Analysis and Performance Measure of Dynamic Cluster Based Hierarchical Real Time Scheduling for Distributed Systems

Efficient scheduling is critical for real-time systems, which are ubiquitous in daily life, as they demand high computational performance while minimizing power consumption and thermal inefficiencies. Multi-core platforms address these requirements but present challenges in task scheduling. Existing scheduling strategies include partitioned scheduling, which statically assigns tasks to processors to eliminate migration costs but suffers from NP-hard task allocation and low CPU utilization, and global scheduling, which allows task migration across processors to improve system utilization but incurs significant migration and preemption overheads. Neither strategy alone is sufficient to handle all real-time task sets effectively, highlighting the need for a hybrid solution for multi-core platforms. To address these challenges, this manuscript proposes a dynamic, cluster-based hybrid real-time scheduling algorithm that employs a hierarchical approach. By grouping cores into clusters, this method balances the trade-offs between partitioned and global scheduling. It minimizes migration and preemption overheads while improving resource utilization and system reliability. Dynamic cluster resizing and task assignment strategies further enhance efficiency by tailoring the scheduling process to workload demands. Simulation results demonstrate the proposed scheduler's superiority over partitioned and global scheduling approaches. It achieves higher resource utilization, better job acceptance rates, and reduced response times while lowering migration, preemption, and scheduling overheads. This work introduces an innovative scheduling framework that combines task assignment and scheduling in a two-step process: (1) Task Assignment: Allocates tasks to cores with controlled migration based on workload. (2) Task Scheduling: Sequences the execution of allocated tasks within clusters to ensure efficiency. The proposed approach offers a scalable and reliable solution for managing real-time tasks on multi-core systems, addressing limitations of traditional scheduling methods.