Asynchronous Start for Timed Functions in Distributed Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current distributed real-time systems face challenges in synchronizing control functions across multiple masters in decentralized architectures, particularly in handling asynchronous events which cannot be scheduled a priori, limiting their versatility and applicability in time-sensitive applications.
Innovation Solution
A decentralized distributed system architecture that incorporates time-sensitive networking features over Ethernet, enabling precise chassis-to-chassis synchronization and supporting asynchronous start events through a signal-based timing infrastructure, allowing timed-functions to transition between future and asynchronous events, and utilizing a Local Signal Group parameter to manage latency and event propagation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a centralized master-slave architecture is used to simplify schedule generation, then the task of calculating network schedules is simplified, but the system cannot distribute control functions among multiple masters
Solution Approach 1:
The patent segments the centralized control architecture into multiple independent master devices, each capable of executing control functions autonomously. This segmentation allows control functions to be distributed across multiple masters while maintaining simplified schedule generation at each individual master level, resolving the contradiction between architectural simplicity and distribution capability.
Solution Approach 2:
The patent introduces a new dimension of operation by enabling masters to function independently without requiring a centralized coordinator. This dimensional shift from centralized-to-distributed control allows the system to achieve both schedule generation simplicity at the local level and control function distribution across multiple masters simultaneously.
2Reliability
If synchronization points are scheduled for all slaves to latch inputs and update outputs simultaneously, then data consistency is ensured, but asynchronous events cannot be handled
Solution Approach 1:
The patent implements dynamic synchronization where each master device independently determines its own synchronization points based on real-time conditions. This dynamic approach allows the system to maintain data consistency through local synchronization while simultaneously handling asynchronous events by adjusting synchronization timing adaptively at each master level.
Solution Approach 2:
The patent prepares masters in advance to handle both synchronous and asynchronous events by configuring them with the capability to operate independently. This preliminary preparation enables masters to latch inputs and update outputs at appropriately timed synchronization points while being ready to respond to asynchronous events without requiring centralized coordination.
3Measurement precision
If the system supports only future time events for scheduled operations, then precise scheduling is achieved, but asynchronous events that cannot be scheduled a priori are limited
Solution Approach 1:
The patent makes each master device universal by enabling it to handle both future time events (scheduled operations) and asynchronous events (unscheduled operations). This multi-functionality allows the system to maintain precise scheduling for planned operations while simultaneously supporting asynchronous events that cannot be scheduled in advance, resolving the contradiction between scheduling precision and event type support.
Data Source
AI summary
Asynchronous event-based start of input/output operations is implemented in a distributed system. Within the distributed system, each master device—of a plurality of master devices coupled to a respective plurality of slave devices via an internal network—may implement one or more timed-functions configured to control timing of physical input operations and/or physical output operations for the respective plurality of slave devices, and streams between the master device and the respective plurality of slave devices. A subset of the slave devices may be further interconnected via a shared signal-based bus, which may be used to propagate an asynchronous event that may be used to start at least one of the one or more timed functions implemented on a master device coupled to at least one slave device of the subset of slave devices. The asynchronous event may be generated by one of the slave devices.