CN117240783A - Time sensitive network flow scheduling method based on transmission time slot planning - Google Patents
Time sensitive network flow scheduling method based on transmission time slot planning Download PDFInfo
- Publication number
- CN117240783A CN117240783A CN202311039111.9A CN202311039111A CN117240783A CN 117240783 A CN117240783 A CN 117240783A CN 202311039111 A CN202311039111 A CN 202311039111A CN 117240783 A CN117240783 A CN 117240783A
- Authority
- CN
- China
- Prior art keywords
- time
- scheduling
- slot
- stream
- time slot
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims description 7
- 235000008694 Humulus lupulus Nutrition 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013468 resource allocation Methods 0.000 abstract description 3
- 230000007246 mechanism Effects 0.000 description 18
- 238000011144 upstream manufacturing Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000002347 injection Methods 0.000 description 4
- 239000007924 injection Substances 0.000 description 4
- 241001522296 Erithacus rubecula Species 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004401 flow injection analysis Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a time sensitive network flow scheduling method based on transmission time slot planning, which comprises the following steps: s1, a node in a time sensitive network receives a service data stream and acquires data stream characteristic information to be scheduled; s2, calculating the scheduling period and the minimum scheduling time slot of the data stream according to the characteristic information of different data streams; s3, ordering the scheduled data streams based on a greedy ordering algorithm of the data stream characteristics, scheduling each data stream one by one under the comprehensive constraint condition, and finding an offset time slot for each stream; s4, giving scheduling priority based on traffic density to all available time slots; s5, selecting an offset time slot with the highest priority, offsetting the sending time slot of the data stream, updating the queue resource and completing the scheduling. The invention realizes the resource allocation of the flow in the time-sensitive network and improves the success rate of the flow dispatching as much as possible.
Description
Technical Field
The invention relates to the technical field of time-sensitive networks, in particular to a time-sensitive network traffic scheduling method based on transmission time slot planning.
Background
With the rapid development of information technology, the fields of industrial automation and the like have put higher demands on the stability and end-to-end delay of a communication network. Although the traditional Ethernet has the characteristics of high expansibility, low cost and the like, the traditional Ethernet belongs to a competitive network, and different types of traffic or different traffic of the same type can compete. To meet the deterministic requirements in industrial applications, such as smart grid control services, two technologies, time-triggered ethernet (Time-triggered Ethernet, TTE) and Time-sensitive network (Time-sensitive networks, TSN), are proposed on the basis of standard ethernet. Time sensitive networks have a strict time synchronization mechanism and a deterministic traffic scheduling mechanism, which can guarantee the quality of service of the network to a large extent. Key technologies of TSN are time synchronization technology and resource scheduling algorithm. At present, the time synchronization technology has detailed standards and algorithms, and resource scheduling has great difference under different models and standards, so that the research of the data traffic resource scheduling method for different industries has great significance for expanding the application field of TSN.
TSN resource scheduling is based on Time synchronization, with many different scheduling models, such as Time-aware shaper (TAS) and round robin queuing forwarding mechanism (cyclic queuing and forwarding mechanism, CQF). Wherein, the scheduling granularity of TAS is a queue. Only one gate control is arranged for each queue, and then the time for opening and closing the gate is controlled through a gate control list. Compared to TAS, CQFs have a more easily configurable scheduling mechanism that configures two queues for each port of each switch, employing a ping-pong transport model. However, when the existing transmission mechanism is used for concurrently transmitting a plurality of data streams, the problems of scheduling failure or congestion and packet loss and the like caused by insufficient flexible resource scheduling exist.
Disclosure of Invention
The invention solves the problem of failure or congestion and packet loss caused by inflexible resource scheduling in the prior art, and provides a time-sensitive network flow scheduling method based on transmission time slot planning, which realizes the resource allocation of flow in a time-sensitive network and improves the success rate of flow scheduling as much as possible.
In order to achieve the above purpose, the following technical scheme is provided:
a time sensitive network flow scheduling method based on transmission time slot planning comprises the following steps:
s1, a node in a time sensitive network receives a service data stream and acquires data stream characteristic information to be scheduled;
s2, calculating the scheduling period and the minimum scheduling time slot of the data stream according to the characteristic information of different data streams;
s3, ordering the scheduled data streams based on a greedy ordering algorithm of the data stream characteristics, scheduling each data stream one by one under the comprehensive constraint condition, and finding an offset time slot for each stream;
s4, giving scheduling priority based on traffic density to all available time slots;
s5, selecting an offset time slot with the highest priority, offsetting the sending time slot of the data stream, updating the queue resource and completing the scheduling. And (3) allocating corresponding queue resources to the stream according to the optimal time slot calculated in the step (S4), finding out a queue resource block on a corresponding time space, and updating the resource block according to the size of the data packet of the stream so as to finish scheduling.
The invention avoids queue resource allocation conflict by adjusting the sending time slot of the data stream in the queue under the CQF mechanism in the time sensitive network, thereby achieving the purpose of improving the success rate of flow scheduling. The invention uses an undirected graph in S1 to represent the network topology of a time-sensitive network, which is denoted as G= { V, E }. Wherein V represents a set of all nodes in the network, including switches and user terminals; e represents connecting any two nodes to a set of directed edges. The switch is simplified to include only two queues for transmitting delay sensitive traffic.
By SW j,k To represent the kth port of the jth switch. The aggregate of all streams is denoted by F, F i Representing the ith stream. The flow characteristics are expressed as follows:
f i ＝{f i .src,f i .des,f i .size,f i prd,f i .ddl,f i .path}
the data in the above set are used to represent the source, destination, packet length, period, deadline, and transmission path length of the ith stream, respectively.
Preferably, the range of values of the minimum scheduling time slot is as follows:
wherein, the queue size For queue length, B is link bandwidth, d hop For intra-switch processing and propagation delay, sync_pre is clock synchronization accuracy, GCD (F.prd) is the greatest common divisor of all stream periods, T slot The time slot is scheduled for the minimum.
Different delay-sensitive streams have different transmission periods, but all have periods of fixed duration, so that all streams within an infinite time need not be scheduled. Only the least common multiple of all stream periods is calculated and recorded as a scheduling period T schedul . Only need to study the scheduling period T schedul The scheduling of all flows in the system can enable the flow scheduling of the whole process to meet the requirements, so that the following researches are established in one T schedul And (c) the inner part. T (T) schedul The least common multiple of all traffic cycles can be used for calculation.
The transmission mechanism of CQF is based on time synchronization, and the time of the whole system is divided into equal time intervals called time slots, which are marked as T slot . The sampling period of all streams in the system should be able to be T slot Integer division, so the slot maximum can be expressed in terms of the greatest common divisor of all stream periods.
Meanwhile, since the transmit time slot of the upstream switch must be the same as the receive time slot of the downstream switch in the CQF, the minimum time slot length should meet the time requirement for the message to be transmitted from the upstream switch to the downstream switch. In summary, the range of values of the minimum scheduling time slot is as follows:
wherein, the queue size For queue length, B is link bandwidth, d hop For intra-switch processing and propagation delay, sync_pre is clock synchronization accuracy and GCD (Greatest Common Divisor) represents the greatest common divisor.
Different delay-sensitive streams have different transmission periods, but all have periods of fixed duration, so that all streams within an infinite time need not be scheduled. Only the least common multiple of all stream periods is calculated and recorded as a scheduling period T schedul . Only need to study the scheduling period T schedul The scheduling of all flows in the system can enable the flow scheduling of the whole process to meet the requirements, so that the following researches are established in one T schedul And (c) the inner part. T (T) schedul The least common multiple of all traffic cycles can be used for calculation.
The transmission mechanism of CQF is based on time synchronization, and the time of the whole system is divided into equal time intervals called time slots, which are marked as T slot . The sampling period of all streams in the system should be able to be T slot Integer division, so the slot maximum can be expressed in terms of the greatest common divisor of all stream periods.
Meanwhile, since the transmit time slot of the upstream switch must be the same as the receive time slot of the downstream switch in the CQF, the minimum time slot length should meet the time requirement for the message to be transmitted from the upstream switch to the downstream switch. In summary, the range of values of the minimum scheduling time slot is as follows:
wherein, the queue size For queue length, B is link bandwidth, d hop For intra-switch processing and propagation delay, sync_pre is clock synchronization accuracy and GCD (Greatest Common Divisor) represents the greatest common divisor.
Preferably, the comprehensive constraint condition includes a transmission slot offset constraint, a queue resource constraint and a deadline constraint.
S3, ordering the scheduled data stream based on a greedy ordering algorithm of the data stream features, wherein the greedy ordering algorithm comprises the packet length, period, deadline and transmission path length features of the data stream, for example, when traffic scheduling is performed, traffic with earlier deadline can be scheduled preferentially according to the criterion of ascending order of deadline. After the data streams are ordered, each data stream is scheduled one by one, and the most suitable offsetable time slot is found for each stream. The offsetable slot selection steps for each stream are as follows:
firstly, all the offsetable time slots meeting the offset time slot constraint of the current stream are found out and form a set, then the time slots meeting the queue resource constraint are found out from the offsetable time slot set, and finally the time slots meeting the cut-off time constraint are found out from the time slots meeting the queue resource constraint. The 3 constraints mentioned above are as follows:
(1) Injection time offset constraint:
under the requirement of the CQF mechanism, the data packet which enters the switch queue buffer in the last time slot must be sent out before the end of the next time slot, so the forwarding delay in the switch needs to be less than or equal to two time slot lengths.
f i .delay≤2T slot
The message is typically sent from the time of generation, but to improve network stability, the transmission time slot of the message needs to be adjusted, called transmission time slot offset, denoted as f i Offset. However, if the offset is too large, the message of the current period is not sent out when the message of the next period is generated, and blocking occurs. Thus, the message needs to be sent out at the latest in the current cycle.
(2) Queue resource constraints:
wherein queue resources inside the switch are divided into individual resource blocks in terms of time and space,the occupation condition of the queue resources is represented, 0 or 1,1 is taken to represent that the queue resources of the t time slot of the kth port of the jth switch are occupied, and the total number of the flows is n; the number of switches on the flow path is m; the number of ports of the switch is p. t represents the position of the current slot and can be calculated by the following equation:
wherein η represents a transmission period in which the stream is located;representing stream f i Arriving at switch SW j,k Number of hops at time.
(3) Cut-off time constraint:
the transmission delay of the stream after adding the offset will also increase. In order to guarantee the quality of service of the network, all messages of the flow must arrive at the destination end before the expiration time.
(f i .offset+hopofpath)*T slot ≤f i .ddl
Wherein hopofath represents the number of hops of the streaming path.
Preferably, the flow density calculation formula is as follows:
here, theIndicated as f in offset time slot i When in offset, the current resource block is occupied with a resource value; the smaller the value, the smaller the evaluation value for the offset slot, the lower its priority at the time of scheduling.
The invention considers the different occupation conditions of the resource blocks in different queues at different times, and should preferentially select the resource blocks with lighter congestion degree, so as to prevent the scheduling failure caused by the aggregation of a large amount of traffic in the same resource block. The invention uses the flow density to evaluate the congestion degree of the resource block, and gives higher priority to the time slot offset with lighter path congestion degree after the time slot offset to carry out priority scheduling, thereby maximizing the scheduling success rate.
Preferably, the step of selecting the offsetable time slot for each stream in S3 includes:
firstly, all the offsetable time slots meeting the offset constraint of the sending time slot of the current stream are found out and form a set, then the time slots meeting the queue resource constraint are found out from the offsetable time slot set, and finally the time slots meeting the cut-off time constraint are found out from the time slots meeting the queue resource constraint.
Preferably, the constraint of the transmit slot offset constraint is as follows:
wherein f i Offset represents the transmission slot offset, f i prd the period of the data stream, T slot Representing the minimum scheduled time slot.
Preferably, the constraints of the queue resource constraint are as follows:
wherein,the occupation condition of the queue resources is represented, 0 or 1,1 is taken to represent that the queue resources of the kth time slot of the kth port of the jth switch are occupied, the total number of flows is n, the number of switches on a flow path is m, the number of ports of the switches is p, t represents the position of the current time slot, and the calculation formula is as follows:
where eta represents the transmission period in which the stream is,representing stream f i Arriving at switch SW j,k Number of hops at time.
Preferably, the data flow characteristics are as follows:
f i ＝{f i .src,f i .des,f i .size,f i prd,f i .ddl,f i .path}
where F represents the set of all streams, F i Represents the ith stream, f i Src denotes the source end of the ith stream, f i Des denotes the destination end of the ith stream, f i Size represents the packet length of the ith stream, f i prd the period of the ith stream, f i Ddl denotes the deadline of the ith stream, f i Path represents the transmission path of the i-th stream.
The beneficial effects of the invention are as follows: aiming at a CQF-based scheduling model in a time-sensitive network, the invention can avoid the backlog of the traffic on the same queue resource by adjusting the sending time slot of the traffic, effectively realize the transmission scheduling of more concurrent data quantity and maximize the resource utilization efficiency. According to the greedy ordering method, the flow scheduling problem based on CQF in TSN is converted into an optimization problem, the flows are ordered according to the flow characteristics to be mapped in sequence, a proper offset time slot is selected for each flow under the comprehensive constraint condition, the congestion degree among different resource blocks is described by introducing flow density when time slot resources are allocated, the optimal time slot is selected, and through planning of the sending time slots of different flows, the resource scheduling success rate is improved, the data forwarding packet loss is reduced, the data transmission delay is reduced, and the like.
Drawings
FIG. 1 is a flow chart of a time-sensitive network traffic scheduling method based on transmission slot planning;
FIG. 2 is a schematic diagram of a round robin queuing forwarding mechanism in a time sensitive network;
fig. 3 is a schematic diagram of the comparison between the adjustment of the flow injection time slot and the adjustment of the flow injection time slot.
Detailed Description
Examples:
the invention is described in further detail below with reference to the drawings.
CQF is a round robin queuing forwarding model proposed by IEEE 802.1Qch, and adopts the same gating mechanism as TAS when receiving and transmitting, but is greatly simplified. The CQF forwarding mechanism is shown in fig. 2. The switch under the CQF mechanism contains two queues inside. The mechanism is based on strict time synchronization, the whole scheduling period is divided into a plurality of equal time intervals, each time interval is called a time slot and is marked as T slot . Two queues inside the switch must ensure that one sends a message while the other is receiving. Messages sent by an upstream switch must be received by a downstream switch in the same time slot. The switch queue must send out in the next time slot after receiving the message. The two queues constantly exchange functions of transmitting and receiving in time slot cycles, and are therefore also referred to as ping-pong forwarding mechanisms. On this basis, all slots are divided into two parts, an odd slot and an even slot. Odd, evenWithin a few slots, queue Q 1 Receive, Q 2 Forwarding; within even slots, queue Q 2 Receive, Q 1 And (5) forwarding.
The comparison between the adjustment of the injection time slot and the adjustment of the injection time slot is shown in fig. 3. Data stream f 1 And f 2 Transmitting data packets to the switch SW at the same time in the time slot 1, and overflowing the switch cache at the moment, f 1 Or f 2 The packets of only one stream will be forwarded in slot 2. If f is to 2 Is shifted backward by one unit as shown in fig. 3 (b). f (f) 1 To SW, f in slot 1 2 To SW in slot 2, then SW receives f in slot 1 1 After the packet of (2) is sent out in time slot 2, and f is received in time slot 2 2 After the data packet of f 3 Emitting. All streams can be successfully transmitted at this time.
The embodiment provides a time-sensitive network traffic scheduling method based on transmission time slot planning, referring to fig. 1, specifically comprising the following steps:
s1, a node in a time sensitive network receives a service data stream and acquires characteristic information of the data stream to be scheduled.
The network topology of a time-sensitive network is represented by an undirected graph, denoted g= { V, E }. Wherein V represents a set of all nodes in the network, including switches and user terminals; e represents connecting any two nodes to a set of directed edges. The switch is reduced to include only two queues for transmitting delay-sensitive flows.
By SW j,k To represent the kth port of the jth switch. The aggregate of all streams is denoted by F, F i Representing the ith stream. The flow characteristics are expressed as follows:
the data in the above set are used to represent the source, destination, packet length, period, deadline, and transmission path length of the ith stream, respectively.
S2, calculating the scheduling period and the minimum scheduling time slot of the stream according to the characteristic information of different data streams.
Different delay-sensitive streams have different transmission periods, but all have periods of fixed duration, so that all streams within an infinite time need not be scheduled. Only the least common multiple of all stream periods is calculated and recorded as a scheduling period T schedul . Only need to study the scheduling period T schedul And the scheduling of all the flows in the whole process can enable the flow scheduling of the whole process to meet the requirements. Thus, the following studies are all based on a T schedul And (c) the inner part. T (T) schedul The least common multiple of all traffic cycles can be used for calculation.
The transmission mechanism of CQF is based on time synchronization, and the time of the whole system is divided into equal time intervals called time slots, which are marked as T slot . The sampling period of all streams in the system should be able to be T slot Integer division, so the time slot can maximally take the greatest common divisor of all stream periods.
Meanwhile, since the transmit time slot of the upstream switch must be the same as the receive time slot of the downstream switch in the CQF, the minimum time slot length should meet the time requirement for the message to be transmitted from the upstream switch to the downstream switch. In summary, the range of values of the minimum scheduling time slot is as follows:
wherein, the queue size For queue length, B is link bandwidth, d hop For intra-switch processing and propagation delay, sync_pre is clock synchronization accuracy and GCD (Greatest Common Divisor) represents the greatest common divisor.
S3, ordering the scheduled data streams based on a greedy ordering algorithm of the data stream characteristics, scheduling each data stream one by one under the comprehensive constraint condition, and finding an offset time slot for each stream.
The step is to sort the scheduled data stream based on the greedy sorting algorithm of the data stream features, wherein the greedy sorting algorithm comprises the packet length, period, deadline and transmission path length features of the data stream, for example, when traffic scheduling is performed, traffic with earlier deadline can be scheduled preferentially according to the criterion of ascending order of deadline. After the data streams are ordered, each data stream is scheduled one by one, and the most suitable offsetable time slot is found for each stream. The offsetable slot selection steps for each stream are as follows:
firstly, all the offsetable time slots meeting the offset time slot constraint of the current stream are found out and form a set, then the time slots meeting the queue resource constraint are found out from the offsetable time slot set, and finally the time slots meeting the cut-off time constraint are found out from the time slots meeting the queue resource constraint. The 3 constraints described above are as follows.
(1) Transmit slot offset constraint
Under the requirement of the CQF mechanism, the data packet which enters the switch queue buffer in the last time slot must be sent out before the end of the next time slot, so the forwarding delay in the switch needs to be less than or equal to two time slot lengths.
f i .delay≤2T slot
The message is typically sent from the time of generation, but to improve network stability, the transmission time slot of the message needs to be adjusted, called transmission time slot offset, denoted as f i Offset. However, if the offset is too large, the message of the current period is not sent out when the message of the next period is generated, and blocking occurs. Thus, the message needs to be sent out at the latest in the current cycle.
(2) Queue resource constraints
Wherein queue resources inside the switch are divided into individual resource blocks in terms of time and space,the occupation condition of the queue resources is represented, 0 or 1,1 is taken to represent that the queue resources of the t time slot of the kth port of the jth switch are occupied, and the total number of the flows is n; the number of switches on the flow path is m; the number of ports of the switch is p. t represents the position of the current slot and can be calculated by the following equation:
wherein η represents a transmission period in which the stream is located;representing stream f i Arriving at switch SW j,k Number of hops at time.
(3) Deadline constraint
The transmission delay of the stream after adding the offset will also increase. In order to guarantee the quality of service of the network, all messages of the flow must arrive at the destination end before the expiration time.
(f i .offset+hopofpath)*T slot ≤f i .ddl
Wherein hopofath represents the number of hops of the streaming path.
And S4, giving scheduling priority based on the traffic density to all available time slots.
In selecting the offset slot size, there is likely to be more than one choice, and then a criterion is required as the criterion for selecting the most appropriate offset slot. Considering that the occupation conditions of the resource blocks in different queues at different times are different, the resource blocks with lower congestion degree should be preferentially selected, so that the scheduling failure caused by aggregation of a large amount of traffic in the same resource block is prevented. The invention uses the flow densityThe congestion degree of the resource block is evaluated, a higher evaluation value is given to the time slot offset with lighter path congestion degree after the time slot is offset, and the time slot with higher evaluation value is preferentially considered during scheduling, so that the scheduling success rate is maximized. Determining an offset time slot f i After offset, the flow density can be calculated by the following formula.
Here->Indicated as f in offset time slot i And (3) when in offset, the current resource block is occupied with a resource value. The smaller the value, the smaller the evaluation value for the offset slot, the lower its priority at the time of scheduling.
And S5, selecting an optimal offset time slot, offsetting the stream injection time, updating the queue resources and completing scheduling.
And (3) allocating corresponding queue resources to the stream according to the optimal time slot calculated in the step (S4), finding out a queue resource block on a corresponding time space, and updating the resource block according to the size of the data packet of the stream so as to finish scheduling.
Claims (8)
1. A time sensitive network flow scheduling method based on transmission time slot planning is characterized by comprising the following steps:
s1, a node in a time sensitive network receives a service data stream and acquires data stream characteristic information to be scheduled;
s2, calculating the scheduling period and the minimum scheduling time slot of the data stream according to the characteristic information of different data streams;
s3, ordering the scheduled data streams based on a greedy ordering algorithm of the data stream characteristics, scheduling each data stream one by one under the comprehensive constraint condition, and finding an offset time slot for each stream;
s4, giving scheduling priority based on traffic density to all available time slots;
s5, selecting an offset time slot with the highest priority, offsetting the sending time slot of the data stream, updating the queue resource and completing the scheduling.
2. The time-sensitive network traffic scheduling method based on transmission time slot planning according to claim 1, wherein the range of values of the minimum scheduling time slot is as follows:
wherein, the queue size For queue length, B is link bandwidth, d hop For intra-switch processing and propagation delay, sync_pre is clock synchronization accuracy, GCD (F.prd) is the greatest common divisor of all stream periods, T slot The time slot is scheduled for the minimum.
3. The method for scheduling time-sensitive network traffic based on transmit slot planning of claim 1, wherein the comprehensive constraints include transmit slot offset constraints, queue resource constraints, and deadline constraints.
4. The method for scheduling traffic of a time-sensitive network based on transmission slot planning of claim 1, wherein the traffic density calculation formula is as follows:
here, theIndicated as f in offset time slot i At the time of offset, the current resource block is occupiedUsing a resource value; the smaller the value, the smaller the evaluation value for the offset slot, the lower its priority at the time of scheduling.
5. The method for scheduling time-sensitive network traffic based on transmission slot planning according to claim 1, wherein the step of selecting the offsetable slot for each stream in S3 is as follows:
firstly, all the offsetable time slots meeting the offset constraint of the sending time slot of the current stream are found out and form a set, then the time slots meeting the queue resource constraint are found out from the offsetable time slot set, and finally the time slots meeting the cut-off time constraint are found out from the time slots meeting the queue resource constraint.
6. The method for scheduling time-sensitive network traffic based on transmit slot planning of claim 5, wherein the constraint of transmit slot offset constraint is as follows:
wherein f i Offset represents the transmission slot offset, f i prd the period of the data stream, T slot Representing the minimum scheduled time slot.
7. The method for scheduling time-sensitive network traffic based on transmit slot planning of claim 5, wherein the constraints of the queue resource constraints are as follows:
wherein,the occupation condition of the queue resources is represented, 0 or 1,1 is taken to represent that the queue resources of the kth time slot of the kth port of the jth switch are occupied, the total number of flows is n, the number of switches on a flow path is m, the number of ports of the switches is p, t represents the position of the current time slot, and the calculation formula is as follows:
where eta represents the transmission period in which the stream is,representing stream f i Arriving at switch SW j,k Number of hops at time.
8. The method for scheduling traffic in a time-sensitive network based on transmit slot planning of claim 1, wherein the data flow characteristics are as follows:
f i ＝{f i .src,f i .des,f i .size,f i prd,f i .ddl,f i .path}
where F represents the set of all streams, F i Represents the ith stream, f i Src denotes the source end of the ith stream, f i Des denotes the destination end of the ith stream, f i Size represents the packet length of the ith stream, f i prd the period of the ith stream, f i Ddl denotes the deadline of the ith stream, f i Path represents the transmission path of the i-th stream.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311039111.9A CN117240783A (en) | 2023-08-17 | 2023-08-17 | Time sensitive network flow scheduling method based on transmission time slot planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311039111.9A CN117240783A (en) | 2023-08-17 | 2023-08-17 | Time sensitive network flow scheduling method based on transmission time slot planning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117240783A true CN117240783A (en) | 2023-12-15 |
Family
ID=89092067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311039111.9A Pending CN117240783A (en) | 2023-08-17 | 2023-08-17 | Time sensitive network flow scheduling method based on transmission time slot planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117240783A (en) |
-
2023
- 2023-08-17 CN CN202311039111.9A patent/CN117240783A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110024339B (en) | Message forwarding method, forwarding equipment and network equipment | |
| CN114422448B (en) | Time-sensitive network traffic shaping method | |
| US20220150159A1 (en) | Control device, switch device and methods | |
| CN115022182B (en) | Real-time flow scheduling optimization method for train communication network based on QSILP algorithm | |
| CN104301933A (en) | Method for calculating bandwidth and distributing bandwidth in wireless ad hoc network | |
| CN112565068A (en) | Redundant flow scheduling method applied to TSN (traffic service network) | |
| CN116711287A (en) | Circular Queue and Forwarding (CQF) segmentation | |
| CN114245424A (en) | Method and apparatus for a communication network | |
| Huang et al. | Flexible cyclic queuing and forwarding for time-sensitive software-defined networks | |
| CN114257554A (en) | Scheduling method for improving TSN (traffic service network) BE (BE) stream bandwidth utilization rate | |
| CN115604193B (en) | Deterministic resource scheduling method and system in hot rolling control system | |
| CN116366550A (en) | End-to-end low-delay scheduling method for time trigger stream of time sensitive network | |
| CN117240783A (en) | Time sensitive network flow scheduling method based on transmission time slot planning | |
| CN115643220A (en) | Deterministic service transmission method and device based on jitter time delay | |
| Tseng et al. | Trading throughput for freshness: Freshness-aware traffic engineering and in-network freshness control | |
| Rashid et al. | Traffic intensity based efficient packet schedualing | |
| Wang et al. | Traffic Scheduling Method for Power Low-Latency Business in TSN Based on Sending Time Scheduled | |
| Nie et al. | TAMCQF: Hybrid Traffic Scheduling Mechanism Integrating TAS and Multi-CQF in TSN | |
| Liu et al. | Tetris: Near-optimal scheduling for multi-path deadline-aware transport protocol | |
| CN115333998B (en) | Time-sensitive network flow scheduling method suitable for power communication network | |
| US20230254264A1 (en) | Software-defined guaranteed-latency networking | |
| Kong et al. | Run-time per-class routing of AVB flows in in-vehicle TSN via composable delay analysis | |
| Zhang et al. | Deterministic transmittable time-based asynchronous scheduler for fronthaul networks | |
| CN117978752A (en) | Circulation queuing forwarding flow scheduling method for power communication network | |
| WO2024021990A1 (en) | Path determination method and related device |
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 |