Time series prediction of solar power generation using trend decomposition

Kavakçı, Gürcan
Accurate predictions are desirable in time series data due to the widespread usage of them in various domains. Each information in the data represents the characteristics of the time series. Making forecasting on data that has trend information is a complicated process. In this thesis, new methods are proposed to make better estimates on time series data which have trend information. In the first part of the study, features such as mean and trend were extracted from the history of the existing data by feature extraction methods and added to the data set as features. When machine learning algorithms were tested with this extended data set, better results were obtained compared to existing methods. In the second part of the study, trend decomposition was applied to the data. More stable data obtained after the decomposition was tested with the existing models, and then the final estimation was achieved by combining the decomposed trend data with the prediction results of the stable data. Higher performance results were observed than what was achieved by using the plain data and also the data with extended features. Then, in the third part of the study, linear estimation method was used to make predictions on the trend data as well. The final results were obtained by combining the predicted results of both the stable time series v data and the trend. At each step, we demonstrate superior or competitive prediction performance than the previous step and the existing method in five different machine learning algorithms. Proposed methods are applied to the renewable energy domain and used in the forecasting of solar power generation in Turkey.


Time Series Forecasting Using Empirical Mode Decomposition and Hybrid Method
Büyükşahin, Ümit Çavuş; Ertekin Bolelli, Şeyda (2018-07-09)
Recently, various applications produce large amount of time series data. In these domains, accurately forecasting time series has been getting important for decision makers. autoregressive integrated moving average (ARIMA) as a linear method and Artificial Neural Networks (ANNs) as a nonlinear method have been widely used to forecast time series. However, many theoretical and empirical studies showed that assembling of those two approaches in hybrid methods can be efficient to improve forecasting performanc...
Prediction Model Selection with Frequency Check on Decomposed Time Series
Büyükşahin, Ümit Çavuş; Ertekin Bolelli, Şeyda (2019-08-22)
High prediction accuracies at time series modeling and forecasting is of the utmost importance for a variety of application domains. Various time series prediction methods exist that use linear and nonlinear models separately or combination of both. These methods highly increase prediction performance results when they are applied on a many number of stationary components obtained by more sophisticated decomposition techniques. Although these stationary components are easily predictable, they each have diff...
Temporal clustering of time series via threshold autoregressive models: application to commodity prices
Aslan, Sipan; Yozgatlıgil, Ceylan; İyigün, Cem (2018-01-01)
The primary aim in this study is grouping time series according to the similarity between their data generating mechanisms (DGMs) rather than comparing pattern similarities in the time series trajectories. The approximation to the DGM of each series is accomplished by fitting the linear autoregressive and the non-linear threshold autoregressive models, and outputs of the estimates are used for feature extraction. Threshold autoregressive models are recognized for their ability to represent nonlinear feature...
Univariate time series prediction leveraging linear and nonlinear patterns
Büyükşahin, Ümit Çavuş; Ertekin Bolelli, Şeyda; Department of Computer Engineering (2020-9)
Making forecasts from time series data has become increasingly important with the increase of data collection capabilities.The forecasting in time series is mostly done in a univariate setting where historical data in the series itself is used for further time steps. Forecasting in univariate time series is a challenging task due to unpredictable variations in the historic data. The objective of this thesis is to develop prediction methods that exhibit better performance results by alleviating the chal...
Consensus clustering of time series data
Yetere Kurşun, Ayça; Batmaz, İnci; İyigün, Cem; Department of Scientific Computing (2014)
In this study, we aim to develop a methodology that merges Dynamic Time Warping (DTW) and consensus clustering in a single algorithm. Mostly used time series distance measures require data to be of the same length and measure the distance between time series data mostly depends on the similarity of each coinciding data pair in time. DTW is a relatively new measure used to compare two time dependent sequences which may be out of phase or may not have the same lengths or frequencies. DTW aligns two time serie...
Citation Formats
G. Kavakçı, “Time series prediction of solar power generation using trend decomposition,” M.S. - Master of Science, Middle East Technical University, 2021.