MET4LOWCAR: Analysis of the solar and wind energy resources of the Iberian Peninsula and development of their forecasting techniques for a low carbon power system (2020-2023)
Project Id: PID2019-107455RB-C22 [Ministry of Science and Innovation (Spain)] Universidad Carlos III de Madrid y Universidad de Jaen
The possibility of low carbon power systems (LCPSs) is becoming increasingly realistic. Nevertheless, such systems present serious challenges to become a reality. This sub-project aims at contributing to several issues involved in the planning and development of optimized future low carbon power system in the Iberian Peninsula (IP). First, by developing machine learning models that estimate electricity production and load demand out of NWP meteorological variables. Second, if the inputs to the models are forecast NWP variables, the problem becomes one of power forecasting, which will be addressed using similar techniques to the first objective, taking into account that forecasting may raise new issues. Third, although deterministic/point forecasts are widely used, the full forecast information is contained only in the density function. An important goal of this project is to address probabilistic forecasting with Deep Neural Networks (DNN) using two uncertainty representations: complete density functions and prediction intervals, taking advantage of recent DNN technologies (automatic differentiation and deep learning frameworks). Fourth, using information about the availability of solar and wind resources, an optimization problem is posed where the aim is to provide a simplified wind and solar optimal distribution of renewable power plants under various design constraints that can be used as guidelines
Metaheuristicas para toma de decisiones bajo cambio estructural. Aplicacion a finanzas (2019-2021)
Project Id: PGC2018-096849-B-I00 [Ministry of Science and Innovation (Spain)]
The aim of this project is tackling this problem of financial decision making under structural change using metaheuristics. To this end, we intend to design new algorithms able to operate either under the assumption of the existence of a market that goes through different states that might repeat over time, or a model that transitions only to new states. The project includes two parallel lines of work. The first one is devoted to low and medium frequency, and it is based on more traditional approaches with algorithmic solutions that include evolutionary computation and ensembles. The second is focused on high frequency. For this reason, it relies approaches suitable for data streams and incremental and on-line learning capabilities.
PROSOL. Integrated model for solar energy forecasting (2016-2019)
Project Id: ENE2014-56126-C2 [Ministry of Science and Innovation (Spain)]
A key issue to increase the competiveness of the solar energy and to increase their share in the electric systems is the improvement in the reliability of the solar energy forecasts. Along the last years solar resources forecasting methodologies have showed a notable development. Particularly, a wide range of forecasting methodologies have been developed, with very different characteristics as the spatial and temporal resolution or their forecasting horizon. Nevertheless, reliability of these forecasts is still limited. In addition, there have been scarce efforts to combine the different forecasting methodologies and, therefore, take advantage of the eventual synergies. Furthermore, few works have conducted neither comprehensive evaluation of solar power forecast nor probabilistic analysis of these forecasts.
MOVES. Efficient and Sustainable Mobility Management(2013-2015)
Project Id: TIN2011-28336 [Ministry of Science and Innovation (Spain)]
Mobility Management is becoming an important issue for multinational companies, aa well as for the local authorities of large cities. Among other issues, Management Mobility attempts to reduce the average time of workers for transportation to the workplace. The reduction in commuting time improves the quality of life, reduces costs, and diminishes environmental impact. In the end, it results in less traffic and less congested cities. To achieve this reduction in travel times, it is necessary to propose solutions that take into account, for instance, workplace location changes, employee assignments, openings of new transport lines, etc. The problems to be solved are quite complex. They are usually NP-hard combinatorial optimization problems. There are also many alternatives and constraints, such as schedules, compatibility, work groups, public transport routes , etc...
MEMENTO: Tools for Analysis, Management and Storage of Big Data in the Cloud (2013-2015)
Project Id: AVANZA2 Plan (Ministry of Industry, Energy and Tourism, Spain)
The global objective of MEMENTO is to expand use of Big Data tools as a key element in current economic models and competitiveness improvement programmes. The project will build a workbench that makes available Big Data technology to small and medium sized enterprises as a simple, flexible, and cloud-based service. In that way the project aim is to democratize and provide global access of Big Data tools to everybody, including individuals. This project is part of the Subprogram on Competitiveness and R&D&I of the Ministry of Industry, Energy and Tourism, Plan AVANZA2.
SEACW: Social Ecosystem for Antiaging, Capacitation and Well-being (2013-2015)
Project Id: EU - CIP - ICT - Pilot B 2013-2015 (EU)
The primary objective of this project is to contribute to the Active and Healthy Ageing and ICT- Aging strategies.
GADE4ALL: Interactive Multiplatform Videogame Design Platform (2011-2013)
Project Id: MITC-11-TSI-090302-2011-11 (AVANZA 2011)
Hardware-software platform for development of multiplatform entertainment software. Gade4all is an innovative proyect whose aim is to develop a platform to build interactive software that allows to create videogame software by just drawing on the screen or narrating a story.
M*: Multiobjective Metaheuristics and Multidisciplinar Aplications (2009-2012)
Project Id: TIN2008-06491-C04-04 [Ministry of Science and Innovation (Spain)]
This project is aimed at innovating in multiple fronts of multiobjective optimization (MO) from the perspective of metaheuristic techniques. The main goals in the subproject MSTAR::UC3M are to create a body of knowledge in MO optimization and in applying the resulting techniques to benchmarks and to problems in the context of Economy and Classification: Adaptation of some methods to Multiobjective problems: Adapt some existing techniques to their use in multiobjective problems. This includes Genetic Algorithms, Evolutionary Strategies, Ant Colony Optimization, Particle Swarm Optimization and Estimation Density Algorithms.
OPLINK: Net Centric Optimization (2005-2008)
TIN2005-08818-C04-01 [Ministry of Science and Education (Spain)]
This project proposal aims at profiting from the present wealth of advanced knowledge in combinatorial optimization to solve problems of high impact in academics, industry, and society. In a world of high connectivity, networks and communications are worthy fields to make research in, and this is why we target them in this proposal. Our main goal is indeed to detect what are the actual hard problems in the core of different net centric applications, and since most times they are of a combinatorial nature, we propose to use exact, heuristic and in general whatever new technique that may lead to solve them in an efficient and accurate way. By net centric we mean here mobile/ad-hoc network design, mobile and satellite channel/frequency allocation, routing, grid technologies, parallel computing, and related applications.
eInkPllusPlus: Intelligent Digital Content Platform
Project Id: TSI-020110-2009-1374 [Ministry of Science and Innovation (Spain)]
The aim of the project is to develop a platform for Intelligent Digital Content. The project will provide new standards to support the development of Intelligent EBooks, a new way to construct and provide providing Intelligent Content and sharing it automatically by using personalized profiles.
CECMP: Evolutionary Computation for Classificaciont in Data Mining (2007)
CCG06-UC3M/ESP-0774 [Comunidad Autónoma de Madrid - Universidad Carlos III de Madrid]
The project proposal considered two research lines about using evolutionary computation methods for classification tasks based on the nearest neighbour rule. We use two different novel techniques: in the first, we coevolve of a distance measure for prototypes using a GA; in the second we develop a new approach for the Particle Swarm algorithm where each particle represents a prototype, thus reducing greatly the search space dimension.
ML-BCI: Machine Learning for Brain Computer Interface (2008)
CCG07-UC3M/ESP-3286 [Comunidad Autónoma de Madrid - Universidad Carlos III de Madrid]
This project belongs to the brain-computer interface (BCI) research field. According to the project proposal, we have developed a tool for aquiring and processing electroencefalographic (EEG) data in real time. It also learns patterns from the EEG data by means of Neural Networks and allows a person to use his thoughts to control a cursor on the screen.
CibMin: Bioinspired Computation for Data Mining (2006)
UC3M-TEC-05-029 [Comunidad Autónoma de Madrid - Universidad Carlos III de Madrid]
This Project is made of two research lines. First, a Genetic Programming engine has been built (GPPE), that projects datasets to spaces of higher or smaller dimension, where classification and regression is easier (cuasi-linear). In the second research line, we have used genetic techniques to evolve regression rules and Particle Swarm Optimisation (PSO). The rules evolved have the property that in addition to obtaining accurate rules, the subspace where each rule is appropriate, is also obtained. Also, the binary PSO for classification rules has been studied, by following an innovative approach where the solution is coded by the whole set of particles (Michigan approach) and not by each one of them (Pittsburg approach).
TRACER: Advanced Optimisation Techniques for Complex Problems (2002-2004)
TIC2002-04498-C05-02 [Ministerio de Ciencia y Tecnología]
TRACER is an MCyT and FEDER funded project aimed at performing research in computer science with roughly two foci: a. Making advances in modern optimization and search techniques b. Solving complex problems at a higher efficiency and accuracy TRACER is intended to provide concrete results to the community: 1. Software facilities for programmers 2. An Internet front end for non-specialized researcher 3. A web site with problems descriptions and detail 4. A network of thematic mini-web sites on specialized research domains
