Schedulable Job-Level Dependencies for Cause-Effect Chains via Graph Neural Networks

2026-07-02

AI Summary

Existing methods for synthesizing job-level dependencies (JLDs) in causal chains struggle to guarantee schedulability under specific scheduling policies. This work proposes the first graph neural network (GNN)-based framework for JLD synthesis, which learns the mapping between causal chain structures and feasible JLD solutions through a two-layer GNN. Integrating a generate-and-verify architecture, the approach ensures solution feasibility by incorporating temperature-controlled sampling, a multi-level verification mechanism, and a dynamic programming-based data age checker. Joint schedulability is rigorously validated using Earliest Deadline First (EDF) scheduling combined with demand-bound testing. Compared to conventional greedy heuristics, the proposed method reduces synthesis time by several orders of magnitude while significantly improving solution quality and overall system schedulability.

Abstract

Modern automotive software architectures comprise large sets of mixed-criticality functions executing on shared multi-core platforms with strict real-time and end-to-end timing requirements. Sensor-to-actuator data propagation in such systems is typically expressed via cause-effect chains with worst-case data-age budgets. Job-level dependencies (JLDs) have been introduced to provide a schedule-agnostic mechanism for bounding the data age independently of the underlying scheduler. The state-of-the-art methods for synthesizing JLDs, however, do not check whether the produced JLDs are enforceable under a concrete scheduling policy or jointly schedulable at the system level. In this paper we propose the first machine-learning-based JLD synthesis method, built around a two-level Graph Neural Network with temperature-controlled sampling that learns the structural patterns connecting cause-effect chain configurations to their JLD solutions. Since learned outputs may not be correct by construction, we embed the GNN in a novel Generate-and-Verify architecture in which a safe DP data-age checker, together with a per-chain EDF feasibility checker and a system-level demand-bound test, accept or reject each candidate. We show that the ML-based generator substantially outperforms the original greedy heuristic while achieving orders-of-magnitude lower synthesis time, demonstrating that learned structural priors can effectively replace exponential propagation-tree enumeration on this class of real-time scheduling problems.

Problem

• Job-Level Dependencies
• Cause-Effect Chains
• Real-Time Scheduling
• Data-Age Budgets
• Schedulability

Innovation

• Graph Neural Networks
• Job-Level Dependencies
• Cause-Effect Chains
• Generate-and-Verify
• Real-Time Scheduling