Real-Time Task Scheduling Using Inexact and Exact Feasibility Testing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for feasibility testing of pre-emptive real-time systems are inefficient, particularly in determining schedulability under both inexact and exact conditions, with inexact testing limited to low system utilization and exact testing being complex and impractical for online systems.

Innovation Solution

A method that sorts tasks into subsets for inexact and exact condition testing, using a combination of Liu & Layland bound and Response Time Analysis, starting from the lowest priority task to determine schedulability, allowing for faster and more practical feasibility analysis in pre-emptive real-time systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If inexact condition testing is used for feasibility testing, then the testing speed is improved, but the system utilization is limited to low levels

Engineering Contradiction:

Improvetesting speedVSAvoidsystem utilization

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent segments the task set into two subsets: a first subset tested using inexact condition testing for fast evaluation, and a second subset tested using exact condition testing for comprehensive verification. This segmentation allows the system to benefit from both the speed of inexact testing and the accuracy of exact testing, resolving the contradiction between testing speed and system utilization capability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent dynamically adjusts the testing approach by first applying inexact condition testing to quickly evaluate tasks that can be efficiently tested this way, then applying exact condition testing to the remaining tasks. This dynamic two-phase approach optimizes overall testing efficiency while maintaining high system utilization

Inventive Principle:

Principle #15Dynamics

2Adaptability or versatility

If exact condition testing is used for feasibility testing, then the system utilization is improved, but the testing complexity increases

Engineering Contradiction:

Improvesystem utilizationVSAvoidtesting complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent divides the task set into two subsets based on their suitability for different testing methods. The first subset is identified as suitable for inexact condition testing, reducing the overall complexity burden. The second subset requires exact condition testing for higher utilization. This segmentation reduces the complexity impact while maintaining high system utilization

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies inexact condition testing to the extent possible (to the first subset of tasks) before applying exact condition testing to the remaining tasks. This partial application of the simpler testing method reduces overall complexity while still achieving high system utilization through the complementary exact testing phase

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If exact condition testing is used for feasibility testing, then the testing accuracy is improved, but the testing time increases

Engineering Contradiction:

Improvetesting accuracyVSAvoidtesting time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments tasks into two groups: those suitable for fast inexact testing and those requiring accurate exact testing. By applying the appropriate testing method to each segment, the system achieves high overall accuracy while minimizing total testing time, as not all tasks require the computationally intensive exact testing method

Inventive Principle:

Principle #1Segmentation

4Ease of manufacture

If traditional feasibility testing methods are used, then the implementation is simple, but the CPU utilization cannot reach 100%

Engineering Contradiction:

Improveimplementation simplicityVSAvoidCPU utilization

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent implements a dynamic two-phase testing process that adapts to each task's characteristics. The first phase uses inexact condition testing for quick evaluation of suitable tasks, and the second phase applies exact condition testing to remaining tasks. This dynamic approach enables 100% CPU utilization while maintaining implementation feasibility through structured processing

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11620160B2Uniprocessor method for real time rate-monotonic scheduling in a communication network

Publication Date: 2023.04.04 IMAM ABDULRAHMAN BIN FAISAL UNIV

AI summary

A real-time feasibility device includes circuitry configured to sort tasks into a first scheduling priority order; split the sorted tasks into a first subset which can be scheduled using an inexact condition test and a second subset which cannot be scheduled using the inexact condition test; test the first subset using the inexact condition test; sort the tested first subset into a second scheduling priority order; sort the second subset into a third scheduling priority order; filter out one or more tasks of the second subset which cannot be scheduled using the inexact condition test or the exact condition test; test remaining tasks of the second subset using the exact condition test; sort the tested remaining tasks of the second subset into a fourth scheduling priority order; and execute the sorted and tested first subset and the sorted and tested remaining tasks of the second subset.