Symposium on Cloud Computing and Networking

This Symposium on Cloud Computing and Networking brings to Universidad de Concepción leading researchers to share their research findings, experiences, and challenges on cloud, distributed, and local lomputing. The symposium will be held on Friday, August 26th 2016 at Room 106, Edificio Central, Faculty of Engineering, Universidad de Concepción.

Agenda

1:40 – 2:00 Registration
2:00 – 2:10 Welcome
2:10 – 3:00 Talk: “Optimization of Cloud Services for Micro-users: Efficient Resource Provisioning via Optimal Workload Allocation, ” Dr. Majeed M. Hayat, University of New Mexico, USA.
3:00 – 3:30 Talk: “Sensor Development for Network Access Sensors though Visible Light Communication, ” Dr. Payman Zarkesh-Ha, University of New Mexico, USA.
3:30 – 4:00 Coffee break and Poster/demo session
4:00 – 4:30 Streaming talk: “Towards Promoting Backup-Sharing in Survivable Virtual Network Design, ” Dr. Sara Ayoubi, Waterloo University, Canada.
4:30 – 5:00 Streaming talk: “Disaster Recovery in Networked Cloud Cyberinfrastructures,” Dr. Nasir Ghani, Univeristy of South Florida, USA.
5:00 – 5:10 Closing

Talks

Optimization of Cloud Services for Micro-users: Efficient Resource Provisioning via Optimal Workload Allocation

Abstract: Today, cloud computing is widely accepted and utilized in the business world. From the perspective of businesses that utilize the cloud, it is critical to deliver services with high performance and reliability that meet their customers’ requirements. Hence, the ability to characterize and optimize the service performance is of great importance. In this presentation a stochastic multi-tenant framework is proposed to model the service of customer requests in a cloud infrastructure comprising of heterogeneous virtual machines. Two cloud-service performance metrics are mathematically characterized, namely the percentile and the mean of the stochastic response time of a customer request. Based on the multi-tenant model, a workload allocation algorithm, termed the max-min-cloud algorithm, is devised to optimize the performance of the cloud service. Furthermore, the resource provisioning problem in cloud services is also studied in light of the max-min-cloud algorithm and the performance metrics. In particular, an efficient resource-provisioning strategy is proposed for serving the dynamically-incoming customer requests. With the help of this work, we hope that businesses can have a better understanding of how much virtual resources they need in the cloud to optimize their cloud-service performance and meet customers’ expectations subject to a cost constraint.

Dr. Majeed M. Hayat is a professor of electrical and computer engineering at the University of New Mexico, where he is also Associate Director of The Center for High Technology Materials. Dr. Hayat received his B.S. degree (summa cum laude) in 1985 in electrical engineering from the University of the Pacific, and he received his M.S. and Ph.D. degrees in electrical and computer engineering from the University of Wisconsin-Madison in 1988 and 1992, respectively. Dr. Hayat’s research contributions cover a broad range of topics in the areas of avalanche photodiodes, optical communication, statistical signal/image processing, algorithms for spectral sensing, complex interdependent networks, networked and distributed computing, as well as statistical communication theory. Prof. Hayat has authored over 90 peer-reviewed journals (with over 3,500 citations and an H-Index of 29), 9 book chapters, and 10 patents (5 commercialized). He was Associate Editor of Optics Express from 2004 to 2010, and he is presently Associate Editor for the IEEE Transactions on Parallel and Distributed Computing. Dr. Hayat is a recipient of the CAREER Award from the National Science Foundation (1997). He is Fellow of IEEE, SPIE and OSA.

Sensor Development for Network Access Sensors though Visible Light Communication

Abstract: LED lighting systems with large color gamuts, with multiple LEDs spanning the visible spectrum, offer the potential of increased lighting efficiency, improved human health and productivity, and visible light communications addressing the explosive growth in wireless communications. The control of this “smart lighting system” requires a silicon-integrated-circuit-compatible, visible, plenoptic (angle and wavelength) detector. In this talk, a new detector element, based on an offset-grating-coupled dielectric waveguide structure and a silicon photodetector, is presented that can address the need of a low cost directional sensor for visible light communication.

Dr. Payman Zarkesh-Ha received the M.S. degree in electrical and computer engineering from Sharif University, Tehran, Iran, in 1994 and the Ph.D. degree in electrical and computer engineering from Georgia Institute of Technology, Atlanta, in 2001.

He was a Senior Research Engineer with LSI Logic Corporation, Milpitas, CA, where he worked on interconnect architecture design for the next ASIC generations. He served as Industry Liaison for LSI Logic Corporation with Semiconductor Research Corporation (SRC) and Microelectronics Advanced Research Corporation (MARCO) from 2001 to 2006. He is currently an Assistant Professor with the Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque. He has published over 50 refereed papers and holds ten issued patents. His research interests are statistical modeling of nanoelectronic devices and systems, and design for manufacturability, low-power, and high-performance VLSI designs.

Dr. Zarkesh-Ha is currently serving as technical Committee Member of System Level Interconnect Prediction Workshop (SLIP) and the International Symposium on Quality Electronic Design (ISQED).

Towards Promoting Backup-Sharing in Survivable Virtual Network Design

Abstract: In a virtualized infrastructure where multiple virtual networks (or tenants) are running atop the same physical network (e.g., a data center network), a single facility node (e.g., a server) failure can bring down multiple virtual machines, disconnecting their corresponding services and leading to millions of dollars in penalty cost. To overcome losses, tenants or virtual networks can be augmented with a dedicated set of backup nodes and links provisioned with enough backup resources to assume any single facility node failure. This approach is commonly referred to as Survivable Virtual Network (SVN) design. The achievable reliability guarantee of the resultant SVN could come at the expense of lowering the substrate network utilization efficiency, and subsequently its admissibility, since the provisioned backup resources are reserved and remain idle until failures occur. Backup-sharing can replace the dedicated survivability scheme to circumvent the inconvenience of idle resources and reduce the footprints of backup resources. Indeed the problem of SVN design with backup-sharing has recurred multiple times in the literature. In most of the existing work, designing an SVN is bounded to a fixed number of backup nodes; further backup-sharing is only explored and optimized during the embedding phase. This renders the existing redesign techniques agnostic to the backup resource sharing in the substrate network, and highly dependent on the efficiency of the adopted mapping approach. In this paper, we diverge from this dogmatic approach, and introduce ProRed, a novel prognostic redesign technique that promotes the backup resource sharing at the virtual network level, prior to the embedding phase. Our numerical results prove that this redesign technique achieves lower-cost mapping solutions and greatly enhances the achievable backup sharing, boosting the overall network’s admissibility.

Dr. Sara Ayoubi received her MSc in 2012 from the Lebanese American University, and her Ph.D. in 2016 from the Concordia Institute for Information and Systems Engineering. She is currently a postdoctoral fellow at the Cheriton School of Computer Science at Waterloo University, and the founding member and executive secretary of the Montreal Operations Research Student Chapter. Dr. Ayoubi’s research interests are in the fields of Operations Research, Cloud Computing, Data Center networks virtualization and resource management.

Disaster Recovery in Networked Cloud Cyberinfrastructures

Abstract: Many cloud-based applications are being hosted at external datacenter sites with abundant storage and computing resources. These setups provide many saliencies, such as high cost efficiency and rapid scalability, and are seeing strong traction today. However, as user demands continue to grow, there is a further need to deploy such applications across multiple datacenter sites to achieve improved responsiveness. As a result, many network operators are using underlying network virtualization techniques to build customized distributed storage/computing configurations for their customer needs, e.g., infrastructure as a service (IaaS) offerings. Nevertheless, as more businesses migrate to the cloud, survivability and continuity concerns are coming to the fore. Of particular concern are large-scale disaster events which can cause multiple correlated datacenter and network system outages, e.g., such as natural disasters, malicious weapons of mass destruction (WMD) attacks, cascading power outages, etc. Clearly, localized intra-site server recovery schemes will not suffice here, and instead more capable network-based strategies are needed. Hence this talk will address this challenging problem space and review a range of disaster recovery solutions for networked cloud cyberinfrastructures. Foremost, various pre-fault protection strategies will be presented to mitigate the impact of potential future disaster occurrences. However, since it is very difficult (impossible) to pre-protect against all randomized faults, further post-fault restoration strategies will also be covered. These solutions include rapid re-mapping schemes as well as more time-staged progressive infrastructure repair/recovery methodologies. The talk will conclude with some discussions on future research directions in this overall area.

Dr. Nasir Ghani is a professor in the Electrical Engineering Department at University of South Florida and Research Liaison for the state-wide Florida Center for Cybersecurity (FC2). Prior to joining USF he was a faculty member and Associate Chair in the ECE Department at the University of New Mexico (2007-2013). He has also been a faculty member at Tennessee Tech University (2003-2007) and has spent over 8 years in industry working at several large hi-tech corporations (including Nokia, IBM, and Motorola) and startups (Sorrento Networks, Array Systems Computing). Currently he is involved in a wide range of research activities in the areas of cyberinfrastructure/network design, disaster recovery, cloud computing, and cyber-physical systems. His research has been supported by various agencies, including the National Science Foundation, Defense Threat Reduction Agency, Department of Energy, Qatar Foundation, Department of Education, and Sprint-Nextel Corporation. He also received the NSF CAREER Award in 2005 and the UNM Lawton-Ellis Award in 2011 for excellence in research, teaching, and outreach. Prof. Ghani has chaired the IEEE Technical Committee on High Speed Networking (TCHSN) from 2007-2010 and is currently an Associate Editor for the IEEE/OSA Journal of Optical Communications and Networking. He has also served on the editorial boards of IEEE Systems and IEEE Communications Letters and has guest-edited special issues of IEEE Network and IEEE Communications Magazine. Furthermore, he has chaired many symposia for IEEE GLOBECOM, IEEE ICC, and IEEE ICCCN. He received his Bachelors degree from the University of Waterloo, his Masters degree from McMaster University, and the Ph.D. degree from the University of Waterloo. He also received several Post Graduate Scholarship (PGS) awards from the Natural Sciences and Engineering Research Council of Canada (NSERC) during his graduate studies.

Posters/Demo Session

  1. “Space-efficient Data Structures for 2D Grids,” J. González, A. Pinto, and D. Seco
  2. “Parallel Construction of Wavelet Trees on Multicore Architectures,” J. Fuentes-Sepúlveda, E. Elejalde, L. Ferres, and D. Seco
  3. “QoSApp: Dynamic Bandwith Management for QoS Applications Using OpenFlow,” D. Lártiga, N. Boettcher, Y. Prieto, and J. E. Pezoa.
  4. “Energy-aware Image Allocation for Distributed Video Processing on Handheld Devices,” S. E. Restrepo, P. Pinaud, J. E. Pezoa, and S. Sobarzo.
  5. “Adaptive Meta-model of Ambient Intelligence Based on Contextual Characteristics, User Profiles, and Intelligent Agents,” S. E. Restrepo, D. A. Ovalle-Carranza, and J. E. Pezoa.
  6. “Nonunifomity Correction and Temperature Stabilization in Infrared Microbolometers,” A. Wolf, J. E. Pezoa, and M. Figueroa
  7. “Real-time Full HD Video Processing for High-Contrast Sport Events,” A. Saavedra, I. Vargas, P. Verdugo, J. E. Pezoa, and M. Figueroa

Sponsors




Deja un comentario

Copyright © 2010 Telecomunicaciones.udec.cl. All rights reserved.
Designed by Theme Junkie. Powered by WordPress.