Democratizing the Edge: A Pervasive Edge Computing Framework

Abstract

The needs of emerging applications, such as augmented and virtual reality, federated machine learning, and autonomous driving, have motivated edge computing-the push of computation capabilities to the edge. Various edge computing architectures have emerged, including multi-access edge computing and edge-cloud, all with the premise of reducing communication latency and augmenting privacy. However, these architectures rely on static and pre-deployed infrastructure, falling short in harnessing the abundant resources at the network's edge.In this paper, we discuss the design of Pervasive Edge Computing (PEC)-a democratized edge computing framework, which enables end-user devices (e.g., smartphones, IoT devices, and vehicles) to dynamically participate in a large-scale computing ecosystem. Our vision of the democratized edge involves the realtime composition of services using available edge resources like data, software, and compute-hardware from multiple stakeholders. We discuss how the novel Named-Data Networking architecture can facilitate service deployment, discovery, invocation, and migration. We also discuss the economic models critical to the adoption of PEC and the outstanding challenges for its full realization.

Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration

“…Still, they are more resource-demanding as they require communication between a large group of agents to reach a consensus. Furthermore, resource optimization algorithms have to be constantly running, which increases the overall resource consumption of orchestration tasks [52].…”

“…Finally, communication overhead may also be a determinant factor. Centralized architectures usually have a higher communication overhead than the distributed ones [52], as they need a high amount of information to be shared between each of the nodes and the central orchestrator (tasks to be deployed, available resources, latency requirements, deadlines...). This intrinsic communication overhead could be a problem in systems with a demand for edge dynamism and low latency.…”