Unified Management and Optimization of Edge-Cloud IoT Applications

TL;DR

This paper introduces Steel, a flexible framework for developing, deploying, and optimizing IoT applications across edge and cloud environments, addressing scalability and latency challenges.

Contribution

Steel provides a unified, extensible platform supporting dynamic service placement and adaptive communication for edge-cloud IoT applications.

Findings

Supports dynamic service migration between edge and cloud

Includes pluggable modules for common optimizations

Addresses workload and environment variability

Abstract

Internet of Things (IoT) applications have seen a phenomenal growth with estimates of growing to a 25 Billion dollar industry by 2020. With the scale of IoT applications growing and stricter requirements on latency, edge computing has piqued the interest for such environments. However, the industry is still in its infancy with no proper support for applications running across the entire edge-cloud environment, and an array of manual tedious per-application optimizations. In this work, we propose Steel, a unified framework for developing, deploying, and monitoring applications in the edge-cloud. Steel supports dynamically adapting and easily moving services back and forth between the edge and the cloud. Steel is extensible where common optimizations (but crucial for the edge) can be built as pluggable and configurable modules. We have added two very common optimizations: placement and adaptive communication, to cope with both short and long-term changes in the workload and environment.