing in the network can be reduced to prevent a decrease in node throughput. be able to. In addition, the number of cells that make up the packet as traffic conditions,
Even if the input speed and the magnitude of the load change, the buffer threshold value can be changed according to those changes.

[0017]

【Example】

(First Embodiment) An embodiment of the cell discarding method of the present invention will be described. In an ATM network, a virtual channel (Virtual Channel: hereinafter simply referred to as VC) is assigned to data communication between terminals to perform communication, and a cell flow of each VC is measured at a switching node. FIG. 2 shows a selected cell discarding device. In the figure, 1 is a cell input device, 2 is a measuring device, 3 is a buffer, 4 is a cell sending device, 5 is a counter,
6 is a threshold value determination device, and 7 is a timer.

The cell input device 1 is a device that receives an input cell from each terminal to the selected cell discard device. The measuring device 2 is a device that detects a packet and a cell received by the buffer 3. In the buffer 3, when the number of cells stored in the buffer 3 is larger than the threshold value B, when a new cell located at the head of the packet arrives, all cells of the packet including the head cell are discarded. Then
The packet is not taken into the buffer 3.
If the number of cells in the buffer 3 is smaller than the threshold value B, the packet is accepted, the cells constituting the packet are held in the buffer 3 until transferred to the cell transmission device 4, and the cell transfer device 4 receives the cells. Transfer one cell at a time. The cell transmission device 4 transfers the cell to the outside of the switching node. Generally, a packet is divided into a plurality of cells and transferred, and in order to discard only a specific packet cell, it is necessary to identify which packet cell that cell is. This must be done by the information (packet configuration information) written in the cell described above.

The counter 5 receives the number of received packets (the number of received packets), the number of incomplete packets in which the cells were discarded but cell discard due to buffer overflow (the number of incomplete packets), and the number of cells of the received packets (the number of received cells) ), The number of cells (the number of incomplete cells) that constitute an incomplete packet in which cell discard has occurred due to buffer overflow of the received packet is counted. Also, the timer 7
The counter 5 is notified of the timing at which the threshold value is changed at regular time intervals (unit time).

The first embodiment of the cell discarding method of the present invention is as follows:
The number of packets received by the switching node (the number of received packets) and the number of incomplete packets in which some cells were discarded (the number of incomplete packets) are counted, and the buffer threshold is calculated based on these values at regular intervals. Is to be updated. FIG. 3 is a flowchart showing the operation of the first embodiment of the present invention. The operation of the first embodiment will be described in detail below with reference to FIG. Step 31: The measuring device 2 detects the received packet and the incomplete packet, and notifies the counter 5 of them.

Step 32: The counter 5 is the measuring device 2
The received packet number counter or the incomplete packet number counter is incremented by +1 depending on whether the notification from is related to the accepted packet or the incomplete packet. Step 33: The timer 7 notifies the counter 5 of the timing at which the threshold value is changed at regular time intervals (unit time). Step 34: When the counter 5 receives the notification from the timer 7 in a certain time period, the value of the received packet number counter (the number of received packets) and the value of the incomplete packet number counter (the number of incomplete packets) are sent to the threshold value determination device 6. ) Is notified, each counter value is set to 0 (reset).

Step 35: When the threshold value determination device 6 receives the notification from the counter 5, it calculates the failure rate = the number of incomplete packets / the number of accepted packets, and the failure rate fails with respect to a predetermined threshold value S. When the rate <S, B: = min {K, B + N} When the failure rate> S, the buffer threshold B is updated as B: = max {0, BN}. That is, when the failure rate is smaller than the predetermined threshold value S, the smaller value of K and B + N is set as the buffer threshold value B, and when the failure rate is larger than the predetermined threshold value S, 0 and BN. The larger value of is set as the threshold value B of the buffer. However, K is a buffer size, and is represented by the number of cells that can be stored, for example, N
Is a predetermined value and represents the step of updating the threshold value of the buffer.

(Second Embodiment) Next, a second embodiment of the present invention will be described. The second embodiment of the present invention is also the above-mentioned first embodiment.
The selected cell discarding device shown in FIG. 2 is used as in the embodiment of FIG. The difference from the first embodiment is that the counter 5 counts cells instead of packets. That is, the number of cells forming the received packet and the number of cells forming the incomplete packet are counted, and the threshold value of the buffer 3 is updated based on these values at regular intervals. FIG. 4 is a flowchart showing the operation of the second embodiment of the present invention. The operation of the second embodiment will be described in detail below with reference to FIG. Step 41: The measuring apparatus 2 detects the cells that form the acceptance packet and the cells that form the incomplete packet, and notifies the counter 5 of them.

Step 42: The counter 5 is the measuring device 2
The received cell number counter or the incomplete cell number counter is incremented by +1 depending on whether the notification from is related to the cell forming the received packet or the cell forming the incomplete packet. Step 43: The timer 7 notifies the counter 5 of the timing at which the threshold value is changed at regular time intervals. Step 44: Upon receiving the notification from the timer 7, the counter 5 notifies the threshold value determining device 6 of the value of the accepted cell number counter (the number of accepted cells) and the value of the incomplete cell number counter (the number of incomplete cells). And set each counter value to 0
Enable (reset).

Step 45: When the threshold value determination device 6 receives the notification from the counter 5, it calculates the failure rate = the number of incomplete cells / the number of accepted cells, and the failure rate fails with respect to a predetermined threshold value S. When the rate <S, B: = min {K, B + N} When the failure rate> S, the buffer threshold B is updated as B: = max {0, BN}. That is, like the first embodiment, when the failure rate is smaller than the predetermined threshold S, the smaller value of K and B + N is set as the buffer threshold B, and the failure rate is lower than the predetermined threshold S. When it is larger, the larger value of 0 and BN is set as the threshold value B of the buffer. However, K is a buffer size, for example, is represented by the number of cells that can be stored, N is a predetermined value, and represents a step of updating the threshold value of the buffer.

(Third Embodiment) Next, a third embodiment of the present invention will be described. FIG. 5 is a configuration diagram of a selected cell discarding device for carrying out the third embodiment of the present invention. In the figure, 1 is a cell input device, 2 is a measuring device, 3 is a buffer,
Reference numeral 4 is a cell transmission device, 5 is a counter, and 6 is a threshold value determination device. 5 is different from FIG. 3 (first and second embodiments) in that
It has no timer. Therefore, the number of received packets is set to a predetermined value by updating the threshold value of the buffer every fixed period (every unit time), which is performed in the first and second embodiments. The threshold of the buffer is updated when it becomes.

Next, a third embodiment of the present invention will be described.
In the third embodiment, the number of accepted packets and the number of incomplete packets in which some cells are discarded are counted by the counter 5,
The number of incomplete packets at the time when the number of received packets reaches a predetermined value is obtained, and the threshold value of the buffer is updated by the value. The cell discarding method of the third embodiment will be described in more detail with reference to the flowchart of FIG. Step 61: The measuring device 2 detects the received packet and the incomplete packet and notifies the counter 5 of the received packet and the incomplete packet.

Step 62: The counter 5 is the measuring device 2
The received packet number counter or the incomplete packet number counter is incremented by +1 depending on whether the notification from is related to the accepted packet or the incomplete packet. Step 63: When the value of the accepted packet number counter (accepted packet number) reaches a predetermined value Apo, the counter 5 notifies the threshold value determination device 6 of the incomplete packet number, and sets the respective counter values. Set to 0.

Step 64: When the threshold value determining device 6 receives the notification from the counter 5, the value of the incomplete packet number counter (the number of incomplete packets) is smaller than the predetermined threshold value Sp, and the incomplete packet number < When Sp, B: = min {K, B + N} When the number of incomplete packets> Sp, B: = max {0, BN} and the buffer threshold B is updated. That is, when the number of incomplete packets is smaller than the predetermined threshold Sp,
The smaller value of K and B + N is set as the buffer threshold B, and when the number of incomplete packets is larger than the predetermined threshold Sp, the larger value of 0 and B−N is set as the buffer threshold B. However, K is a buffer size, for example, is represented by the number of cells that can be stored, N is a predetermined value,
The step of updating the threshold value of the buffer is shown.

(Fourth Embodiment) Next, a fourth embodiment of the present invention will be described. The fourth embodiment of the present invention is also the above-mentioned third embodiment.
The selected cell discarding device shown in FIG. 5 is used as in the embodiment of FIG. The difference from the third embodiment is that the counting target is a cell instead of the number of packets. That is,
Instead of measuring every fixed period (every unit time) as in the first and second embodiments, the number of cells forming the acceptance packet (the number of acceptance cells) and the number of cells discarded Count the number of cells that make up a complete packet (the number of incomplete cells), find the number of incomplete cells when the number of received cells reaches a predetermined value, and update the buffer threshold with that value. It is the one.

The cell discarding method of the fourth embodiment will be described in more detail with reference to the flowchart of FIG. Step 71: The measuring apparatus 2 detects the cells that form the acceptance packet and the cells that form the incomplete packet, and notifies the counter 5 of them. Step 72: The counter 5 increments the acceptance cell number counter or the incomplete cell number counter by +1 depending on whether the notification from the measuring device 2 is about the cell forming the acceptance packet or the cell forming the incomplete packet.
I do. Step 73: When the value of the acceptance cell number counter reaches the predetermined value Aco, the counter 5 notifies the threshold value determining device 6 of the incomplete cell number and sets each counter value to 0.

Step 74: When the threshold value determining device 6 receives the notification from the counter 5, the value of the incomplete cell number counter (the number of incomplete cells) is smaller than the predetermined threshold value Sc by the incomplete cell number < When Sc, B: = min {K, B + N} When the number of incomplete cells> Sc, the buffer threshold B is updated as B: = max {0, BN}. That is, when the number of incomplete cells is smaller than the predetermined threshold Sc, the smaller value of K and B + N is set as the buffer threshold B, and when the number of incomplete cells is larger than the predetermined threshold Sc, 0
The larger value of B and N is set as the buffer threshold value B. However, K is a buffer size, for example, is represented by the number of cells that can be stored, N is a predetermined value, and represents a step of updating the threshold value of the buffer.

The third and fourth embodiments are simpler methods because neither a timer nor calculation of failure rate is required. Obviously, the timer is no longer needed in the third and fourth embodiments. Although the calculation of the failure rate involves division, in the third embodiment, the total number of received packets Ap corresponding to the denominator of the failure rate is a constant (predetermined constant Ap.
o), no division is needed. In the fourth embodiment, the total number of cells Ac of the received packets, which is the denominator of the failure rate, is a constant (a predetermined constant Apo), so that division is not necessary. By eliminating the need for these timers and calculation of the failure rate, the processing at the switching node is simplified.

Next, the effect of the embodiment of the present invention will be shown from the viewpoint of throughput performance of effective packets using a simple model. First, the cell discarding method of the first embodiment is targeted. The simulation model considered here is shown in FIG. In this simulation model, it is assumed that the cell discard at the switching node occurs only in the output buffer and does not occur in other parts such as the switch. Further, here, for simplification, priority processing in the buffer is not assumed. Furthermore, each packet handled by this simulation model is composed of 36 cells, the arrival time interval at the node for each packet is Poisson arrival (the arrival time interval is Poisson distribution), and the arrival speed of each cell in the same packet is Assume a constant peak delivery rate.

When the cell discarding method of the first embodiment of the present invention is applied to the simulation model shown in FIG.
The throughput performance with respect to the load is shown in FIGS. 9 and 10. 9 and 10, for comparison, in addition to the method of the present invention, an uncontrolled, Early Pocket Discard (EP
D) and throughput performance in the case of Partial Packet Discrd (PPD) are also shown. However, Early Pa
The buffer threshold for cket Discard is 165 (fixed:
(Value for 165 cells). Here, the buffer size K is set to 200 (size for 200 cells). The step size for changing the buffer threshold B is N = 1 (one cell), and the failure rate threshold is S = 0.02. The cell output speed of the cell output from the buffer is 1.5 Mbps. The threshold update time interval is 200 ms.

FIG. 9 is a simulation result of the throughput of the effective packet when the peak transmission rate of the input cell of each VC is 1.5 Mbps, and FIG. 10 is each V
It is a figure which shows the throughput of an effective packet when the peak transmission rate of the input cell of C is set to 6.3 Mbps. The load value on each horizontal axis is load = number of arriving packets per unit time / maximum transmittable number of packets per unit time, and the vertical axis indicates throughput of effective packets, which is an evaluation item (performance). ing.

From FIG. 9, no control or EPD / PPD
It can be seen that the method of the present invention can maintain the throughput of valid packets even in a situation where the load is high, as compared with the above case. Also in the case of FIG. 10, it can be seen that the method of the present invention can maintain the throughput of effective packets. Further, it can be seen that the method of the present invention can maintain the throughput regardless of the peak transmission rate of the input cell.

Also in the method of the third embodiment, the first threshold value is set by appropriately setting the threshold value Apo of received packets.
Since it substantially coincides with the time period of the threshold value update of the method of the first embodiment, it exhibits the same performance characteristics as the method of the first embodiment,
Its effectiveness can be confirmed from the above results. Also in the methods of the second and fourth embodiments, since the number of discarded cells and the number of packets including discarded cells are in a substantially proportional relationship,
Since the failure rate obtained from the number of discarded cells and the failure rate obtained from the number of packets in the method of the first embodiment are substantially the same, their effectiveness can be confirmed from the above results.

[0039]

According to the present invention, even if the number of cells forming a packet, the input speed, or the magnitude of load changes as traffic conditions, the buffer threshold value is changed to an optimum value according to those changes. Therefore, it is possible to suppress the packets and cells that are wastefully transferred to a certain ratio or less, reduce invalid processing in the network, and prevent a decrease in node throughput.

[Brief description of the drawings]

FIG. 1 is a diagram showing how a part of a cell is discarded when a plurality of packets decomposed into cells are transferred.

FIG. 2 is a configuration diagram of a cell discarding device in a switching node according to the first and second embodiments of the present invention.

FIG. 3 is a flowchart of a cell discarding method according to the first embodiment of this invention.

FIG. 4 is a flowchart of a cell discard method according to a second embodiment of the present invention.

FIG. 5 is a configuration diagram of a cell discarding device in a switching node according to a third embodiment and a fourth embodiment of the present invention.

FIG. 6 is a flowchart of a cell discard method according to a third embodiment of the present invention.

FIG. 7 is a flowchart of a cell discard method according to a fourth embodiment of the present invention.

FIG. 8 is a simulation model of the present invention.

FIG. 9 is a simulation result showing the effect of the present invention (peak transmission rate of input cell of each VC = 1.5 Mbp)
s).

FIG. 10 is a simulation result showing the effect of the present invention (peak transmission rate of input cell of each VC = 6.3 Mb).
ps).

[Explanation of symbols]

1: Cell input device, 2: Measuring device, 3: Buffer, 4:
Cell sending device, 5: counter, 6: threshold value determining device, 7:
Timer, 11: sending terminal, 12: receiving terminal

Claims (4)

[Claims] 1. When a predetermined threshold value B is set in a buffer of an exchange node in a data communication network that divides a packet into a plurality of cells and transfers the cell storage amount of the buffer exceeds the threshold value B of the buffer. , In the cell discard method of the switching node, which accepts the first cell of the newly arrived packet, identifies the packet to which the cell belongs, and discards all the cells of the identified packet. The total number of packets Hp in which cells constituting packets are discarded due to buffer overflow and the total number of packets Ap received are measured, and the failure rate = Hp / Ap is calculated for each unit time, and the failure rate is predetermined. Comparing thresholds S,
When failure rate> threshold value S, the threshold value B of the buffer is reduced,
A cell discarding method in a switching node, wherein a threshold value B of a buffer is increased when failure rate <threshold value S. 2. When a predetermined threshold value B is set in a buffer of a switching node in a data communication network that transfers a packet by dividing it into a plurality of cells and the cell storage amount of the buffer exceeds the threshold value B of the buffer. In the cell discard method of the switching node, which accepts the first cell of the newly arrived packet, identifies the packet to which the cell belongs, and discards all cells of the identified packet, the accepted packet The total number of cells Hc discarded by a buffer overflow and the total number Ac of cells of the received packets, which are cells constituting the above, are measured, and a failure rate = Hc / Ac is calculated for each unit time. Comparing a predetermined threshold S,
When failure rate> threshold value S, the threshold value B of the buffer is reduced,
A cell discarding method in a switching node, wherein a threshold value B of a buffer is increased when failure rate <threshold value S. 3. When a predetermined threshold value B is set in a buffer of a switching node in a data communication network that transfers a packet by dividing it into a plurality of cells, and the cell storage amount of the buffer exceeds the threshold value B of the buffer. , In the cell discard method of the switching node, which accepts the first cell of the newly arrived packet, identifies the packet to which the cell belongs, and discards all the cells of the identified packet. The total number of packets Hp and the total number of received packets Ap in which cells constituting a packet are discarded due to a buffer overflow are measured, and a packet is overflowed due to a buffer overflow every time the total number of received packets reaches a predetermined threshold Apo. The total number Hp of packets whose constituent cells are discarded and a predetermined threshold S
Compared with p, the threshold value B of the buffer is made smaller when Hp> the threshold value Sp, and the threshold value B of the buffer is made larger when Hp <the threshold value Sp. 4. When a predetermined threshold value B is set in a buffer of a switching node in a data communication network which divides a packet into a plurality of cells and transfers the cell, and the cell storage amount of the buffer exceeds the threshold value B of the buffer. In the cell discard method of the switching node, which accepts the first cell of the newly arrived packet, identifies the packet to which the cell belongs, and discards all cells of the identified packet, the accepted packet The total number of cells Hc discarded by a buffer overflow and the total number Ac of cells of the received packet are measured, and the total number of cells of the received packet is a predetermined value Aco.
Every time, the total number Hc of cells that compose the received packet but are discarded due to buffer overflow is compared with a predetermined threshold Sc, and when Hc> threshold Sc, the threshold B of the buffer Is reduced, and when Hc <threshold value Sc, the threshold value B of the buffer is increased.