TSN Traffic Scheduling via Gate Control Lists
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the fully distributed model of Time-Sensitive Networking (TSN), the existing implementation causes high latency and unstable latency between the talker device and the listener device due to the conventional queue scheduling mechanism, which is not optimized for low latency and synchronization requirements.
Innovation Solution
A traffic scheduling method is introduced where the first network device receives talker and listener attribute messages to determine traffic scheduling information and transmission paths, generating a gate control list to manage port states, thereby optimizing data stream transmission between the talker and listener devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a conventional queue scheduling mechanism is used in the fully distributed TSN model, then device complexity is reduced, but latency increases and becomes unstable
Solution Approach 1:
The patent applies preliminary action by having network devices pre-calculate and reserve transmission resources before actual data flow occurs. The fully distributed model enables each device to advance resource reservation decisions, establishing transmission parameters in advance rather than reacting to real-time conditions, thereby reducing latency while maintaining distributed simplicity
Solution Approach 2:
The patent changes the scheduling parameters from conventional queue-based timing to time-division multiplexing with explicit time slots and periods. This parameter transformation enables microsecond-level precision by defining transmission moments rather than relying on software queue processing, directly addressing the latency issue while keeping the distributed architecture intact
2Device complexity
If a conventional queue scheduling mechanism is used in the fully distributed TSN model, then implementation simplicity is maintained, but latency stability deteriorates
Solution Approach 1:
By performing resource reservation and time slot allocation in advance, the system eliminates variability in transmission timing. The preliminary establishment of fixed time slots ensures consistent latency performance across multiple transmissions, transforming unstable latency into stable, predictable delays while maintaining implementation simplicity through distributed algorithms
Solution Approach 2:
The patent incorporates feedback mechanisms where network devices monitor transmission conditions and adjust time slot allocations accordingly. This feedback loop enables the system to compensate for variations in network state, maintaining latency stability without requiring complex centralized control, thus resolving the contradiction between simplicity and stability
Data Source
AI summary
A traffic scheduling method includes determining, by a first network device, first traffic scheduling information and a transmission path of a first data stream based on a first talker attribute message received from a talker device and a listener attribute message received from a listener device, and then sending, by the first network device, a first traffic scheduling message to a network device on the transmission path. The first traffic scheduling message includes the first traffic scheduling information. The first traffic scheduling information indicates the network device on the transmission path to generate a gate control list. The gate control list indicates the network device on the transmission path to control, based on the gate control list, a state of a port used to transmit the first data stream.