Scalable and Bounded-time Decisions on Edge Device Network using Eclipse Zenoh

Abstract

The enhanced computing platforms, which are on edge networks and used for embedding computing services, enable the processing of sensing data on edge and sharing the data with the peers of interest. Smart factories and autonomous vehicles are two typical examples. However, existing real-time communication protocols have limits on cross-network domains and complex data structures. To resolve the problems above, this work investigates a new distributed data exchange framework, Zenoh. As a unified and transparent middle-ware for devices over heterogeneous networks, Zenoh enables peers in different network domains to exchange messages in real-time by pub/sub data exchange pattern. Furthermore, it provides high flexibility and scalability by configurable end-to-end and hop-to-hop reliability and congestion control QoS profiles. This work proposes a bounded-time decision algorithm by Reliable Broadcast and CRDT based on Zenoh. This work also benchmarks the protocol’s capability over cross-domain networks and investigate the overhead of our algorithms implemented on Zenoh. The throughput and latency performance shows the potential for practical communication between robots in factories or autonomous vehicles on roads.