This thesis deals with predicting the latency between two network nodes, such as the two stations, two servers or server and station. The main reason for adoption of effective latency prediction techniques is the elimination of network load caused by unnecessary repeated transmissios or by direct measurement of the latency. Of the many proposed methods of latency estimation, this thesis is focused on methods using artificial coordinate systems with primary focus on the Vivaldi algorithm. Characteristics of the latency prediction methods and properties of various coordinate systems used in practice are evaluated. The issue of the number of dimensions of space defined only by the latency matrix between nodes is also mentioned. Furthermore, some other systems, based on logical clustering of nearby nodes, are mentioned. Description of simulation software VivaldiMonitor developed as part of the thesis is included. The primary purpose is analysis of the behavior of overlay networks implementing Vivaldi algorithm with less than a few hundred nodes. The Vivaldi algorithm is assessed by several simulations carried out using the aforementioned software.

Indiana University-Purdue University Indianapolis (IUPUI) / Graph Neural Networks (GNNs) have become excessively popular and prominent deep learning techniques to analyze structural graph data for their ability to solve complex real-world problems. Because graphs provide an efficient approach to contriving abstract hypothetical concepts, modern research overcomes the limitations of classical graph theory, requiring prior knowledge of the graph structure before employing traditional algorithms. GNNs, an impressive framework for representation learning of graphs, have already produced many state-of-the-art techniques to solve node classification, link prediction, and graph classification tasks. GNNs can learn meaningful representations of graphs incorporating topological structure, node attributes, and neighborhood aggregation to solve supervised, semi-supervised, and unsupervised graph-based problems. In this study, the usefulness of GNNs has been analyzed primarily from two aspects - clustering and classification. We focus on these two techniques, as they are the most popular strategies in data mining to discern collected data and employ predictive analysis.