Frontier Research in Energy Forecasting

Dear Colleagues,

The modern-day energy sector includes many challenges that affect secure and reliable electricity generation and delivery. Utilities, generation companies, system operators, and other parties have been continually seeking methods to cope with the various challenges. Among the methods, forecasting holds a prominent role in energy systems. Accurate forecasts can limit the technical and economic risks of energy systems operations. Demand forecasting is essential in power generation scheduling, fuel import planning, interconnection operation, and others. Generation forecasting can transform variable energy resources such as photovoltaics and wind turbines into dispatchable sources. Thus, energy forecasting is a scheme with many applications. According to the literature, there is a variety of different energy forecasting models. Time series models refer to autoregressive time functions. These models have historically been the first to be implemented. Recent approaches include machine learning architectures such as neural networks, neuro-fuzzy systems, support vector machines, and others. Machine learning models can effectively simulate nonlinear time series. Finally, a new research trend is deep learning; the scope is to train neural networks in more detail so as to achieve better accuracy. In the context of these challenges, the main scope of this Special Issue is to propose new methods in energy forecasting. State-of-the-art papers together with innovative case studies are invited. Multidisciplinary research and cutting-edge approaches are welcomed in order to address the challenges that are raised by contemporary energy systems and deregulated energy markets.

Dr. Ioannis Panapakidis
Dr. Minas Alexiadis
Dr. Aggelos S. Bouhouras
Topic Editors