Dynamic topologies for sustainable and energy efficient traffic routing Alexander A. Kist ⇑ , Abdelnour Aldraho The University of Southern Queensland, Toowoomba, Queensland, Australia article info Article history: Received 3 April 2010 Received in revised form 3 February 2011 Accepted 19 March 2011 Available online 1 April 2011 Responsible Editor: M. Ajmone Marsan Keywords: Energy efficient networking Network optimisation Network transformation Dynamic topologies abstract In light of the global focus on greenhouse gas emissions, energy consumption of commu- nication networks has become an important research area. Networks are major energy con- sumers and are generally dimensioned for peak loads. For extended periods, resources consume power, but are lightly or unused. This research investigates the concept of dynamic topologies, i.e. networks that adapt their topology according to traffic volume. The key aim of this study is to investigate power reductions that can be achieved by dynamic topologies. It proposes a network transformation and introduces mathematical programming models that results in energy optimal topologies for given traffic loads. This paper focuses on the optimisation problems and investigates gains in static environments. Numerical results are presented for example networks using a large set of traffic matrices. For the test networks, dynamic topologies reduce the average network power consump- tion, depending on the network load, by approximately 12–52%. Ó 2011 Elsevier B.V. All rights reserved. 1. Introduction Energy efficiency and greenhouse gas (GHG) emission footprint have become major concerns for environmental, as well as economic reasons. This is particularly relevant to the Information and communication technology (ICT) sector as it is both, an enabler for energy reductions, as well as an industry with its own GHG emissions footprint [1]. In 2007, the IT sector was responsible for approxi- mately 2% of the global carbon foot print [2]. This figure in- cludes all components, such as personal computers and network infrastructure and is comparable in size to the global aviation industry. Furthermore, it is expected that the contribution will grow at 6% each year until 2020 [1]. It is estimated that network related GHG emissions ac- count for 30% [2] to 37% [1] of the sector’s contributions. In contrast, telecommunication networks operate at utili- sations of below 30% [3] to below 50% [4]. The main reason for this is the cyclic nature of traffic and the practise to over provision systems to support QoS requirements at peak loads. In light of global warming and GHG emissions, green information and communication technology is receiving growing attention, both, in the business as well as the research community. In the ICT research commu- nity, energy efficiency has been a concern for low powered devices such as wireless networks [e.g. 5–7], sensor net- works [e.g. 8] and general mobile and battery powered de- vices. Recent studies have approached the topic of energy efficiency from a variety of different angles and span all as- pects of computing and communication, from software development to packet forwarding and switching fabric. For example, [9] investigates the carbon footprint of the Internet and potential carbon reductions by replacing car and air travel by Internet-based telecommuting and tele- conferencing services. Increased energy consumption of computing hardware is multiplied by increased energy use of cooling infrastruc- ture. To reduce energy consumption of computer net- works, a number of areas have to be addressed: infrastructure, such as cooling and power delivery; server hardware and software, such as dense racking and power efficient processors; as well as intelligent resource man- agement, such as virtualisation and traffic engineering. This research focuses on teletraffic engineering and inves- 1389-1286/$ - see front matter Ó 2011 Elsevier B.V. All rights reserved. doi:10.1016/j.comnet.2011.03.008 ⇑ Corresponding author. E-mail addresses: kist@ieee.org (A.A. Kist), aldraho@usq.edu.au (A. Aldraho). Computer Networks 55 (2011) 2271–2288 Contents lists available at ScienceDirect Computer Networks journal homepage: www.elsevier.com/locate/comnet