$π$-ROAD: a Learn-as-You-Go Framework for On-Demand Emergency Slices in V2X Scenarios
Armin Okic,
Lanfranco Zanzi,
Vincenzo Sciancalepore
et al.
Abstract:Vehicle-to-everything (V2X) is expected to become one of the main drivers of 5G business in the near future. Dedicated network slices are envisioned to satisfy the stringent requirements of advanced V2X services, such as autonomous driving, aimed at drastically reducing road casualties. However, as V2X services become more mission-critical, new solutions need to be devised to guarantee their successful service delivery even in exceptional situations, e.g. road accidents, congestion, etc. In this context, we pr… Show more
“…Additionally, slicing has been a fruitful field of application for online convex optimization [12], [26], [13]. Moreover, reinforcement learning [27], [28] for resource orchestration has been recently applied on the problem On the other hand, DNNs [10], [5], [24], [8], [18] with early exit(s), is a recent and promising research avenue with many under-exploited applications. Moreover, a key quantity is the amount of information transmitted to the remote layers.…”
Network slicing has been proposed as a paradigm for 5G+ networks. The operators slice physical resources from the edge, all the way to datacenter, and are responsible to micromanage the allocation of these resources among tenants bound by predefined Service Level Agreements (SLAs). A key task, for which recent works have advocated the use of Deep Neural Networks (DNNs), is tracking the tenant demand and scaling its resources. Nevertheless, for edge resources (e.g. RAN), a question arises whether operators can: (a) scale edge resources fast enough (often in the order of ms) and (b) afford to transmit huge amounts of data towards a cloud where such a DNNbased algorithm might operate. We propose a Distributed-DNN architecture for a class of such problems: a small subset of the DNN layers at the edge attempt to act as fast, standalone resource allocator; this is coupled with a Bayesian mechanism to intelligently offload a subset of (harder) decisions to additional DNN layers running at a remote cloud. Using the publicly available Milano dataset, we investigate how such a DDNN should be jointly trained, as well as operated, to efficiently address (a) and (b), resolving up to 60% of allocation decisions locally with little or no penalty on the allocation cost.
“…Additionally, slicing has been a fruitful field of application for online convex optimization [12], [26], [13]. Moreover, reinforcement learning [27], [28] for resource orchestration has been recently applied on the problem On the other hand, DNNs [10], [5], [24], [8], [18] with early exit(s), is a recent and promising research avenue with many under-exploited applications. Moreover, a key quantity is the amount of information transmitted to the remote layers.…”
Network slicing has been proposed as a paradigm for 5G+ networks. The operators slice physical resources from the edge, all the way to datacenter, and are responsible to micromanage the allocation of these resources among tenants bound by predefined Service Level Agreements (SLAs). A key task, for which recent works have advocated the use of Deep Neural Networks (DNNs), is tracking the tenant demand and scaling its resources. Nevertheless, for edge resources (e.g. RAN), a question arises whether operators can: (a) scale edge resources fast enough (often in the order of ms) and (b) afford to transmit huge amounts of data towards a cloud where such a DNNbased algorithm might operate. We propose a Distributed-DNN architecture for a class of such problems: a small subset of the DNN layers at the edge attempt to act as fast, standalone resource allocator; this is coupled with a Bayesian mechanism to intelligently offload a subset of (harder) decisions to additional DNN layers running at a remote cloud. Using the publicly available Milano dataset, we investigate how such a DDNN should be jointly trained, as well as operated, to efficiently address (a) and (b), resolving up to 60% of allocation decisions locally with little or no penalty on the allocation cost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.