Donal O’ Mahony
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Donal O’ Mahony has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Linda Doyle
Trinity College Dublin, Dublin, Ireland
19 shared publications - Marco Ruffini
Trinity College Dublin
10 shared publications - Joseph Doyle
Queen Mary University of London, London, United Kingdom
5 shared publications Patroklos Argyroudis
Centre for Telecommunications Value-chain Research (CTVR), Department of Computer Science, Trinity College Dublin, Ireland
4 shared publications- Kostas Katrinis
IBM Research, Ireland
3 shared publications P. Mackenzie
3 shared publications
Latest Publications
- Open Access
- 11 May 2015
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 47 (4) , 1-35
Accounting and Accountability in Content Distribution Architectures
Many content distribution architectures offer desirable elements that lead to less bandwidth usage, reduced network congestion, higher content availability, and reduced costs. However, their level of adoption and utilization in commercial environments depends on the level of content accounting and accountability they offer. Content accounting refers to any information that a content distributor needs to track relating to the delivery of content to its intended consumers. In contrast, content accountability refers to the willingness of the communicating infrastructure to produce accurate and verifiable information about the content distribution process. This article surveys existing and proposed future content delivery architectures detailing their methodologies for providing efficient low-cost content distribution, content accounting, and accountability across trustworthy and untrustworthy infrastructures. We use two methods to help identify the drawbacks and merits of these architectures. The first is a taxonomy for accounting information based on our analysis of logging information gathered from the surveyed systems. The second is a generic model for content distribution based on a synthesis of desirable elements from the surveyed architectures. These methods help highlight key architectural elements required for efficient low-cost content distribution. Finally, we identify outstanding challenges related to establishing accountability in accounting information produced for content distributed across trusted and untrusted infrastructures.
- 11 May 2015
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 47 (4) , 1-35
Open AccessAccounting and Accountability in Content Distribution Architectures
Many content distribution architectures offer desirable elements that lead to less bandwidth usage, reduced network congestion, higher content availability, and reduced costs. However, their level of adoption and utilization in commercial environments depends on the level of content accounting and accountability they offer. Content accounting refers to any information that a content distributor needs to track relating to the delivery of content to its intended consumers. In contrast, content accountability refers to the willingness of the communicating infrastructure to produce accurate and verifiable information about the content distribution process. This article surveys existing and proposed future content delivery architectures detailing their methodologies for providing efficient low-cost content distribution, content accounting, and accountability across trustworthy and untrustworthy infrastructures. We use two methods to help identify the drawbacks and merits of these architectures. The first is a taxonomy for accounting information based on our analysis of logging information gathered from the surveyed systems. The second is a generic model for content distribution based on a synthesis of desirable elements from the surveyed architectures. These methods help highlight key architectural elements required for efficient low-cost content distribution. Finally, we identify outstanding challenges related to establishing accountability in accounting information produced for content distributed across trusted and untrusted infrastructures.
- 1 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 188-190
Savant: A framework for supporting content accountability in information centric networks
The Information Centric Networking (ICN) paradigm offers solutions to some of the functional and performance limitations of the current Internet architecture by offering secure, efficient and scalable mechanisms for the delivery of content to end-users. However, ICN architectures fail to provide adequate content accountability for the content distribution process. (We use accountability and feedback interchangeably to refer to the logging information collected as part of the content distribution process). In this paper we propose the Savant architecture, which is a scalable accountability framework for ICN content distribution. We outline our current work and some preliminary results, which demonstrate the viability and scalability of the Savant architecture. Finally, we briefly outline avenues for future work.
- 1 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 188-190
Savant: A framework for supporting content accountability in information centric networks
The Information Centric Networking (ICN) paradigm offers solutions to some of the functional and performance limitations of the current Internet architecture by offering secure, efficient and scalable mechanisms for the delivery of content to end-users. However, ICN architectures fail to provide adequate content accountability for the content distribution process. (We use accountability and feedback interchangeably to refer to the logging information collected as part of the content distribution process). In this paper we propose the Savant architecture, which is a scalable accountability framework for ICN content distribution. We outline our current work and some preliminary results, which demonstrate the viability and scalability of the Savant architecture. Finally, we briefly outline avenues for future work.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-336
Nihil: Computing Clouds with Zero Emissions
Over the past five years there has been an increasing desire to reduce the environmental impact of cloud computing. Recent proposals have suggested taking a "net-zero" energy approach, where the data centre supplies as much energy to the grid as it takes to reduce the environmental impact. In this paper we propose the Nihil system which uses energy storage and load balancing based upon energy storage levels to provide a system which delivers reliable cloud service with no carbon emissions and no reliance on the grid.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-336
Nihil: Computing Clouds with Zero Emissions
Over the past five years there has been an increasing desire to reduce the environmental impact of cloud computing. Recent proposals have suggested taking a "net-zero" energy approach, where the data centre supplies as much energy to the grid as it takes to reduce the environmental impact. In this paper we propose the Nihil system which uses energy storage and load balancing based upon energy storage levels to provide a system which delivers reliable cloud service with no carbon emissions and no reliance on the grid.
- 24 July 2013
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 25 (17) , 2412-2432
Tailoring the network to the problem: topology configuration in hybrid electronic packet switched/optical circuit switched interconnects
SUMMARY: We consider a hybrid electronic packet switched and optical circuit switched interconnection network for future high performance computing and datacenter systems. Given the logical task‐to‐task communication graph of an application, our objective is to cluster the logical parallel tasks to compute resources and configure the (reconfigurable) optical part of the hybrid interconnect to efficiently serve application communication requirements. We formulate the clustering and topology configuration problem in such a network, prove that it is NP‐complete, and provide an optimal algorithm to solve it based on an integer linear programming formulation. The integer linear programming algorithm is used to optimally solve small‐scale instances of the problem for the purpose of obtaining performance bounds. Aiming at large‐scale, we also present a heuristic based on simulated annealing that trades‐off performance for responsiveness. We measure the performance of a hybrid interconnect employing the proposed algorithm using real workloads, as well as extrapolated traffic, and compare it against application mapping on conventional fixed, electronic‐only interconnects based on toroidal topologies. Copyright © 2013 John Wiley & Sons, Ltd.
- 24 July 2013
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 25 (17) , 2412-2432
Tailoring the network to the problem: topology configuration in hybrid electronic packet switched/optical circuit switched interconnects
SUMMARY: We consider a hybrid electronic packet switched and optical circuit switched interconnection network for future high performance computing and datacenter systems. Given the logical task‐to‐task communication graph of an application, our objective is to cluster the logical parallel tasks to compute resources and configure the (reconfigurable) optical part of the hybrid interconnect to efficiently serve application communication requirements. We formulate the clustering and topology configuration problem in such a network, prove that it is NP‐complete, and provide an optimal algorithm to solve it based on an integer linear programming formulation. The integer linear programming algorithm is used to optimally solve small‐scale instances of the problem for the purpose of obtaining performance bounds. Aiming at large‐scale, we also present a heuristic based on simulated annealing that trades‐off performance for responsiveness. We measure the performance of a hybrid interconnect employing the proposed algorithm using real workloads, as well as extrapolated traffic, and compare it against application mapping on conventional fixed, electronic‐only interconnects based on toroidal topologies. Copyright © 2013 John Wiley & Sons, Ltd.
- Open Access
- 1 March 2013
- Published by Institution of Engineering and Technology (IET) in IET Control Theory & Applications
- Vol. 7 (4) , 612-622
Distributed thermal aware load balancing for cooling of modular data centres
Thermal management in data centres requires a complicated trade‐off between cooling costs and thermally induced equipment failure rates. Using ideas from cooperative control and distributed rate limiting, in this study the authors describe a distributed architecture that can be used for thermal aware load balancing for a common type of modular data centre; namely an algorithm that, for a given demand D *, distributes load to individual machines such that the temperatures in the individual modules are equalised. The benefit of shifting load based on thermal considerations is that significant gains in cooling cost can be achieved. We evaluate the performance of the algorithm using computational fluid dynamics and Matlab simulations. The results show that significant cost savings can be made by applying such algorithms, and that these can be achieved without the need for detailed modelling and tuning of controllers.
- 1 March 2013
- Published by Institution of Engineering and Technology (IET) in IET Control Theory & Applications
- Vol. 7 (4) , 612-622
Open AccessDistributed thermal aware load balancing for cooling of modular data centres
Thermal management in data centres requires a complicated trade‐off between cooling costs and thermally induced equipment failure rates. Using ideas from cooperative control and distributed rate limiting, in this study the authors describe a distributed architecture that can be used for thermal aware load balancing for a common type of modular data centre; namely an algorithm that, for a given demand D *, distributes load to individual machines such that the temperatures in the individual modules are equalised. The benefit of shifting load based on thermal considerations is that significant gains in cooling cost can be achieved. We evaluate the performance of the algorithm using computational fluid dynamics and Matlab simulations. The results show that significant cost savings can be made by applying such algorithms, and that these can be achieved without the need for detailed modelling and tuning of controllers.
- Open Access
- 1 January 2013
- Published by Springer Nature
- p. 713-724
Accelerating Communication-Intensive Parallel Workloads Using Commodity Optical Switches and a Software-Configurable Control Stack
- 1 January 2013
- Published by Springer Nature
- p. 713-724
Open AccessAccelerating Communication-Intensive Parallel Workloads Using Commodity Optical Switches and a Software-Configurable Control Stack
- 20 February 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 16 (4) , 550-553
"Fair-Share" for Fair Bandwidth Allocation in Cloud Computing
Current mechanisms for controlling network resources cannot prevent users from interfering with each other in a shared cloud environment. Proposals made to rectify this, use mechanisms which require interrupts with high timing precision, and usually unevenly distribute bandwidth to TCP flows. We propose the use of an alternative mechanism to manage network resources and compare the performance of both.
- 20 February 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 16 (4) , 550-553
"Fair-Share" for Fair Bandwidth Allocation in Cloud Computing
Current mechanisms for controlling network resources cannot prevent users from interfering with each other in a shared cloud environment. Proposals made to rectify this, use mechanisms which require interrupts with high timing precision, and usually unevenly distribute bandwidth to TCP flows. We propose the use of an alternative mechanism to manage network resources and compare the performance of both.
- 1 January 2012
- Published by Springer Nature
- p. 701-715
Topology Configuration in Hybrid EPS/OCS Interconnects
- 1 January 2012
- Published by Springer Nature
- p. 701-715
Topology Configuration in Hybrid EPS/OCS Interconnects
- Open Access
- 19 August 2011
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Server selection for carbon emission control
- 19 August 2011
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessServer selection for carbon emission control
- Open Access
- 25 October 2010
- Published by Association for Computing Machinery (ACM)
- p. 1-2
An experimental evaluation of distributed rate limiting for cloud computing applications
- 25 October 2010
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessAn experimental evaluation of distributed rate limiting for cloud computing applications