Akademik Veri Yönetim Sistemi
Tezin Türü: Yüksek Lisans
Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Türkiye
Tezin Onay Tarihi: 2015
Öğrenci: CEYDA ER KÖKSOY
Eş Danışman: PINAR KARAGÖZ, AYŞE NUR BİRTÜRK
Özet:Wind is an important renewable energy source to produce electricity thanks to its reliable, omnipresent and economically feasible characteristics and it has a growing proportion in overall energy production worldwide. However, integration of the generated wind power into the existing transmission grid is an issue due to inherently volatile and intermittent behavior of wind. Moreover, the power plant owners need reliable information about day-ahead power production for market operations. Therefore, wind power forecasting approaches have been gaining importance in renewable energy research area. There are many applicable wind power forecasting models including physical model, several statistical models such as ANN and SVM, and hybrid models. However, all of them have different advantages and disadvantages according to the wind characteristic of wind power plant region. At this point, forecast combination approaches stand out not to rely on a single forecast model, and also utilize forecast diversification. A combined forecast should be better than the individual forecasts, or at least be equal to the best performed one in order to be regarded as an ideal combination. Within the scope of this thesis, various forecast combination methods are proposed to provide ideally combined forecasts. These combination methods have been verified on forecasts data of The Wind Power Monitoring and Forecast System for Turkey (RİTM). The experimental results show that all of the applied combination methods give better forecast error rates for most of the wind power plants compared to individual forecasts.