FRRQ - Producción de Investigación

Permanent URI for this communityhttp://48.217.138.120/handle/20.500.12272/2846

Browse

Author: search.filters.author.Alarcón, Martín AlejandroStart date: 2023

Search Results

Now showing 1 - 7 of 7
  • Thumbnail Image
    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, Antonio
    Abstract: 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.
  • Thumbnail Image
    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 Germán
    Las 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.
  • Thumbnail Image
    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, Antonio
    Abstract: 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.
  • Thumbnail Image
    Item
    A scenario-based economic-stochastic model predictive control for the management of microgrids
    (ScienceDirect, 2023-12) Alarcón, Martín Alejandro; Alarcón, Rodrigo Germán; González, Alejandro H.; Ferramosca, Antonio
    Abstract The world’s electricity generation is heavily dependent on the consumption of fossil fuels. Electric generation from renewable resources is necessary due to the imperative need to reduce greenhouse gases to avoid a climate crisis. These resources exhibit random and intermittent behaviour. Therefore, there is a need to develop new management and control tools for these insertions into the current electricity system. Microgrids have become an effective tool to solve this problem, where these control systems play a principal role. For this reason, an optimal control structure consisting of two Model Predictive Control strategies is proposed for a microgrid Energy Management System. The first controller aims to optimise the microgrid’s economic performance under an established criterion, using nominal forecasts of the disturbances on the system, such as the energy generated by renewable resources. The second is a stochastic approach using scenario-based methods to consider forecast errors in the nominal predictions used for the disturbances. The simulations were carried out on a microgrid model corresponding to the National Technological University, Reconquista Regional Faculty, highlighting that actual samples of energy consumption are available. It is worth noting that with the proposed structure, optimal solutions are obtained considering the random behaviour of the disturbances, without making assumptions about the distribution functions of the random variables. Moreover, it applies to different scales of microgrids.
  • Thumbnail Image
    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, Antonio
    ABSTRACT 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.
  • Thumbnail Image
    Item
    LSTM recurrent neural network for energy demand forecasting
    (2023-05-16) Alarcón, Rodrigo Germán; Alarcón, Martín Alejandro; González, Alejandro H.; Ferramosca, Antonio
    Abstract—Recurrent Neural Networks (RNN) of the Long Short Term Memory (LSTM) type provide high accuracy in predicting sequential models in various application domains. As in most process control problems, their dynamics include non manipulated variables that need to be predicted. This paper proposes using an LSTM neural network for energy demand forecasting, which applies to an Economic Model Predictive Control (EMPC) as a forecasting tool. For the training, data are taken from a three-phase intelligent power quality analyser located at the National Technological University, Reconquista Regional Faculty (Santa Fe, Argentina). A recursive strategy is used to update the state of the neural network and forecast over different prediction horizons. The accuracy achieved in training the neural network is measured using the root mean square error (RMSE) metric. Experimental results show that the proposed LSTM neural network has excellent generalisation capability.
  • Thumbnail Image
    Item
    Cooperative n-personal games in the coalitional economic control of a microgrid community
    (2023-05-16) Alarcón, Martín Alejandro; Alarcón, Rodrigo Germán; González, Alejandro H.; Ferramosca, Antonio
    Abstract—The deployment of microgrids connected to an electricity grid is increasing every day. These energy districts with their control system are the intelligent nodes of future electricity grids; therefore, strategies for managing these new systems must be developed and proposed. This paper presents a novel coalitional economic model predictive control strategy for managing a microgrid community. Because coalitional control considers the dynamic variation of coalitions of agents, a coop erative n-personal game with economic aspects occurs to decide which coalition to build, where the optimal control strategy to solve for each of these coalitions also takes place. Furthermore, an example proposes an economic criterion for using both the cooperative game and the control strategy for each coalition. Finally, some results on coalition formation are presented for the example mentioned above.