Vol.:(0123456789) 1 3
J Ambient Intell Human Comput
DOI 10.1007/s12652-017-0527-z
ORIGINAL RESEARCH
Energy‑efcient anycast scheduling and resource allocation
in optical grids
Saja Al Mamoori
1
· Darshil Rami
1
· Arunita Jaekel
1
Received: 19 February 2017 / Accepted: 17 April 2017
© Springer-Verlag GmbH Germany 2017
approach for anycast and unicast routing models. Our simu-
lation results demonstrate that the proposed approach can
lead to signifcant reductions in energy consumption, com-
pared to traditional routing schemes.
Keywords Optical-grid networks · Energy-aware
routing · Sliding window scheduled trafc · Demand
holding times · Anycasting · Unicasting
1 Introduction
Grid computing refers to high performance computing
resource sharing using optical backbone networks to sup-
port data-intensive applications. Grid computing provides
a solution to better utilize these resources, for applications
where the physical location of the resource is not impor-
tant. Grids provide a form of distributed computing (Tafani
et al. 2012) whereby a super virtual computer is composed
of many networked loosely coupled computers, acting
together to perform large tasks (Mishra et al. 2017). For the
grid computing the basic requirement is high speed with
low delay time. Optical communications technology with
wavelength division multiplexing (WDM) networks fulflls
the requirements for optical grid computing as it can carry
large amount of data with reliability. Recent studies have
shown that the energy consumption can become the bot-
tleneck for the high speed data communication (Shen and
Tucker 2009; Gupta and Singh 2003; Kukreja et al. 2017)
in today’s networks. Efcient routing schemes and resource
allocation both in optical and electrical domain can be
used to help mitigate this problem (Orgerie et al. 2014). A
transparent IP-over-WDM network can be utilized to allow
trafc to optically bypass the electronic components, e.g.
IP routers and switches, which typically consumes more
Abstract In recent years, optical grid networks has been
used as an ideal infrastructure to support high-performance
computing environment, data intensive applications and
interconnection of data centers. Due to rapid increase in
the high-bandwidth applications, the power consumption
of communications equipment for such networks has been
increasing steadily over the past decade. Therefore, energy
efcient routing schemes and trafc models can be devel-
oped to reduce the energy consumption. In many applica-
tions it is possible to select the destination node from a set
of possible destinations, which have the required comput-
ing/storage resources. This is known as anycasting com-
pared to unicasting where there is only one destination
for each communication. In this paper we adopt the slid-
ing scheduled trafc model, where setup and tear down
times may vary within larger window frame. We propose a
novel problem that exploits knowledge of demand holding
times using anycasting model. We show how the fexibil-
ity of anycast routing can lead to additional energy saving.
The problem was formulated as an integer linear program
to optimally schedule demands (in time) and route them
in order to minimize overall network energy consump-
tion. The problem of energy consumption is addressed
by switching of idle network components in low utiliza-
tion periods. We analyze the performance of the proposed
* Arunita Jaekel
arunita@uwindsor.ca
Saja Al Mamoori
almamo@uwindsor.ca
Darshil Rami
rami@uwindsor.ca
1
School of Computer Science, University of Windsor,
Windsor, Canada