Artificial intelligence (AI) is an extensive scientific discipline which enables computer systems to solve problems by emulating complex biological processes such as learning, reasoning and self-correction. This paper presents a comprehensive review of the application of AI techniques for improving performance of optical communication systems and networks. The use of AI-based techniques is first studied in applications related to optical transmission, ranging from the characterization and operation of network components to performance monitoring, mitigation of nonlinearities, and quality of transmission estimation. Then, applications related to optical network control and management are also reviewed, including topics like optical network planning and operation in both transport and access networks. Finally, the paper also presents a summary of opportunities and challenges in optical networking where AI is expected to play a key role in the near future

Utilizing the dormant path diversity through multipath routing in the Internet to reach end users-thereby fulfilling their QoS requirements-is rather logical. While offering better resource utilization, better reliability, and often even much better quality of experience (QoE), multipath routing and provisioning was shown to help network and data center operators achieve traffic engineering in the form of load balancing. In this survey, we first highlight the benefits and basic Internet multipath routing components. We take a top-down approach and review various multipath protocols, from application to link and physical layers, operating at different parts of the Internet. We also describe the mathematical foundations of the multipath operation, as well as highlight the issues and challenges pertaining to reliable data delivery, buffering, and security in deploying multipath provisioning in the Internet. We compare the benefits and drawbacks of these protocols operating at different Internet layers and discuss open issues and challenges.

Traffic prediction and utilization of past information are essential requirements for intelligent and efficient management of resources, especially in optical data center networks (ODCNs), which serve diverse applications. In this paper, we consider the problem of traffic aggregation in ODCNs by leveraging the predictable or exact knowledge of application-specific information and requirements, such as holding time, bandwidth, traffic history, and latency. As ODCNs serve diverse flows (e.g., long/elephant and short/mice), we utilize machine learning (ML) for prediction of time-varying traffic and connection blocking in ODCNs. Furthermore, with the predicted mean service time, passed time is utilized to estimate the mean residual life (MRL) of an active flow (connection). The MRL information is used for dynamic traffic aggregation while allocating resources to a new connection request. Additionally, blocking rate is predicted for a future time interval based on the predicted traffic and past blocking information, which is used to trigger a spectrum reallocation process (also called defragmentation) to reduce spectrum fragmentation resulting from the dynamic connection setup and tearing-down scenarios. Simulation results show that ML-based prediction and initial setup times (history) of traffic flows can be used to further improve connection blocking and resource utilization in space-division multiplexed ODCNs.

The automatic identification system (AIS) reports vessels' static and dynamic information, which are essential for maritime traffic situation awareness. However, AIS transponders can be switched off to hide suspicious activities, such as illegal fishing, or piracy. Therefore, this paper uses real world AIS data to analyze the possibility of successful detection of various anomalies in the maritime domain. We propose a multi-class artificial neural network (ANN)-based anomaly detection framework to classify intentional and non-intentional AIS on-off switching anomalies. The multi-class anomaly framework captures AIS message dropouts due to various reasons, e.g., channel effects or intentional one for carrying illegal activities. We extract position, speed, course and timing information from real world AIS data, and use them to train a 2-class (normal and anomaly) and a 3-class (normal, power outage and anomaly) anomaly detection models. Our results show that the models achieve around 99.9% overall accuracy, and are able to classify a test sample in the order of microseconds.

Understanding and representing traffic patterns are key to detecting anomalous trajectories in the transportation domain. However, some trajectories can exhibit heterogeneous maneuvering characteristics despite confining to normal patterns. Thus, we propose a novel graph-based trajectory representation and association scheme for extraction and confederation of traffic movement patterns, such that data patterns and uncertainty can be learned by deep learning (DL) models. This paper proposes the usage of a recurrent neural network (RNN)-based evidential regression model, which can predict trajectory at future timesteps as well as estimate the data and model uncertainties associated, to detect anomalous maritime trajectories, such as unusual vessel maneuvering, using automatic identification system (AIS) data. Furthermore, we utilize evidential deep learning classifiers to detect unusual turns of vessels and the loss of transmitted signal using predicted class probabilities with associated uncertainties. Our experimental results suggest that the graphical representation of traffic patterns improves the ability of the DL models, such as evidential and Monte Carlo dropout, to learn the temporal-spatial correlation of data and associated uncertainties. Using different datasets and experiments, we demonstrate that the estimated prediction uncertainty yields fundamental information for the detection of traffic anomalies in the maritime and, possibly in other domains.

Elastic optical networks are prone to spectrum fragmentation, resulting in poor resource utilization and often higher blocking probability. To overcome the spectrum fragmentation, a defragmentation (DF) of the spectrum can be applied by reconfiguring some or all active connections. However, reconfiguration is generally not desirable, as it can interrupt the services of the existing connections. In this paper, we propose two novel connection reconfiguration schemes to efficiently address spectrum DF: (i) a reactive–disruptive scheme and (ii) a proactive–non-disruptive scheme. Both schemes utilize the information of holding times of the existing connections in order to reduce fragmentation and thus improve resource utilization and minimize connection blocking. The reactive–disruptive reconfiguration scheme tries to allocate an incoming connection, which could not be accepted otherwise, by reconfiguring some existing connections. The proactive–non-disruptive reconfiguration method, on the other hand, allows us to reconfigure only such connections, which can be shifted without crossing over the spectrum of other connections. This paves the way for a non-disruptive DF when setting up a new connection, which is a desirable feature. Simulation results show that the reconfiguration schemes with holding-time awareness can be effectively utilized to reduce the spectrum fragmentation and, hence, result in better resource utilization and overall lower connection blocking probability.