Tasks Scheduling Using Dynamic Cluster-Based Hierarchical Real-Time Scheduler for Autonomous Car

The recent advancement in information technologies makes autonomous cars in reality. The complexity of such cars increases day by day which results in high real-time computational demand. The existing multi-core real-time scheduling algorithms are based on partitioned and global scheduling approaches. The partitioned based algorithms having drawbacks like poor utilization bound, load balancing, not compatible with an open system environment and the global scheduling approach faces problems like high scheduling overhead. Cluster scheduling represents a hybrid scheduling approach that consists of a set of the processor as a cluster and tasks schedule to each processor of clusters using a global scheduling approach. The different task assignments heuristics are investigated for the homogeneous and heterogeneous cluster as well as a static and dynamic cluster that used the harmonic period aware technique. A new dynamic cluster-based hierarchical real-time scheduling algorithm for autonomous cars and compare the result with benchmarking algorithms in global and partitioned based real-time scheduling has been presented here. Experimentation performed on Simso multiprocessor real-time simulator.