Collaboration of Heterogeneous Edge Computing Paradigms: How to Fill the Gap Between Theory and Practice

Abstract

Edge computing paradigms such as cloudlet, mobile edge computing (MEC) and fog computing, are promising to reduce network transmission delay while meeting intensive computing requirements at the network edge. As always assumed in theoretical studies, to expand service capability, it is desirable to integrate edge resources into a unified resource pool and make different edge facilities collaborate. However, this collaboration is difficult in practice since the heterogeneity among paradigms leads to resource isolation. This article focuses on clarifying and shielding heterogeneity among edge computing paradigms for collaboration. First, based on cloudlet, mobile edge computing and fog computing, three main edge computing paradigms, i.e., small cloudy edge paradigm (SmallC), mobile integrated edge paradigm (MobInt) and front ad hoc edge paradigm (FrontAH), are defined. So that the heterogeneity among them can be analyzed, according to which, collaboration challenges in computing resource trading, information communication and resource sharing are identified. Promising techniques such as blockchain-based smart contract, media-independent handover (MIH), and software-defined network and network function virtualization (SDN/NFV) are then introduced and integrated into a complete collaboration solution. Finally, taking the unmanned vehicular navigation as an example, the performance of collaboration is evaluated, considering additional costs introduced by collaborations, including trading, network handoff and data transmission among edge facilities in different paradigms. Simulation results show that compared with existing schemes of the three paradigms, the collaboration can reduce the cost (i.e. weighted sum of energy consumption and delay) by at least 45.6%.