Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Real-time digital twin prototype for cyber-physical analysis of anomalies in PV-PEM-BESS systems for green hydrogen production

  • Hueros Barrios, Pablo José|||0000-0003-1861-7642
  • Espolio Maestro, Jorge
  • Rodríguez Carrasco, Sergio
  • Santos Pérez, Carlos
  • Rodríguez Sánchez, Francisco Javier|||0000-0001-8508-1898
  • Martín Sánchez, Pedro|||0000-0003-3204-4510
  • Tradacete Ágreda, Miguel|||0000-0002-9255-8532
  • Blaabjerg, Frede
The deployment of hybrid green hydrogen systems faces challenges due to complex integration and exposure to cyber threats. The lack of secure testbeds to replicate severe anomalies limits the analysis of fault propagation without endangering physical assets. Consequently, it is necessary to develop a testbed to replicate anomalies in the operation of a green hydrogen generation system to facilitate its physical implementation. This article presents the development of a real-time Digital Twin Prototype (DTP) testbed for green hydrogen production systems integrating photovoltaic (PV) generation, a proton exchange membrane water electrolyzer (PEMWE), and a battery energy storage system (BESS), structured with a DC bus and a supercapacitor. The platform is implemented using Hardware In the Loop (HIL) to emulate system dynamics, enabling the safe testing of cyber-physical anomalies such as False Data Injection Attacks (FDIA) and DC bus short circuits. Historical weather data, including irradiance and temperature from a real-site weather station, are streamed to the HIL-based model via User Datagram Protocol (UDP) communication, replicating realistic operating conditions. A cost-effective real-time monitoring architecture is established using a low-cost Single Board Computer (SBC), with data logged in InfluxDB and visualized through Grafana. Results are analysed through flowcharts depicting failure propagation, offering insights into system resilience and control performance. The testbed facilitates the validation of anomaly detection techniques and Energy Management Systems (EMS), while minimizing the need for physical prototyping. This approach enhances operational safety and accelerates development efficiency in renewable hydrogen infrastructures., Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha, Comunidad de Madrid, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

A deep reinforcement learning approach to DC-DC power electronic converter control with practical considerations

  • Mazaheri Tehrani, Nafiseh
  • Santamargarita Mayor, Daniel|||0000-0003-3848-5886
  • Bueno Peña, Emilio José|||0000-0003-0401-4576
  • Pizarro Pérez, Daniel|||0000-0003-0622-4884
  • Cóbreces Álvarez, Santiago|||0000-0002-3308-4613
In recent years, there has been a growing interest in using model-free deep reinforcement learning (DRL)-based controllers as an alternative approach to improve the dynamic behavior, efficiency, and other aspects of DC–DC power electronic converters, which are traditionally controlled based on small signal models. These conventional controllers often fail to self-adapt to various uncertainties and disturbances. This paper presents a design methodology using proximal policy optimization (PPO), a widely recognized and efficient DRL algorithm, to make near-optimal decisions for real buck converters operating in both continuous conduction mode (CCM) and discontinuous conduction mode (DCM) while handling resistive and inductive loads. Challenges associated with delays in real-time systems are identified. Key innovations include a chattering-reduction reward function, engineering of input features, and optimization of neural network architecture, which improve voltage regulation, ensure smoother operation, and optimize the computational cost of the neural network. The experimental and simulation results demonstrate the robustness and efficiency of the controller in real scenarios. The findings are believed to make significant contributions to the application of DRL controllers in real-time scenarios, providing guidelines and a starting point for designing controllers using the same method in this or other power electronic converter topologies., Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha, Universidad de Alcalá