Hardware setups to measure power consumption of software

Components:

PM = Power Meter
SUT = System Under Test
DAE = Data Aggregator and Evaluator
WG = Workload Generator

Green Metrics Tool

Green Metrics Tool Cluster:

Fujitsu ESPRIMO P956 - Blue Angel compatible (Ubuntu)
Fujitsu TX1330 M2 - Single-Tenant Server (Ubuntu) → RAPL + DC +AC
Quanta Leopard - Multi-Tenant Server - SoftAWERE compatible (Ubuntu)
Intel Mac 13" Q3-2015
M1 Mac 13" Q1-2022

Sources:

Devices & Tools

See devices-tools-overview.md · KDE Eco / be4foss · GitLab

Reference Systems:

Fujitsu Desktop Computer Esprimo P920 / P956 / P957 / P958 (Blauer Engel recommended)
Hyndai Pentio H-Series AIO MT B85
Mac mini "Core i5" 2.6, 3.0 (Blauer Engel recommended)

Power Meters & Software:

GUDE Expert Power Control 1202
- Python script from Achim Guldner (GPL v3.0)
Gosund SP111 (inexpensive power plug) with Tasmota firmware (GPL v3.0)
- Kst (GPL v2.0, KDE software)
- See Volker Krause's blog post

Guldner & Murach (2023)

Paper: Guldner, A., & Murach, J. (2023). Measuring and Assessing the Resource and Energy Efficiency of Artificial Intelligence of Things Devices and Algorithms. In V. Wohlgemuth, S. Naumann, G. Behrens, H.-K. Arndt, & M. Höb (Eds.), Advances and New Trends in Environmental Informatics (pp. 185–199). Springer International Publishing. https://doi.org/10.1007/978-3-031-18311-9_11

Zotero:

Source: https://gitlab.rlp.net/a.guldner/resource-and-energy-efficiency-of-aiot

PC-SUT:

CPU: Intel (R) Core (TM) i7-6700K CPU @ 4.00GHz
OS: Ubuntu 20.04.4 LTS

Raspberry-SUT:

CPU: Broadcom BCM2711, Cortex-A72 (ARM v8) 64-bit SoC @ 1.5GHz
OS: Raspberry Pi OS (Lite)

Junger et al. (2022)

Paper: Junger, D., Wohlgemuth, V., & Kammer, E. (2022). Conception and test of a measuring station for the analysis of the resource and energy consumption of material floworiented environmental management information systems (EMIS). Gesellschaft für Informatik e.V. http://dl.gi.de/handle/20.500.12116/39396

Zotero:

SUT:

Windows 10
Hardware? Dell …
Monitor: Philips 241B8QJEB
- 60 Hz
- 1920 x1080 pixels

PM: Gude Expert Power Control 1202

Kreten (2021)

Paper: Kreten, S. (2021). Modellbildung und Umsetzung von Methoden zur energieeffizienten Nutzung von Containertechnologien [Dissertation, Universität Trier]. https://ubt.opus.hbz-nrw.de/files/1834/Promotion_Kreten.pdf

Zotero:

PM: Gude Expert Power Control 1202 [Gude, 2021]
SUT: 2x Udoo x86 Advanced Plus (Intel Celeron N3160 2.24 GHz (4 Kerne), 4 GB RAM)
DAE: Lenovo Thinkpad U430
WG: Lenovo Thinkpad U430