|
|
Raspberry Pi 4 Cluster Management in Nix
Živčák, Adam ; Burget, Radek (referee) ; Rychlý, Marek (advisor)
The scope of this thesis is to design and implement a system for deploying, managing and monitoring a Raspberry Pi cluster using Nix technologies. The thesis describes the benefits of the functional approach of Nix and the subsystems that are based on it. The thesis also results in a supporting web application, providing an intuitive environment for working with cluster configuration deployments and clearly displaying information about the utilization of individual nodes using dashboards. The final part of the thesis is devoted to testing cluster performance using sample distributed computing jobs.
|
|
|
Distributed Artificial Life Simulator
Weiss, Martin ; Kočí, Radek (referee) ; Martinek, David (advisor)
Along with the artificial intelligence modelling and related studies, distributed computing ranks amongs the most discussed scientific topics nowadays and one can be certain that it will not fade away anytime soon. This work is also concerned about the above mentioned topics, more precisely its its main goal is to design and implement a distributed artificial intelligence simulator. The mentioned application was realized during as an firm part of this work and some benchmarks were run to determine and observe some properties inherent to distributed systems. The actual realization takes into account different approaches to distributing simulation resources. The final product did not prove as that convenient for simulation of rather simple AI models, which it if fact, even slowed down at times. In the future the project should be aimed towards more computationally challenging problems, that can truly use the capacity and advantages of such a computational system.
|
|
|
Web-Based Collaborative Real-Time Editor
Konečný, Martin ; Jaša, Petr (referee) ; Rychlý, Marek (advisor)
Real-time collaboration editing is research area that has been studied for over 20 years. It involves multiple users editing a document such as plain-text, rich-text or an image concurrently over a high-latency network. Many problems involving consistency between users are associated with concurrent document editing, and an innovative technique called Operational Transformation developed by the GROVE (GRoup Outline Viewing Editor) system in 1989 addresses some of these issues. This paper will compare and contrast current implementations of real-time collaborative editors, and on the basis of this analysis describe the creation of a new web-based editor with support for concurrent editing. The design of our web editor will focus on methods of mutual communication between the individual instances of the editors, propagation of text changes, how to solve conflicts between multiple operations, and communication failures.
|
|
|
Client-Server Application Based on CORBA
Majtán, Martin ; Mašek, Jan (referee) ; Karásek, Jan (advisor)
Bachelor thesis deals with client-server applications and software technologies used to implement client-server applications in the Java programming language. The goal of bachelor thesis is the parallelization of genetic algorithm for knapsack problem and create two distributed models for technology CORBA and Hessian. In the teoretical part of the thesis are describes the basic concept of network communication, explanation client-server model of network communication, there are discussed technologies Java RMI, CORBA and Hessian. In the thesis is described the parallel and the distributed model of data processing, genetic algorithm and its use to solve the knapsack problem. In the practical part is created parallel and distributed model of a genetic algorithm for knapsack problem using technology CORBA and Hessian. In the thesis is done comparison of parallel model and distributed models in terms of calculation time. Results of measurement time are displayed in tables.
|
|
|
Captured Communication Processing on Distributed System
Hvězda, Matěj ; Lichtner, Ondrej (referee) ; Pluskal, Jan (advisor)
When you need to assess or troubleshoot network by analysing capture file, you want it done as fast as possible and you do not always have a high-performance computer. Here comes the distributed system, which allows you to use his high computing power and lot of available memory. I introduce distributed application, which is scalable, extensible and capable of processing captured network communication and is developed for Windows platform. That provides technology, like Microsoft HPC Pack and Windows Communication foundation. The application supports multiple capture formats. In parallel system (cluster), exists database in order to save statistics and data of captured communication in order to save user's computer memory so client's application can be used for low-performance computers or make data available to a client after distributed processing.
|
|
|
Scalable preprocessing of data using Hadoop tool
Marinič, Michal ; Šmirg, Ondřej (referee) ; Burget, Radim (advisor)
The thesis is concerned with scalable pre-processing of data using Hadoop tool which is used for processing of large volumes of data. In the first theoretical part it focuses on explaining of functioning and structure of the basic elements of Hadoop distributed file system and MapReduce methods for parallel processing. The latter practical part of the thesis describes the implementation of basic Hadoop cluster in pseudo-distributed mode for easy program-debugging, and also describes an implementation of Hadoop cluster in fully-distributed mode for simulation in practice.
|
|
|
Cryptovirology and Future of Malware
Prchal, Josef ; Říha, Zdeněk (referee) ; Cvrček, Daniel (advisor)
Malware is connected to information technology. They influence each other. The aim of this thesis is to describe various types of this software and give a brief account of its history and development. It also discusses main trends of this area and tries to foretell the future development.
|
|
|
Parallel Deep Learning
Šlampa, Ondřej ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
Aim of this thesis is to propose how to evaluate favourableness of parallel deep learning. In this thesis I analyze parallel deep learning and I focus on its length. I take into account gradient computation length and weight transportation length. Result of this thesis is proposal of equations, which can estimate the speedup on multiple workers. These equations can be used to determine ideal number of workers for training.
|
|
|
Distributed Tool for Extraction of Information from Network Flows
Sedlák, Michal ; Grégr, Matěj (referee) ; Žádník, Martin (advisor)
This work deals with the extraction of information from flow records that are the result of network monitoring by the IPFIX system. The goal of the work is to design a tool that allows querying stored network flows created by the open-source collector IPFIXcol2. Querying is performed with the highest possible efficiency and performance in mind, which is achieved by using appropriate data structures and thread-level parallelization, as well as by using multiple machines.
|
|
|
Porting of Plaso Extractors to the Apache Spark Platform
Baláž, Miroslav ; Burget, Radek (referee) ; Rychlý, Marek (advisor)
The theoretical part discusses the functioning and architecture of the Plaso tool. The thesis further explores current tools that implement distributed computational models. It describes their architecture, data abstracts and how they work. The thesis also describes current tools that implement distributed storage. The work includes the creation of the Plasospark tool, which converts the computation of the Plaso tool to the Spark platform and uses the Hadoop HDFS storage for forensic data.
|
guest ::
