Deep Reinforcement Learning-Based Controller for SOC Management of Multi-Electrical Energy Storage System

Gorostiza, Francisco Sanchez; González-Longatt, Francisco

doi:10.1109/tsg.2020.2996274

Cited by 55 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See [124] for a review on RL-based EV charging management systems. References [125]- [127] adopt DQN and DDPG to learn the charging/discharging strategy for controlling battery systems considering unknown degradation models. In terms of building HVAC control, there are multiple uncertainty factors such as random zone occupancy, unknown thermal dynamics models, uncertain outdoor temperature and electricity price, etc.…”

Section: Energy Managementmentioning

confidence: 99%

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

150

View full text Add to dashboard Cite

With large-scale integration of renewable generation and distributed energy resources, modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility. Meanwhile, more and more data are becoming available owing to the widespread deployment of smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. This paper provides a comprehensive review of various RL techniques and how they can be applied to decision-making and control in power systems. In particular, we select three key applications, i.e., frequency regulation, voltage control, and energy management, as examples to illustrate RL-based models and solutions. We then present the critical issues in the application of RL, i.e., safety, robustness, scalability, and data. Several potential future directions are discussed as well.

show abstract

Section: Energy Managementmentioning

confidence: 99%

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

150

View full text Add to dashboard Cite

show abstract

“…A concise review of DRL-based smart building energy management methods is summarized in [21]. More recently, various DRL-based BEMS methods have been developed, including the scheduling of the ESS and HVAC in residential buildings based on a deep deterministic policy gradient (DDPG) method [22], the management of utility-scale interruptible loads in a dueling deep Q network [23], actor-critic-based demand response management for industrial facilities [24], and the control of the state of charge of a group of multiple ESSs using the DDPG method [25].…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach

Lee

Xie

Choi

2021

Sensors

View full text Add to dashboard Cite

This paper proposes a privacy-preserving energy management of a shared energy storage system (SESS) for multiple smart buildings using federated reinforcement learning (FRL). To preserve the privacy of energy scheduling of buildings connected to the SESS, we present a distributed deep reinforcement learning (DRL) framework using the FRL method, which consists of a global server (GS) and local building energy management systems (LBEMSs). In the framework, the LBEMS DRL agents share only a randomly selected part of their trained neural network for energy consumption models with the GS without consumer’s energy consumption data. Using the shared models, the GS executes two processes: (i) construction and broadcast of a global model of energy consumption to the LBEMS agents for retraining their local models and (ii) training of the SESS DRL agent’s energy charging and discharging from and to the utility and buildings. Simulation studies are conducted using one SESS and three smart buildings with solar photovoltaic systems. The results demonstrate that the proposed approach can schedule the charging and discharging of the SESS and an optimal energy consumption of heating, ventilation, and air conditioning systems in smart buildings under heterogeneous building environments while preserving the privacy of buildings’ energy consumption.

show abstract

“…The PEC is an enabling technology, and it has been a critical element in the integration of new low-carbon technologies providing the needed interface between two or more energy systems [1], [4]. Nevertheless, what is the issue arising from the massive integration of power converters?…”

Section: Introductionmentioning

confidence: 99%

On Short Circuit of Grid-Forming Converters Controllers: A glance of the Dynamic Behaviour

Habibullah

González-Longatt

Montalvo

et al. 2021

2021 IEEE PES Innovative Smart Grid Technologies Conference - Latin America (ISGT Latin America)

View full text Add to dashboard Cite

Power electronic converter (PEC) is an enabling technology for the energy transition, but the massive integration of PEC raises several issues. The use of Voltage source converters (VSCs) enabled with grid forming control offer a long-term solution of PEC-dominated power systems. This paper shows a glance of the dynamic performance during shortcircuit of three common grid forming controller types emulating synchronous generation are implemented: Virtual Synchronous Machine (VSM), the Synchronverter and grid forming droop control; and compared with a classic synchronous generator. Simulation results, considering a single generator contacted to an infinite bus, show the grid-forming converters' high-speed and different behaviour compared to the synchronous generator.

show abstract

Deep Reinforcement Learning-Based Controller for SOC Management of Multi-Electrical Energy Storage System

Cited by 55 publications

References 27 publications

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach

On Short Circuit of Grid-Forming Converters Controllers: A glance of the Dynamic Behaviour

Contact Info

Product

Resources

About