Energy-Efficient Task Scheduling Based on Traffic Mapping in Heterogeneous Mobile-Edge Computing: A Green IoT Perspective

Abstract

As a key enabler of emerging 6G applications, mobile edge computing (MEC) improves the system performance by coordinating the computation resources between the mobile devices and edge. However, the energy consumption and carbon emission are boosted as the device number increases. This paper constructs a hierarchical network-assisted task offloading architecture for Green Internet of Things (IoT). Then the authors propose an energy-efficient scheduling based on traffic mapping with energy slack-space proportional pre-allocation algorithm (ESTMP) in the heterogeneous edge computing system to minimize the schedule length under certain energy constraints. The proposed algorithm is suitable for delay-sensitive mobile applications such as Augmented Reality (AR)/Virtual Reality (VR)/Mixed Reality (MR), which process massive multi-modal data. Simulation results demonstrate the significant advantages of the algorithm in terms of the schedule length of arriving parallel tasks, resource utilization and energy consumption.