Scholarlink

<p>The design and verification of safety-critical real-time systems rely on schedulability analysis. Exact tests may provide correctness guarantees, but they are often scheduler specific, computationally intractable at high scale, and pessimistic when used in iterative analysis pipelines. The paper introduces the <b>SAFE-TSFormer</b> algorithm to handle periodic real-time task-sets of variable cardinality under multiple uniprocessor scheduling policies. The <b>SAFE-TSFormer</b> approach employs a two-stage strategy. At the outset, it performs non-linear feature encoding at the task level, generating encoded representations for each task. These representations are then processed using transformer-based sequence modeling with masked attention to capture inter-task interactions. <b>SAFE-TSFormer</b> is designed as a conservative screening mechanism, prioritizing the suppression of false positives through a safety-aware training objective. We present results from experiments conducted on a large set of inflated periodic real-time task sets comprising over 3,&#xa0;60,&#xa0;000 instances. The proposed model generalizes to task-set sizes (number of real-time tasks) significantly higher than those observed during training. Specifically, on entirely new sets of tasks containing up to thirty-two tasks, SAFE-TSFormer’s overall accuracy reaches <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(96.56\%\)</EquationSource> </InlineEquation>. The results demonstrate the ability of a learner-based schedulability predictor to operate as a complementary technology within a solution optimization system, which rapidly and scalably screens candidates for feasibility without sacrificing safety, with high accuracy (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(98.98\%\)</EquationSource> </InlineEquation>) and very low false positive rates (<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(&lt;0.4\%\)</EquationSource> </InlineEquation>).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A safety-aware deep learning framework for scalable schedulability analysis of variable-length real-time task sets

  • 期刊论文

  • 发表日期：

    2026年6月27日

查看全文
  • Lalatendu Behera,
  • Gopendra Vikram Singh

摘要

The design and verification of safety-critical real-time systems rely on schedulability analysis. Exact tests may provide correctness guarantees, but they are often scheduler specific, computationally intractable at high scale, and pessimistic when used in iterative analysis pipelines. The paper introduces the SAFE-TSFormer algorithm to handle periodic real-time task-sets of variable cardinality under multiple uniprocessor scheduling policies. The SAFE-TSFormer approach employs a two-stage strategy. At the outset, it performs non-linear feature encoding at the task level, generating encoded representations for each task. These representations are then processed using transformer-based sequence modeling with masked attention to capture inter-task interactions. SAFE-TSFormer is designed as a conservative screening mechanism, prioritizing the suppression of false positives through a safety-aware training objective. We present results from experiments conducted on a large set of inflated periodic real-time task sets comprising over 3, 60, 000 instances. The proposed model generalizes to task-set sizes (number of real-time tasks) significantly higher than those observed during training. Specifically, on entirely new sets of tasks containing up to thirty-two tasks, SAFE-TSFormer’s overall accuracy reaches \(96.56\%\) . The results demonstrate the ability of a learner-based schedulability predictor to operate as a complementary technology within a solution optimization system, which rapidly and scalably screens candidates for feasibility without sacrificing safety, with high accuracy ( \(98.98\%\) ) and very low false positive rates ( \(<0.4\%\) ).