Kubernetes on Edge Day Europe 2022
2022-05-17
Valencia, Spain
[Kubernetes on Edge Day Europe 2021, Kubernetes on Edge Day Europe 2022, Kubernetes on Edge Day Europe 2023, Kubernetes on Edge Day Europe 2024, Kubernetes on Edge Day Europe 2025, Kubernetes on Edge Day Europe 2026]
as the organisers put it
register explore the schedule VIEW ATTENDEE GUIDE SUBMIT TO SPEAK That’s a wrap on Kubernetes on Edge Day at KubeCon + CloudNativeCon EU 2022! Thank you to all the attendees…
who it's for
edge engineers, platform engineers, site reliability engineers, embedded engineers, iot engineers, machine learning engineers, networking engineers, cloud architects
topics
k3s on ARM devices; KubeEdge orchestration split; WebAssembly (WasmEdge) on Kubernetes; model serving with ModelMesh/Triton; ML observability using eBPF and Pixie; RTP media streaming mesh in Kubernetes; Cilium cross-cluster networking and Hubble; SD-EWAN overlay controller with OpenWRT CNFs; immutable edge OSes and GitOps delivery; multi-node Raspberry Pi Kubernetes clusters; model caching and LRU eviction for edge; cross-cluster placement and anycast steering
| title | author | length |
|---|---|---|
| Opening Remarks | Steven Wong | 10m |
Survey of where edge is headed with concrete claims and tools: generational gains from analog to internet‑connected controllers, real deployments of occupancy… | ||
| Keynote: Pushing the Boundaries of Open Source for a Brand New Edge | Saad Malik | 07m |
Argues that edge Kubernetes must be lightweight and cost‑efficient (single‑node support, avoid n+1), run on immutable OSes like Ubuntu Core or Flatcar, and use… | ||
| Keynote Edge Native is the new Cloud Native Modern Apps at the Edge | Marco Nicosia | 08m |
Argues that edge must be treated like cloud by making sites disposable infrastructure—stop backing up edge boxes, recreate them; accept fewer than five nines… | ||
| MLExray: Observability for Machine Learning on the Edge | Michelle Nguyen | 23m |
Describes MLExray’s end to end debug pipeline that logs per-layer inputs and outputs, end-to-end and per-layer latency, and resource and sensor metadata, then… | ||
| Introduction to Media Streaming Mesh | Giles Heron | 23m |
A concrete design that makes RTP-based real-time media first-class in Kubernetes: a per-node RTP data-plane daemonset plus a tiny 500-line Rust stub that… | ||
| Lightning Talk: Connecting Klusters on the Edge with Deep Dive into Cilium Cluster Mesh | Raymond de Jong | 10m |
Cilium uses eBPF and the Cilium agent plus Hubble to advertise endpoints across many clusters so services become global services with cross-cluster load… | ||
| Lightning Talk: Join the Cloud Native Journey to Shuttle Back and Forth Applications Across Edges | Ruoyu Ying, Qiang Ren | 10m |
An open source SD-EWAN stack is built to stitch multi‑edge Kubernetes clusters using an overlay controller + Kubernetes CRD controller that provisions IPsec… | ||
| Lightning Talk: The Adaptive Edge: Balancing Cost Efficiency, Usability, and Performance Tradeoffs | Tom McCollough | 11m |
Claim: run hundreds of edge instances adaptively to get low latency without the cost of everywhere by continuously moving workloads based on health… | ||
| Model Serving at the Edge Made Easier | Paul Van Eck, Animesh Singh | 27m |
ModelMesh is deployed on a Jetson Nano running MicroShift and registers about 17 DenseNet ONNX models (~36 MB each) as ready; inference is sub-second when a… | ||
| Separation of Orchestration and Computation in KubeEdge, Understand the Why and How | Harshita Sharma | 26m |
KubeEdge splits orchestration to the cloud and computation to the edge by running cloudcore controllers and a lightweight edgecore agent; it uses… | ||
| Edge Kubernetes and Healthcare: A Next-Gen Architecture that Scales Across Thousands of Locations | Benjamin Beeman, Jeremy Oakey | 30m |
Claims a production system that manages K8s and VMs across thousands of hospital sites with zero tolerance for mistakes, using Spectro Cloud Palette as a… | ||
| Managing WebAssembly apps with Kubernetes | Shivay Lamba | 25m |
Wasm apps run inside WasmEdge VMs and can be managed by Kubernetes using runtimes like crun-w layered over crun, and orchestration via containerd or cri-o; OCI… | ||
| Building a Multi-Node Cluster with K3s Using ARM Devices | Sergio Mendez | 28m |
Step-by-step build of a working three‑node K3s cluster on ARM using Raspberry Pi 3B/4B running Ubuntu, installed with one‑line K3s server and agent scripts… | ||
| Closing Remarks | Steven Wong | 14m |
Announces that the Kubernetes IoT Edge Working Group is migrating to moving under CNCF between now and KubeCon NA, with Slack, GitHub and meeting times likely… | ||
| Empower Heterogeneous Edge AI Acceleration with K8s | Tiejun Chen, Zitong Xu | 24m |
Kubernetes extension detects PCI/USB IDs with Node Feature Discovery, auto-labels devices, and deploys vendor device plugins so scheduler places pods on… | ||
| nothing matches | ||