End-to-end deterministic latency communication method based on ipv6 extension header

Abstract

The application discloses an end-to-end deterministic delay communication method based on an IPv6 extension header, and relates to the technical field of deterministic network communication, and solves the technical problems of lacking real-time monitoring and early warning of hop-by-hop delay consumption and lacking a dynamic adjustment mechanism when a delay budget is insufficient.The application decomposes an end-to-end maximum delay budget hop by hop into a delay budget of each hop by a network controller, and issues the decomposition result to each forwarding node on a path, so that each hop node has a definite delay budget constraint, realizes a leap from extensive management to fine hop-by-hop distribution of the end-to-end delay budget, and then the intermediate forwarding node in each hop actively judges whether the residual delay budget is less than the sum of the theoretical minimum required delay of the residual hop number after updating the residual delay budget, realizes real-time monitoring and active early warning of the delay consumption, links the delay monitoring and the forwarding decision in real time, and can actively identify risks before delay violation occurs.

Description

Technical Field

[0001] This invention relates to the field of deterministic network communication technology, specifically to an end-to-end deterministic delay communication method based on IPv6 extension headers. Background Technology

[0002] Deterministic Networking (DetNet) aims to provide time-sensitive services with extremely low packet loss rates and bounded end-to-end latency. However, as Deterministic Networking expands to large-scale nodes and long-distance transmission scenarios, existing technologies face a series of controversial issues, such as traffic scheduling and dynamic stream processing. To address the enhanced requirements of large-scale Deterministic Networking, the industry has proposed various technical solutions based on IPv6 extension headers.

[0003] Existing solutions mostly focus on hop-by-hop delay marking and queue scheduling, but lack a real-time monitoring mechanism for the cumulative effect of end-to-end delay. During hop-by-hop forwarding, intermediate forwarding nodes cannot perceive whether the current consumed delay is sufficient relative to the remaining path delay budget, and lack the ability to make real-time judgments and early warnings based on the remaining delay budget. Secondly, existing technical solutions lack a dynamic adjustment mechanism when the remaining delay budget is insufficient. When the actual forwarding delay of a certain hop exceeds the expectation, resulting in insufficient remaining delay budget, the existing solutions cannot trigger adjustments in time and can only passively wait for the end-to-end delay to exceed the standard before processing, lacking closed-loop control capabilities. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an end-to-end deterministic latency communication method based on IPv6 extension headers, which solves the problems of lack of real-time monitoring and early warning of hop-by-hop latency consumption and lack of dynamic adjustment mechanism when latency budget is insufficient.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an end-to-end deterministic delay communication method based on IPv6 extension headers, which specifically includes the following steps: Step S1: The network controller receives a deterministic service request initiated by the source device and determines whether the latency requirement can be met based on the current network topology and resource status. If it can be met, the explicit path is calculated based on the source and destination addresses of the service flow. Step S2: The network controller obtains the link latency information and node forwarding latency capability information for each hop on the explicit path, decomposes the end-to-end maximum latency budget into the latency budget for each hop, and sends the hop-by-hop latency budget allocation result to each forwarding node on the path. Step S3: The source device constructs an IPv6 deterministic delay extension header based on the path information and delay budget allocation results. The source device inserts the deterministic delay extension header into the extension header chain of the IPv6 data packet and begins deterministic transmission. Step S4: After receiving the IPv6 data packet carrying the deterministic delay extension header, the intermediate forwarding node calculates the actual forwarding delay of this hop based on the arrival timestamp and departure timestamp of the data packet, updates the consumed delay and remaining delay budget in the deterministic delay extension header, and determines whether the updated remaining delay budget is less than the sum of the theoretical minimum required delay for the remaining hops. If it is less, the dynamic adjustment mechanism is triggered. Step S5: Based on the triggered dynamic adjustment mechanism, send fast feedback information to the network controller; the network controller recalculates the latency budget allocation for the remaining paths according to the fast feedback information and generates an updated hop-by-hop latency budget allocation scheme.

[0006] As a further aspect of the present invention, the end-to-end maximum delay budget D max Decompose into the delay budget d for each hop i satisfy D margin The reserved margin for delay budget, of which .

[0007] As a further aspect of the present invention, the IPv6 deterministic delay extension header includes option type, option length, flow identifier, end-to-end delay budget, consumed delay, remaining delay budget, and current hop index; Record the arrival and departure timestamps of data packets, and calculate the actual forwarding delay d for this hop. c =Departure time - Arrival time.

[0008] As a further aspect of the present invention, after updating the remaining delay budget, each hop node determines whether the remaining delay budget is less than the sum of the theoretical minimum required delays for the remaining hops of the path. If the current hop index is k, then the remaining hop count is nk-1. Then, the remaining delay budget R is determined. 剩余 and The size relationship, where D 剩余 Represents the remaining delay budget for the remaining path, if R 剩余 > If it does, it will forward normally; otherwise, a dynamic adjustment mechanism will be triggered.

[0009] As a further aspect of the present invention, after the current node triggers the dynamic adjustment mechanism, it also executes rapid remedial measures according to the local policy. The rapid remedial measures include at least one of the following methods: Elevate packets to a higher-priority deterministic queue, select alternative forwarding paths within a node, and adjust the window size to fit the current latency in scenarios that support sliding receive windows.

[0010] As a further aspect of the present invention, the network controller recalculates the delay budget allocation for the remaining paths, specifically including: Get the actual delay D that the current data packet has consumed. 消耗 According to formula R 剩余1 =D max -D 消耗 The remaining available delay budget R is calculated. 剩余1 Then allocate the remaining available latency budget R 剩余1 The remaining hops are redistributed to generate an updated hop-by-hop delay budget allocation scheme.

[0011] As a further aspect of the present invention, if the latency budget requirement still cannot be met after the dynamic adjustment mechanism, a destination processing step is also included: After receiving the data packet, the destination device parses the deterministic delay extension header and extracts the end-to-end delay budget D. max Actual consumed delay D actual , hop-by-hop timestamps and status flags, compare D max With D actual The size relationship, if D actual ≤D max If the end-to-end latency of the data packet meets the deterministic requirement, the latency compliance status is recorded; otherwise, it does not meet the deterministic requirement, and the latency non-compliance status is recorded. Then, the destination calculates the end-to-end jitter J based on the hop-by-hop timestamp. If J > jitter threshold J... max Then, calculate the compensation delay C and apply a controllable delay to the data packet in the destination buffer.

[0012] As a further aspect of the present invention, the end-to-end jitter is calculated as follows: for consecutively arriving data packets m and m+1 in the same stream, the jitter... .

[0013] As a further aspect of the present invention, the compensation delay C is calculated as follows: The destination extracts the actual forwarding delay d for each packet at each hop from the deterministic delay extension header. c-i Given i = 1, 2, ..., n, for consecutive data packets m and m+1, calculate the jitter contribution for each hop. And identify the jump segment that contributes the most to jitter. Then according to the formula The compensation amount C is calculated.

[0014] This invention provides an end-to-end deterministic delay communication method based on IPv6 extension headers. Compared with existing technologies, it has the following advantages: This invention decomposes the end-to-end maximum latency budget into hop-by-hop latency budgets through a network controller and distributes the decomposition results to each forwarding node along the path. This ensures that each hop node has a clear latency budget constraint, achieving a leap from extensive management to refined hop-by-hop allocation of the end-to-end latency budget. Furthermore, after updating the remaining latency budget, each intermediate forwarding node proactively determines whether the remaining latency budget is less than the sum of the theoretical minimum required latency for the remaining hops. This enables real-time monitoring and proactive early warning of latency consumption, linking latency monitoring with forwarding decisions in real time, and proactively identifying risks before latency defaults occur.

[0015] When the present invention detects that the remaining latency budget is insufficient, the current node immediately sets an emergency flag in the extension header and sends a rapid feedback message to the controller. The controller recalculates the remaining available latency budget based on the feedback message and reallocates it among the remaining hops to generate an updated hop-by-hop latency budget allocation scheme. This mechanism transforms latency protection from a passive response to an active prevention, overcoming the shortcomings of existing technologies that lack dynamic adjustment capabilities.

[0016] The present invention extracts the actual forwarding delay of each data packet in each hop from the deterministic delay extension header, calculates the jitter contribution of each hop and identifies the hop segment with the largest jitter contribution, and calculates the compensation amount according to the formula, thereby achieving accurate location and targeted compensation of jitter sources. At the same time, the present invention links delay compliance verification with jitter compensation, and dynamically adjusts the jitter compensation strategy according to the delay verification results, thereby achieving joint protection of both delay and jitter dimensions. Attached Figure Description

[0017] Figure 1 This is a flowchart of the end-to-end deterministic delay communication method of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] First Embodiment Please see Figure 1 This application provides an end-to-end deterministic delay communication method based on IPv6 extension headers, which specifically includes the following steps: Step S1: The network controller receives a deterministic service request initiated by the source device and determines whether the latency requirement can be met based on the current network topology and resource status. If it can be met, the explicit path is calculated based on the source and destination addresses of the service flow. Step S2: The network controller obtains the link latency information and node forwarding latency capability information for each hop on the explicit path, decomposes the end-to-end maximum latency budget into the latency budget for each hop, and sends the hop-by-hop latency budget allocation result to each forwarding node on the path. Step S3: The source device constructs an IPv6 deterministic delay extension header based on the path information and delay budget allocation results. The source device inserts the deterministic delay extension header into the extension header chain of the IPv6 data packet and begins deterministic transmission. Step S4: After receiving the IPv6 data packet carrying the deterministic delay extension header, the intermediate forwarding node calculates the actual forwarding delay of this hop based on the arrival timestamp and departure timestamp of the data packet, updates the consumed delay and remaining delay budget in the deterministic delay extension header, and determines whether the updated remaining delay budget is less than the sum of the theoretical minimum required delay for the remaining hops. If it is less, the dynamic adjustment mechanism is triggered. Step S5: Based on the triggered dynamic adjustment mechanism, send fast feedback information to the network controller; the network controller recalculates the latency budget allocation for the remaining paths according to the fast feedback information and generates an updated hop-by-hop latency budget allocation scheme.

[0020] Second Embodiment As a second embodiment of the present invention, the difference from the first embodiment is as follows: The specific processing procedure of step S1 is as follows: The source device receives the latency requirement parameters of the deterministic service, including the end-to-end maximum latency budget, the maximum jitter budget, and the service flow identifier. When the source device initiates a deterministic service request to the network controller, the network controller determines whether the latency requirement can be met based on the current network topology and resource status. If it cannot be met, the response is rejected. If it can be met, the network controller calculates one or more candidate explicit paths based on the source and destination addresses of the service flow.

[0021] The specific processing procedure of step S2 is as follows: The network controller obtains the link latency information and node forwarding latency capability information for each hop on the display path, and the link latency information obtains deterministic link metrics through the extension of the internal gateway protocol; the node forwarding latency capability information includes queue scheduling latency and processing latency, and the end-to-end maximum latency budget D is calculated. max Decompose the time delay budget di for each hop, where i = 1, 2, ..., n, and n is the number of hops in the path. D margin The budget is reserved for the margin of delay. Then, the hop-by-hop delay budget allocation results are sent to each forwarding node on the path; Next, the source device constructs an IPv6 deterministic delay extension header based on the path information and delay budget allocation results. The deterministic delay extension header includes option type, option length, flow identifier, end-to-end delay budget, consumed delay, remaining delay budget, and current hop index. Based on the generated deterministic delay extension header, the source device inserts it into the extension header chain of the IPv6 packet and begins deterministic transmission.

[0022] Third Embodiment As a third embodiment of the present invention, it is implemented based on the second embodiment, and the difference from the second embodiment is as follows: Step 1: After receiving the IPv6 packet with the Deterministic Delay Extension header, the intermediate forwarding point parses the flow identifier and current hop index to identify the deterministic flow to which the packet belongs and its corresponding current path position. Simultaneously, it records the packet's arrival and departure timestamps and calculates the actual forwarding delay d for this hop. c =Departure time - Arrival time, and forwarding is performed according to the queue and scheduling policy allocated to the flow by this node, where the queue and scheduling policy includes periodic queue scheduling based on TCQF (Tagged Cyclic Queuing and Forwarding), scheduling based on strict priority queue (SPQ), or circular queue forwarding based on CQF (Cyclic Queuing and Forwarding). Step 2: After updating the remaining latency budget, each hop node checks whether the remaining latency budget is less than the sum of the theoretical minimum required latency for the remaining hops of the path. If the current hop index is k, then the remaining hops are nk-1. Then, the remaining latency budget R is determined. 剩余 The relationship between the sum of the theoretical minimum required delays and the remaining hop count, where the sum of the minimum required delays is... D 剩余 Represents the remaining delay budget for the remaining path, if R 剩余 If the sum of the remaining hops is the theoretical minimum required latency, then normal forwarding will occur; otherwise, a dynamic adjustment mechanism will be triggered.

[0023] Step 3: Based on the trigger-based dynamic adjustment mechanism, the current node sets an emergency flag in the status flag of the deterministic delay extension header and sends rapid feedback information, including the flow identifier, current hop index, consumed delay, remaining delay budget, and current node identifier. Then, the current node executes rapid remedial measures according to local policies, including elevating the packet to a higher priority deterministic queue, selecting an alternative forwarding path within the node, and adjusting the window size to adapt to the current delay in scenarios that support sliding receive windows. Based on the received rapid feedback information, the network controller recalculates the latency budget allocation for the remaining path and obtains the actual latency D of the current data packet consumption. 消耗 According to formula R 剩余1 =D max -D 消耗 The remaining available delay budget R is calculated. 剩余1 Then allocate the remaining available latency budget R 剩余1 The remaining hops are redistributed to generate an updated hop-by-hop delay budget allocation scheme.

[0024] Fourth embodiment As a fourth embodiment of the present invention, it is implemented based on the third embodiment, and the difference from the third embodiment is that, after the remedial measures and reallocation of the third embodiment, the delay budget requirement still cannot be met, then the destination end performs subsequent processing according to this state, and the specific processing method is as follows: After receiving the data packet, the destination device parses the deterministic delay extension header and extracts the end-to-end delay budget D. max Actual consumed delay D actual , hop-by-hop timestamps and status flags, compare D max With D actual The size relationship, if D actual ≤D max If the end-to-end latency of the data packet meets the deterministic requirement, the latency compliance status is recorded; otherwise, it does not meet the deterministic requirement, and the latency non-compliance status is recorded. Next, the destination calculates the end-to-end jitter J based on the hop-by-hop timestamp. Specifically, for consecutively arriving data packets m and m+1 within the same flow, the jitter... The calculated end-to-end jitter J is then compared with the jitter threshold J. max Compare, if J≤J max If J > J, then no compensation is needed; otherwise, if J > J max The destination end then calculates the amount of delay that needs to be compensated based on the hop-by-hop timestamp information, and the specific calculation method is as follows: The destination extracts the actual forwarding delay d for each packet at each hop from the deterministic delay extension header. c-i Given i = 1, 2, ..., n, for consecutive data packets m and m+1, calculate the jitter contribution for each hop. And identify the jump segment that contributes the most to jitter. Then according to the formula The compensation amount C is calculated.

[0025] Fifth embodiment As a fifth embodiment of the present invention, the focus is on combining the implementation processes of all the above embodiments.

[0026] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0027] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An end-to-end deterministic delay communication method based on IPv6 extension headers, characterized in that, The method specifically includes the following steps: Step S1: The network controller receives a deterministic service request initiated by the source device and determines whether the latency requirement can be met based on the current network topology and resource status. If it can be met, the explicit path is calculated based on the source and destination addresses of the service flow. Step S2: The network controller obtains the link latency information and node forwarding latency capability information for each hop on the explicit path, decomposes the end-to-end maximum latency budget into the latency budget for each hop, and sends the hop-by-hop latency budget allocation result to each forwarding node on the path. Step S3: The source device constructs an IPv6 deterministic delay extension header based on the path information and delay budget allocation results. The source device inserts the deterministic delay extension header into the extension header chain of the IPv6 data packet and begins deterministic transmission. Step S4: After receiving the IPv6 data packet carrying the deterministic delay extension header, the intermediate forwarding node calculates the actual forwarding delay of this hop based on the arrival timestamp and departure timestamp of the data packet, updates the consumed delay and remaining delay budget in the deterministic delay extension header, and determines whether the updated remaining delay budget is less than the sum of the theoretical minimum required delay for the remaining hops. If it is less, the dynamic adjustment mechanism is triggered. Step S5: Based on the triggered dynamic adjustment mechanism, send fast feedback information to the network controller; the network controller recalculates the latency budget allocation for the remaining paths according to the fast feedback information and generates an updated hop-by-hop latency budget allocation scheme.

2. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, The end-to-end maximum delay budget D max Decompose into the delay budget d for each hop i satisfy D margin The reserved margin for delay budget, of which .

3. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, The IPv6 deterministic delay extension header includes option type, option length, flow identifier, end-to-end delay budget, consumed delay, remaining delay budget, and current hop index; Record the arrival and departure timestamps of data packets, and calculate the actual forwarding delay d for this hop. c =Departure time - Arrival time.

4. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, After updating the remaining latency budget, each hop node checks whether the remaining latency budget is less than the sum of the theoretical minimum required latency for the remaining hops of the path. If the current hop index is k, then the remaining hop count is nk-1. Then, the remaining latency budget R is checked. 剩余 and The size relationship, where D 剩余 Represents the remaining delay budget for the remaining path, if R 剩余 > If it does, it will forward normally; otherwise, a dynamic adjustment mechanism will be triggered.

5. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, After the current node triggers the dynamic adjustment mechanism, it also executes quick remedial measures according to the local policy. The quick remedial measures include at least one of the following methods: Elevate packets to a higher-priority deterministic queue, select alternative forwarding paths within a node, and adjust the window size to fit the current latency in scenarios that support sliding receive windows.

6. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, The network controller recalculates the latency budget allocation for the remaining paths, specifically including: Get the actual delay D that the current data packet has consumed. 消耗 According to formula R 剩余1 =D max -D 消耗 The remaining available delay budget R is calculated. 剩余1 Then allocate the remaining available latency budget R 剩余1 The remaining hops are redistributed to generate an updated hop-by-hop delay budget allocation scheme.

7. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 1, characterized in that, If the latency budget requirement still cannot be met after dynamic adjustment, the following destination processing steps are also included: After receiving the data packet, the destination device parses the deterministic delay extension header and extracts the end-to-end delay budget D. max Actual consumed delay D actual , hop-by-hop timestamps and status flags, compare D max With D actual The size relationship, if D actual ≤D max If the end-to-end latency of the data packet meets the deterministic requirement, the latency compliance status is recorded; otherwise, it does not meet the deterministic requirement, and the latency non-compliance status is recorded. Then, the destination calculates the end-to-end jitter J based on the hop-by-hop timestamp. If J > jitter threshold J... max Then, calculate the compensation delay C and apply a controllable delay to the data packet in the destination buffer.

8. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 7, characterized in that, The end-to-end jitter is calculated as follows: for consecutively arriving data packets m and m+1 in the same stream, the jitter... .

9. The end-to-end deterministic delay communication method based on IPv6 extension headers according to claim 7, characterized in that, The compensation delay C is calculated as follows: The destination extracts the actual forwarding delay d for each packet at each hop from the deterministic delay extension header. c-i Given i = 1, 2, ..., n, for consecutive data packets m and m+1, calculate the jitter contribution for each hop. And identify the jump segment that contributes the most to jitter. Then according to the formula The compensation amount C is calculated.

Images