A network transmission method suitable for time deterministic services

Abstract

The present application relates to the technical field of network communication, in particular to a network transmission method suitable for time deterministic service, which realizes transmission support for time deterministic service by receiving and analyzing time deterministic service demand and maintaining a soft time division time matrix composed of time windows; a full-link sensing method is used to acquire network resources and link state, and then appropriate route and sending time slice are allocated to the service through route allocation and time slice allocation, and relevant strategy is issued to each forwarding node, and the result of executing the strategy by the forwarding node meets the requirement of time determinacy of the service. Through the network transmission method, controllable transmission of deterministic service can be met, and maximum network throughput is maintained.

Description

Technical Field

[0001] This invention relates to the field of network communication technology, and in particular to a network transmission method suitable for time-deterministic services. Background Technology

[0002] With the rapid development of industrial automation, intelligent transportation, and other real-time applications, the demand for low latency and high reliability in network communication is increasing. Against this backdrop, deterministic transmission has become an important direction in network technology development. Deterministic transmission means that data packets can be transmitted accurately from the source node to the destination node within a predetermined time window. However, current IP network architectures struggle to guarantee deterministic transmission across the entire network, especially in complex and dynamically changing network environments. Traditional time-deterministic schemes, based on clock synchronization mechanisms, require maintaining a global clock on each relevant node, resulting in additional overhead and system complexity.

[0003] Software-defined (SD) is a system design philosophy that aims to improve network programmability and management flexibility by decoupling control logic and data forwarding functions from hardware devices. While SD technology offers significant advantages in load balancing, network security, and traffic management, it still faces a number of technical challenges in achieving deterministic transmission.

[0004] Time Division Multiplexing (TDM) is a method for multiplexing signals over a single communication channel. In TDM, the time axis is divided into multiple small time slots, each allocated to a specific signal source. This method has been widely used in traditional telecommunications networks, but its application in modern packet-switched networks is relatively limited. As mentioned above, TDM also requires maintaining the consistency of a global clock, i.e., clock synchronization is essential.

[0005] While these technologies each have their own advantages and application scenarios, effectively integrating them to achieve deterministic transmission with low latency, high reliability, and programmability remains an unsolved problem. For example, how to implement timeline allocation within a software-defined architecture, and how to ensure high-throughput transmission while using the timeline.

[0006] Therefore, seeking a new method that can comprehensively utilize deterministic transmission, software-defined technology, and time-division technology, while abandoning the requirement of clock synchronization, to achieve more reliable, efficient, and flexible network communication has important theoretical significance and practical application value. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention proposes a network transmission method suitable for time-deterministic services, which can satisfy the controllable transmission of deterministic services and maintain maximum network throughput.

[0008] This invention is achieved by adopting the following technical solution:

[0009] A network transmission method suitable for time-deterministic services includes the following steps:

[0010] Step S1. Perform a demand analysis on the time-deterministic services received by each source node, including the deterministic arrival time analysis of the time-deterministic services at the destination node, the routing demand analysis of the time-deterministic services, and the resource demand analysis of the time-deterministic services.

[0011] Step S2. Use a full-link awareness method to obtain network operating status;

[0012] Step S3. Based on the demand analysis results of time-deterministic services in Step S1 and the network operation status in Step S2, allocate routes for time-deterministic services at the current moment;

[0013] Step S4. Based on the routing information allocated to each time-deterministic service, determine the transmission deadline of each forwarding node in the route;

[0014] Step S5. Based on the constructed soft time-division time matrix, allocate a transmission time slice for the time-deterministic service within the time window of each forwarding node participating in the routing of the time-deterministic service;

[0015] Step S6. After allocating the routing and transmission time slices for all time-deterministic services, update the network status and the occupancy status of the soft time-division matrix, and feed back the updated status;

[0016] Step S7. Wait for the next batch of time-deterministic transactions and repeat steps S1 to S6 above.

[0017] The network operation status in step S2 includes the overall network resource usage and link availability.

[0018] The soft time-division time matrix is ​​constructed as follows: a time window is created for each forwarding node, and the time window consists of multiple time slices; the time windows of each forwarding node are combined together to form the soft time-division time matrix.

[0019] In the soft time-division time matrix, the starting time of the time window for each forwarding node is the same.

[0020] As the network runs for a period of time, the time window destroys the time slices prior to the current moment.

[0021] The route allocation in step S3 specifically includes the following steps:

[0022] Step S 31 Analyze the connectivity of each link in the current network, the overall network resource usage, the resource consumption of the current time-deterministic services, the routing requirements of the time-deterministic services themselves, and the deterministic time requirements for the arrival at the destination node of the time-deterministic services.

[0023] Step S 32 Step S 31 Using the conditions as constraints, a transmission route for current-time deterministic services is generated from the source node to the destination node.

[0024] If multiple feasible transmission routes exist, the route with the lowest resource consumption is selected; if two or more transmission routes have the lowest resource consumption, a random route is selected.

[0025] Step S5 specifically includes the following steps:

[0026] Step S 51 Analyze the time window occupancy of forwarding nodes on the current time-deterministic service route;

[0027] Step S 52 Based on the time window occupancy of forwarding nodes and the transmission deadline, a transmission time slice is allocated for current time deterministic services on the soft time-division time matrix.

[0028] If a transmission time slice cannot be found for the time-deterministic service, the route for the time-deterministic service will be reallocated.

[0029] If the number of times a time-deterministic service is rerouted reaches a threshold, but the time-deterministic service still cannot meet its deterministic requirements or cannot be assigned a suitable route, the time-deterministic service will be rejected.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0031] 1. This invention addresses the transmission problem of deterministic services in the current network communication field. It employs software-defined and time-division multiplexing methods to design a time-deterministic service transmission method based on software-defined technology, referred to as soft time-division. This invention maintains a global network timeline in the server, abandoning the global clock synchronization mechanism, and assigns appropriate routes and forwarding times at each routing node to each arriving time-deterministic service, thereby achieving deterministic service transmission.

[0032] This invention proposes a network transmission method (i.e., soft time division) suitable for time-deterministic services, aiming to achieve deterministic transmission of network services through time slot partitioning technology. This invention significantly improves the determinism of data transmission, making it particularly suitable for applications with high real-time requirements, such as video conferencing and industrial automation. By dynamically adjusting network resource allocation, this invention optimizes bandwidth utilization, reduces network congestion, and achieves maximum throughput for deterministic services. This invention is easily integrated with existing network environments, supports technology expansion, and supports various network applications. Overall, this invention not only improves the efficiency and stability of network transmission but also enhances network flexibility, possessing significant application value in the field of modern network communication.

[0033] 2. In this invention, as the network runs for a period of time, the time window will destroy the time slices before the current moment, which can reduce the computing load on the planning server.

[0034] 3. In this invention, a closed-loop feedback mechanism is adopted, which facilitates the dynamic adjustment of subsequent data transmission strategies based on the actual transmission situation. Attached Figure Description

[0035] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments, wherein:

[0036] Figure 1 This is a schematic diagram illustrating the process of deterministic transmission using a soft time-division time axis in this invention.

[0037] Figure 2 This is a schematic diagram of the soft time-division system in this invention;

[0038] Figure 3 This is a schematic diagram illustrating the planned server functions in this invention; Detailed Implementation

[0039] Example 1

[0040] As a basic embodiment of the present invention, the present invention includes a network transmission method suitable for time-deterministic services, comprising the following steps:

[0041] Step S1. Perform a demand analysis on the time-deterministic services received by each source node, including the deterministic arrival time analysis of the time-deterministic services at the destination node, the routing demand analysis of the time-deterministic services, and the resource demand analysis of the time-deterministic services.

[0042] Step S2. Use the end-to-end sensing method to obtain the network operating status.

[0043] Step S3. Based on the demand analysis results of time-deterministic services in Step S1 and the network operation status in Step S2, allocate routes for time-deterministic services at the current moment.

[0044] Step S4. Based on the routing information allocated to each time-deterministic service, determine the transmission deadline of each forwarding node in the route.

[0045] Step S5. Based on the constructed soft time-division time matrix, allocate a transmission time slice for the time-deterministic service within the time window of each forwarding node participating in the routing of the time-deterministic service.

[0046] Step S6. After allocating the routing and transmission time slices for all time-deterministic services, update the network status and the occupancy status of the soft time-division matrix, and feed back the updated status.

[0047] Step S7. Wait for the next batch of time-deterministic transactions and repeat steps S1 to S6 above.

[0048] Example 2

[0049] As a preferred embodiment of the present invention, the present invention includes a network transmission method suitable for time-deterministic services, comprising the following steps:

[0050] Step S1. Perform a demand analysis on the time-deterministic services received by each source node, including the deterministic arrival time analysis of the time-deterministic services at the destination node, the routing demand analysis of the time-deterministic services, and the resource demand analysis of the time-deterministic services.

[0051] Step S2. Use the end-to-end sensing method to obtain the network operation status, including the overall network resource usage and link availability.

[0052] Step S3. Based on the demand analysis results of time-deterministic services in Step S1 and the network operation status in Step S2, assign a suitable route to the time-deterministic service at the current moment. The route for the time-deterministic service includes a source node, a destination node, and multiple forwarding nodes.

[0053] Step S4. Based on the routing information allocated to each time-deterministic service, determine the transmission deadline of each forwarding node in the route.

[0054] Step S5. Based on the constructed soft time-division time matrix, allocate an appropriate transmission time slice for the time-deterministic service within the time window of each forwarding node participating in the routing of the time-deterministic service.

[0055] The soft time-division time matrix is ​​constructed as follows: a time window is created for each forwarding node, and the time window consists of multiple time slices; the time windows of each forwarding node are combined together to form a soft time-division time matrix.

[0056] Step S6. Distribute the routing policy and soft time-division time axis policy to each forwarding node in the network. In actual network transmission, service data will pass through each forwarding node sequentially according to the planned routing policy. When each node receives service data, it will forward the service to the next node according to the plan in its soft time-division time axis, when the current time reaches the preset sending window.

[0057] After allocating routing and transmission time slices for all time-deterministic services, update the network status and the occupancy status of the soft time-division matrix, and then feed back the updated status.

[0058] Step S7. Wait for the next batch of time-deterministic transactions and repeat steps S1 to S6 above.

[0059] Example 3

[0060] In another preferred embodiment of the present invention, the present invention includes a network transmission method suitable for time-deterministic services, comprising the following steps:

[0061] Step S1. Perform a demand analysis on the time-deterministic services received by each source node, including the deterministic arrival time analysis of the time-deterministic services at the destination node, the routing demand analysis of the time-deterministic services, and the resource demand analysis of the time-deterministic services.

[0062] Step S2. Use the end-to-end sensing method to obtain the network operating status.

[0063] Step S3. Based on the demand analysis results of time-deterministic services in Step S1 and the network operation status in Step S2, allocate routes for time-deterministic services at the current moment, specifically including the following steps:

[0064] Step S 31 Analyze the connectivity of each link in the current network, the overall network resource usage, the resource consumption of currently processing time-deterministic services, the routing requirements of the time-deterministic services themselves, and the deterministic time requirements for the arrival at the destination node for the time-deterministic services.

[0065] Step S 32 Step S 31 Using the conditions as constraints, a transmission route for current-time deterministic services is generated from the source node to the destination node.

[0066] Step S4. Based on the routing information allocated to each time-deterministic service, determine the transmission deadline of each forwarding node in the route.

[0067] Step S5. Based on the constructed soft time-division time matrix, allocate a transmission time slice for the time-deterministic service within the time window of each forwarding node participating in the routing of the time-deterministic service. This specifically includes the following steps:

[0068] Step S 51 Analyze the time window occupancy of forwarding nodes on the current time-deterministic service route.

[0069] Step S 52 Based on the time window occupancy of forwarding nodes and the transmission deadline, a transmission time slice is allocated for current time deterministic services on the soft time-division time matrix.

[0070] Step S6. After allocating the routing and transmission time slices for all time-deterministic services, update the network status and the occupancy status of the soft time-division matrix, and feed back the updated status.

[0071] Step S7. Wait for the next batch of time-deterministic transactions and repeat steps S1 to S6 above.

[0072] Example 4

[0073] As the preferred embodiment of the present invention, the present invention includes a network transmission method suitable for time-deterministic services, which can be implemented based on a soft time-division system. See the appendix to the specification for details. Figure 2 The soft time-division system includes a planning server, a soft time-division time matrix, and deterministic transmission routes. The planning server generates appropriate routes and time slices for time-deterministic services at forwarding nodes based on network operation and service deterministic requirements. (See attached specification.) Figure 3 The main functions of the planning server are: to analyze business requirements, allocate business routes, determine the transmission time slices of each forwarding node in the route, and issue software-defined policies.

[0074] Refer to the instruction manual appendix Figure 1 The network transmission method specifically includes the following steps:

[0075] Step S1. Various types of services arrive at the source nodes of the physical network. The source nodes send the time-deterministic services (hereinafter referred to as services) to the planning server. The planning server performs demand analysis on the services received by each source node, including deterministic arrival time analysis of the services at the destination node, routing demand analysis of the services, and resource demand analysis of the services.

[0076] The deterministic arrival time of the service at the destination node indicates that the service needs to arrive at the destination node at a specific time; it cannot arrive early or late, but there is an acceptable threshold for this time. That is, the actual arrival time cannot be less than the ideal time minus the threshold, and cannot be greater than the ideal time plus the threshold. In this embodiment, the deterministic arrival time of the destination node can be 1.3 ± 0.1 seconds. The routing requirements of the service include which forwarding nodes the service must pass through and the order in which they pass through the forwarding nodes. In this embodiment, the node that must be passed through can be forwarding node 2. The resource requirements of the service mainly refer to the link bandwidth required, and the computing and storage resources required by the forwarding nodes. In this embodiment, the bandwidth required is 2MB.

[0077] Step S2. Using the software-defined controller component in the planning server, adopt the end-to-end awareness method to obtain the network operation status, including the overall network resource usage and link availability.

[0078] Step S3. Based on the service demand analysis results in Step S1 and the network operation status in Step S2, plan the server to allocate appropriate routes for the services at the current moment. The service route includes the source node, destination node, and multiple forwarding nodes.

[0079] The specific steps involved in route allocation are as follows:

[0080] Step S 31 Analyze the connectivity of each link in the current network, the overall network resource usage, the resource consumption of the current processing business, the routing requirements of the business itself, and the deterministic timing requirements for the business to reach the destination node.

[0081] Step S 32 Step S 31 Using the conditions as constraints, the current service's transmission route from the source node to the destination node is generated.

[0082] If multiple feasible paths exist, the route with the lowest resource consumption is selected; if two or more routes have the lowest resource consumption, one is selected randomly.

[0083] Step S4. Based on the routing information allocated to each service, determine the transmission deadline for each forwarding node in the route. The transmission deadline of a forwarding node refers to the time slice in which the service must be sent before that time; otherwise, the service cannot meet the time determinism requirement of its destination node.

[0084] Step S5. The planning server allocates an appropriate transmission time slice for the service within the time window of each forwarding node participating in the routing of the service, based on the constructed soft time-division time matrix.

[0085] The soft time-division time matrix is ​​constructed as follows: the planning server creates a time window for each forwarding node, and the time window consists of multiple time slices. The size of each time slice ensures that the service can complete processing and transmission within that time slice. The time windows of each forwarding node are combined to form the soft time-division time matrix. This soft time-division time matrix is ​​maintained by the planning server.

[0086] In this system, each forwarding node's time window starts at the same time, which by default is the time when the earliest deterministic service was sent from its corresponding source node. As the network runs, time slices prior to the current time are destroyed within the time window to reduce the computational load on the planning server. Furthermore, time slices only apply to the specified time when deterministic services are sent at a particular forwarding node; non-deterministic services are not subject to time slice constraints.

[0087] The allocation of a suitable transmission time slice in step S5 specifically includes the following steps:

[0088] Step S 51 Analyzing the time window occupancy of the forwarding nodes on the current service route, the main reason for the occupancy is that other deterministic services use certain time slices for transmission at this forwarding node.

[0089] Step S 52 The planning server allocates a suitable transmission time slice for the current service based on the time window occupancy of the forwarding nodes and the transmission deadline on the soft time-division matrix. If the planning server cannot find a suitable transmission time slice for the service, it will reallocate the route for the service and repeat the above steps.

[0090] When the planning server replans a service a certain number of times, but the service still cannot meet its deterministic requirements or cannot be assigned a suitable route, the service will be rejected.

[0091] Step S6. The routing policy and soft time-division time axis policy are distributed to each forwarding node in the network through the software-defined controller. After allocating the routes and transmission time slices for all services, the network status and the occupancy status of the soft time-division time matrix are updated, and the updated status is fed back.

[0092] Step S7. Wait for the next batch of business and repeat steps S1 to S6 above.

[0093] In summary, any other corresponding modifications made by those skilled in the art after reading this invention document, without requiring creative mental effort, based on the technical solutions and concepts of this invention, are all within the scope of protection of this invention.

Claims

1. A network transmission method suitable for time-deterministic services, characterized in that: Includes the following steps: Step S1. Perform a demand analysis on the time-deterministic services received by each source node, including the deterministic arrival time analysis of the time-deterministic services at the destination node, the routing demand analysis of the time-deterministic services, and the resource demand analysis of the time-deterministic services. Step S2. Use a full-link awareness method to obtain network operating status; Step S3. Based on the demand analysis results of time-deterministic services in Step S1 and the network operation status in Step S2, allocate routes for time-deterministic services at the current moment; Step S4. Based on the routing information allocated to each time-deterministic service, determine the transmission deadline of each forwarding node in the route; Step S5. Based on the constructed soft time-division time matrix, allocate a transmission time slice for the time-deterministic service within the time window of each forwarding node participating in the routing of the time-deterministic service; Step S6. After allocating the routing and transmission time slices for all time-deterministic services, update the network status and the occupancy status of the soft time-division matrix, and feed back the updated status; Step S7. Wait for the next batch of time-deterministic transactions and repeat steps S1 to S2 above. 6； The soft time-division time matrix is ​​constructed as follows: a time window is created for each forwarding node, and the time window consists of multiple time slices; the time windows of each forwarding node are combined together to form a soft time-division time matrix.

2. The network transmission method for time-deterministic services according to claim 1, characterized in that: The network operation status in step S2 includes the overall network resource usage and link availability.

3. The network transmission method for time-deterministic services according to claim 1, characterized in that: In the soft time-division time matrix, the starting time of the time window for each forwarding node is the same.

4. A network transmission method for time-deterministic services according to claim 3, characterized in that: As the network runs for a period of time, the time window destroys the time slices prior to the current moment.

5. A network transmission method for time-deterministic services according to claim 2, characterized in that: The route allocation in step S3 specifically includes the following steps: Step S 31 Analyze the connectivity of each link in the current network, the overall network resource usage, the resource consumption of the current time-deterministic services, the routing requirements of the time-deterministic services themselves, and the deterministic time requirements for the arrival at the destination node of the time-deterministic services. Step S 32 Step S 31 Using the conditions as constraints, a transmission route for current-time deterministic services is generated from the source node to the destination node.

6. A network transmission method for time-deterministic services according to claim 5, characterized in that: If multiple feasible transmission routes exist, the route with the lowest resource consumption is selected; if two or more transmission routes have the lowest resource consumption, a random route is selected.

7. A network transmission method for time-deterministic services according to claim 2, characterized in that: Step S5 specifically includes the following steps: Step S 51 Analyze the time window occupancy of forwarding nodes on the current time-deterministic service route; Step S 52 Based on the time window occupancy of forwarding nodes and the transmission deadline, a transmission time slice is allocated for current time deterministic services on the soft time-division time matrix.

8. A network transmission method for time-deterministic services according to claim 7, characterized in that: If a transmission time slice cannot be found for the time-deterministic service, the route for the time-deterministic service will be reallocated.

9. A network transmission method for time-deterministic services according to claim 8, characterized in that: If the number of times a time-deterministic service is rerouted reaches a threshold, but the time-deterministic service still cannot meet its deterministic requirements or cannot be assigned a suitable route, the time-deterministic service will be rejected.

Images