FRRQ - Producción de Investigación
Permanent URI for this communityhttp://48.217.138.120/handle/20.500.12272/2846
Browse
4 results
Search Results
Item A custom loss function approach for data-driven Economic Model Predictive Control(IEEE Xplore, 2025-11-27) Alarcón, Rodrigo Germán; Alarcón, Martín Alejandro; González, Alejandro H.; Ferramosca, AntonioAbstract: This paper proposes a new controller that takes advantage of the properties of the recurrent neural network of the long short-term memory (RNN-LSTM) to imitate the behavior of an economic model predictive control (economic MPC). The approach introduces specific knowledge of the benchmark controller optimization problem and modifies the loss function during the training stage of the RNN-LSTM. This method is easy to implement, and its effectiveness demonstrates itself in a practical application: the energy management system of a microgrid on a university campus. The results show that the modification of the loss function improves the accuracy of the proposed controller compared to the traditional training method.Item Gestión de Recursos y Estaciones de Carga de Vehículos Eléctricos en una Microrred Basada en MPC(Asociación Argentina de Mecánica Computacional, 2025-12-04) Alarcón, Martín Alejandro; Alarcón, Rodrigo GermánLas microrredes y los vehículos eléctricos son conceptos muy relacionados, ya que ambos tienen el objetivo de modificar la matriz energética hacia recursos más amigables con el medio ambiente. La necesidad de contar con estaciones de carga distribuidas sin comprometer la estabilidad de la red eléctrica es cada vez más necesario, y precisamente una microrred tiene la estructura apropiada para dar solución de forma local y eficiente. En este trabajo se propone una estrategia de control predictivo económico basado en modelo como sistema de gestión de la energía para una microrred con estaciones para la carga de vehículos. Para mostrar el desempeño se realizaron simulaciones sobre una microrred con generación renovable, un sistema de almacenamiento, tres estaciones de carga y que opera conectada a una red. En los puestos de carga se consideraron dos modos: carga controlada y el concepto de vehículo a la red. Los resultados muestran un funcionamiento correcto en diversos escenarios, donde las acciones de control óptimas se ajustan a las directrices del funcional propuesto en el controlador. Finalmente, estos resultados servirán también para establecer políticas de incentivo en el modo de vehículo a la red.Item Approximating the solution of an economic MPC using artificial neural networks(IEEE Xplore, 2024-05-21) Alarcón, Rodrigo Germán; Alarcón, Martín Alejandro; González, Alejandro H.; Ferramosca, AntonioAbstract: Economic model predictive control is a recognized advanced control strategy which calculates control actions by solving an optimization problem in real time. The issue of numerical computation is the main barrier to implementing this type of controller. Deep learning has emerged as a promising solution to reduce the computational cost. This paper proposes a deep learning approximation of an Economic MPC, particularly with artificial neural networks, of the control strategy for managing energy resources in a residential microgrid. Operational data were generated from the solution established by the controller to train, validate and test the neural network using Matlab. Simulation results showed that the proposed approach can approximate the control strategy correctly.Item Artificial neural networks for energy demand prediction in an economic MPC-Based energy management system(International Journal of Robust and Nonlinear Control, 2024-10-20) Alarcón, Rodrigo Germán; Alarcón, Martín Alejandro; González, Alejandro H.; Ferramosca, AntonioABSTRACT Microgrids are a development trend and have attracted a lot of attention worldwide. The control system plays a crucial role in implementing these systems and, due to their complexity, artificial intelligence techniques represent some enabling technologies for their future development and success. In this paper, we propose a novel formulation of an economic model predictive control (economic MPC) applied to a microgrid designed for a faculty building with the inclusion of a predictive model to deal with the energy demand disturbance using a recurrent neural network of the long short-term memory (RNN-LSTM). First, we develop a framework to identify an RNN-LSTM using historical data registered by a smart three-phase power quality analyzer to provide feedforward power demand predictions. Next, we present an economic MPC formulation that includes the prediction model for the disturbance within the optimization problem to be solved by the MPC strategy. We carried out simulations with different scenarios of energy consumption, available resources, and simulation times to highlight the results obtained and analyze the performance of the energy management system. In all cases, we observed the correct operation of the proposed control scheme, complying at all times with the objectives and operational restrictions imposed on the system.