Federated Learning With Heterogeneity-Aware Probabilistic Synchronous Parallel on Edge

With the massive amount of data generated from mobile devices and the increase of computing power of edge devices, the paradigm of Federated Learning has attracted great momentum. In federated learning, distributed and heterogeneous nodes collaborate to learn model parameters. However, while providing benefits such as privacy by design and...

Scheduling Workloads of Workflows in Clusters and Clouds

This dissertation addresses three key challenges that are characteristic to the online scheduling of workloads of workflows in modern distributed computing systems. The first challenge is the realistic estimation of the resource demand of a workflow, as it is important for making good task placement and resource allocation decisions. Usually,...

Distributing Load Flow Computations Across System Operators Boundaries Using the Newton–Krylov–Schwarz Algorithm Implemented in PETSc

The upward trends in renewable energy penetration, cross-border flow volatility and electricity actors’ proliferation pose new challenges in the power system management. Electricity and market operators need to increase collaboration, also in terms of more frequent and detailed system analyses, so as to ensure adequate levels of quality and...

Design, Analysis and Experimental Evaluation of a Distributed Community Detection Algorithm

Complex networks are a special type of graph that frequently appears in nature and in many different fields of science and engineering. Studying complex networks is the key to solve the problems in these fields. Complex networks have unique features which we cannot find in regular graphs, and the study of complex networks gives rise to many...

Interactive distributed optimisation for multidisciplinary design

This paper presents the development of a multidisciplinary optimisation system for the Architecture Engineering and Construction (AEC) industry. The system consists of two major components, namely a multidisciplinary optimisation framework and a distributed cloud-based analysis framework. The former utilises an interactive optimisation search...

Adding Cycle Scavenging Support to the Koala Grid Resource Manager

Cycle scavenging (CS) is the process of using otherwise idle computational resources to provide large, aggregate, amounts of computational power. It is the core principle of so-called desktop grids and volunteer computing, which use the idle cycles of desktop computers to do computations. However, resources in a multicluster grid likewise may...

3D visualization of extra large data arrays by means of scientificVR® visualizer

Visualization of data is nowadays an indispensable part of scientific research and effect analysis practically in any field of natural sciences. Graphic presentation of the results in the form of color lay-outs or functional dependence diagrams makes it considerably easier to perceive new information and contributes to a more sophisticated and...