On October 27, we organized a scientific seminar on “Do Sequences Matter? Application for Carbon Emission Prediction of the Electricity Grid“. The scientific seminar was led by Roman Kohút, a PhD student at Slovak University of Technology in Bratislava. The scientific seminar was organized in the framework of the FrontSeat project as part of the seminar series on “Research Seminar on Smart Cybernetics”.
This talk focuses on sequential modeling using the Hidden Markov Model (HMM) with an application for carbon emission prediction of the electricity grid. The presented method will adapt the state estimation theory to decrease the observation and model error. In recent years, with the increase in computational power, machine learning methods become a powerful tool that can be used in many applications. One of the most popular is system identification with nonlinear models, which can be directly used in Model Predictive Control (MPC) to enhance performance. However, from an incredible amount of state-of-the-art methods, it is tough to choose the right approach, where, in many cases, we still end up using Artificial Neural Networks (ANN). This topic is focused on an alternative modeling technique that challenges the dominance of ANN. We will explore the efficiency of the HMM in capturing sequential patterns within the electricity grid’s carbon emissions data.
This project has received funding from the European Union’s Horizon under grant no. 101079342 (Fostering Opportunities Towards Slovak Excellence in Advanced Control for Smart Industries).