Distributed intelligence for pervasive optical network telemetry

Abstract

Optical network automation and failure management require measuring the status and the performance of the different network devices to anticipate any degradation and ensure the quality of the provided services, i.e., optical connectivity. Such pervasive network telemetry entails collecting large amounts of measurements and events from different sources and with very fine granularity, which given the amount and variety of telemetry sources and the size of each measurement and event, imposes requirements that are hard to achieve without large investments. In this paper, we analyze the main limitations of telemetry architectures relying exclusively on centralized systems for data analysis and propose an architecture with distributed intelligence. Data aggregation techniques, especially conceived for optical network telemetry, are presented with the objective of reducing data dimensionality. Illustrative results from our experimental telemetry system reveal a reduction of 3 orders of magnitude in terms of total data volume without introducing significant error and processing delay and, more importantly, helping network automation algorithms to identify meaningful changes in the network status.

Context-Based e2e Autonomous Operation in B5G Networks

“…Then, the new mapping π s is computed from graph ρ s (line 11). After this computation, the stored slice capacity is subtracted from all the x ecm variables belonging to the stored mapping (lines 12-14), whereas the new capacity is added to the x ecm variables of the new mapping (lines [15][16][17]. Finally, the slice capacity, mapping, and context are updated (lines [18][19][20].…”

“…This is particularly interesting when the digital sub-carrier multiplexing (DSCM) technology is used, as sub-carriers can be activated and deactivated in near real time, which leads to operational benefits, including energy savings [ 15 ]. Note that this AI-based operation can be built on top of a distributed architecture that enables local control loops and efficient resource management without saturating the centralized systems in charge of, e.g., e2e service provisioning [ 16 ].…”

TAPI-based Telemetry Streaming in Multi-domain Optical Transport Network

“…Nonetheless, the work is mentioned as ongoing and network automation techniques are not discussed. Conversely, the approaches [4,5] give a comprehensive overview of the telemetry pipeline architecture and evaluate protocols for transporting the telemetry data. The evaluation part focuses on intelligent data aggregation and data summarization techniques.…”