Presentation on Demand Forecasting in Future Grid States
06/27/2024Our colleague Daniel Bayer presented our paper entitled “Electricity Demand Forecasting in Future Grid States: A Digital Twin-Based Simulation Study“ at the 9th International Conference on Smart and Sustainable Technologies (SpliTech 2024) in Split, Kroatia.
In this study, we explored the challenges and opportunities of predicting residential electricity demand in future grid states. Based on a simulated future energy system state using a digital twin, we compared traditional methods with Machine Learning (ML) approaches. Our findings highlight the potential of ML techniques, especially Long Short-Term Memory (LSTM) models, in improving demand predictions. However, all prediction approaches perform worse in future grid states, reinforcing the need for further research.
The presented work is a collabiration with Felix Haag and Konstantin Hopf from the University of Bamberg.
Link to the conference: splitech.org
