20.500.12556/RUL-188220 Napovedovanje odziva verige malih hidroelektrarn z uporabo simulacijskega modela in strojnega učenja Prediction of the Response of a Small Hydropower Plant Cascade Using a Simulation Model and Machine Learning V magistrski nalogi smo raziskali možnost uporabe simulacijskega modela, razvitega v okolju Simulink, za generiranje sintetičnih podatkov za učenje modelov strojnega učenja XGBoost in naključni gozd. Modela sta bila uporabljena za napovedovanje minimalnega vodostaja in časa prihoda dvojne vode v verigi dveh malih hidroelektrarn. Za učenje in preverjanje modelov so bili uporabljeni sintetični podatki, pridobljeni s simulacijskim modelom, ter meritve dejanskega sistema. Rezultati kažejo, da so sintetični podatki primerni za napovedovanje minimalnega vodostaja in omogočajo zadovoljivo napoved njegovega odziva. Pri napovedi časa prihoda dvojne vode pa rezultati niso bili dovolj zanesljivi, saj simulacijski model tega pojava še ne opisuje dovolj natančno. Ugotovitve kažejo potencial uporabe simulacijskih podatkov, hkrati pa izpostavljajo potrebo po nadaljnji izboljšavi simulacijskega modela. In this master's thesis, we investigated the possibility of using a simulation model developed in the Simulink environment to generate synthetic data for training machine learning models, namely XGBoost and Random Forest. The models were used to predict the minimum water level and the arrival time of the double flow in a chain of two small hydropower plants. Synthetic data obtained from the simulation model, as well as measurements from the actual system, were used for training and evaluating the models. The results show that synthetic data are suitable for predicting the minimum water level and enable a satisfactory prediction of its response. However, the results for predicting the arrival time of the double flow were not sufficiently reliable, as the simulation model does not yet describe this phenomenon accurately enough. The findings demonstrate the potential of using simulation data while also highlighting the need for further improvement of the simulation model. male hidroelektrarne simulacijski modeli strojno učenje XGBoost Random Forest small hydropower plants simulation models machine learning XGBoost Random Forest true false false [R. Peternelj] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2026-09-19 08:30:33 2026-09-19 08:30:43 2026-09-22 07:59:59 0000-00-00 00:00:00 2026 0 Ljubljana 0 XX, 57 str. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 621.311.21:004.942:004.85(043.2) 290706 291909635 49656.pdf 49656.pdf 1 2CF2371A7BD75A2B77BD74949BCC6BF0 676aa60f851c514d3db3127c6282e6c1e1cd3bd78272db6fb2184b825fdafbb2 96336079-b3f3-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=248249 Fakulteta za strojništvo 0 0 0