Abstract:
The introduction of computational resources at the network edge allows us to offload computation from clients and/or servers, thereby reducing response latency, backbone bandwidth, and computational requirements on clients. More fundamentally, edge-computing moves us from a client-server model to a client-edge-server model. While this is an attractive paradigm for many applications, it raises the question of how to design client-edge-server systems so they can tolerate edge failures and client mobility. This is particularly challenging when edge processing is stateful. In this talk we propose a design for meeting this challenge.
Bio:
Yotam Harchol is a postdoctoral scholar at the University of California, Berkeley, where he works with Prof. Scott Shenker on edge computing, fault tolerance, distributed systems, and Internet architecture. Before joining UC Berkeley, Yotam has spent one year as a postdoctoral researcher at VMware Research, focusing mainly on network systems security. Yotam holds Ph.D. and M.Sc. degrees, both in Computer Science, from the Hebrew University of Jerusalem, Israel, and a B.A. degree in Computer Science (magna cum laude) from IDC Herzliya, Israel. Yotam is the recipient of the Hans Wiener Prize for Excellent Ph.D. Dissertation, the Hebrew University Cybersecurity Research Center Post-Doctoral Fellowship, Intel Award for Graduate Students, Hammer Fellowship for Graduate Students, and the Chais Scholarship for Excellent Undergraduate Students.
