Application of artificial neural networks for short term wind speed forecasting in Mardin, Turkey

Abstract

Artificial neural network models were used for short term wind speed forecasting in the Mardin area, located in the Southeast Anatolia region of Turkey. Using data that was obtained from the State Meteorological Service and that encompassed a ten year period, short term wind speed forecasting for the Mardin area was performed. A number of different ANN models were developed in this study. The model with 60 neurons is the most successful model for short term wind speed forecasting. The mean squared error and approximation values for training of this model were 0.378088 and 0.970490, respectively. The ANN models developed in the study have produced satisfactory results. The most successful among those models constitutes a model that can be used by the Mardin Electric Utility Control Centre.

Predicting Climatic Meteorological Parameters by Using the Artificial Dynamics Neural Networks: Case Study, Bushehr City

“…In recent decades, most researchers have used statistical methods such as multiple, polynomial regression, AR, MA, ARIMA to model and predict meteorological processes. Indeed, the models incorporate parameters linearly in decision-making processes so that most often, it can properly analyze complicated climate issues, hence it seems necessary to introduce more efficient models to predict complicated nonlinear phenomena [12][13][14][15][16][17]. Formulas of AR, MA, ARIMA models, respectively can be presented as follows:…”

Previsão Da Velocidade Do Vento a Curto Prazo Em Região Tropical Utilizando Wavelets E Inteligência Artificial

“…These problems can effectively be resolved if wind speed can be predicted accurately [9]. Therefore, improving the accuracy of short-term wind speed forecasting and developing new studies on this, are crucial for the operation of wind power plants, as in [10], [11], [12] and [13]. Furthermore, it is possible to cite recent studies of short-term wind speed forecasting, for example: [14], [15] and [5].…”

Diferansiyel Gelişim Algoritma Tabanlı Uyarlamalı Sinirsel Bulanık Çıkarım Sistemi ile Kısa Dönem Rüzgar Hızı Kestirimi

“…Sonuçlar ele alındığında, tahmin yöntemlerinin otomatik bir rüzgar gücü bilgi sistemini tasarlamak için yeterli sonuçlara ulaşıldığı görülmüştür. Türkiye'de yapılan çalışmalara bakıldığında; Akıncı, farklı yapay sinir ağı modelleri kullanarak Batman bölgesi için kısa dönemli rüzgar hızı tahmini gerçekleştirirken, Nogay ve arkadaşları benzer analizler kullanarak Mardin bölgesi için çalışmalarını yapmışlardır [19,20]. Bilgili ve arkadaşları yapay sinir ağlarını kullanarak Türkiye'deki Akdeniz bölgesinde bulunan 8 farklı ölçüm istasyonundaki verilerden yararlanarak rüzgar hızı tahmini üzerine çalışmalarda bulunmuşlardır.…”