Abstract
Time-triggered systems are widely deployed in safety-critical applications due to their deterministic timing behavior. To enhance adaptability under dynamic workloads and environmental changes, adaptive time-triggered systems have received increasing attention. Existing approaches either consume excessive memory or introduce adaptation delays. Proactive speculative scheduling, driven by event prediction, has emerged as a promising alternative. Its core component is an event prediction model. Despite the availability of various time-series and event log datasets in other domains, no suitable dataset exists for event prediction in time-triggered systems. This paper introduces Autonomous Driving Time-Triggered System Dataset (AD-TTS), a dataset tailored for learning-based event prediction in multi-task time-triggered systems. We extend an autonomous driving simulation from CARLA into a multi-task time-triggered system that consists of 21 tasks and 32 event types. Events are logged at each scheduling cycle along with metadata such as timestamps, task identifiers, CPU utilization, memory usage, and event attributes. AD-TTS provides a foundation for future research on event prediction models and adaptive scheduling techniques in time-triggered systems.
Funding Information
  • Chips Joint Undertaking