Energy-Aware Policies in Ubiquitous Computing Facilities - Cloud Computing with e-Science Applications - page 268

Summary
Next-generation e-science applications such as the ones found in smart cities,
e-health, or ambient intelligence, require constantly increasing high com-
putational demands to capture, process, aggregate, and analyze data and
offer services to users. Research has traditionally paid much attention to the
energy consumption of the sensor deployments that support this kind of
application. However, computing facilities are the ones presenting a higher
economic and environmental impact due to their very high power consump-
tion. In this chapter, we provide a vision of the increasing energy problem
in computing facilities with a focus on cloud computing, under the new
computational paradigms, and propose solutions from a global, multilayer
perspective, describing a novel system architecture, power models, and
optimization algorithms. This chapter is organized as follows: Section 12.1
introduces the topic; Section 12.2 briefly describes the related work.
Section 12.3 describes a novel system architecture for the global energy opti-
mization of next-generation e-science applications. Section 12.4 describes
the power models developed for the architecture, and Sections 12.5 and 12.6
briefly describe some optimization techniques. Finally, Section 12.7 summa-
rizes the most important aspects.
12.1 Introduction
Data centers are easily found in every sector of the worldwide economy.
They provide the required infrastructure for the execution of a wide range
of applications and services, including social and business networking,
web mail, web search, electronic banking, Internet marketing, distributed
storage, high-performance computing (HPC), and so on. The increasing
demand for higher computer resources has recently facilitated the rapid
proliferation and growth of data center facilities. In recent years, popu-
lation-monitoring applications (such as e-health applications or ambient
intelligence), e-science, and applications for smart cities have experienced
significant development, mainly because of the advances in the miniatur-
ization of processors and the proliferation of embedded systems in many
different objects and applications (e.g., communications, industrial, auto-
motive, defense, and health care environments). Next-generation systems
consist of a large set of nodes, distributed among the population. Data
obtained by these sensor nodes are communicated to the embedded pro-
cessing elements by means of wireless connections. Huge sets of data must
be processed, stored, and analyzed. To deal efficiently with such compu-
tationally intensive tasks, the use of cloud services is devised since cloud