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.
Citation Formats
G. Kavakçı, “Time series prediction of solar power generation using trend decomposition,” M.S. - Master of Science, Middle East Technical University, 2021.