PUE for end users - Are you interested in more than bread toasting?

Page created by Michiel Cuijpers on 26 Apr 2013 08:21

Presented by Kay Grosskop (SIG) at Energy Aware Software-Engineering and Development EASED@BUIS 25.04.2013 in Oldenburg Germany

PUE for end users - Are you interested in more than bread toasting?

The Power Usage Effectiveness (PUE) indicator for efficiency of data center infrastructure has been very successful. But focusing solely on PUE tends to restrict action to data center infrastructure management and in some situations even gives a perverse stimulus against optimization at the IT equipment and software levels. Despite the high relevance, no accepted metric has emerged to support optimization and allow the rating of the energy efficiency of the whole stack. This paper presents a metric, the Consumption Near Sweetspot(CNS), that for a part can fill this gap. It captures how well the system-relative energy efficiency optimum and its utilization are aligned. A key advantage is that it allows comparison of functionally very different services. The metric is compared to the Fixed to Variable Energy Ratio (FVER) metric for data centers recently proposed by the British Computer Society and to Digital Service Efficiency (DSE), a service level energy indicator presented by Ebay.
Mirco Josefiok, Marcel Schröder, Andreas Winter
An Energy Abstraction Layer for Mobile Computing Devices
Since the growing popularity of smartphones and tablet devices, energy-efficiency in mobile computing is an increasingly interesting topic. But in case of software development engineering energy-efficiency is widely neglected, even clear and simply applicable means to measure and visualize energy consumption caused by software usage is still in its infancy. This work provides basic research in the field of measuring energy and power related information on mobile computing devices and proposes an abstract specification for implementing a measurement infrastructure on different mobile computing devices.
Patrick Heinrich
Towards Network-Wide Energy Estimation for Adaptive Embedded Systems
This paper discusses the next steps towards how system developers can easily and accurately evaluate the impact of their system design choices on energy consumption during the early stages of the design process. To do this, energy estimations in every phase of system development are necessary. Our research focuses on adaptive systems, where applications are activated according to the actual need. In this paper we present an approach which derives the energy consumption per application using a combination of energy relevant software and hardware parameters. The aim is to create energy building blocks for applications to estimate the energy consumption of a system with multiple applications running on it. This approach utilizes the high environmental interaction of embedded systems where sensors and actors consume more energy than CPUs. The granularity of the energy estimation is the application level, due to focusing on adaptive systems.
Dmitriy Shorin, Armin Zimmermann
Evaluation of Embedded System Energy Usage with Extended UML Models
Energy consumption as an increasingly important decision criterion has to be included in the search for good architectural and design alternatives to make an embedded system as energy-efficient as possible. The proposed method describes a system with dedicated extended UML models for applications and hardware components and evaluates the energy use via a transformation into an analyzable stochastic Petri net.


paper on EASED2013 or paper on this wiki

Add a New Comment
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License