On May 24, Orbs organized the 2018 Israeli Networking Day together with the Israeli site of VMware Research, an annual event of the local networking community that brings together researchers and engineers from both academia and industry to discuss their recent research.
I had the chance to chair the event together with Dr. Yaniv Ben-Itzhak from VMware. The event included 24 talks, describing recently published academic papers and ongoing works.
Roughly 100 attendees participated in the event, representing universities and research institutions such as Technion, Hebrew University, Ben Gurion University, Tel Aviv University, Haifa University, Bar Ilan University, IDC, Mälardalen University (Sweden), IMDEA Networks Institute (Spain), and a range of industrial powerhouses like IBM Research, Mellanox Technologies, Amazon Web Services, Marvell, Intel, Apple, General Motors, LightBits Labs, Radware, Huawei, NSA, and Nokia Bell Labs.
Among the two dozens speakers, my team at Orbs had the chance to take the stage, and it was one of the highlights of the day — in my opinion.
1. Yangguang Shi: Economies of Scale and Energy Efficiency
Also among the speakers was Yangguang Shi, a postdoctoral researcher at the Technion whose research focuses on developing randomized algorithms for optimizing the energy efficiency for large-scale distributed networks.
“Approximating Generalized Network Design under (Dis)economies of Scale with Applications to Energy Efficiency” — co-written with Yuval Emek, Shay Kutten and Ron Lavi — Yangguang spoke on graph-related approximation algorithms for scaling the design of energy efficient distributed network. This work will appear later in June in the ACM Symposium on the Theory of Computing (ACM STOC).
2. William K. Moses: Balanced Allocation
William K. Moses, who is also a postdoctoral researcher at the Technion, described a statistical balls-and-bin model for server load balancing.
Presenting “Balanced Allocation: Patience is not a Virtue” — co-written with John Augustine, Amanda Redlich and Eli Upfal — he described a technique achieving a fair balance among the loads of servers while only a small number of load probes is required before insertion.
3. Ido Grayevsky: Orbs’ Helix Consensus Algorithm
Orbs’ very own Ido Grayevsky discussed fairness aspects of Helix, Orbs’ recently suggested transactions ordering service, while focusing on the impact of network quality on the achieved fairness.
Presenting the paper, “A Fair and Scalable Consensus Algorithm for Transactions Ordering” — a paper co-authored with Avi Asayag, Gad Cohen, Maya Leshkowitz, myself, Ronen Tamari and David Yakira — Ido demonstrated how improved network performance strengthens the achieved fairness between the network nodes in the time it takes transactions to appear in issued blocks.
It was a tremendous event and an incredible experience. These 24 wide-scope research works presented along the day, demonstrate the potential and depth of Israel’s networking community and its international collaborations.