Extending P4 in-band telemetry to user equipment for latency- and localization-aware autonomous networking with AI forecasting

Abstract

In Beyond-5G Networks, detailed end-to-end monitoring of specific application traffic will be required along with the access-backhaul-cloud continuum to enable low latency service thanks to local edge steering. Current monitoring solutions are confined to specific network segments. In-band telemetry (INT) technologies for SDN programmable data planes based on the P4 language are effective in the backhaul network segment, although limited to inter-switch latency, therefore link latencies including wireless and optical segments are excluded from INT monitoring. Moreover, information such as user equipment geolocation information would allow detailed mobility monitoring and improved cloud-edge steering policies. However, the synchronization between latency and location information, typically provided by different platforms, is hard to achieve with current monitoring systems. In this paper P4-based INT is proposed to be thoroughly extended involving the user equipment (UE). The novel INT mechanism is designed to provide synchronized and accurate end-to-end latency and geolocation information, enabling decentralized steering policies, i.e. involving the UE and selected switches, without the SDN controller intervention. The proposal also includes an Artifical Intelligence (AI)-assisted forecast system able to predict latency and geolocation in advance and trigger faster edge steering.

P4 Telemetry collector

“…Considering that the comprehensive collection of network data made available by PDP opens the door for many possible applications in the network and brings in Artificial Intelligence (AI) to the decisionmaking. Where the AI can have an important role in steering user traffic to the best serving node for lower latency and better Quality of Service (QoS) as in [10], or even provide filtering of traffic based on signatures that are generated from packet features for enhanced detection and mitigation of DDoS attacks [11].…”

Enabling P4 Network Telemetry in Edge Micro Data Centers With Kubernetes Orchestration

“…Specifically, such work proposed extensions to ONOS for supporting INT that later have been included in the ONOS official distribution. More recently, the work in [39], focused on 5G networks, proposes the extension of the INT-MD technique up to the user equipment to enable the evaluation of fully end-to-end (e2e) latency. In general, INT telemetry features the generation of a report packet for each data plane packet.…”

Applications of P4-based Network Programmability in Optical Networks

“…For example, In-band Telemetry (INT) enables the introduction of custom packet headers including metadata such as timestamps and the time spent in the traversed queues. This enables accurate monitoring across the whole packet and optical network, potentially leading to improved traffic engineering solutions [9][10][11]. B. Latency-aware scheduling and forwarding.…”

“…The possibility to accurately monitor edge-to-cloud latency performance through INT, besides global optimizations, enables dynamic local scheduling and QoS-driven forwarding operations. For example, the local selection among alternative routes across optical and packet resources (e.g., optical bypass) may be dynamically performed even on a per-flowlet basis, instead of adopting the relatively rigid tributary traffic assignment implemented with today's muxponders and transponders [11,12]. C. 5G function acceleration.…”