MACHINE LEARNING FOR TIME SERIES FORECASTING, APPLICATION ON SOLAR IRRADIANCE
Real-world time series forecasting is challenging for a whole host of reasons, it is one of the most applied data science techniques in business, used extensively in finance, in supply chain management and in production and inventory planning, and it has a well-established theoretical grounding in statistics and dynamic systems theory.
In this seminar, first part will be a fully informed description of some classical linear models for time series forecasting, sufficiently enough to understand them and can be used to explore challenging datasets. All models are followed with their Python code to give a head start for practical utilization. In second part, we will tackle a real world problem; forecasting daily solar irradiance using a machine learning approach. The integration of solar energy into electricity networks requires reliable forecast information of solar resources enabling it to quantify the available energy and allowing it to optimally manage the transition between intermittent and conventional energies.