Energy-Aware Scheduling of Streaming Applications on Edge-Devices in IoT-Based Healthcare

The reliance on Network-on-Chip (NoC)-based Multiprocessor Systems-on-Chips (MPSoCs) is proliferating in modern embedded systems to satisfy the higher performance requirement of multimedia streaming applications. Task level coarse grained software pipeling also called re-timing when combined with Dynamic Voltage and Frequency Scaling (DVFS) has shown be an effective approach significantly reducing energy consumption multiprocessor at expense additional delay. In this article we develop a novel energy-aware scheduler considering tasks conditional constraints Island (VFI)-based heterogeneous NoC-MPSoCs deploying integrated DVFS for real-time We propose task R-CTG integrate it non linear programming-based scheduling voltage scaling referred as ALI-EBAD. aims minimize latency caused by without compromising energy-efficiency. Compared R-DAG, state-of-the-art designed traditional Directed Acyclic Graph (DAG)-based graphs, reduces because only re-times that free up wasted slack. To validate our claims performed experiments using 12 real benchmarks, results demonstrate ALI-EBAD out performs CA-TMES-Search CA-TMES-Quick schedulers terms