How to (easily) evaluate the energy consumption of your software ?
summary
A test bench runs the voice‑as‑a‑service platform in Docker, measures power with a physical meter and then with PowerAPI plus Grafana, and drives load via Rest Assured tests. Results show idle plus load peaking at 48 W total, about 80% of power on two telephony servers, an optimal cost near 5 J per call, throughput limits causing errors around six calls/s and rising failures after 8 calls/s. CI integration of these measures is proposed but not yet automated.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:15Welcome
- 3:00What is Fast for Voice
- 4:05The Sustainable Challenge
- 5:30Impact by Design Approach
- 7:30Measure
- 8:45Test Bench
- 10:55Demo
- 15:40Ideas
- 17:00Conclusion
- 18:15Questions
related talks
22mHow to (easily) evaluate the energy consumption of your software ?
23mFull-stack energy consumption test bench for developers
42mEnergy-Efficient Software Architecture for Developers
09mAplikacionet e gjelbra - efikasiteti i energjisë në software
13mPerformance and Energy Efficiency in Docker
50mEnergy Efficient Design Principles of Software Engineering
39mCreate an Eco-Friendly World with Green Software Engineering
28mMore Data Please: Hands on Green Cloud Experiments