Federated reinforcement learning for smart building joint peer-to-peer energy and carbon allowance trading

Qiu, Dawei; Xue, Juxing; Zhang, Tingqi; Wang, Jianhong; Sun, Mingyang

doi:10.1016/j.apenergy.2022.120526

Cited by 35 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure that private information of individual households is not shared with the central control or aggregator, distributed learning frameworks such as federated learning (FL) are introduced. In this essence, FL is integrated with RL as a federated reinforcement learning to optimise the energy and carbon trading jointly [108].…”

Section: Machine Learning Approachesmentioning

confidence: 99%

A Review of Peer-to-Peer Energy Trading Markets: Enabling Models and Technologies

Islam

2024

Energies

View full text Add to dashboard Cite

This paper presents a detailed review of the existing literature on peer-to-peer (P2P) energy trading considering market architectures, trading strategies, and enabling technologies. P2P energy trading enables individual users in the electricity network to act as sellers or buyers and trade energy among each other. To facilitate the discussion on different aspects of P2P energy trading, this paper focuses on P2P market mechanisms, relevant bidding strategies, and auction models. In addition, to solve the energy management problems associated with P2P energy trading, this paper investigates widely used solution methods such as game-theoretic models, mathematical optimisation, as well as more recent machine learning techniques and evaluates them in a critical manner. The outcomes of this investigation along with the identification of the challenges and limitations will allow researchers to find suitable P2P energy trading mechanisms based on different market contexts. Moreover, the discussions on potential future research directions are expected to improve the effectiveness of P2P energy trading technologies.

show abstract

Section: Machine Learning Approachesmentioning

confidence: 99%

A Review of Peer-to-Peer Energy Trading Markets: Enabling Models and Technologies

Islam

2024

Energies

View full text Add to dashboard Cite

show abstract

“…The paper then proposed a solution to the joint resource allocation problem, taking into account constraints such as training time, energy supply, and sensing quality for each edge device. Finally, the paper in [ 156 ] introduced a multi-agent reinforcement learning framework for a joint energy and carbon allowance trading mechanism in a building community. The proposed approach included an FL technique to accelerate the training process and protect the privacy of individual building data.…”

Section: Data Analysis Approachmentioning

confidence: 99%

Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions

Khan,

Zedadra,

Guerrieri

et al. 2024

Sensors

View full text Add to dashboard Cite

In today’s world, a significant amount of global energy is used in buildings. Unfortunately, a lot of this energy is wasted, because electrical appliances are not used properly or efficiently. One way to reduce this waste is by detecting, learning, and predicting when people are present in buildings. To do this, buildings need to become “smart” and “cognitive” and use modern technologies to sense when and how people are occupying the buildings. By leveraging this information, buildings can make smart decisions based on recently developed methods. In this paper, we provide a comprehensive overview of recent advancements in Internet of Things (IoT) technologies that have been designed and used for the monitoring of indoor environmental conditions within buildings. Using these technologies is crucial to gathering data about the indoor environment and determining the number and presence of occupants. Furthermore, this paper critically examines both the strengths and limitations of each technology in predicting occupant behavior. In addition, it explores different methods for processing these data and making future occupancy predictions. Moreover, we highlight some challenges, such as determining the optimal number and location of sensors and radars, and provide a detailed explanation and insights into these challenges. Furthermore, the paper explores possible future directions, including the security of occupants’ data and the promotion of energy-efficient practices such as localizing occupants and monitoring their activities within a building. With respect to other survey works on similar topics, our work aims to both cover recent sensory approaches and review methods used in the literature for estimating occupancy.

show abstract

“…Federated learning can also be used with the reinforcement learning. In [26], a federated reinforcement learning method is designed for the peer-to-peer energy trading and the carbon allowance trading. Article [27] uses the horizontal federated reinforcement learning to predict the wind power which can leverage the wind farms in a cluster.…”

Section: Previous Study and Literature Reviewmentioning

confidence: 99%

Privacy Preserving Ultra-Short-term Wind Power Prediction Based on Secure Multi Party Computation

Fan¹,

Fan²,

Hao³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Federated reinforcement learning for smart building joint peer-to-peer energy and carbon allowance trading

Cited by 35 publications

References 32 publications

A Review of Peer-to-Peer Energy Trading Markets: Enabling Models and Technologies

A Review of Peer-to-Peer Energy Trading Markets: Enabling Models and Technologies

Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions

Privacy Preserving Ultra-Short-term Wind Power Prediction Based on Secure Multi Party Computation

Contact Info

Product

Resources

About