diplomsko delo
Rene Rajzman (Author), Milan Zorman (Mentor), Robert Meolic (Co-mentor)

Abstract

Diplomsko delo prikazuje uporabo različnih kombinacij metod strojnega učenja, kot sta naključni gozd in gradientno povečevanje, ki jih ponuja Python knjižnica Sklearn, pri optimizaciji rezultatov vremenskih napovednih modelov. Obravnavani vremenski napovedni modeli se uporabljajo na področju elektroenergetskih sistemov za izračun dinamične termične meje daljnovodov. Končni sistem, ki za optimizacijo podatkov vremenskih napovednih modelov uporablja metode strojnega učenja, lahko izboljša natančnost izračunane termične meje, ki je ključnega pomena za dobro elektroenergetsko logistiko.

Keywords

strojno učenje;Python;DTR;vremenski modeli;optimizacija podatkov;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [R. Rajzman]
UDC: 004.85:004.6(043.2)
COBISS: 220105475 Link will open in a new window
Views: 0
Downloads: 12
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Optimising weather model data using advanced machine learning methods
Secondary abstract: This thesis demonstrates the use of different combinations of machine learning methods, such as random forest and gradient boosting, provided by the Python library Sklearn, to optimise the results of weather forecasting models. The weather prediction models considered are used in the field of power systems to calculate the dynamic thermal limit of transmission lines. The final system, which uses machine learning methods to optimise the data from the weather prediction models, can improve the accuracy of the calculated thermal boundary when applied, which is crucial for good power logistics.
Secondary keywords: machine learning;Python;DTR;weather models;data optimization;bachelor's degrees;
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: 1 spletni vir (1 datoteka PDF (XI, 73 f.))
ID: 24756379