Home CPES Science and Technology Forecasting
Document Actions


Forecasting models for short-term and very short-term load and renewable energy production, forecasting error analysis with probabilistic descriptions of uncertainties, time series studies and knowledge discovery in databases, application and selection of regression technologies: classic models, neural networks, regression trees, evaluation and estimation on confidence levels.

Our team at the Centre for Power and Energy Systems (CPES) has solid experience in the creation of methodologies and forecasting models that support the operation of energy systems, including short-term, medium-term and long-term forecasting with or without weather ensemble predictions:

  • Load forecasting
  • Spatial load forecasting
  • Market price forecasting
  • Wind power forecasting
  • Wind power forecasting with weather ensemble predictions
  • Solar power forecasting
  • Solar power forecasting with weather ensemble predictions
  • Synergies between wind power and solar energy and loads

These models employ tools based on neural networks, information theory, machine learning, data mining, entropy and correntropy and scenario building in order to characterise uncertainties.



CPES +351 22 209 4198