A survey on system level energy optimisation for MPSoCs in IoT and consumer electronics

Internet-of-Things (IoT) is an appealing service to revolutionise Smart City (SC) initiatives across the globe. IoT interconnects a plethora of digital devices known as Sensor Nodes (SNs) Internet. Due their high performance and exceptional Quality-of-Service (QoS) Multiprocessor System-on-Chip (MPSoC) computing architectures are gaining increasing popularity for computationally extensive workloads in both consumer electronics. In this survey, we have explored balance between paradigm its applications SC while introducing Wireless Network (WSN), including structure SN. We considered MPSoCs systems relation characteristics such architecture communication technology involved. This provides insight into benefits coupling with IoT. paper, also investigates prevalent software level energy optimisation techniques extensively reviews workload mapping scheduling approaches since 2001 until today savings using (1) Dynamic Voltage Frequency Scaling (DVFS) and/or Power Management (DPM) (2) Inter-processor reduction (3) Coarse-grained pipelining integrated DVFS. paper constructively summarises findings these algorithms identifying insightful directions future research avenues.