Cost-Effective Task Scheduling for Collaborative Cross-Edge Analytics

Collaborative cross-edge analytics is a new computing paradigm in which Inter⁃ net of Things (IoT) data analytics is performed across multiple geographically dispersed edge clouds. Existing work on collaborative cross-edge analytics mostly focuses on reduc⁃ ing either analytics response time or wide-area network (WAN) traffic volume. In this work, we empirically demonstrate that reducing either analytics response time or network traffic volume does not necessarily minimize the WAN traffic cost, due to the price hetero⁃ geneity of WAN links. To explicitly leverage the price heterogeneity for WAN cost minimi⁃ zation, we propose to schedule analytic tasks based on both price and bandwidth heteroge⁃ neities. Unfortunately, the problem of WAN cost minimization underperformance con⁃ straint is shown non-deterministic polynomial (NP)-hard and thus computationally intrac⁃ table for large inputs. To address this challenge, we propose priceand performanceaware geo-distributed analytics (PPGA) , an efficient task scheduling heuristic that im⁃ proves the cost-efficiency of IoT data analytic jobs across edge datacenters. We imple⁃ ment PPGA based on Apache Spark and conduct extensive experiments on Amazon EC2 to verify the efficacy of PPGA.