The Universitat Politècnica de València and Ansbach University of Applied Sciences have been cooperating for several years. This includes joint exchange, mutual support and collaboration on projects and doctorates. As part of this cooperation, Prof. Trull visited Ansbach University of Applied Sciences once again last week and was also a guest at the Feuchtwangen campus.

Prof. Trull studied industrial engineering at the Universitat Politècnica de València in Spain. He wrote his thesis in collaboration with the Technical University of Ilmenau in Germany. After graduating, he worked for several years at Alstom in the rail vehicle sector and later in the automotive supply industry before becoming a lecturer in mechanical manufacturing organization and projects in Valencia.

In 2009, Oscar Trull decided to do a further Master’s degree in Data Analysis, Process Improvement and Decision Making, also at the Universitat Politècnica de València. He has been a professor there since 2013.

“Energy production from clean and renewable sources is being implemented faster and faster around the world. In particular, the possibility of operating small decentralized production units, including private ones, is increasing interest in this type of energy production. However, one of the main problems here is the difficulty of making accurate predictions about potential production, as these energy sources are heavily dependent on weather conditions. This is where artificial intelligence gains particular interest due to its versatility in making time series predictions that are difficult to model,” says the professor.

With his expertise in statistics, particularly in the areas of load forecasting and load forecasting, Prof. Trull organized a seminar day on time series analysis at the Feuchtwangen campus together with Prof. Mathias Moog. After a theoretical part in the morning, hands-on training for various AI models for forecasting took place in the afternoon.

he seminar day offered the participants valuable insights and practical experience in the application of modern AI models for energy forecasting.