Timely, Reliable, and Cost-Effective Internet Transport Service using Structured Overlay Networks
Yair Amir ,
Johns Hopkins University –
Emerging applications such as remote manipulation and remote robotic surgery require communication that is both timely and reliable, but the Internet natively supports only communication that is either completely reliable with no timeliness guarantees (e.g. TCP) or timely with only best-effort reliability (e.g. UDP). We present an overlay transport service that can provide highly reliable communication while meeting stringent timeliness guarantees (e.g. 130ms round-trip latency across the US) over the Internet. To enable routing schemes that can support the necessary timeliness and reliability, we introduce dissemination graphs, providing a unified framework for specifying routing schemes ranging from a single path, to multiple disjoint paths, to arbitrary graphs. Based on an extensive analysis of real-world network data, we develop a timely dissemination-graph-based routing method that can add targeted redundancy in problematic areas of the network. We show that this approach can cover close to 99% of the performance gap between a traditional single-path approach and an optimal (but prohibitively expensive) scheme.
Yair Amir is Professor of Computer Science and the director of the Distributed Systems and Networks (DSN) lab at Johns Hopkins University. From June 2015 to June 2018, he served as the Chair of the Department of Computer Science. His goal is to invent resilient, performant and secure distributed systems that make a difference, collecting friends along the way.
Dr. Amir holds B.Sc. (1985) and M.Sc. (1990) from the Technion, Israel Institute of Technology, and a Ph.D (1995) from the Hebrew University of Jerusalem, Israel. Dr. Amir is the recipient of the Alumni Association Excellence in Teaching Award for 2014, the highest teaching award in the Whiting School of Engineering, Johns Hopkins University. He was a finalist for the Excellence in Mentoring and Advising award in 2014 and for an Excellence in Teaching award in 2013. Dr. Amir was nominated for the DARPA agency-wide “Performer with Significant Technical Achievement” award in 2004, and was the recipient of the DARPA Dynamic Coalitions program Bytes-for-Buck trophy in 2002. His work received the Best Paper award in the IEEE Internationl Conference on Distributed Computing Systems (ICDCS) in 2017. Dr. Amir served on various technical program committees including co-chair of the IFIP/IEEE Dependable Systems and Networks (DSN) for 2015, and as an Associate Editor for the IEEE Transactions on Dependable and Secure Computing (2010-2013). He is a creator of the Spread toolkit (www.spread.org), the first scalable group communication system with strong semantics. He led Secure Spread, developing the first robust key agreement protocols, as well as the Spines overlay network platform (www.spines.org), the SMesh wireless mesh network (www.smesh.org), the first seamless 802.11 mesh with fast lossless handoff, the Prime Byzantine replication engine, the first to provide performance guarantees while under attack, and the Spire intrusion-tolerant SCADA for the power grid (www.dsn.jhu.edu), the first to protect against both system-level and network-level attacks and compromises. Some of these technologies are deployed in mission critical systems, support data center applications, are included in commercial products, and are used for research and teaching in universities and research labs around the world. Until 2016, Dr. Amir led the development of the LTN cloud (www.ltnglobal.com). He continues to provide technical leadership at LTN. LTN offers a global transport service for broadcast-quality live TV that is used by major broadcasters including CNN, Fox, Disney, ABC, Bloomberg, CBS, CNBC, ESPN, NBC, PBS, and Turner.
Date: 2018-Oct-17 Time: 17:00:00 Room: 336
For more information:
Mathematics, Physics & Machine Learning Seminar Series (Online)
The Mathematics, Physics & Machine Learning seminar series has started on October 2020 and runs until March 2021.
The seminars aim to bring together mathematicians and physicists interested in machine learning (ML) with ML and AI experts interested in mathematics and physics, with the goal of introducing innovative Mathematics and Physics-inspired techniques in Machine Learning and, reciprocally, applying Machine Learning to problems in Mathematics and Physics.
Attendance is free but registration is required.
More information is available here.
International European Conference on Parallel and Distributed Computing
The 27th International European Conference on Parallel and Distributed Computing (Euro-Par 2021) will take from August 30 to September 3 2021 in Lisbon.
Euro-Par is the prime European conference covering all aspects of parallel and distributed processing, ranging from theory to practice, from small to the largest parallel and distributed systems and infrastructures, from fundamental computational problems to full-fledged applications, from architecture, compiler, language and interface design and implementation, to tools, support infrastructures, and application performance aspects.
The 2021 edition of Euro-Par will be organized as a collaboration between INESC-ID and Instituto Superior Técnico (IST).
– Abstract Submission: February 5, 2021
– Paper Submission Deadline: February 12, 2021
– Author Notification: April 30, 2021
– Camera-Ready Papers: June 6, 2021
More information is available here.