Tania Panayiotou

Sadananda Behera, Tania Panayiotou, Georgios Ellinas

This work proposes a real-time anomaly detection scheme that leverages the multi-step ahead prediction capabilities of encoder-decoder (ED) deep learning models with recurrent units. Specifically, an encoder-decoder is used to model soft-failure evolution over a long future horizon (i.e., for several days ahead) by analyzing past quality-of-transmission (QoT) observations. This information is subsequently used for real-time anomaly detection (e.g., of attack incidents), as the knowledge of how the QoT is expected to evolve allows capturing unexpected network behavior. Specifically, for anomaly detection, a statistical hypothesis testing scheme is used, alleviating the limitations of supervised (SL) and unsupervised learning (UL) schemes, usually applied for this purpose. Indicatively, the proposed scheme eliminates the need for labeled anomalies, required when SL is applied, and the need for on-line analyzing entire datasets to identify abnormal instances (i.e., UL). Overall, it is shown that by utilizing QoT evolution information, the proposed approach can effectively detect abnormal deviations in real-time. Importantly, it is shown that the information concerning soft-failure evolution (i.e., QoT predictions) is essential to accurately detect anomalies.

Sadananda Behera, Tania Panayiotou, Georgios Ellinas

In this work, the capabilities of an encoder-decoder learning framework are leveraged to predict soft-failure evolution over a long future horizon. This enables the triggering of timely repair actions with low quality-of-transmission (QoT) margins before a costly hard-failure occurs, ultimately reducing the frequency of repair actions and associated operational expenses. Specifically, it is shown that the proposed scheme is capable of triggering a repair action several days prior to the expected day of a hard-failure, contrary to soft-failure detection schemes utilizing rule-based fixed QoT margins, that may lead either to premature repair actions (i.e., several months before the event of a hard-failure) or to repair actions that are taken too late (i.e., after the hard failure has occurred). Both frameworks are evaluated and compared for a lightpath established in an elastic optical network, where soft-failure evolution can be modeled by analyzing bit-error-rate information monitored at the coherent receivers.

Giannis Savva, Hafsa Maryam, Venkatesh Chebolu et al.

In this work, multi-step traffic predictions are leveraged to enable multi-period planning in reconfigurable optical networks. The proposed framework aims to achieve spectrum savings by adapting the network to predicted time-varying conditions while ensuring the necessary quality-of-service (QoS) levels. Since frequent network (re)configurations may lead to undesired service disruptions, traffic predictions spanning various prediction horizons are exploited to balance the trade-off between spectrum savings and service disruptions. For multi-step-ahead prediction, an encoder-decoder deep learning model is employed to analyze real traffic traces. Subsequently, an Integer Linear Programming (ILP) formulation and heuristic algorithms are developed that use the predictions to proactively (re)optimize future network configurations, enhancing spectrum efficiency while minimizing service disruptions. The approaches are utilized under different scenarios, with the ILP achieving better solutions overall, and the heuristics achieving solutions close to the ILP at significantly lower running times. Further, the results present the effect of the prediction horizon on disruptions and over- and under- provisioning, showcasing that the prediction horizon selection greatly depends on the network operator targets in both network performance and predefined service level agreements.

Dinesh Cyril Selvaraj, Christian Vitale, Tania Panayiotou et al.

In pursuit of autonomous vehicles, achieving human-like driving behavior is vital. This study introduces adaptive autopilot (AA), a unique framework utilizing constrained-deep reinforcement learning (C-DRL). AA aims to safely emulate human driving to reduce the necessity for driver intervention. Focusing on the car-following scenario, the process involves (i) extracting data from the highD natural driving study and categorizing it into three driving styles using a rule-based classifier; (ii) employing deep neural network (DNN) regressors to predict human-like acceleration across styles; and (iii) using C-DRL, specifically the soft actor-critic Lagrangian technique, to learn human-like safe driving policies. Results indicate effectiveness in each step, with the rule-based classifier distinguishing driving styles, the regressor model accurately predicting acceleration, outperforming traditional car-following models, and C-DRL agents learning optimal policies for humanlike driving across styles.

Dinesh Cyril Selvaraj, Christian Vitale, Tania Panayiotou et al.

Intersection crossing represents one of the most dangerous sections of the road infrastructure and Connected Vehicles (CVs) can serve as a revolutionary solution to the problem. In this work, we present a novel framework that detects preemptively collisions at urban crossroads, exploiting the Multi-access Edge Computing (MEC) platform of 5G networks. At the MEC, an Intersection Manager (IM) collects information from both vehicles and the road infrastructure to create a holistic view of the area of interest. Based on the historical data collected, the IM leverages the capabilities of an encoder-decoder recurrent neural network to predict, with high accuracy, the future vehicles' trajectories. As, however, accuracy is not a sufficient measure of how much we can trust a model, trajectory predictions are additionally associated with a measure of uncertainty towards confident collision forecasting and avoidance. Hence, contrary to any other approach in the state of the art, an uncertainty-aware collision prediction framework is developed that is shown to detect well in advance (and with high reliability) if two vehicles are on a collision course. Subsequently, collision detection triggers a number of alarms that signal the colliding vehicles to brake. Under real-world settings, thanks to the preemptive capabilities of the proposed approach, all the simulated imminent dangers are averted.

Hafsa Maryam, Tania Panayiotou, Georgios Ellinas

A multi-period planning framework is proposed that exploits multi-step ahead traffic predictions to address service overprovisioning and improve adaptability to traffic changes, while ensuring the necessary quality-of-service (QoS) levels. An encoder-decoder deep learning model is initially leveraged for multi-step ahead prediction by analyzing real-traffic traces. This information is then exploited by multi-period planning heuristics to efficiently utilize available network resources while minimizing undesired service disruptions (caused due to lightpath re-allocations), with these heuristics outperforming a single-step ahead prediction approach.

Tania Panayiotou, Giannis Savva, Ioannis Tomkos et al.

Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G's diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work we examine the ML-based Quality-of-Transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different QoT requirement. We examine ML-based QoT frameworks with the aim of finding QoT model/s that are fine-tuned according to the diverse QoT requirements. Centralized and distributed frameworks are examined and compared according to their accuracy and training time. We show that the distributed QoT models outperform the centralized QoT model, especially as the number of diverse QoT requirements increases.