Litcius/Paper detail

Dynamic Split Computing Framework in Distributed Serverless Edge Clouds

Haneul Ko, Hyeonjae Jeong, Daeyoung Jung, Sangheon Pack

2023IEEE Internet of Things Journal16 citationsDOI

Abstract

Distributed serverless edge clouds and split computing are promising technologies to reduce the inference latency of large-scale deep neural networks (DNNs). In this article, we propose a dynamic split computing framework (DSCF) in distributed serverless edge clouds. In DSCF, the edge cloud orchestrator dynamically determines 1) splitting point and 2) warm status maintenance of container instances (i.e., whether or not to maintain each container instance in a warm status). For optimal decisions, we formulate a constrained Markov decision process (CMDP) problem to minimize the inference latency while maintaining the average resource consumption of distributed edge clouds below a certain level. The optimal stochastic policy can be obtained by converting the CMDP model into a linear programming (LP) model. The evaluation results demonstrate that DSCF can achieve less than half the inference latency compared to the local computing scheme while maintaining sufficient low resource consumption of distributed edge clouds.

Topics & Concepts

Computer scienceCloud computingDistributed computingEdge computingLatency (audio)InferenceMarkov decision processEnhanced Data Rates for GSM EvolutionEdge deviceMarkov processContainer (type theory)Resource allocationLow latency (capital markets)Computer networkArtificial intelligenceMathematicsTelecommunicationsOperating systemMechanical engineeringStatisticsEngineeringIoT and Edge/Fog ComputingStochastic Gradient Optimization TechniquesBrain Tumor Detection and Classification