Deterministic Workload Orchestration for Virtualized Control Tasks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control tasks in industrial plants face challenges in achieving deterministic computation and communication within millisecond boundaries, limiting flexibility in virtualized computing environments.
Innovation Solution
A computer-implemented method for orchestrating workload execution on computing platforms, determining resource consumption and performance requirements, and negotiating with management entities to ensure deterministic execution and communication, allowing for flexible deployment of control functions in virtualized environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If control tasks are executed on dedicated hardware to guarantee deterministic computation and communication, then timing precision and reliability are improved, but flexibility and adaptability deteriorate
Solution Approach 1:
The patent segments the control task execution into multiple independent virtual controllers that can be allocated to different physical controllers. Each virtual controller encapsulates specific control functions, allowing deterministic execution to be maintained through structured segmentation while enabling flexible reconfiguration by reallocating virtual controllers across the physical controller pool.
Solution Approach 2:
The patent creates a universal pool of physical controllers that can execute multiple different virtual controllers. This multi-functionality allows the same physical hardware to serve various control tasks deterministically, achieving both timing precision through controlled allocation and flexibility through reusable hardware resources.
2Adaptability or versatility
If control tasks are migrated to virtualized computing environments to increase flexibility, then adaptability and ease of deployment are improved, but deterministic execution and timing precision deteriorate
Solution Approach 1:
The patent performs preliminary actions by pre-defining virtual controllers with specific control functions and pre-establishing allocation rules before actual execution. This advance structuring enables the virtualized environment to maintain deterministic timing by ensuring that resource allocation and execution parameters are predetermined, eliminating runtime uncertainties.
Solution Approach 2:
The patent introduces virtual controllers as intermediary layers between the virtualized computing environment and physical hardware. These intermediaries abstract the deterministic execution requirements from the flexible virtualization layer, allowing timing precision to be maintained through controlled interfaces while preserving adaptability in the upper management layers.
3Productivity
If multiple control functions are allocated to shared physical controllers to improve resource utilization, then productivity and efficiency are improved, but reliability and isolation deteriorate
Solution Approach 1:
The patent segments control functions into distinct virtual controllers that are logically isolated even when executed on shared physical hardware. This segmentation maintains reliability by preventing interference between different control tasks while improving productivity through efficient sharing of the underlying physical controller resources.
Solution Approach 2:
The patent creates virtual copies of controller functionality through virtual controllers that run on shared physical hardware. These virtual copies provide the necessary isolation and reliability for each control function while enabling multiple instances to coexist on the same physical platform, thus improving resource utilization without sacrificing task independence.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method (100) for orchestrating the deterministic execution of a given workload (3) on at least one computing platform (4), comprising the steps of: • determining (110) a consumption (3a) of at least one computing resource and a consumption (3b) of at least one communications resource that result from executing a given workload (3) or a part thereof; • determining (120), from these consumptions (3a, 3b) and a given set of requirements (5) that relate to the timing, synchronicity and/or availability of executing the given workload (3) or part thereof, at least one performance requirement (6) with respect to execution of the workload (3) or part thereof; and • negotiating (130), with a management entity (40) of the computing platform (4), execution of the workload (3) or part thereof on the computing platform (4) according to the at least one performance requirement (6).