izpis_h1_title_alt

Prilagodljivo kratkoročno napovedovanje lokalnih vremenskih parametrov : diplomsko delo
ID Kotnik, Denis (Author), ID Kukar, Matjaž (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (8,53 MB)
MD5: 1CB811B8FDFD44588381C82B2B5677E1
PID: 20.500.12556/rul/5b5d2373-cc0e-4480-93f0-e5366bbffd88

Abstract
Cilj diplomskega dela je preizkusiti, ali lahko z uporabo regresijskih metod ali umetnih nevronskih mrež popravimo oziroma izboljšamo napoved hitrosti vetra za določeno območje Slovenije. Za ta namen smo uporabili podatke meritev s cestnovremenskih postaj Družbe za avtoceste v Republiki Sloveniji in napovedne podatke sistema INCA-CE Agencije Republike Slovenije za okolje. Omenjene podatke smo za potrebe modeliranja primerno pripravili s programskim jezikom Python. V programskem okolju R smo ustvarili parameter napaka, katerega smo definirali kot razliko med napovedano vrednostjo za čas t + ∆t in izmerjeno vrednostjo v času t + ∆t. Slednjega smo z uporabo regresijskih metod in umetnih nevronskih mrež napovedovali za do 11 ur vnaprej, ga odšteli ustreznim prvotnim napovedim, rezultate pa vizualizirali. Ugotovili smo, da lahko že z uporabo enostavnejših regresijskih metod popravimo napoved hitrosti vetra za leto 2014 za do 1 m/s v prvih napovednih urah.

Language:Slovenian
Keywords:nevronska mreža, napaka, podatki, vremenski parameter, napoved, hitrost vetra, vrednost, cestnovremenska postaja, meteorologija, računalništvo, visokošolski strokovni študij, računalništvo in informatika, diplomske naloge
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Publisher:D. Kotnik
Year:2014
Number of pages:87 str.
PID:20.500.12556/RUL-29531 This link opens in a new window
COBISS.SI-ID:1536010691 This link opens in a new window
Publication date in RUL:22.09.2014
Views:1929
Downloads:454
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Adaptable short-term forecasting of local-weather parameters
Abstract:
The goal of this research is to explore if we could improve the wind speed forecasts, with the regression methods and artificial neural networks. We utilized measurements data, which we obtained from road-weather stations of Direkcija Republike Slovenije za avtoceste and forecast data of INCA-CE system of Agencija Republike Slovenije za okolje. We used the Python programming language for the purpose of data preparation process. In the R programming environment we created the parameter error, which we defined as the difference between the predicted value for time t + ∆t and the measured value in time t+∆t. We predicted the error for subsequent 11 hours with the usage of regression methods and artificial neural networks, then we subtracted it from the INCA-CE predictions and visualised the results. We came to the conclusion that wind speed forecasts for 2014 could be corrected by up to 1 m/s in the early predicted hours with the usage of simple regression methods or neural networks.

Keywords:neural network, error, data, weather parameter, forecast, wind speed, value, road weather station, meteorology, forecast, wind speed, value, road weather station, meteorology, computer science, computer and information science, diploma

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back