Skip to main content

Benchmarking of artificial intelligence methods for energy generation and consumption forecasting

D . Linaro, F. Bizzarri, D. del Giudice, S. Grillo , A. Brambilla, N. Lu, Y. Li, P. Musilek

  • PES
    Members: Free
    IEEE Members: $25.00
    Non-members: $40.00
    Pages/Slides: 47
Panel 18 Jul 2023

Energy resources forecasting is crucial in current and future power and energy systems. With the increasing penetration of renewable energy sources, with high associated uncertainty due to the dependence on natural conditions, such as wind speed or solar intensity, the need to balance the fluctuation of generation with the flexibility from the consumer side increases considerably. In this way, significant work has been done on the development of energy consumption and generation forecasting methods, able to deal with different forecasting circumstances, e.g., the prediction time horizon, the available data, the frequency of data, or even the quality of data measurements. The main conclusion is that different methods are more suitable for different prediction circumstances, and there it is not clear that a certain method can outperform all others in all situations. This panel fosters the benchmarking of artificial intelligence methods for generation and consumption forecasting, by bringing together different perspectives from panelists of diverse backgrounds. This panel benefits from the new edition of the Competition on energy generation and consumption forecasting, organized by the Open Data Sets (ODS) Task Force, taking place during 2022 and 2023. The session welcomes different experts as panelists. The authors of the methods that will present the best results in the competition will be invited to shortly present their works and to join the discussion with the panelists and the audience. Presentations in this panel session: - Application of Long Short-Term Memory Neural Networks to PV Production Forecasting (23PESGM0680) - Advanced Forecasting for Energy Time Series (23PESGM3979) - TCN-based Hybrid Spatial-Temporal Hours-ahead PV Forecasting Framework (23PESGM3973)

Zita Vale, Tiago Pinto
Primary Committee:
Analytic Methods for Power Systems (AMPS)
Sponsor Committees:
Intelligent Systems