GOXN: Energy Modeling and Experimentation for Cloud-Native Microservices

Julian Legler has published an artifact paper presenting GOXN, an energy experimentation engine that measures service-level compute, network, and storage energy for Kubernetes-based microservices (arXiv submission v1, 23 Jan 2026).

• Main announcement: The paper introduces GOXN (Green Observability eXperiment eNginE), an energy experimentation engine for Kubernetes-based microservices and an additive energy model that derives service-level energy from container-level metrics; evaluated on the OpenTelemetry Demo under steady synthetic load using metrics from Kepler and cAdvisor, and the artifact is listed as Accepted Artifact Paper at ICSOC2025.
• Details & findings: The evaluation shows that excluding network and storage can underestimate auxiliary-service energy by up to 63%, and that high tracing loads shift energy dominance toward network and storage; submission metadata includes arXiv:2601.16635 (v1), PDF/HTML/TeX source links, and a DataCite-issued DOI pending registration.