Jon Ander Zapirain Manrique

Spain is diferent!

1

1 comentario

From the AI4Software Spanish Research Network Research Network, we are pleased to present the paper "On the interaction between the search parameters and the nature of the search problems in search-based model-driven engineering", published in the journal Software: Practice and Experience. This achievement is the result of the collaboration between two nodes of the network: Universidad San Jorge and Universitat Politècnica de València (UPV). In this paper, the authors (Isis Roca Mainer, Jaime Font Burdeus, Lorena Arcega Rodríguez, and Carlos Cetina) evaluate the impact of different search parameter values on the performance of an evolutionary algorithm whose population is in the form of software models. The evaluation includes 1895 model fragment location problems (characterized by five accepted measures) from two industrial case studies and uses 625 different combinations of search parameter values. The search-based model-driven engineering community could benefit from the outcome of this work by accounting for the influence of search parameter values and the nature of model fragment location problems in their studies. Further details of this work can be found at: https://lnkd.in/dzjYRAyN. In addition, this work will be presented as part of #CEDI, in the "Arquitecturas Software y Variabilidad" (ASV) track of the XXVIII "Jornadas de Ingeniería del Software y Bases de Datos" (JISBD), on Monday 17 June, from 10:30 to 12:00, Room A.3.1.

6

BRINE MINING FOR METALS AND MINERALS. Sea4Value is the first attempt to recover #minerals and #metals from #brines produced in #seawater #desalinisation plants in a cost-effective way. To do that, a multimineral and modular process will be developed for #brine #mining. Separating, concentrating and crystallising #technologies for ten #metals and #minerals will be validated within the first 30 months of the project in laboratories. Afterward, during the last 18 months of the project’s lifetime, a moving lab will be designed and installed at 2 operating #plants to #validate the technical #feasibility in 2 different oceanic settings: #Mediterranean (Denia, Spain) and #Atlantic (Fonsalia, Canary Islands, Spain).

2

Practical data sheet for pythonists.

7

🚀 Indra strengthens its space portfolio by acquirirng Elecnor Deimos 🌌 Indra´s Board of Directors has approved the creation of the Space NewCo, presented in the #LeadingTheFuture" Strategic Plan. This new entity will provide comprehensive capabilities throughout the entire space industry value chain. To enhance its portfolio, Indra has signed a contract with Elecnor to acquire Deimos, improving its capabilities in all phases of a space mission, from satellite design and integration to ground segment operations. Additionally, Indra's 50% stake in Startical will be incorporated into the NewCo, improving its positioning in the downstream segment for the exploitation of space capabilities 🔗https://lnkd.in/dN9ERNkw #Indra #Innovation #Space #Technology #Acquisition #Deimos #Startical #LeadingTheFuture

388

1 comentario

In CITCEA-UPC Escola Tècnica Superior d'Enginyeria Industrial de Barcelona (ETSEIB - UPC) Universitat Politècnica de Catalunya and eRoots Analytics we are working on different tools to accelerate the calculation of optimal power flow (OPF) problems. The paper "Physics-Informed Neural Networks for Power Systems Warm-Start Optimization" led by Àlex Tudoras Miravet and coauthored with Eduardo Prieto Araujo and Esteban Gonzalez Iakl, presents our work on scalable physics-informed neural network (PINN) to calculate good approximations of the OPF which can be used directly or to initialize the OPF for a precise calculation. The paper is available in IEEE Access https://lnkd.in/dUnyKvsU . Abstract: Several studies have demonstrated the potential of machine learning methods to solve optimal power flow problems. However, designing a scalable physics-informed neural network (PINN) model that can improve its performance being trained in diverse scenarios by considering the significance of its several elements remains a challenging task. Here, we propose an approach that leverages the inclusion of physical constraints into the loss function using a penalty factor and the utilization of bounds of optimization variables in the activation functions to enhance the generalization performance of tuned neural networks. The results indicate that this method significantly improves the success rate and computational speed gains of AC-optimal power flow (AC-OPF) calculations, especially when forward predictions are employed as warm-start points. Our PINN models are trained using accurate AC-OPF solutions from slow high-precision interior-point solvers across several power system scenarios. Furthermore, we examine and demonstrate the critical role of adjusting PINN’s hyperparameters and architecture design in achieving the optimal tradeoff between empirical error and constraint violation to make accurate and feasible predictions. A combination of stochastic methods and grid search is utilized to establish a reliable and efficient way of performing optimization calculations for a wide range of power systems using collected data. The proposed PINN model offers a promising solution for adapting neural networks to diverse scenarios of a physical problem. Furthermore, it offers a robust methodology for successfully addressing optimal power flow (OPF) problems in power systems.

77

3 comentarios