V. Álvarez, S. Mazuelas Franco, J. A. Lozano
Load forecasting is crucial for multiple energy management tasks such as scheduling generation capacity, planning supply and demand, and minimizing energy trade costs. Conventional load forecasting techniques obtain single-value load forecasts by exploiting consumption patterns of past load demand. However, such techniques cannot assess intrinsic uncertainties in load demand, and cannot capture dynamic changes in consumption patterns. To address these problems, we present an algorithm for adaptive probabilistic load forecasting (APLF) based on the online learning of hidden Markov models. We propose learning and forecasting techniques for APLF method with theoretical guarantees, and experimentally assess their performance in multiple scenarios. The performance of APLF method is evaluated using multiple datasets corresponding with regions that have different sizes and display assorted time-varying consumption patterns.
Palabras clave: Online learning, load forecasting, machine learning
Programado
Sesión Invitada Math-In. Industrial Applications II
8 de junio de 2022 16:00
Aula Magna
