Time-Triggered Ethernet Scheduling for Resource Contention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current algorithms for scheduling in Time-Triggered Ethernet (TTE) networks fail to converge on a valid global schedule for proper traffic throughput due to physical resource contentions and serialization issues, especially when dealing with low-rate, low-latency data sets and switched interlink connectivity, which limits the parallel usage of network resources.
Innovation Solution
A pre-processing method using a Network Scheduling Tool (NST) that detects and stores Virtual Link (VL) information for common physical resources, performs a two-pass scheduling procedure with conflict detection and resolution logic, including double-sided timing windows, to prioritize and schedule VLs efficiently, avoiding conflicts and optimizing bin placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current scheduling algorithms are used for TTE networks, then the scheduling process is simple, but the algorithms fail to converge on a valid global schedule and cannot handle physical resource contentions effectively
Solution Approach 1:
The patent applies preliminary action by performing pre-processing of Virtual Link information before the actual scheduling procedure. The system detects and stores VL information associated with common physical resources in advance, creating a foundation for conflict detection during scheduling. This preliminary detection and storage of resource contention information enables the algorithm to converge more reliably on valid global schedules by anticipating and preparing for potential conflicts before they arise in the scheduling process.
Solution Approach 2:
The patent implements feedback mechanisms through conflict detection logic that monitors resource contentions during scheduling and uses this information to adjust scheduling decisions. The system detects physical resource contentions, stores this information, and uses it to identify conflicting VLs during the scheduling procedure. This feedback loop allows the algorithm to adapt to resource constraints and converge on valid schedules by learning from detected conflicts and adjusting scheduling assignments accordingly.
2Productivity
If VLs are scheduled without detecting physical resource contentions, then the scheduling process is faster, but serialization occurs on common physical resources blocking new VLs from being scheduled
Solution Approach 1:
The patent applies preliminary action by detecting and storing VL information associated with common physical resources before the scheduling procedure begins. This pre-detection of resource contentions allows the system to identify potential serialization issues in advance and adjust scheduling decisions to avoid them, thereby increasing the number of VLs that can be successfully scheduled without causing queuing delays during actual operation.
Solution Approach 2:
The patent converts the harmful effect of physical resource contentions into a beneficial scheduling optimization. By detecting resource contentions and identifying conflicting VLs during pre-processing, the system uses this conflict information to make smarter scheduling decisions that avoid serialization. What would normally be a blocking constraint becomes a guide for optimizing VL placement and timing, thereby increasing overall network productivity and reducing queuing delays.
3Adaptability or versatility
If low-rate, low-latency data sets are scheduled with current algorithms, then the basic assumptions of rate and latency tracking are violated, but the algorithms still fail to produce valid schedules
Solution Approach 1:
The patent implements feedback through conflict detection logic that monitors resource contentions and uses this information to adjust scheduling for diverse data sets. The system detects VL information associated with common physical resources and uses this feedback to identify conflicting VLs, allowing it to handle low-rate, low-latency data sets that violate basic assumptions by adapting scheduling decisions based on actual resource contention patterns rather than relying on rate-latency tracking assumptions.
Solution Approach 2:
The patent applies parameter changes by using detected conflict information to dynamically adjust scheduling parameters for different VLs. Instead of relying on fixed assumptions about rate and latency relationships, the system changes scheduling parameters based on actual resource contention detection, allowing it to accommodate diverse data sets including low-rate, low-latency traffic while maintaining schedule validity through adaptive parameter adjustment.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods, systems, and apparatuses for scheduling a plurality of Virtual Links (VLs) in a Time-Triggered Ethernet (TTE) network by pre-processing, by a scheduling algorithm implemented by a Network Scheduling Tool (NST), VL information prior to initiating a scheduling procedure by, detecting VL information associated with VLs that having common physical resources that include a common direction of a switching port or an egress end system port; and storing the VL information associated with the set of VLs for retrieval by the NST to parse a VL list for scheduling to determine one or more conflicting VLs in functionalities with a VL that is to be scheduled by a first pass that attempts favoring scheduling a VL into a bin when previously scheduled VLs fail to exhibit conflicts; and a second pass that attempts to resolve at least one conflict exhibited in the scheduling procedure by offsetting a transmit time.