Abstract: There is provided a method and system for communication network management. There is provided an active TE architecture and procedure that rely on the epistemic uncertainty obtained from traffic forecasting models. According to embodiments, the traffic forecasting models can predict the mean of the network traffic demand and can extract one or more of the features relating epistemic uncertainty and the aleatoric uncertainty. According to embodiments, the epistemic uncertainty is used to vary the sampling frequency of network statistics in TE applications, for specific times or specific flows. A time-window can be used to predict network traffic can be varied (e.g. increased or decreased) to adjust the epistemic uncertainty.

Abstract: There are provided a method, system and computer program product for preventing unauthorized use of a deep reinforcement learning agent. The DRL agents are trained to behave as expected only when they observe the one or more required secret operational keys. In some embodiments, the DRL agents are further trained to operate at a diminished capacity when the one or more required secret operational keys are unused.

Abstract: Methods and systems that enable communication network traffic engineering functions or application functions using combinations of neural network (NN) encoders and NN decoders are provided. A first network element has a NN encoder deployed thereat and receives input data based on which the NN encoder generates a latent representation. The latent representation is provided to a second network element that has a NN decoder deployed thereat and is configured to process the latent representation in accordance with a traffic engineering function to produce a traffic engineering output, which may be used to modify an operational state variable of the communication network. The input data are values of operational state variables of the communication network obtained at the first network element.

Abstract: There is provided a method and system for communication network management. There is provided an active TE architecture and procedure that rely on the epistemic uncertainty obtained from traffic forecasting models. According to embodiments, the traffic forecasting models can predict the mean of the network traffic demand and can extract one or more of the features relating epistemic uncertainty and the aleatoric uncertainty. According to embodiments, the epistemic uncertainty is used to vary the sampling frequency of network statistics in TE applications, for specific times or specific flows. A time-window can be used to predict network traffic can be varied (e.g. increased or decreased) to adjust the epistemic uncertainty.

Abstract: There are provided a method, system and computer program product for preventing unauthorized use of a deep reinforcement learning agent. The DRL agents are trained to behave as expected only when they observe the one or more required secret operational keys. In some embodiments, the DRL agents are further trained to operate at a diminished capacity when the one or more required secret operational keys are unused.