Energy optimization for regional buildings based on distributed reinforcement learning

Qin, Yude; Ji, Ke; Wang, Biao; Fedorovich, Filaretov Gennady

doi:10.1016/j.scs.2021.103625

Cited by 27 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analyzing the specific drivers behind the observed consumption trends would provide valuable insights into, for example, the sources of any wasted energy use and the enduses that would benefit most from further smart optimizations. Submetering different equipment and areas of the building can enable more targeted strategies based on detailed consumption profiles [15,[129][130][131] In summary, this case study both supports existing research on the relationships between weather, building attributes, and energy use and highlights future opportunities to leverage advanced tools like AI and renewable energy for next-level building energy efficiency and sustainability. By continuing to gather and analyze multi-year data, as well as learning from larger trends across the research, smart building systems can reach their full potential as a key strategy for a greener future.…”

Section: Discussionsupporting

confidence: 59%

Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus

Karimi,

Adibhesami,

Hoseinzadeh

et al. 2024

Buildings

View full text Add to dashboard Cite

This study introduces a novel framework that leverages artificial intelligence (AI), specifically deep learning and reinforcement learning, to enhance energy efficiency in architectural design. The goal is to identify architectural arrangements that maximize energy efficiency. The complexity of these models is acknowledged, and an in-depth analysis of model selection, their inherent complexity, and the hyperparameters that govern their operation is conducted. This study validates the scalability of these models by comparing them with traditional optimization techniques like genetic algorithms and simulated annealing. The proposed system exhibits superior scalability, adaptability, and computational efficiency. This research study also explores the ethical and societal implications of integrating AI with architectural design, including potential impacts on human creativity, public welfare, and personal privacy. This study acknowledges it is in its preliminary stage and identifies its potential limitations, setting the stage for future research to enhance and expand the effectiveness of the proposed methodology. The findings indicate that the model can steer the architectural field towards sustainability, with a demonstrated reduction in energy usage of up to 20%. This study also conducts a thorough analysis of the ethical implications of AI in architecture, emphasizing the balance between technological advancement and human creativity. In summary, this research study presents a groundbreaking approach to energy-efficient architectural design using AI, with promising results and wide-ranging applicability. It also thoughtfully addresses the ethical considerations and potential societal impacts of this technological integration.

show abstract

Section: Discussionsupporting

confidence: 59%

Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus

Karimi,

Adibhesami,

Hoseinzadeh

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…The Non-Dominated Neighbor Immune Algorithm (NNIA) proposed based on the mechanism of the artificial immune system [11,12] is a representative multi-objective optimization genetic algorithm, which draws on and improves the elite retention strategy in the Non-Dominated Sorting Genetic Algorithm -II (NSGA -II) [13,14] and performs better in multiple classic problems. This paper uses NNIA as the core algorithm to solve the dual objective optimization problem in the planning process of highway corridor strips, which mainly focuses on environmental sensitivity factors and construction cost factors.…”

Section: Corridor Strip Search Methods Based On Nnia and Ap Clusterin...mentioning

confidence: 99%

Corridor selection method of new highway based on NNIA genetic algorithm

Wu,

Zhu,

Wang

et al. 2024

Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023)

View full text Add to dashboard Cite

The selection of the highway corridor is very significant in the early stage of highway construction, and its rationality determines the economy, environmental protection, and safety of the whole life cycle of the construction project. Existing corridor selection methods are mainly based on the subjective experience of designers and lack intelligent corridor selection technology with strong operability. Therefore, a corridor selection method for new highways based on Nondominated Neighbor Immune Algorithm (NNIA) and Affinity Propagation (AP) clustering algorithm was proposed. Firstly, the mathematical model of the corridor was built. Secondly, considering the environmental and economic factors during the corridor selection stage, the optimization objective function was established. Lastly, the corridor was generated by using the NNIA and AP clustering algorithms. This method was applied to the project from Dezhou to Shangrao Highway from Qimen to the boundary of Anhui and Jiangxi provinces. The corridor generated was consistent with the trend of the actual route of the project, which had certain engineering feasibility.

show abstract

“…To address the above problems, RL has been studied and adopted in various fields, including district heating [15] and energy management [16]. To address the peak-shaving problem in district heating, RL was combined with a thermodynamic model and agent-based model, and this novel method achieved better results than the baseline [15].…”

Section: Related Workmentioning

confidence: 99%

“…Since wind power curtailment is inevitable in integrated electricity and DHS dispatch, a double-check RL was proposed to promote the integration of wind power by improving operational flexibility [17]. Qin et al proposed a distributed RL-based control strategy for building energy optimization, compared with model productive control and evolutionary algorithm, the proposed method is the most energy-efficient [16]. To achieve distributed energy scheduling and strategy-making, a multi-agent RL approach was proposed, and an optimal equilibrium selection mechanism was applied to improve the performance of RL from benefit fairness, execution efficiency, and privacy protection [18].…”

Section: Related Workmentioning

confidence: 99%

Application of reinforcement learning for energy consumption optimization of district heating system

Deng,

Eklund,

Sierla

et al. 2023

2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE)

View full text Add to dashboard Cite

Heating residential spaces consumed 64 percent of total household energy consumption in Finland. Considering the heat transfer and time delay in the district heating system, the calculation of setpoints of supply temperature requires a comprehensive understanding of the real system, and experienced operators need to manually determine the setpoints. To save energy, a more effective and accurate method is needed for setpoints calculation. In this paper, a reinforcement learning based method is proposed. Through interacting with an Aprosbased simulation model, the agents learn to calculate supply temperature parallelly for lowering energy costs. Simulation results show that the proposed method outperforms the existing method and has the potential to address the problem in real factories.

show abstract

Energy optimization for regional buildings based on distributed reinforcement learning

Cited by 27 publications

References 29 publications

Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus

Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus

Corridor selection method of new highway based on NNIA genetic algorithm

Application of reinforcement learning for energy consumption optimization of district heating system

Contact Info

Product

Resources

About