DEEP: Edge-based Dataflow Processing with Hybrid Docker Hub and Regional Registries
Narges Mehran, Zahra Najafabadi Samani, Reza Farahani, Josef Hammer, Dragi Kimovski
TL;DR
The paper tackles the challenge of reducing energy consumption for edge-enabled microservice deployments by leveraging a hybrid Docker registry approach. It introduces DEEP, a DAG-based dataflow and Nash-equilibrium scheduling framework that selects between Docker Hub and a MinIO-based regional registry to minimize energy on edge devices, integrating with Kubernetes for orchestration. The authors design a regional registry, formulate a Nash-based optimization for registry and device selection, and validate the approach on a two-device edge testbed with video and text processing workloads, reporting measurable energy savings (e.g., $0.34\%$ for text, $0.2\%$ for video) when using regional registries. The results demonstrate that energy efficiency can be improved through selective regional caching and cooperative scheduling, with practical implications for sustainable edge computing and dataflow processing. Future work aims to extend the model to cloud–edge hybrids, broadening applicability and impact in energy-aware distributed systems.
Abstract
Reducing energy consumption is essential to lessen greenhouse gas emissions, conserve natural resources, and help mitigate the impacts of climate change. In this direction, edge computing, a complementary technology to cloud computing, extends computational capabilities closer to the data producers, enabling energy-efficient and latency-sensitive service delivery for end users. To properly manage data and microservice storage, expanding the Docker Hub registry to the edge using an AWS S3-compatible MinIO-based object storage service can reduce completion time and energy consumption. To address this, we introduce Docker rEgistry-based Edge dataflow Processing (DEEP) to optimize the energy consumption of microservice-based application deployments by focusing on deployments from Docker Hub and MinIO-based regional registries and their processing on edge devices. After applying nash equilibrium and benchmarking the execution of two compute-intensive machine learning (ML) applications of video and text processing, we compare energy consumption across three deployment scenarios: exclusively from Docker Hub, exclusively from the regional registry, and a hybrid method utilizing both. Experimental results show that deploying 83% of text processing microservices from the regional registry improves the energy consumption by 0.34% (18J) compared to microservice deployments exclusively from Docker Hub.