An effective resource scheduling model for edge cloud oriented AIoT

Abstract

Artificial Intelligence of Things (AIoT) is a new research area in AI and IoT. For the massive data and connections at the edge of AIoT, how to schedule the resource load is a key problem to be solved. For the multi-objective resource scheduling problem in a cross-domain environment, this article proposes a resource scheduling method based on edge computing and multi-objective algorithms. First, a cloud-edge hybrid AIoT hierarchical network resource management architecture is constructed. Then, the resource scheduling problem is modeled and a linear weighting strategy is designed for search space "pruning", which is then optimized by three multi-objective algorithms. Finally, we conducted a series of experiments based on the iFogSim platform. The simulation results show that the proposed resource scheduling strategy can effectively reduce the processing delay of AIoT and effectively improve the energy utilization efficiency of devices in the network.