Predviđanje proizvodnje energije pomoću analize vremenskih serija

master's thesis

• Title (english): Energy Generation Prediction Using Time Series Analysis
• Author: Sara Zorčić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu kreirani su modeli strojnog učenja u svrhu predviđanja vremenskih serija za studijski slučaj predikcije proizvedene energije u vjetroelektrani. Opisane su metode analize vremenskih serija i objašnjene metode prognoziranja neuronskim mrežama. Koristeći Pythonove biblioteke programski su ostvareni modeli LSTM mreže, GRU mreže i dvosmjerno povratne mreže. Pomoću njih je napravljeno predviđanje budućih vrijednosti energije na temelju vremenskih uvjeta brzine i smjera vjetra. Mjerama vrednovanja napravljena je usporedba točnosti modela. Svi rezultati ispitivanja prikazani su grafički.

Abstract (english)

In this thesis, machine learning models were created in order to predict time series for case study of predicting energy production of wind power plant. Methods of time series analysis and time series prediction using neural networks are described. Python based libraries are used to implement models of LSTM network, GRU network, and bidirectional recursive neural network. With those models using wind speed and wind direction variables from dataset, prediction of future energy production values was made. Using forecast metrics models were evaluated and compared. All study results are described and visualized.

• Keywords: vremenska serija; predviđanje vremenskih serija; LSTM; GRU; energija; neuronske mreže
• Keywords (english): time series; predicting time series; LSTM; GRU; energy; neural networks
• Language: croatian
• URN:NBN: urn:nbn:hr:168:806501
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:23:22