Exploring Kepler's Next Chapter: Achieving Cloud Native Sustainability With MCP Integration
summary
Kepler runs as a DaemonSet reading CPU/DRAM energy from MSRs and /sys and attributes watts to pods via cgroups, Prometheus scrapes those metrics and Grafana visualizes them; MCP (fastMCP 2.0) layers regulatory context and answers queries like which pod exceeds 0.1 kg CO2/day or fails PUE <1.4; a demo deploys on AWS t5 bare metal with K3s, shows live compliance checks, migration recommendations, and a CLI/chat client — it works end‑to‑end and the C5 lab costs about $4/hour.
AI-written summary · about
chapters (12)
- 0:00Cloud sustainability intro
- 1:24Carbon emissions in cloud
- 3:08What Kepler is
- 8:48Energy split and Kepler math
- 10:13Why Kepler needs context
- 12:01MCP for carbon accountability
- 14:07Demo goals and KPIs
- 20:23Live demo setup
- 23:17MCP server integration
- 24:51MCP client interactions
- 26:19Carbon compliance tips
- 27:23Key takeaways
related talks
20mMonitoring Energy Consumption and Building Energy Efficient Systems the Cloud Native Way
20mKepler - Optimized power usage monitoring for Kubernetes
18mKeynote: Sustainability Chronicles: Innovate Through Green Technology with...
35mSustainability Research the Cloud Native Way
20mEnergy Efficient Placement of Edge Workloads
05mProject Lightning Talk: Kepler Project Updates
12mKeynote: Cloud Native Sustainability - How You Can Help Right Now!
26mAccelerating Science, Decelerating Carbon: Sustainable Computing...