Architecture and Mechanisms of Energy Auto-Tuning

Abstract

<jats:p>Energy efficiency of IT infrastructures has been a well-discussed research topic for several decades. The resulting approaches include hardware optimizations, resource management in operating systems, network protocols, and many more. The approach the authors present in this chapter is a self-optimization technique for IT infrastructures, which takes hard- and software components as well as users of software applications into account. It is able to ensure minimal energy consumption for a user request along with a set of non-functional requirements (e.g., the refresh rate of a data extraction tool). To optimize the ratio between utility of end users and the cost in terms of energy consumption, the system needs inherent variability leading to differentiated energy profiles and mechanisms to reconfigure the system at runtime. The authors present their approach called Energy Auto-Tuning (EAT) comprised of these mechanisms and an architecture which automatically tunes the energy efficiency of IT systems.</jats:p>

A tool-supported approach for modular design of energy-aware software

“…Extending software with energy optimization functionality is a typical way to make software energy adaptive [16,19,15]. In contrast to our approach, these approaches fix the optimization functionality, and do not provide means to analyze the impact of various optimizers on the overall energy consumption of software to guide designers to choose suitable optimizers accordingly.…”

“…However, Götz et al [19] propose a model-driven component-based approach for software systems that can be optimized w.r.t. their provided quality and energy consumption at runtime.…”

A design method for modular energy-aware software

“…The way in which users interact with software can have a large influence on the overall energy consumption [4]. For example, if a media-player application adopts a caching mechanism, caching would not be effective if a user disturbs the normal stream of video by seeking forward and backward.…”

“…However, there is a lack of methods and techniques that take software modularity into account. For example, adopting the solution proposed by Gotz et al [4] requires to design and implement the software such that it complies with their component model. However, this might not be an effective solution; first because large-scale commercial software might not be implemented in this component model; and second there are already a large number of legacy software systems that must be extended with energy optimization functionality, and re-implementing them according to a new component model might not be considered suitable.…”