3 results
Search Results
Now showing 1 - 3 of 3
Article Citation - WoS: 8Citation - Scopus: 10Computing Reliability Indices of a Wind Power System Via Markov Chain Modelling of Wind Speed(Sage Publications Ltd, 2024) Eryilmaz, Serkan; Bulanik, Irem; Devrim, YilserStatistical modelling of wind speed is of great importance in the evaluation of wind farm performance and power production. Various models have been proposed in the literature depending on the corresponding time scale. For hourly observed wind speed data, the dependence among successive wind speed values is inevitable. Such a dependence has been well modelled by Markov chains. In this paper, the use of Markov chains for modelling wind speed data is discussed in the context of the previously proposed likelihood ratio test. The main steps for Markov chain based modelling methodology of wind speed are presented and the limiting distribution of the Markov chain is utilized to compute wind speed probabilities. The computational formulas for reliability indices of a wind farm consisting of a specified number of wind turbines are presented through the limiting distribution of a Markov chain. A case study that is based on real data set is also presented.Article Citation - WoS: 4Citation - Scopus: 6Statistics and Probability Theory in Renewable Energy: Teaching and Research(Wiley, 2023) Eryilmaz, Serkan; Kateri, Maria; Devrim, YilserIn this paper, the key-role and utility of statistics and probability theory in the field of renewable energy are emphasized and illustrated via specific examples. It is demonstrated that renewable energy is a very suitable field to effectively teach and implement many statistical and probabilistic concepts and techniques. From a research point of view, statistical and probabilistic methods have been successfully employed in evaluating renewable energy systems. These methods will continue to be of core interest for the renewable energy sector in the future, as new and more complex renewable energy systems are developed and installed. In this context, some future research directions in relation to the evaluation of renewable energy systems are also presented.Article Citation - WoS: 9Citation - Scopus: 9A Hybrid Deep Learning Methodology for Wind Power Forecasting Based on Attention(Taylor & Francis inc, 2024) Akbal, Yildirim; Unlu, Kamil DemirberkWind energy, as a sustainable energy source, poses challenges in terms of storage. Therefore, careful planning is crucial to utilize it efficiently. Deep learning algorithms are gaining popularity for analyzing complex time series data. However, as the "no free lunch" theorem suggests, the trade-off is: they need a lot of data to achieve the benefits. This even brings up a severe challenge for time series analysis, as the availability of historical data is often limited. This study aims to address this issue by proposing a novel shallow deep learning approach for wind power forecasting. The proposed model utilizes a fusion of transformers, convolutional and recurrent neural networks to efficiently handle several time series simultaneously. The empirical evidence demonstrates that the suggested innovative method exhibits exceptional forecasting performance, as indicated by a coefficient of determination (R2) of 0.99. When the forecasting horizon reaches 48, the model's performance declines significantly. However, when dealing with long ranges, utilizing the mean as a metric rather than individual point estimates would yield superior results. Even when forecasting up to 96 hrs in advance, obtaining an R2 value of 0.50 is considered a noteworthy accomplishment in the context of average forecasting.
