ECOSystem: managing energy as a first class operating system resource

By Heng Zeng, Carla Schlatter Ellis, Alvin R. Lebeck, Amin Vahdat. ASPLOS X, 2002

488 citations recorded by the source corpus.

Energy consumption has recently been widely recognized as a major challenge of computer systems design. This paper explores how to support energy as a first-class operating system resource. Energy, because of its global system nature, presents challenges beyond those of conventional resource management. To meet these challenges we propose the Currentcy Model that unifies energy accounting over diverse hardware components and enables fair allocation of available energy among applications. Our particular goal is to extend battery lifetime by limiting the average discharge rate and to share this limited resource among competing task according to user preferences. To demonstrate how our framework supports explicit control over the battery resource we implemented ECOSystem, a modified Linux, that incorporates our currentcy model. Experimental results show that ECOSystem accurately accounts for the energy consumed by asynchronous device operation, can achieve a target battery lifetime, and proportionally shares the limited energy resource among competing tasks.

Subfields: Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/13af5a89928171cc716a9e9916522cbc6fa1c25c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Hardware and Architecture

Citations in the corpus

Energy Efficient Resource Management in Virtualized Cloud Data Centers (2010, unknown): “Early work in energy aware resource management is devoted to mobile devices with the objective of improving battery lifetime [11, 18].”
Self-constructive high-rate system energy modeling for battery-powered mobile systems (2011, background): “The experiment results show that Sesame is able to generate system energy models of 95% accuracy at one estimation per second and of 88% accuracy at one estimation per 10 ms, without any external assistance.”
Making Scheduling "Cool": Temperature-Aware Workload Placement in Data Centers (2005, background): “The last few years have seen a push to treat energy as a first-class resource in hardware and operating system design, from low-power processors to OS schedulers [29, 31].”
Energy-Efficient Management of Data Center Resources for Cloud Computing: A Vision, Architectural Elements, and Open Challenges (2010, background): “Existing energy-efficient resource allocation solutions proposed for various computing systems [14][15][16] cannot be implemented for Green Cloud computing.”
Power-aware scheduling for periodic real-time tasks (2004, unknown): “can exceed 50 % for CPU-intensive workloads [24, 31 ].”
A Taxonomy and Survey of Energy-Efficient Data Centers and Cloud Computing Systems (2010, background): “[37,38] have proposed and developed ECOsystem—a framework for managing energy as a first-class OS resource aimed at battery-powered devices.”
Server-Level Power Control (2007, background): “For example, a server could dynamically adjust its operation to the highest performance possible that did not violate power and thermal constraints.”
Empowering developers to estimate app energy consumption (2012, methodology): “In [24] resource usage of each component is tracked per application, and power models from the data sheet specs are used to estimate app energy.”
No "power" struggles: coordinated multi-level power management for the data center (2008, unknown): “The MilliWatt [37][38] and GRACE [30] projects have examined cross-cutting issues in power management across the OS-applications and hardwaresoftware layers respectively.”
Runtime power monitoring in high-end processors: methodology and empirical data (2003, methodology): “This report includes the extensions to the paper appearing in the 36th International Symposium on Microarchitecture (MICRO-36), San Diego, CA, December 2003 power [ 14 ], instruction power profile based energy estimation [11, 8], IPC [1] as proxies for power measures.”
Mercury: a wearable sensor network platform for high-fidelity motion analysis (2009, background): “ECOsystem [47] tunes OS scheduling parameters to manage battery life, while Puppeteer [24] supports bandwidth adaptations.”
AppScope: Application Energy Metering Framework for Android Smartphone Using Kernel Activity Monitoring (2012, background): “Additionally, understanding the energy consumption of each process or hardware component is a key area of interest for application and system software developers [1-5].”
Architecture support for disciplined approximate programming (2012, background): “Software efforts have explored managing energy as an explicit resource [30], shutting down unnecessary hardware, and energy-aware compiler optimizations [28].”