Service Continuity in Edge Computing Through Edge Proxies and HTTP Alternative Services

Abstract

Edge computing brings computation facilities in close proximity to users, hence paving the way to a plethora of applications characterized by stringent requirements. Edge systems are highly dynamic, and clients may have to access their edge services at different locations over time. When this happens, it is fundamental to guarantee seamless service continuity, i.e., letting endpoints reach each other transparently and with no or negligible impact on performance. In this work, we propose a service-continuity solution for edge environments that leverages an ecosystem of distributed edge proxies as its core element. Edge proxies mediate between client applications and edge services and are dynamically reconfigured by a system orchestrator to ensure service continuity when the proxy for a client needs to change. Our proxies exploit HTTP Alternative Services, an extension of the HTTP standard, to inform clients of the new proxy to reach. Our approach is fully transparent to the application logic and does not require any non-standard protocol modification. We implemented a Proof-of-Concept and used it to assess our solution over a small-scale testbed. We considered different experimental scenarios and variants of the proposed strategy, comparing it against alternative approaches, namely one where the edge proxy does not change and one based on DNS resolution. Experimental results show the validity and superior performance of the proposed methodology.