• A bilevel framework for decision-making under uncertainty with contextual information 

      Morales González, Juan Miguel; Pineda Morente, Salvador; Muñoz Díaz, Miguel Ángel (Elsevier, 2021-11-22)
      In this paper, we propose a novel approach for data-driven decision-making under uncertainty in the presence of contextual information. Given a finite collection of observations of the uncertain parameters and potential ...
    • Chronological Time-Period Clustering for Optimal Capacity Expansion Planning 

      Morales González, Juan Miguel; Pineda Morente, Salvador (2018-07-06)
      To reduce the computational burden of capacity expansion models, power system operations are commonly accounted for in these models using representative time periods of the planning horizon such as hours, days or weeks. ...
    • Chronological time-period clustering for optimal capacity expansion planning 

      Morales González, Juan Miguel; Pineda Morente, Salvador (2018-07-12)
      To reduce the computational burden of capacity expansion models, power system operations are commonly accounted for in these models using representative time periods of the planning horizon such as hours, days or weeks. ...
    • Electricity Cost-Sharing in Energy Communities Under Dynamic Pricing and Uncertainty 

      Gržanić, Mirna; Morales, Juan M.; Pineda Morente, Salvador; Capuder, Tomislav (IEEE, 2021-02-15)
      Most of the prosumers nowadays are constrained to trade only with the supplier under a flat tariff or dynamic time-of-use price signals. This paper models and discusses the cost-saving benefits of flexible prosumers as ...
    • Feature-driven improvement of renewable energy forecasting and trading 

      Muñoz, Miguel Ángel; Morales, Juan Miguel; Pineda Morente, Salvador (2020-02-26)
      Inspired from recent insights into the common ground of machine learning, optimization and decision-making, this paper proposes an easy-to-implement, but effective procedure to enhance both the quality of renewable energy ...
    • Individualized exercises for continuous assessment in engineering 

      Pineda Morente, Salvador; Alguacil Conde, Natalia; Perez-Ruiz, Juan; Martin-Rivas, Sebastian; Ruiz-Gonzalez, Antonio Francisco (2019-05-27)
      This project focuses on the development of a web application that automatically grades the solution to engineering exercises. The input data of each exercise is different for each student in order to reduce plagiarism and ...
    • Inverse optimization with kernel regression: Application to the power forecasting and bidding of a fleet of electric vehicles 

      Fernández-Blanco, Ricardo; Morales, Juan Miguel; Pineda Morente, Salvador; Porras, Álvaro (Elsevier, 2021-10)
      This paper considers an aggregator of Electric Vehicles (EVs) who aims to learn the aggregate power of his/her fleet while also participating in the electricity market. The proposed approach is based on a data-driven inverse ...
    • Is learning for the unit commitment problem a low-hanging fruit? 

      Pineda Morente, Salvador; Morales, Juan Miguel (Elsevier, 2022-06)
      The blast wave of machine learning and artificial intelligence has also reached the power systems community, and amid the frenzy of methods and black-box tools that have been left in its wake, it is sometimes difficult ...
    • Is learning for the unit commitment problem a low-hanging fruit? 

      Pineda Morente, Salvador; Morales González, Juan Miguel (Elsevier, 2022-02-16)
      The blast wave of machine learning and artificial intelligence has also reached the power systems community, and amid the frenzy of methods and black-box tools that have been left in its wake, it is sometimes difficult to ...
    • Learning the price response of active distribution networks for TSO-DSO coordination 

      Pineda Morente, Salvador; Morales González, Juan Miguel; Dvorkin, Yury (IEEE, 2021)
      The increase in distributed energy resources and flexible electricity consumers has turned TSO-DSO coordination strategies into a challenging problem. Existing decomposition/decentralized methods apply divide-and-conquer ...