A Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations-Nafiseh Mazaheri * , Daniel Santamargarita , Emilio Bueno , Daniel Pizarro and Santiago Cobrece

A Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations Nafiseh Mazaheri * , Daniel Santamargarita , Emilio Bueno , Daniel Pizarro and Santiago Cobreces Department of Electronics, Alcalá University (UAH), Plaza San Diego S/N, 28801 Madrid, Spain

Abstract: 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. 

ORIGINAL LINK: https://www.mdpi.com/1996-1073/17/14/3578 

NORMAS INTERNACIONAIS E NACIONAIS ESPECIFICAS QUE DEVEM TER OS UPS ONLINE PARA APLICAÇOES EM HOSPITAIS E EM SALAS DE CIRURGIA E TI

 

VER O ARTIGO COMPLETO:

 https://www.mediafire.com/file/0j0pag27e3amie8/NORMAS+INTERNACIONAIS+E+NACIONAIS+ESPECIFICAS+QUE+DEVEM+TER+OS+UPS+ONLINE+PARA+APLICAÇOES+EM+HOSPITAIS+E+EM+SALAS+DE+CIRURGIA+E+TI.pdf/file

Inertia Supervision for BESS Grid-forming Inverter TESI DI LAUREA MAGISTRALE IN Electrical ENGINEERING INGEGNERIA Elettrica Author: Seifeldin Nafea-POLITECNICO MILANO

Inertia Supervision for BESS Grid-forming Inverter TESI DI LAUREA MAGISTRALE IN Electrical ENGINEERING INGEGNERIA Elettrica Author: Seifeldin Nafea 

 Introduction 

 In recent years, the renewable energy generation started to rise dramatically for most countries. In Europe, following the introduction of the renewable energy directive 2009/28/EC, the region increased the share of renewable energies in energy consumption to 20% by 2020, according to Eurostat [1]. Out of such energy consumption, 23% was consumed by the electricity sector as the second highest source of energy consumption [1]. Nevertheless, renewable energy generation is expected to continue rising in the coming years as part of the decarbonization plan. The directive EU/2018/2001 has set the renewable energy target to reach 32% by the year 2030 [2]. Subsequently, a provisional agreement was accepted to raise that target to at least 42.5%, with an aim for 45% [2]. The Continuous rise of renewable generation in the electricity sector can cause some problems for the grid, which need to be addressed. In traditional power systems, the synchronous generator is the main source offering support to the grid through its kinetic energy and governor control. The synchronous machine has the capability to participate in the primary frequency control using the governor speed control mechanism and dampen the system dynamics through its inertia. However, the power converters connecting renewables with the grid do not possess such capabilities. In fact, their control structure is more focused on extracting the maximum power from the renewable source. With the growth of renewable energy sources, the use of synchronous machines is expected to decline, hence decreasing the system inertia and support [3]. Remarkable efforts are focused on developing a control approach that allows power converters to mimic the behavior of a synchronous machine. A captivating control family has emerged, called ‘Grid-forming Inverters,’ allowing the inverters to provide some of the synchronous machine functionalities like primary frequency control, oscillation damping, and contributing to system inertia. This control methodology is best suited to be implemented with batteries. The high ramp rate along with power and energy characteristics of batteries ensures compliance with the control output power signals. The grid-forming presents multiple control approaches [10], with the utmost attention focused on the so called “Virtual Synchronous Machine”. It directs the power converters to act in a similar manner to a synchronous generator, thus providing all its functions mentioned above.

FULL THESIS: https://www.politesi.polimi.it/retrieve/ba4f7e7c-20a1-4e1f-8f4b-e57e7549afc7/Inertia%20Supervision%20for%20BESS%20Grid%20Forming%20Inverter.pdf

M-ulti-objective operation strategy for a PV-integrated hybrid UPS-ESS using predictive heuristics and receding-horizon control-Seong-Soo Jeong-Department of Electrical and Computer Engineering The Graduate School Sungkyunkwan University

 

Abstract 

 A Multi-Objective Operation Strategy for a PV-Integrated Hybrid UPS–ESS using Predictive Heuristics and Receding-Horizon Control In recent industry, the adoption of renewable energy using photovoltaics (PV) has been promoted as part of efforts to address climate change. In precision manufacturing facilities, an uninterruptible power supply (UPS) is required to respond to momentary voltage sags and outages, and an energy storage system (ESS) is essential to compensate for the intermittent output of PV. Accordingly, this study investigates a multi-objective control strategy for a hybrid UPS–ESS (HUE) system integrated with PV. Short-term forecasts of load and PV generation are performed using a Long Short-Term Memory (LSTM) model. Based on these forecasts, the minimum state of charge (SOC) required to secure HUE reserve power and the target SOC for system operation are calculated at each time step. Subsequently, the weights of each objective function are derived using Multi-Criteria Decision Making (MCDM), and a real-time operation strategy is constructed by combining predictive heuristics and Receding-Horizon Control (RHC). The predictive heuristic determines charge and discharge actions under operational constraints, while RHC updates the control decision at each time step by incorporating both forecasted and actual values. The proposed control aims to maintain an adequate SOC headroom for UPS readiness, suppress grid peaks to reduce electricity costs, and limit unnecessary SOC fluctuations that accelerate battery degradation. Simulation results demonstrate that the proposed multi-objective operation strategy combining predictive heuristics and RHC outperforms the comparison scenarios in terms of SOC stability, grid operation reliability, and cost efficiency.

Development of Large-Scale Seawater Battery Cells for High Energy Density-저자 Youngjin Kim 발행사항 울산 : Ulsan National Institute of Science and Technology, 2023 학위논문사항 학위논문(박사) -- Ulsan National Institute of Science and Technology , Engineering Energy Engineering (Battery Science and Technology) , 2023

 

ABSTRACT Lithium-ion batteries (LIBs) are the most widely used rechargeable energy storage systems. However, the future expanding of the LIB technology is limited due to the high cost and scarcity of both core elements of lithium and cobalt. The use of cheap earth-abundant metals such as sodium, aluminum, potassium, calcium, and magnesium in their corresponding metal-based batteries which working on the same principle as LIBs, would greatly reduce the cost of battery technology. Nevertheless, despite the economic advantage of production process, the large-scale production of these metal-based batteries have been limited by their lower gravimetric and volumetric energy densities. Rechargeable seawater batteries (SWBs) are regarded as sustainable alternatives to Li-ion batteries due to the use of an unlimited and free source of Na ion active materials. Although many approaches including the introduction of new catalysts have successfully improved the performance of SWBs, reconsidering the cell design is an urgent requirement to improve the performance and scale up the production of practical batteries. In this study, by adjusting the maximum space efficiency, a rectangular cell is developed which due to its unique architecture, benefits from optimized contact to improve the overall charge transfer in the system. In view of the rigidity of the solid electrolyte, the novel cell model is intended to have adequate flexibility to be easily transported and practically utilized. At the same time as the development of the cell platform, energy efficiency was also improved by improving the materials and assembly methods for each part of the seawater battery, which will be an indicator for future battery development. Furthermore, the enhanced efficiency of the parallel stacked modules, indicates the capability of this cell in practical use. The seawater battery module was actually operated in the ocean to prove its potential, and an automated pilot design for uniform cell production was also carried out. The designed catalyst-free cell system shows a record capacity of 3.8 Ah (47.5 Ah kg−1), energy of 11 Wh (137.5 Wh kg−1), and peak power of 523 mW for individual unit cell, while it also retains performance up to 100 cycles. This design paves the way for commercializing rechargeable seawater batteries.

ORIGINAL LINK: 

https://www.riss.kr/search/detail/DetailView.do?p_mat_type=be54d9b8bc7cdb09&control_no=b3b401c8481ee0b7ffe0bdc3ef48d419&keyword=BATTERY%20%20UPS%20%20IN%20PARALLEL