CN116366550A - End-to-end low-delay scheduling method for time trigger stream of time sensitive network - Google Patents
End-to-end low-delay scheduling method for time trigger stream of time sensitive network Download PDFInfo
- Publication number
- CN116366550A CN116366550A CN202310206255.2A CN202310206255A CN116366550A CN 116366550 A CN116366550 A CN 116366550A CN 202310206255 A CN202310206255 A CN 202310206255A CN 116366550 A CN116366550 A CN 116366550A
- Authority
- CN
- China
- Prior art keywords
- time slot
- time
- slot
- link
- selecting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000001960 triggered effect Effects 0.000 claims abstract description 11
- 230000008447 perception Effects 0.000 claims abstract description 6
- 230000005540 biological transmission Effects 0.000 claims description 38
- 238000005457 optimization Methods 0.000 claims description 16
- 230000001351 cycling effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/18—End to end
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2425—Traffic characterised by specific attributes, e.g. priority or QoS for supporting services specification, e.g. SLA
- H04L47/2433—Allocation of priorities to traffic types
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L5/00—Arrangements affording multiple use of the transmission path
- H04L5/003—Arrangements for allocating sub-channels of the transmission path
- H04L5/0078—Timing of allocation
Abstract
The invention relates to an end-to-end low-delay scheduling method of time-triggered streams of a time-sensitive network, which belongs to the field of industrial Internet and comprises the following steps: s1: acquiring information of all TT flows of the switch, and performing time slot allocation for all links through which all TT flows pass from a source node to a destination node according to the priority; s2: reducing the end-to-end delay of the TT stream by local time slot searching; s3: and according to the optimized time slot occupation table, the number of time perception shapers is reduced as much as possible, the door opening times are reduced, and a corresponding gating list is generated. The invention reduces the end-to-end delay of TT flow and also reduces the number of time perception shapers.
Description
Technical Field
The invention belongs to the field of industrial Internet, and relates to an end-to-end low-delay scheduling method of time trigger streams of a time sensitive network.
Background
Time Sensitive Networks (TSNs) are a set of standards that improve the real-time performance of current ethernet networks, including a series of standards defined in the IEEE802.1 standardization organization TSN task group. Due to the recent increase in demand for industrial system functions, data communication in industrial systems faces many challenges, such as automatic driving automobiles and intelligent factories, many complex intelligent sensors and cameras are widely used, which require a large amount of communication bandwidth while satisfying their timing requirements with high data and high exchange amounts, and ensuring deterministic transmission of communication. This places further stress on the data communication design of such systems. Time sensitive networks address these recent challenges of increasing demands for industrial system functionality, mainly by deterministic stream scheduling (ieee 802.1 qbv), enhanced time synchronization (ieee 802.1 as), etc.
Although IEEE802.1Qbv proposes a mechanism for communicating scheduling information in the TSN, a gating list is proposed by the design user. In time sensitive networks, the part of the delay that can be optimized as a scheduling decision maker is mainly the switch part. As shown in FIG. 1Time-triggered flow is shown to be delayed from source node to destination node as D in a time-sensitive network ETE By time delay of transmission
Propagation delay->
Processing delay->
And queuing delay->
Four parts are composed of:
in local area networks, the transmission length is generally small, and the propagation delay is compared to the propagation rate of electromagnetic waves on a channel
Negligible; the delays that occur inside the switch are: transmission delay->
Processing delay->
Queuing delay->
Wherein the transmission delay->
The message length and the sending speed of the switch port are related to the following steps:
processing delay time
Related to the performance of the switch, typically considered as a constant value;
queuing delay
Is the delay caused by the waiting of the data frame in the queuing buffer queue of the switch, as shown in fig. 2; after two frames arrive at the switch at the same time, a frame is necessarily sent first and then sent later, and queuing delay is generated for the frame which is sent later. The prior art cannot minimize this queuing delay.
Disclosure of Invention
Accordingly, the present invention is directed to an end-to-end low latency scheduling method for time triggered streams in a time sensitive network.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an end-to-end low-delay scheduling method of time-triggered streams of a time-sensitive network comprises the following steps:
s1: acquiring information of all TT flows of the switch, and performing time slot allocation for all links through which all TT flows pass from a source node to a destination node according to the priority;
s2: reducing the end-to-end delay of the TT stream by local time slot searching;
s3: and according to the optimized time slot occupation table, the number of time perception shapers is reduced as much as possible, the door opening times are reduced, and a corresponding gating list is generated.
Further, the step S1 specifically includes:
s11: reading and collecting information of all TT flows in a network, wherein the information comprises TT flow period, message size and priority information;
s12: sequencing all TT flows from high priority to low priority, and calculating the comprehensive scheduling period T of the TT flows A And calculate each TT stream
Relative to the integrated scheduling period T A The number of transmission frames N i And calculating a Slot transmission basic unit Slot;
s13: selecting a first TT stream
And the TT stream is routed to select the first link +.>
Judging the ith time slot occupying variable of the link from node m to node n>
If equal to 1, if not equal to 1, occupying the lower transmission
The required time slot->
And will->
Setting as 1; if the current time slot->
Then representing that the current time slot is occupied, skipping the current time slot, selecting the next time slot +.>
And repeating step S13;
s14: let N i ＝N i -1, judge N i Whether or not 0, if N i Not equal to 0, the time slot occupation time is added to
Period T of (2) i And is occupied again, and the device is used up again,namely: make->
And let N i ＝N i -1, wherein->
Indicating that time slot i is at time slot length T i The following time slot, repeating step S14 until N i ＝0；
S15: judging the TT flow
Whether all the time slots of all the links are allocated or not, if not, selecting the next link;
s16: judging whether all TT flows are scheduled, if not, selecting the next TT flow and then entering step S13;
s17: the preliminary slot occupancy table is obtained and output via steps S11-S16.
Further, the integrated scheduling period T in step S12 A The method comprises the following steps:
T A ＝LCM(T 1 ，T 2 ，...，T i )
wherein LCM represents the least common multiple, T 1 ～T i Representing TT flow
Is a period of (2);
each TT stream
Relative to the integrated scheduling period T A The number of transmission frames N i The calculation is as follows:
the Slot transmission basic unit Slot is:
where GCD represents the greatest common divisor,
indicate TT flow->
The required time slot size:
wherein SP is s Indicating the speed of the switch port transmission,
indicate TT flow->
Is a data frame size of (c).
Further, the step S2 of reducing the end-to-end delay of the TT stream by the local time slot search specifically includes:
s21: reading the preliminary time slot occupation table and selecting a first TT stream
Selecting a link closest to the destination node;
s22: from TT stream with lowest priority
Begin searching, select->
Selecting TT flow +.>
The ith time slot from node m to node nWith variable->
Is a time slot of (2); find forward from the time slot, judge +.>
In adjacent link->
Whether there is an idle slot on it, i.e. TT stream +.>
Ith time slot occupancy variable from node n to node o
If yes, step S23 is carried out, if no, the next link is selected, and after the link is judged, the next TT flow is selected;
s23: determine whether or not it is possible to
In link->
The time slot occupied by the last slot is moved back and then it is determined whether the time slot can be reduced after the movement>
If so, removing the spare time slot by the movement of the time slot occupation, and updating the time slot occupation table, and if the end-to-end delay cannot be reduced, selecting the next link;
s24: checking whether all TT flows are optimized, and if so, generating a time slot occupancy table after optimization.
Further, the step S3 specifically includes:
s31: reading a time slot occupation table generated after time slot occupation optimization, and selecting a time slot occupation table of a first link;
s32: selecting the first time slot of the link, judging
Whether or not equal to 1, if->
Eye->
Judging whether the priorities of TT streams occupying the two time slots are equal, if so, combining the two time slots, and if not, selecting the next time slot; if->
Eye(s) for the treatment of a person suffering from a disorder>
Then the two unoccupied time slots are combined; cycling until the last slot of the current link;
s33: selecting the first time slot of the link, judging
Whether or not equal to 1, if->
Generating a gating list parameter with gating priority parameter +.>
According to the binary number of Slot i Determining a time slot parameter by the time slot size; if it is
The gating priority parameter is set to all 1's according to Slot i Determining a time slot parameter by the time slot size; cycling until the last slot of the current link;
s34: checking whether all links have generated the gating list, outputting the generated gating list if all have generated the gating list, and selecting a link to repeat steps S32-S33 if there are links not generating the gating list.
The invention has the beneficial effects that: compared with the traditional strict priority algorithm, the method optimizes the end-to-end time delay and the time slot number, can reduce the end-to-end time delay of TT flow, and can also reduce the number of time perception shapers.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a TSN network delay;
FIG. 2 is a queuing delay diagram;
FIG. 3 is a schematic diagram of door opening and closing time;
FIG. 4 is a schematic diagram of slot merging;
FIG. 5 is a diagram of strict priority based look-ahead scheduling;
FIG. 6 is a strict priority based look-ahead scheduling flowchart;
FIG. 7 is a schematic diagram of end-to-end delay optimization based on local slot search;
FIG. 8 is a flow chart of end-to-end delay optimization based on local slot search;
FIG. 9 is a diagram of a gating list optimization output algorithm;
fig. 10 is a network topology diagram of the first embodiment;
fig. 11 is a preliminary time slot occupancy representation of the first embodiment;
fig. 12 is a schematic diagram of an optimized slot occupancy according to the first embodiment.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to limit the invention; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc., that indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but not for indicating or suggesting that the referred device or element must have a specific azimuth, be constructed and operated in a specific azimuth, so that the terms describing the positional relationship in the drawings are merely for exemplary illustration and should not be construed as limiting the present invention, and that the specific meaning of the above terms may be understood by those of ordinary skill in the art according to the specific circumstances.
The invention provides a scheduling method for providing event trigger flow in a time sensitive network, wherein parameters shown in table 1 are referred to in the invention:
TABLE 1
In this time-sensitive network, there are the following constraints:
network constraints:
the whole network is a single-path, loop-free network and defines a link variable
Indicate TT flow->
Whether or not to pass, the link from node m to node n, if so +.>
If it does not pass->
After the source node and the destination node in the network are separated, all the remaining nodes need to meet the requirement of full-reliable transmission, and the packet loss rate is 0, namely the inflow flow is equal to the outflow flow:
for the source node, all traffic is sent from the source node, and then the following needs to be satisfied:
for the destination node, all the receiving ends of the traffic are slave destination nodes, and the destination node cannot send out the traffic, so that the following needs to be satisfied:
flow constraint:
the TT stream is a time triggered stream and is sent periodically. This requires
Transmission time from m to n->
Must be greater than 0 and require +.>
The transmission is completed in its period, namely:
time slot occupancy constraint:
in the process of transmitting TT streams by the switch, a port can only transmit one TT stream at the same moment, and in the same period, the same time slot can only be occupied by one TT stream. Defining a time slot occupancy variable
The TT flow is represented on the link from node m to node n +.>
In the integrated scheduling period T A If the i-th slot resource is occupied>
Occupying the time slot ∈ ->
Otherwise, 0. Then on the link from node m to node n, the port slot occupancy constraint for the same switch is as follows:
time slot optimization constraints:
judging whether one TT stream can be optimized or not, and meeting two conditions: (1) TT flow
Is to be used for the current end-to-end delay of (a)
Whether or not it is greater than the delay caused by its transmission, i.e. whether or not queuing delay is generated during transmission:
(2) whether enough empty time slots exist for TT flow adjustment or not, and queuing delay is reduced so as to reduce end-to-end delay
Wherein a is a time slot of the TT stream sent from the source node, and b is a time slot of the destination node receiving the TT stream:
time-aware shaper number constraint:
in one comprehensive dispatching period T A Each TT stream
The number of the transmitted data frames is N i There is a time-aware shaper operation for each transmission of a data frame. Defining a time-aware shaper event consisting of a door open time, a slot transmission occupancy time, a door close time, a door open time delta and a door close time delta are consumed for each time-aware shaper operation, as shown in fig. 3. Therefore, in order to reduce the resource consumption of the system and improve the utilization rate of the bandwidth, a plurality of time slots of continuous transmission can be combined, and the number of time perception shapers is reduced.
For two TT traffic with the same priority for adjacent transmissions on the same link within the same scheduling period:
or adjacent unoccupied slots on the same link during the same scheduling period:
for satisfying the above conditions, two time-aware shapers may be combined, as shown in fig. 4.
The method comprises the following three stages:
the first stage: acquiring the information such as the period, the message size, the priority and the like of all TT flows of the switch, and calculating the comprehensive scheduling period T A Slot transmission basic unit Slot according to priority level
Ordering TT flows, and preferentially scheduling +.>
High TT stream, corresponding time slots are allocated according to the path sequence thereof, as shown in FIGS. 5-6, specific packetsThe method comprises the following steps:
step 1-1: reading all information of the existing network, and collecting information of all TT flows in the current network;
step 1-2: sequencing all TT flows from high to low according to priority, and calculating the comprehensive scheduling period T of the TT flows A And calculate each TT stream
Relative to the integrated scheduling period T A The number of transmission frames N i And calculating a Slot transmission basic unit Slot;
the integrated scheduling period is determined by all TT stream periods, and the integrated scheduling period considers the transmission time of all TT streams on each link in the whole network, so that the streams reach the receiving end before the worst delay time. Thus, the overall scheduling period T A Is defined as the least common multiple (Least Common Multiple, LCM) of all TT stream periods, where T i Representing TT flow
The calculation formula is as follows:
T A ＝LCM(T 1 ,T 2 ,…,T i )
the TT flow can be calculated through the comprehensive scheduling period and needs to be transmitted for a plurality of times in the scheduling period, and the flow is triggered in time
The number of transmission frames in the comprehensive scheduling period is N i ：
According to switch port sending speed SP s TT stream
Data frame size +.>
Calculate->
The size of the required time slot
According to the time Slot size required by each TT stream transmission, calculating a time Slot transmission basic unit Slot which is defined as all
The greatest common divisor (Greatest Common Divisor, GCD) of the slot sizes required for transmission is calculated as follows:
step 1-3: selecting a first TT stream
And the TT stream is routed to select the first link +.>
Judging +.>
Whether or not 1 is equal (if 1 is representing that the current time slot is occupied), and if not 1 is occupied, transmitting +.>
When neededGap->
And will->
Setting as 1; if the current time slot->
The current time slot is skipped and the next time slot is selected +.>
And repeating the steps 1-3;
step 1-4: n (N) i ＝N i -1, judge N i Whether or not 0, if N i Not equal to 0, then time slot
Occupancy of, make
And let N i ＝N i -1, repeating steps 1-4 until N i ＝0；
Step 1-5: judging whether the TT stream is the one
Whether all the time slots of all the links are allocated or not, if not, selecting the next link;
step 1-6: judging whether all TT flows are scheduled, if not, selecting the next TT flow and then entering the step 1-3;
step 1-7: and outputting the preliminary time slot occupation table.
And a second stage: after the initial allocation of slots for all TT flows, the second phase of scheduling attempts to reduce the end-to-end delay of TT flows by local slot search, as shown in FIGS. 7-8.
Step 2-1: reading a time slot occupation table generated after advanced scheduling, and selecting a first TT stream
Selecting a link closest to the destination node;
step 2-2: from TT stream with lowest priority
Begin searching, select->
Selecting +.>
Is allocated to the time slot of the mobile station. Find forward from the time slot, judge +.>
In adjacent link->
Whether or not there is an idle time slot, i.e
If yes, a third step is carried out, if no, a next link is selected, and after the link is judged, a next TT flow is selected;
step 2-3: determine whether or not it is possible to
In link->
The time slot occupied by the last slot is moved backwards, and then whether the time slot can be reduced after the time slot is moved is judged>
End-to-end delay of (c) if any, by shifting of slot occupancyDynamically removing the free time slot, and updating a link time slot occupation table, and selecting the next link if the end-to-end delay cannot be reduced;
step 2-4: checking whether all TT flows are optimized, and if so, generating a time slot occupancy table after optimization.
And a third stage: according to the optimized time slot allocation table, the door opening times are reduced as much as possible, and a corresponding gating list is generated, as shown in fig. 9, comprising the following steps.
Step 3-1: reading an optimized time slot occupation table generated after time slot occupation optimization, and selecting a time slot occupation table of a first link;
step 3-2: selecting the first time slot of the link, judging
Whether or not it is equal to 1. If->
And is also provided with
Judging whether the priorities of TT streams occupying the two time slots are equal, if so, combining the two time slots, and if not, selecting the next time slot; if->
And->
Then the two unoccupied time slots are combined; cycling until the last slot of the current link;
step 3-3: selecting the first time slot of the link, judging
Whether or not it is equal to 1. If->
Then give birth toA gating list parameter, gating priority parameter is +.>
According to the binary number of Slot i Determining a time slot parameter by the time slot size; if->
The gating priority parameter is set to all 1's according to Slot i Determining a time slot parameter by the time slot size; cycling until the last slot of the current link;
step 3-4: checking whether all links have generated gating lists, outputting the generated gating list if all the links have generated gating lists, and selecting the link to repeat the steps 3-2 to 3-3 if no gating list is generated for any link.
Embodiment one:
in the network topology of the network as in fig. 10, the network is composed of two source nodes, two destination nodes, two TSN switches, wherein the ports of the switches transmit speed SP s For 100Mbps, there are 3 TT flows in the whole network, and specific information is shown in Table 2.
TABLE 2
Fig. 11 shows a flow of the primary schedule section, which includes links through which all TT flows must be transmitted from a source node to a destination node, described in brackets, for example, [ source node 1, TSN switch 1] and [ TSN switch 1, TSN switch 2]. The horizontal axis is time, and this slot occupancy table is a slot transmitted by allocating frames transmitted by the TT stream to links directed to its destination, but actually occupied ports.
TT stream with highest priority according to scheduling algorithm of preliminary time slot occupation
Starting. Because ofThis first takes TT stream +.>
And occupies a link from source node 1 to TSN switch 1, i.e. [ source node 1, TSN switch 1]]TSN switch 1, TSN switch 2]And [ TSN switch 2, destination node 1]]. TT flow->
The occupied link time Slot is represented by a block whose length corresponds to the Slot required for transmission 1 ＝125×8bit/100Mbps＝10μs。
Next, the TT stream of priority 6 will be
The links allocated to the links needed to reach the destination node have lengths corresponding to the slots Slot needed for transmission 4 =375×8bit/100 mbps=30 μs. Next, the TT stream of priority 5 is +.>
The links allocated to the links needed to reach the destination node have lengths corresponding to the slots Slot needed for transmission 3 =250×8bit/100 mbps=20 μs. Finally TT stream of priority 4 +.>
The links allocated to the links needed to reach the destination node have lengths corresponding to the slots Slot needed for transmission 2 ＝125×8bit/100Mbps＝10μs。
The final preliminary slot occupancy table is shown in FIG. 11, and it can be seen that TT flows
Is delayed at TSN switch 1 because TT stream +.>
Upon arrival at TSN switch 1, TSN switch 1 is transmitting TT flow +_ to destination node 2>
Fig. 12 shows a flow of the slot optimization section, and the link slot occupancy table includes all TT stream slot occupancy after the primary scheduling.
TT stream with highest priority according to time slot occupation optimization algorithm
Optimization is started. Firstly, TT stream +.>
The links traversed from the source node to the destination node are: [ Source node 3, TSN switch 1][ TSN switch 1, destination node 2]. At the position of
And if no free time slot exists in the transmission process, selecting the next TT stream for optimization.
Next, a TT stream of priority 6 is selected
Optimizing (I)>
The links traversed from the source node to the destination node are: [ Source node 2, TSN switch 2][ TSN switch 2, destination node 1]. At->
And if no free time slot exists in the transmission process, selecting the next TT stream for optimization.
TT stream of priority 5 is then selected
Optimizing (I)>
From source nodeThe links traversed by the point to the destination node are: [ Source node 2, TSN switch 2]TSN switch 2, TSN switch 1][ TSN switch 1, destination node 2]. At->
In the transmission process of [ TSN switch 2, TSN switch 1]]And [ TSN switch 1, destination node 2]]Free time slots are between the two links, then select move +.>
In [ TSN switch 2, TSN switch 1]The occupied time slot on the base station eliminates the spare time slot. After the link is optimized in the same way, for [ source node 2, TSN switch 2]As does this link.
The finally generated optimized time slot occupation table is shown in fig. 12, and it can be seen by comparing the preliminary time slot occupation table that TT stream
The end-to-end delay of (c) is reduced by 20 mus due to the optimization.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (5)
1. An end-to-end low-delay scheduling method of time-triggered streams of a time-sensitive network is characterized in that: the method comprises the following steps:
s1: acquiring information of all TT flows of the switch, and performing time slot allocation for all links through which all TT flows pass from a source node to a destination node according to the priority;
s2: reducing the end-to-end delay of the TT stream by local time slot searching;
s3: and according to the optimized time slot occupation table, the number of time perception shapers is reduced as much as possible, the door opening times are reduced, and a corresponding gating list is generated.
2. The end-to-end low latency scheduling method of time-triggered streams of a time-sensitive network of claim 1, wherein: the step S1 specifically comprises the following steps:
s11: reading and collecting information of all TT flows in a network, wherein the information comprises TT flow period, message size and priority information;
s12: sequencing all TT flows from high priority to low priority, and calculating the comprehensive scheduling period T of the TT flows A And calculate each TT stream
Relative to the integrated scheduling period T A The number of transmission frames N i And calculating a Slot transmission basic unit Slot;
s13: selecting a first TT stream
And the TT stream is routed to select the first link +.>
Judging the ith time slot occupying variable of the link from node m to node n>
Whether or not equal to 1, if not equal to 1, occupy the lower transmission +.>
The required time slot->
And will->
Setting as 1; if the current time slot->
Then representing that the current time slot is occupied, skipping the current time slot, selecting the next time slot +.>
And repeating step S13;
s14: let N i ＝N i -1, judge N i Whether or not 0, if N i Not equal to 0, the time slot occupation time is added to
Period T of (2) i And again occupy, namely: make->
And let N i ＝N i -1, wherein->
Indicating that time slot i is at time slot length T i The following time slot, repeating step S14 until N i ＝0；
S15: judging the TT flow
Whether all the time slots of all the links are allocated or not, if not, selecting the next link;
s16: judging whether all TT flows are scheduled, if not, selecting the next TT flow and then entering step S13;
s17: the preliminary slot occupancy table is obtained and output via steps S11-S16.
3. The end-to-end low latency scheduling method of time-triggered streams of a time-sensitive network of claim 2, wherein: the comprehensive scheduling period T in step S12 A The method comprises the following steps:
T A ＝LCM(T 1 ,T 2 ,…,T i )
wherein LCM represents the least common multiple, T 1 ～T i Representing TT flow
Is a period of (2);
each TT stream
Relative to the integrated scheduling period T A The number of transmission frames N i The calculation is as follows:
the Slot transmission basic unit Slot is:
where GCD represents the greatest common divisor,
indicate TT flow->
The required time slot size:
wherein SP is s Indicating the speed of the switch port transmission,
indicate TT flow->
Is a data frame size of (c).
4. The end-to-end low latency scheduling method of time-triggered streams for a time-sensitive network of claim 3, wherein: the step S2 of reducing the end-to-end delay of the TT stream by local time slot search specifically includes:
s21: reading the preliminary time slot occupation table and selecting a first TT stream
Selecting a link closest to the destination node;
s22: from TT stream with lowest priority
Begin searching, select->
Selecting TT flow +.>
The i-th slot occupancy variable from node m to node n +.>
Is a time slot of (2); find forward from the time slot, judge +.>
In adjacent link->
Whether there is an idle slot on it, i.e. TT stream +.>
Ith time slot occupancy variable from node n to node o
If yes, step S23 is carried out, if no, the next link is selected, and after the link is judged, the next TT flow is selected;
s23: determine whether or not it is possible to
In link->
The time slot occupied by the last slot is moved back and then it is determined whether the time slot can be reduced after the movement>
If so, removing the spare time slot by the movement of the time slot occupation, and updating the time slot occupation table, and if the end-to-end delay cannot be reduced, selecting the next link;
s24: checking whether all TT flows are optimized, and if so, generating a time slot occupancy table after optimization.
5. The end-to-end low latency scheduling method of time-triggered streams of a time-sensitive network of claim 4, wherein: the step S3 specifically comprises the following steps:
s31: reading a time slot occupation table generated after time slot occupation optimization, and selecting a time slot occupation table of a first link;
s32: selecting the first time slot of the link, judging
Whether or not equal to 1, if->
And->
Slot i+1 =1, judging whether the priorities of TT streams occupying the two time slots are equal, if so, combining the two time slots, and if not, selecting the next time slot; if->
And->
Then the two unoccupied time slots are combined; cycling until the last slot of the current link;
s33: selecting the first time slot of the link, judging
Whether or not equal to 1, if->
Generating a gating list parameter with gating priority parameter +.>
According to the binary number of Slot i Determining a time slot parameter by the time slot size; if->
The gating priority parameter is set to all 1's according to Slot i Determining a time slot parameter by the time slot size; cycling until the last slot of the current link;
s34: checking whether all links have generated the gating list, outputting the generated gating list if all have generated the gating list, and selecting a link to repeat steps S32-S33 if there are links not generating the gating list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206255.2A CN116366550A (en) | 2023-03-03 | 2023-03-03 | End-to-end low-delay scheduling method for time trigger stream of time sensitive network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206255.2A CN116366550A (en) | 2023-03-03 | 2023-03-03 | End-to-end low-delay scheduling method for time trigger stream of time sensitive network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116366550A true CN116366550A (en) | 2023-06-30 |
Family
ID=86938750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310206255.2A Pending CN116366550A (en) | 2023-03-03 | 2023-03-03 | End-to-end low-delay scheduling method for time trigger stream of time sensitive network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116366550A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596200A (en) * | 2024-01-15 | 2024-02-23 | 之江实验室 | Time-sensitive network route scheduling method, electronic equipment and medium |
-
2023
- 2023-03-03 CN CN202310206255.2A patent/CN116366550A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596200A (en) * | 2024-01-15 | 2024-02-23 | 之江实验室 | Time-sensitive network route scheduling method, electronic equipment and medium |
| CN117596200B (en) * | 2024-01-15 | 2024-05-07 | 之江实验室 | Time-sensitive network route scheduling method, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108777660B (en) | Method for scheduling service in time-triggered FC network | |
| WO2019084970A1 (en) | Packet forwarding method, forwarding device, and network device | |
| CN114422448B (en) | Time-sensitive network traffic shaping method | |
| CN113424500B (en) | Method for routing in a time-sensitive network | |
| CN115460130B (en) | Multipath joint scheduling method in time sensitive network | |
| CN112953830A (en) | Routing planning and scheduling method and device for flow frames in time-sensitive network | |
| US7391777B2 (en) | Distance-sensitive scheduling of TDM-over-packet traffic in VPLS | |
| CN114553697B (en) | Industrial wireless and TSN fusion-oriented network scheduling method | |
| CN114448894A (en) | Multi-level service scheduling engine facing time sensitive network and implementation method | |
| CN113032938A (en) | Time-sensitive flow routing scheduling method, device, electronic equipment and medium | |
| CN112468412A (en) | Method for generating schedules for mixed-critical computer networks | |
| US20150131443A1 (en) | Method For Transmitting Data In A Packet-Oriented Communications Network And Correspondingly Configured User Terminal In Said Communications Network | |
| CN104301933A (en) | Method for calculating bandwidth and distributing bandwidth in wireless ad hoc network | |
| CN114830611A (en) | Centralized network configuration entity and time-sensitive network control system comprising same | |
| CN116366550A (en) | End-to-end low-delay scheduling method for time trigger stream of time sensitive network | |
| CN115883438A (en) | Routing and scheduling method and device of time trigger flow in time-sensitive network and readable storage medium | |
| CN117560106A (en) | Scheduling method for time trigger flow in time sensitive network | |
| CN113630335B (en) | Optimized selection method for switching Ethernet data flow control strategy | |
| CN115604193B (en) | Deterministic resource scheduling method and system in hot rolling control system | |
| CN116132374A (en) | Power communication network transmission delay control method combining routing and gating planning | |
| CN114915597B (en) | Deterministic resource scheduling method for time-sensitive network | |
| US8355403B2 (en) | Stale data removal using latency count in a WiMAX scheduler | |
| CN114363270A (en) | Data forwarding method and related device | |
| Kong et al. | Run-time per-class routing of AVB flows in in-vehicle TSN via composable delay analysis | |
| CN115333998B (en) | Time-sensitive network flow scheduling method suitable for power communication network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |