In the beyond 5G era, AI/ML empowered real-world digital twins (DTs) will enable diverse network operators to collaboratively optimize their networks, ultimately improving end-user experience. Although centralized AI-based learning techniques have been shown to achieve significant network traffic accuracy, resulting in efficient network operations, they require sharing of sensitive data among operators, leading to privacy and security concerns. Distributed learning, and specifically federated learning (FL), that keeps data isolated at local clients, has emerged as an effective and promising solution for mitigating such concerns. Federated learning poses, however, new challenges in ensuring fairness both in terms of collaborative training contributions from heterogeneous data and in mitigating bias in model predictions with respect to sensitive attributes. To address these challenges, a fair FL framework is proposed for collaborative network traffic prediction and resource allocation. To demonstrate the effectiveness of the proposed approach, noniid and imbalanced federated datasets based on real-word traffic traces are utilized for an elastic optical network. The assumption is that different optical nodes may be managed by different operators. Fairness is evaluated according to the coefficient of variations measure in terms of accuracy across the operators and in terms of quality-of-service across the connections (i.e., reflecting end-user experience). It is shown that fair traffic prediction across the operators result in fairer resource allocations across the connections.

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.

An upper bound on the delay in the control channels is necessary as control state inconsistency significantly degrades the performance of a logically-centralized and physically-distributed control plane. Statistically multiplexing control traffic with the data traffic (in-fiber in-band) or reserving a low-rate control channel does not ensure QoS guarantees in terms of delay specially if the network is congested. Therefore, control traffic must be viewed and treated differently from data traffic. This article presents ac MILP and a heuristic to design distributed SDN-based in-fiber out-of-band control plane for elastic optical network (EON). The objective is to minimize the number of controllers while reserving resources for the control traffic to ensure that delay in the control channel is bounded. The designed inter-controller virtual tree topology avoids control traffic replication. For better resource utilization it requires OEO conversion at every controller node for grooming control traffic and this incurs queuing delay at each controller node. The design takes into account queuing delay along with transmission and propagation delay in control plane links and maintains the total delay within a specified bound. To the best of our knowledge, this is the first work to analyze queuing delay along with transmission and propagation delay in inter-controller links of the control plane. We further present a MILP to make this virtual control plane tree topology survivable against single link failure by utilizing the concept of fundamental cycles. The numerical results show that our proposed control plane design performs better than existing control plane designs where control traffic is statistically multiplexed with data traffic in terms of delay in the control plane and blocking probability in the data plane.