Knowledge Inference Engine for Deterministic Network Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current deterministic communication networking technologies, such as TSN, face challenges in meeting high bandwidth demands and ensuring real-time transmission in large-scale IoT networks, particularly due to limitations in schedulability and scalability, as well as the neglect of inter-stream dependencies and varying network topologies.
Innovation Solution
A knowledge inference engine system that utilizes a stream partitioning model and online scheduling module to learn data stream attributes and historical schedule information, enabling improved schedulability and rapid scheduling solution generation by partitioning TT streams based on relevance metrics and employing incremental scheduling algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional deterministic communication networking based on low-bandwidth fieldbuses is used, then deterministic and real-time transmission is achieved, but high bandwidth demands cannot be satisfied
Solution Approach 1:
The patent merges Ethernet's high bandwidth capability with TSN's deterministic transmission guarantees by implementing time-aware shaping at switch ports. This combines the advantages of both technologies: Ethernet provides high bandwidth for massive IoT data, while TSN's programmable gating mechanism ensures deterministic and real-time transmission for time-sensitive applications.
2Reliability
If IEEE 802.1Qbv time-aware shaping is implemented, then high bandwidth transmission with timing guarantees is achieved, but additional scheduling configurations are needed to achieve deterministic delay and bounded jitter
Solution Approach 1:
The patent implements self-service scheduling by enabling switches to automatically generate Gate Control Lists (GCL) based on pre-configured policies without requiring complex manual scheduling configurations. The time-aware shaping mechanism automatically enables and disables egress ports according to predefined periodic schedules, reducing operational complexity while maintaining deterministic delay and bounded jitter guarantees.
3Reliability
If modeling methods such as SMT and ILP are used for scheduling, then deterministic and real-time transmission behavior is guaranteed, but execution time becomes excessively high for large-scale networks
Solution Approach 1:
The patent segments the scheduling problem by dividing TT streams into multiple partitions based on their characteristics and requirements. Each partition can be scheduled independently using simpler algorithms, avoiding the computational complexity of solving the entire scheduling problem globally. This segmentation approach maintains deterministic and real-time transmission guarantees while significantly reducing execution time for large-scale networks.
4Adaptability or versatility
If random stream partitioning is used, then schedulability solution space is increased, but inter-stream dependency relationships are ignored affecting traffic schedulability
Solution Approach 1:
The patent applies local quality by considering inter-stream dependency relationships when partitioning streams, rather than using uniform random partitioning. Streams with strong dependencies are placed in the same partition to maintain their scheduling relationships, while streams with weak or no dependencies can be distributed differently. This approach increases schedulability solution space while ensuring traffic schedulability by respecting inter-stream dependencies.
5Productivity
If offline scheduling optimization is used, then scheduling solutions can be generated rapidly, but the system cannot adapt to varying network topologies and requirements
Solution Approach 1:
The patent implements dynamics by enabling the scheduling system to adapt to varying network topologies and requirements through online adjustments. The time-aware shaping mechanism can dynamically modify Gate Control Lists in response to changing network conditions, allowing the system to maintain optimal scheduling performance whether the network is static or dynamic. This combines rapid scheduling solution generation with adaptability to varying conditions.
Data Source
AI summary
The present invention discloses a knowledge inference engine system and a method of implementation, relating to the field of wired communication networking technology. The system includes a data generation module, a stream partitioning model, an offline scheduling module, an online scheduling module, a scheduling solution base and a historical information base module, the data generation module used to generate a dataset and divide it into a plurality of partitions, the stream partitioning model used to partition the dataset, the offline scheduling module used to generate a scheduling solution for static network requirements, the online scheduling module used to rapidly generate a scheduling solution for a new TT stream, the scheduling solution base used to store a result of the partitioning, an iterative scheduling order for the partitions and the offline scheduling solution, the historical information base used to update and store relevant data information and performance indicators. The method of implementation proposed in the present invention combines and collaboratively operates offline iterative partition scheduling and an online incremental backtracking algorithm, addressing the problem that existing deterministic scheduling methods cannot simultaneously ensure scalability and schedulability.