Transferable Reinforcement Learning for Smart Homes

Zhang, Xiangyu; Jin, Xin; Tripp, Charles; Biagioni, David; Gräf, Peter; Jiang, Huaiguang

doi:10.1145/3427773.3427865

Cited by 15 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TL is used in the building sector for two mean reasons: prediction and occupancy detection and activity recognition [133]. Using transfer learning for HVAC control in buildings has several advantages, including better performance [134,135], the ability to transfer knowledge from one building to another with minimal effort [136,137], and a reduced training time [138]. The use of transfer learning in HVAC control for buildings has been studied in a few papers; in [139], transfer learning was applied to environmental sensor data to predict the occupancy status in an educational building.…”

Section: Transfer Learning (Tl)mentioning

confidence: 99%

Balancing Sustainability and Comfort: A Holistic Study of Building Control Strategies That Meet the Global Standards for Efficiency and Thermal Comfort

Azzi,

Tabaa,

Chegari

et al. 2024

Sustainability

View full text Add to dashboard Cite

The objective of energy transition is to convert the worldwide energy sector from using fossil fuels to using sources that do not emit carbon by the end of the current century. In order to achieve sustainability in the construction of energy-positive buildings, it is crucial to employ novel approaches to reduce reliance on fossil fuels. Hence, it is essential to develop buildings with very efficient structures to promote sustainable energy practices and minimize the environmental impact. Our aims were to shed some light on the standards, building modeling strategies, and recent advances regarding the methods of control utilized in the building sector and to pinpoint the areas for improvement in the methods of control in buildings in hopes of giving future scholars a clearer understanding of the issues that need to be addressed. Accordingly, we focused on recent works that handle methods of control in buildings, which we filtered based on their approaches and relevance to the subject at hand. Furthermore, we ran a critical analysis of the reviewed works. Our work proves that model predictive control (MPC) is the most commonly used among other methods in combination with AI. However, it still faces some challenges, especially regarding its complexity.

show abstract

Section: Transfer Learning (Tl)mentioning

confidence: 99%

Balancing Sustainability and Comfort: A Holistic Study of Building Control Strategies That Meet the Global Standards for Efficiency and Thermal Comfort

Azzi,

Tabaa,

Chegari

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…This approach ensured a reduction of the training time of target device controllers by around 25 %. Similarly, the transfer of a RL agent controlling appliances was investigated by Zhang et al [56]. In this case, the use of TL resulted in a reduction of the RL controller training time on the target buildings, improving its performance from the early stages of implementation compared to the case without transfer.…”

Section: Related Work On Tl Applications For Advanced Controllers In ...mentioning

confidence: 99%

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

et al. 2023

View full text Add to dashboard Cite

“…However, TL is crucial when adopting RL for smart buildings' general controls, as it is computationally demanding, and therefore resource-and time-consuming to train RL-based load predictors for each new building [61]. Currently, most TL applications with RL-based models are proposed for smart building energy management [57,[84][85][86]. This may help in deploying more RL-based methods within the TL frameworks for cross-building energy load forecasting.…”

Section: Future Directions and Perspectivesmentioning

confidence: 99%

Transfer Learning for Renewable Energy Systems: A Survey

Al-Hajj

Assi²,

Neji

et al. 2023

Sustainability

View full text Add to dashboard Cite

Currently, numerous machine learning (ML) techniques are being applied in the field of renewable energy (RE). These techniques may not perform well if they do not have enough training data. Additionally, the main assumption in most of the ML algorithms is that the training and testing data are from the same feature space and have similar distributions. However, in many practical applications, this assumption is false. Recently, transfer learning (TL) has been introduced as a promising machine-learning framework to mitigate these issues by preparing extra-domain data so that knowledge may be transferred across domains. This learning technique improves performance and avoids the resource expensive collection and labeling of domain-centric datasets; furthermore, it saves computing resources that are needed for re-training new ML models from scratch. Lately, TL has drawn the attention of researchers in the field of RE in terms of forecasting and fault diagnosis tasks. Owing to the rapid progress of this technique, a comprehensive survey of the related advances in RE is needed to show the critical issues that have been solved and the challenges that remain unsolved. To the best of our knowledge, few or no comprehensive surveys have reviewed the applications of TL in the RE field, especially those pertaining to forecasting solar and wind power, load forecasting, and predicting failures in power systems. This survey fills this gap in RE classification and forecasting problems, and helps researchers and practitioners better understand the state of the art technology in the field while identifying areas for more focused study. In addition, this survey identifies the main issues and challenges of using TL for REs, and concludes with a discussion of future perspectives.

show abstract

Transferable Reinforcement Learning for Smart Homes

Abstract: This report is available at no cost from the National Renewable Energy Laboratory (NREL) at www.nrel.gov/publications. U.S. Department of Energy (DOE) reports produced after 1991 and a growing number of pre-1991 documents are available free via www.OSTI.gov.

Cited by 15 publications

References 9 publications

Balancing Sustainability and Comfort: A Holistic Study of Building Control Strategies That Meet the Global Standards for Efficiency and Thermal Comfort

Balancing Sustainability and Comfort: A Holistic Study of Building Control Strategies That Meet the Global Standards for Efficiency and Thermal Comfort

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

Transfer Learning for Renewable Energy Systems: A Survey

Contact Info

Product

Resources

About