3 results
Search Results
Now showing 1 - 3 of 3
Article Citation - WoS: 18Citation - Scopus: 21A Data-Driven Model To Forecast Multi-Step Ahead Time Series of Turkish Daily Electricity Load(Mdpi, 2022) Unlu, Kamil Demirberk; Ünlü, Kamil Demirberk; Ünlü, Kamil Demirberk; Industrial Engineering; Industrial EngineeringIt is critical to maintain a balance between the supply and the demand for electricity because of its non-storable feature. For power-producing facilities and traders, an electrical load is a piece of fundamental and vital information to have, particularly in terms of production planning, daily operations, and unit obligations, among other things. This study offers a deep learning methodology to model and forecast multistep daily Turkish electricity loads using the data between 5 January 2015, and 26 December 2021. One major reason for the growing popularity of deep learning is the creation of new and creative deep neural network topologies and significant computational advancements. Long Short-Term Memory (LSTM), Gated Recurrent Network, and Convolutional Neural Network are trained and compared to forecast 1 day to 7 days ahead of daily electricity load. Three different performance metrics including coefficient of determination (R-2), root mean squared error, and mean absolute error were used to evaluate the performance of the proposed algorithms. The forecasting results on the test set showed that the best performance is achieved by LSTM. The algorithm has an R-2 of 0.94 for 1 day ahead forecast, and the metric decreases to 0.73 in 7 days ahead forecast.Article Citation - WoS: 17Citation - Scopus: 18Daily Pm10, Periodicity and Harmonic Regression Model: the Case of London(Pergamon-elsevier Science Ltd, 2020) Okkaoglu, Yasin; Akdi, Yilmaz; Unlu, Kamil DemirberkOne of the most important and distinguishable features of the climate driven data can be shown as the seasonality. Due to its nature air pollution data may have hourly, daily, weekly, monthly or even seasonal cycles. Many techniques such as non-linear time series analysis, machine learning algorithms and deterministic models, have been used to deal with this non-linear structure. Although, these models can capture the seasonality they can't identify the periodicity. Periodicity is beyond the seasonality, it is the hidden pattern of the time series. In this study, it is aimed to investigate the periodicity of daily Particulate Matter (PM10) of London between the periods 2014 and 2018. PM10 is the particulate matter of which aerodynamic diameter is less than 10 mu m. Firstly, periodogram based unit root test is used to check the stationarity of the investigated data. Afterwards, hidden periodic structure of the data is revealed. It is found that, it has five different cycle periods as 7 days, 25 days, 6 months, a year and 15 months. Lastly, it is shown that harmonic regression performs better in forecasting monthly and daily averages of the data.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.
