Daniel Szostak

Wroclaw University of Science and Technology | WUT · Department of Systems and Computer Networks

This work focuses on finding efficient Machine Learning (ML) method for traffic prediction in optical network. Considering optical networks’ characteristics, we predict fixed bitrate levels. For the considered problem, we propose two ML approaches, namely classification and regression, for which we compare performance of single ML algorithms and en...

Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we...

Knowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource management. Machine Learning (ML) algorithms can be employed for forecasting traffic with high accuracy. In this paper we describe a methodology for predicting traffic in a dynamic optical netwo...

In this paper, we focus on the problem of resource allocation for time-varying traffic in translucent space-division multiplexing (SDM) elastic optical networks (EON) with back-to-back (B2B) signal regeneration. The performance is measured in terms of bandwidth blocking probability, usage of spectral resource (i.e. minimizing allocated bandwidth ov...

Knowledge about future traffic in a dynamic optical network can be used to improve various performance metrics, including network cost and to reduce complexity of solving network optimization problems. In this paper, we propose a machine learning approach of predicting demands in a dynamic optical network serving Virtual Network Function (VNF) chai...