Making Edge Computing Reliable

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 one can design such a Client-Edge-Server system to tolerate edge failures and client mobility when the edge processing is stateful (e.g., the processing depends on state it has previously seen from the client and/or server). In this project we propose a design for meeting this challenge called Client-Edge-Server for Stateful Network Applications (CESSNA).

(A preliminary paper on CESSNA has been accepted to SIGCOMM's MECOMM 2018 workshop on mobile edge communication)