Research

RECAP: Reliable Capacity Provisioning and Enhanced Remediation for Distributed Cloud Applications

• Funding Body: Co-funded under the ICT theme of the 7th Framework Programme (FP7) of the European Union
• Size: €4.76 Million
• Duration: 36 Months, January 2017 – December 2019
• Partners: DCU, BT, Intel, SATEC, Tieto, Linknovate, Umea University, Ulm University, Imdea Networks
• Link: www.recap-project.eu

In the past decade, data centres have seen historically unrivalled development in scale, automation, and energy efficiency for ICT resource provisioning. Yet even with this unprecedented scale of technological development, cloud systems are still pushing the boundaries of what data centres can deliver in terms of reliable ICT capacity and energy efficiency, and the coming challenges from the Internet of Things (IoT) and the networked society are placing increasingly high demands on intelligent automation and adaptive resource provisioning as clouds grow out and between data centres.

See more at www.recap-project.eu

User demand and new technologies are driving  a dramatic increase in cloud infrastructure scale, heterogeneity and complexity. Demand for better energy efficiency has led to a variety of different technological options to build servers from different CPU architectures optimised for energy efficiency or performance as well as specialised options for highly parallel tasks such as manycore systems or General Purposed Graphical Processing Units, GPGPUs. Additionally the service complexity has evolved from models very similar to traditional server hosting to more interactive services (e.g. remote rendering or gaming) as well as moving towards more complex services on top of hardware and basic platform services. Similarly data centres have made significant investments in energy efficient buildings, server racks and facility management technology and understand themselves as Smart Consumers in evolving SmartGrid environments.

To cope with the challenge to optimise the mapping of services to a variety of different resources, both hardware and software related (e.g. licenses), requires topology-aware map-pings. This mapping needs to consider place-ment of the services across geographically distributed centres and demands new intelligent and cross-domain integration of actual and historical data.

CACTOS addresses the challenges of this increased complexity and heterogeneity from several angles.

• An intensive modelling activity will deliver models for heterogeneous workloads, infrastructure landscapes as well as facility management information and energy supplier information.
• Collection and analysis of historical use data and derivation of intelligent management strategies integrating research results from the cloud and data centre management field as well as from Mathematics and operations research build the basis for the optimisation and topology aware placement
• Dynamic workload placement, scheduling and migration by continuous optimization across multiple partially orthogonal or correlated criteria (consumer contracts; provider contracts e.g. for energy, network bandwidth, capacity, licenses, energy efficiency and costs)
• A simulation framework for conducting costs and risk analysis in order to validate the developed intelligent context-aware cloud topology optimisation strategies for robustness on a large scale beyond the limits of prototypical installations and deployments
• Validation by deployment in three distinct scenarios for business analytics, enterprise applications and technical computing use cases.

• Project Website: Click Here
• Project Fact Sheet: Click Here
• LinkedIn: Click Here
• Twitter: Click Here
• Facebook: Click Here

CACTOS: Context-Aware Cloud Topology Optimisation and Simulation

• Funding Body: Co-funded under the ICT theme of the 7th Framework Programme (FP7) of the European Union
• Size: €4.76 Million
• Duration: 36 Months, October 2013 – September 2016
• Partners: RealTECH, Umea University, Ulm University, FZI, Queen’s University Belfast, Flexiant
• Link: www.cactosfp7.eu

CACTOS is a €4.7 Million FP7 European funded project, with DCU partnering RealTECH, Umea University, Ulm University, FZI, Queen’s University Belfast and Flexiant.

Within the DCU Business School, the Modelling and Simulation Research Group are primarily involved in leading the research in relation to Simulation of Cloud.

CACTOS delivers three major results. CactoScale: A set of tools and methods to acquire and analyse application behaviour and infrastructure performance data. CactoOpt: Mathematical models and their realisation to determine the best fitting resources within a provider context. CactoSim: A prediction and simulation environment for diverse application workloads.

See more at www.cactosfp7.eu

User demand and new technologies are driving  a dramatic increase in cloud infrastructure scale, heterogeneity and complexity. Demand for better energy efficiency has led to a variety of different technological options to build servers from different CPU architectures optimised for energy efficiency or performance as well as specialised options for highly parallel tasks such as manycore systems or General Purposed Graphical Processing Units, GPGPUs. Additionally the service complexity has evolved from models very similar to traditional server hosting to more interactive services (e.g. remote rendering or gaming) as well as moving towards more complex services on top of hardware and basic platform services. Similarly data centres have made significant investments in energy efficient buildings, server racks and facility management technology and understand themselves as Smart Consumers in evolving SmartGrid environments.

To cope with the challenge to optimise the mapping of services to a variety of different resources, both hardware and software related (e.g. licenses), requires topology-aware map-pings. This mapping needs to consider place-ment of the services across geographically distributed centres and demands new intelligent and cross-domain integration of actual and historical data.

CACTOS addresses the challenges of this increased complexity and heterogeneity from several angles.

• An intensive modelling activity will deliver models for heterogeneous workloads, infrastructure landscapes as well as facility management information and energy supplier information.
• Collection and analysis of historical use data and derivation of intelligent management strategies integrating research results from the cloud and data centre management field as well as from Mathematics and operations research build the basis for the optimisation and topology aware placement
• Dynamic workload placement, scheduling and migration by continuous optimization across multiple partially orthogonal or correlated criteria (consumer contracts; provider contracts e.g. for energy, network bandwidth, capacity, licenses, energy efficiency and costs)
• A simulation framework for conducting costs and risk analysis in order to validate the developed intelligent context-aware cloud topology optimisation strategies for robustness on a large scale beyond the limits of prototypical installations and deployments
• Validation by deployment in three distinct scenarios for business analytics, enterprise applications and technical computing use cases.

• Project Website: Click Here
• Project Fact Sheet: Click Here
• LinkedIn: Click Here
• Twitter: Click Here
• Facebook: Click Here

SME-SIM: SME Data Adapter for  Advanced Simulation Modelling 

• Funding Body: Enterprise Ireland Commercialisation Fund Programme
• Duration: 24 Months, March 2013 – February 2015
• Link: www.sme-sim.com

Discrete Event Simulation (DES) is a very powerful technique used extensively and effectively by large companies to optimize their processes. However, DES is not used widely by SMEs as it is complex and costly. This project addresses the single biggest challenge to the use of DES in SMEs, which is data gathering and preparation. The proposed solution is a “software adapter” that connects to existing data sources and/or fills data gaps using a data generator, including processes and procedures for implementation scenarios. The solution connects to existing simulation tools (open source, commercial and bespoke) using open standard interfaces where possible.

See more at  www.sme-sim.com

A Discrete Event Simulation (DES) model is a computer based surrogate for actually experimenting with a real system, which is often infeasible or not cost-effective. DES models primarily consists of entities (e.g. products, customers), which have attributes (e.g. product/customer type), which require processing resources (e.g. machines, employees) and which closely mimic characteristics of a real-life process or systems (e.g. operational logic), such as randomness or variability (e.g. machine breakdowns, demand changes). DES is extensively used in situations where real systems cannot be used for experimentation. DES is widely used in a vast array of industrial sectors right across the world. DES as a technique has three main phases:

Phase 1: Data Gathering and Preparation

Phase 2: Model Development

Phase 3: Model Experimentation

What is being researched in this proposal is Phase 1: Data Gathering and Preparation with a particular focus on SMEs. However, as DES in SMEs is limited the remainder of this section will discuss data gathering and model development for the typical markets of larger organizations.

DES is a very powerful technique used extensively and effectively by large companies to optimize their processes. However, DES is not used widely by SMEs as it is complex and costly. This project addresses the single biggest challenge to the use of DES in SMEs, which is data gathering and preparation. The proposed solution is a “software adapter” that connects to existing data sources and/or fills data gaps using a data generator, including processes and procedures for implementation scenarios. The solution connects to existing simulation tools (open source, commercial and bespoke) using open standard interfaces where possible. The result is a powerful solution that can work in real time and also has the potential to be deployed as a cloud based service to enable SMEs take full advantage of the benefits of DES.

• Project Website: Click Here
• LinkedIn: Click Here

ICMR: Irish Centre for Manufacturing Research

• Funding Body: An Enterprise Ireland and IDA Ireland Initiative
• Partners: Boston Scientific, Intel, Analog Devices, Ceramicx, EMC, DePuy, Bombardier, Pfizer, Seagate, Vistakon, DCU, University of Limerick
• Link: www.icmr.ie

ICMR is a consortium of leading Irish manufacturers collaborating to conduct embedded research and innovation. The industry-led research agenda is designed to deliver the breakthrough solutions required to maintain  partners’ competitive edge. By addressing these needs, continued investment in Ireland is encouraged, ensuring that Ireland remains the location of choice for advanced manufacturing in Europe.

See more at  www.icmr.ie

• Project Website: Click Here
• LinkedIn: Click Here

Development of a Healthcare Management Research Cluster

• Funding Body: Enhanced Performance Initiatives, DCU
• Duration: 12 Months, February 2014 – January 2015

This proposed initiative is designed to consolidate and expand the development of a Healthcare Management Research Cluster in DCUBS. A number of the members of the cluster have been actively engaged with initiatives with a locally based hospital who continue to provide support, data and expert input on an on-going basis. Process improvement tools and techniques is a key skill which resides within this cluster and the execution in the healthcare sector is a research translation activity, which is based on significant past successes in manufacturing settings. To date the following initiatives have been undertaken by the group in the health sector:

Process Improvement Survey – A detailed survey has been developed and administered in the hospital to determine the drivers; inhibitors; current usage and perceptions of business process improvement. The results of this survey have been published as a conference paper (EurOMA 2013).

Process Mapping and Simulation Modelling – A process map has been developed for the Physiotherapy Department. This has been used in the development of a discrete event simulation model. The results of this work have been published in a conference paper (CAMAN2012).

Emergency Department (ED) Data – A data set for one full year has been received from the hospital and ongoing analysis is being undertaken.

This proposed initiative is designed to consolidate and expand the development of a Healthcare Management Research Cluster in DCUBS. A number of the members of the cluster have been actively engaged with initiatives with a locally based hospital who continue to provide support, data and expert input on an on-going basis. Process improvement tools and techniques is a key skill which resides within this cluster and the execution in the healthcare sector is a research translation activity, which is based on significant past successes in manufacturing settings. To date the following initiatives have been undertaken by the group in the health sector:

Process Improvement Survey – A detailed survey has been developed and administered in the hospital to determine the drivers; inhibitors; current usage and perceptions of business process improvement. The results of this survey have been published as a conference paper (EurOMA 2013).

Process Mapping and Simulation Modelling – A process map has been developed for the Physiotherapy Department. This has been used in the development of a discrete event simulation model. The results of this work have been published in a conference paper (CAMAN2012).

Emergency Department (ED) Data – A data set for one full year has been received from the hospital and ongoing analysis is being undertaken.