Combined approaches for prediction of short-term wind power and applications in electirical energy systems

With the continuous increase of wind power penetration in power systems, the problems caused by the volatile nature of wind speed and occurring in the system operations such as scheduling and dispatching have drawn attention from system operators, utilities and researchers towards to the state-of-the-art wind speed and power forecasting methods. These methods have the required capability of reducing the influence of the intermittent wind power on system operations as well as of harvesting the wind energy effectively. In this context, combining different methodologies in order to circumvent the challenging model selection and take advantage of the unique strength of plausible models have been recently emerged as a promising research area. Therefore, in this thesis, a comprehensive research about the combined models is realized and the combined forecasting approaches are classified according to their structure for the first time in the literature of wind forecasting. Then, the best performing approaches are determined by utilizing the obtained knowledge and these approaches are applied to two different fields with the aim of improving the system performance. In the first field, a combined approach is used in a stand-alone hybrid system composed of a variable speed wind turbine (WT), a fuel cell (FC) and a battery, in order to optimize the hydrogen utilization while guaranteeing the load balance implicitly as well as to achieve proper FC operation. Herein, a wind power prediction based controller is proposed in order to take action according to foreseen amount of power deficit or excess in the system. The results obtained provide insights about the advantages of utilizing wind power predictions in a hybrid system. In the latter field, the benefits of a combined prediction method on the concept of virtual power plant are investigated and an economic operation based load dispatching strategy that can interactively adapt to the real measured wind and solar power production values is proposed. Hence, it is aimed to participate in the electricity market more efficiently with the improved predictions. Finally, this thesis points out the possible further research directions of combined techniques so as to help researchers in the field develop more effective wind speed and power forecasting methods, and utilize the predictions in different application areas effectively.