Human-in-the-Loop Safe Reinforcement Learning: Applications in Power and Energy Systems

A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".

Deadline for manuscript submissions: closed (28 February 2025) | Viewed by 1040

Special Issue Editors


E-Mail Website
Guest Editor Assistant
Department of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI 48128, USA
Interests: control of DC/AC microgrids; robust control of power converters; consensus control; virtual impedance shaping; power quality; non-linear control; electric vehicle control; hardware in loop control applications

E-Mail Website
Guest Editor Assistant
Department of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI 48128, USA
Interests: artificial intelligence; computational intelligence; data mining; machine learning; optimization; intelligent systems

Special Issue Information

Dear Colleagues,

It is our pleasure to invite submissions to the Special Issue on “Human-in-the-Loop Safe Reinforcement Learning: Applications in Power and Energy Systems”.

The integration of deep reinforcement learning (DRL) with human-in-the-loop systems represents a significant advancement in the optimization and management of power and energy systems. This synergy combines the adaptive learning capabilities of DRL with the safety assurances necessary for critical infrastructure environments, such as power and energy systems. Human-in-the-loop systems enrich this framework by incorporating human expertise and oversight, ensuring robust decision-making and operational resilience in dynamic energy landscapes.

This Special Issue aims to explore cutting-edge research and practical applications of human-in-the-loop safe RL in power and energy systems. We invite researchers from both academia and industry to submit original research articles, reviews, and case studies that advance our understanding of how human-in-the-loop safe RL can enhance the efficiency, reliability, and sustainability of power and energy systems. Our goal is to foster interdisciplinary dialogue and innovation at the intersection of AI, human factors, and energy infrastructure, paving the way for transformative advancements in the field.

Topics of interest for publication include, but are not limited to:

  • Applications of artificial intelligence (AI) in the operation and control of power and energy systems;
  • Building energy management systems;
  • Charging stations with DRL;
  • Decentralized and distributed operation and control of power and energy systems;
  • Energy management systems;
  • Integration of renewable energy sources and mobile loads;
  • Integration of human expertise with AI in energy management;
  • Operation and control of power and energy systems;
  • Peer-to-peer energy trading in power systems;
  • Novel safe RL algorithms and applications in power and energy systems;
  • Multi-energy systems with combined cooling, heat, and power;
  • Multiagent deep reinforcement learning applications.

Dr. Van-Hai Bui
Guest Editor

Dr. Shivam Chaturvedi
Dr. Srijita Das
Guest Editor Assistants

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • building energy management systems
  • combined cooling, heat, and power systems
  • deep reinforcement learning
  • deep learning
  • distributed energy resources
  • distributed operation and control
  • double auction
  • game theory
  • human in the loop machine learning
  • energy management systems
  • machine learning algorithms
  • multi-agent reinforcement learning
  • microgrids
  • muti-energy system
  • multi-agent system
  • peer-to-peer communication optimization
  • optimal energy trading
  • safe reinforcement learning
  • smart grid

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issue

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 799 KiB  
Article
A GNN-Based False Data Detection Scheme for Smart Grids
by Junhong Qiu, Xinxin Zhang, Tao Wang, Huiying Hou, Siyuan Wang and Tiejun Yang
Algorithms 2025, 18(3), 166; https://doi.org/10.3390/a18030166 - 14 Mar 2025
Viewed by 502
Abstract
A Cyber-Physical System (CPS) incorporates communication dynamics and software into phsical processes, providing abstractions, modeling, design, and analytical techniques for the system. Based on spatial temporal graph neural networks (STGNNs), anomaly detection technology has been presented to detect anomaly data in smart grids [...] Read more.
A Cyber-Physical System (CPS) incorporates communication dynamics and software into phsical processes, providing abstractions, modeling, design, and analytical techniques for the system. Based on spatial temporal graph neural networks (STGNNs), anomaly detection technology has been presented to detect anomaly data in smart grids with good performance. However, since topological changes of power networks in smart grids often already predict the occurrence of anomalies, traditional models based on STGNNs to portray network evolution cannot be directly utilized in smart grids. Our research proposed a smart grid anomaly detection method on the grounds of STGNNs, which used evolution in the information of several attributes that affected the power network to represent the evolution of the power network, subsequently used STGNNs to obtain the time-space dependencies of nodes in several information networks, and used a cross-domain method to help the anomaly detection of the power network through anomaly information of other related networks. Laboratory findings reveal that the abnormal data detection rate of our scheme reaches 90% in the initial stage of data transmission and outperforms other comparative methods, and as time goes by, the detection rate becomes higher and higher. Full article
Show Figures

Figure 1

Back to TopTop