☆ 4.8 Article

A laboratory test of an Offline-trained Multi-Agent Reinforcement Learning Algorithm for Heating Systems

APPLIED ENERGY (2023)

Related references

Note: Only part of the references are listed.

Article Construction & Building Technology

Towards optimal HVAC control in non-stationary building environments combining active change detection and deep reinforcement learning

Xiangtian Deng et al.

Summary: This study proposes a novel HVAC control method, combining active building environment change detection and deep Q network (DQN), to address non-stationarity. The simulation results demonstrate that this method outperforms existing methods in terms of energy savings and thermal comfort. Additionally, the method shows stability against disturbances and generalization to unseen environments.

BUILDING AND ENVIRONMENT (2022)

Add to Collection

Article Construction & Building Technology

Optimal control method of HVAC based on multi-agent deep reinforcement learning

Qiming Fu et al.

Summary: This paper proposes a Multi-Agent deep reinforcement learning method for building Cooling Water System Control (MA-CWSC) to optimize the load distribution, cooling tower fan frequency, and cooling water pump frequency of different types of chillers. Experimental results show that the MA-CWSC method achieves significant energy saving performance and has a faster learning rate compared to other control methods.

ENERGY AND BUILDINGS (2022)

Add to Collection

Article Computer Science, Information Systems

MBRL-MC: An HVAC Control Approach via Combining Model-Based Deep Reinforcement Learning and Model Predictive Control

Liangliang Chen et al.

Summary: This article proposes a novel learning-based control strategy, named MBRL-MC, for the HVAC system by combining model-based deep reinforcement learning (DRL) and model predictive control (MPC). The proposed algorithm utilizes a supervised learning algorithm to learn a thermal dynamic model and then designs a neural network planning framework. The effectiveness of the proposed algorithm is validated through simulation experiments and comparisons with existing algorithms.

IEEE INTERNET OF THINGS JOURNAL (2022)

Add to Collection

Article Thermodynamics

Data-driven Offline Reinforcement Learning for HVAC-systems

Christian Blad et al.

Summary: This paper presents a novel framework for Offline Reinforcement Learning with online fine-tuning for HVAC systems. The framework enables pre-training in a black box model environment and can be applied to various HVAC control applications. The paper also explores the use of Artificial Neural Network methods for designing efficient controllers and demonstrates the effectiveness of the framework.

ENERGY (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Safe Building HVAC Control via Batch Reinforcement Learning

Chi Zhang et al.

Summary: This paper studies safe building HVAC control through batch reinforcement learning. By introducing noise and model evaluation, this method achieves safety during exploration and performance improvement during deployment. Compared with rule-based controllers, this method shows significant performance improvements.

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING (2022)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Safe HVAC Control via Batch Reinforcement Learning

Hsin-Yu Liu et al.

Summary: Buildings account for 30% of global energy use, with HVAC systems contributing to approximately half of it. Prior works on reinforcement learning (RL) for HVAC energy efficiency have limitations with online methods and historical data-driven models. Batch RL methods can learn from historical data and improve existing policies without interacting with real buildings or simulators. Our algorithm incorporates KL regularization term and achieves significant energy reduction in a real multi-zone, multi-floor building, surpassing state-of-the-art methods and enhancing occupants' thermal comfort.

2022 13TH ACM/IEEE INTERNATIONAL CONFERENCE ON CYBER-PHYSICAL SYSTEMS (ICCPS 2022) (2022)

Add to Collection

Article Energy & Fuels

Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning

Yan Du et al.

Summary: In this study, a novel deep reinforcement learning method, DDPG, is applied to optimize the HVAC control in residential buildings with the goal of minimizing energy consumption cost while maintaining user comfort. The simulation results demonstrate that the DDPG-based control strategy outperforms the state-of-the-art methods in reducing energy consumption cost and improving comfort level. Additionally, experiments with different building and price models show that the well-trained DDPG-based strategy has high generalization and adaptability for real-world applications.

APPLIED ENERGY (2021)

Add to Collection

Article Energy & Fuels

A Multi-Agent Reinforcement Learning Approach to Price and Comfort Optimization in HVAC-Systems

Christian Blad et al.

Summary: This paper addresses the challenge of minimizing training time for the control of HVAC systems using a novel approach to MARL. The simulations show that the agent can reduce heating costs, learn and generalize across seasons, and decrease room temperature oscillations compared to traditional control methods.

ENERGIES (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

Liang Yu et al.

Summary: This paper investigates the minimization of energy consumption of HVAC systems in commercial buildings, taking into account random zone occupancy, thermal comfort, and indoor air quality comfort. Research shows that the HVAC control algorithm based on multi-agent deep reinforcement learning has effectiveness, robustness, and scalability demonstrated through real-world trace simulations.

IEEE TRANSACTIONS ON SMART GRID (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-task deep reinforcement learning for intelligent multi-zone residential HVAC control

Yan Du et al.

Summary: In this communication, a data-driven deep reinforcement learning method is applied to optimize HVAC users' energy consumption costs while ensuring comfort. By conducting multi-task learning, the efficiency of the deep RL method is enhanced, and its effectiveness and generality in optimizing HVAC operation are verified through comparisons with other algorithms.

ELECTRIC POWER SYSTEMS RESEARCH (2021)

Add to Collection

Article Construction & Building Technology

Building HVAC control with reinforcement learning for reduction of energy cost and demand charge

Zhanhong Jiang et al.

Summary: Researchers have developed a Deep Q-Network (DQN) and reward shaping technique to address energy efficiency optimization in building control, demonstrating that the customized DQN outperforms baseline policies by saving close to 6% of total cost with demand charges and close to 8% without demand charges.

ENERGY AND BUILDINGS (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Applications of reinforcement learning in energy systems

A. T. D. Perera et al.

Summary: Energy systems are transitioning to accommodate renewable energy technologies and face challenges in controlling energy flows. Research has shown potential for reinforcement learning in improving performance, but certain complexities remain unresolved, indicating room for further development.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Add to Collection

Article Energy & Fuels

Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control

Marco Biemann et al.

Summary: Controlling HVAC systems using model-free reinforcement learning shows potential for improving energy efficiency. This study evaluates four actor-critic algorithms in a simulated data center, with the Soft Actor Critic algorithm outperforming others in maintaining thermal stability and reducing energy consumption.

APPLIED ENERGY (2021)

Add to Collection

Proceedings Paper Automation & Control Systems

Safe Reinforcement Learning Control for Water Distribution Network

Jorge Val et al.

Summary: Reinforcement Learning (RL) is an optimal control method used for regulating the behavior of dynamical systems with unknown models. The proposed model-free control method introduces a policy supervisor block in the control loop to ensure safety in operation while learning the optimal policy, by evaluating trajectories on a standard linear model in real-time. Simulation and experimental results show the effectiveness of this method in ensuring robust operation in large-scale infrastructures like Water Distribution Networks.

5TH IEEE CONFERENCE ON CONTROL TECHNOLOGY AND APPLICATIONS (IEEE CCTA 2021) (2021)

Add to Collection

Article Energy & Fuels

Reinforcement learning for building controls: The opportunities and challenges

Zhe Wang et al.

APPLIED ENERGY (2020)

Add to Collection

Article Green & Sustainable Science & Technology

Evaluating the Adaptability of Reinforcement Learning Based HVAC Control for Residential Houses

Kuldeep Kurte et al.

SUSTAINABILITY (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Online Energy Management for a Sustainable Smart Home With an HVAC Load and Random Occupancy

Liang Yu et al.

IEEE TRANSACTIONS ON SMART GRID (2019)

Add to Collection

Article Energy & Fuels

Multi-agent reinforcement learning for modeling and control of thermostatically controlled loads

Hussain Kazmi et al.

APPLIED ENERGY (2019)

Add to Collection

Proceedings Paper Energy & Fuels

Advanced Building Control via Deep Reinforcement Learning

Ruoxi Jia et al.

INNOVATIVE SOLUTIONS FOR ENERGY TRANSITIONS (2019)

Add to Collection

Proceedings Paper Engineering, Environmental

The impact of the work under partial load on the energy efficiency of an air-to-water heat pump

Krzysztof Piechurski et al.

9TH CONFERENCE ON INTERDISCIPLINARY PROBLEMS IN ENVIRONMENTAL PROTECTION AND ENGINEERING (EKO-DOK 2017) (2017)

Add to Collection

Proceedings Paper Construction & Building Technology

Analysis and Comparison Study on Different HFC Refrigerants for Space Heating Air Source Heat Pump in Rural Residential Buildings of North China

Jinzhe Nie et al.

10TH INTERNATIONAL SYMPOSIUM ON HEATING, VENTILATION AND AIR CONDITIONING, ISHVAC2017 (2017)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

Deep Reinforcement Learning for Building HVAC Control

Tianshu Wei et al.

PROCEEDINGS OF THE 2017 54TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC) (2017)

Add to Collection

Article Energy & Fuels

Experimental analysis of data-driven control for a building heating system

G. T. Costanzo et al.

SUSTAINABLE ENERGY GRIDS & NETWORKS (2016)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

Modelling and Simulation of Underfloor Heating System Supplied from Heat Pump

Muhammad Akmal et al.

2016 UKSIM-AMSS 18TH INTERNATIONAL CONFERENCE ON COMPUTER MODELLING AND SIMULATION (UKSIM) (2016)

Add to Collection

Article Construction & Building Technology

A new model predictive control scheme for energy and cost savings in commercial buildings: An airport terminal building case study

Hao Huang et al.

BUILDING AND ENVIRONMENT (2015)

Add to Collection

Review Construction & Building Technology

Theory and applications of HVAC control systems - A review of model predictive control (MPC)

Abdul Afram et al.

BUILDING AND ENVIRONMENT (2014)

Add to Collection

Article Engineering, Electrical & Electronic

Demand Response Optimization for Smart Home Scheduling Under Real-Time Pricing

K. M. Tsui et al.

IEEE TRANSACTIONS ON SMART GRID (2012)

Add to Collection

Article Construction & Building Technology

Model predictive control of a building heating system: The first experience

Samuel Privara et al.

ENERGY AND BUILDINGS (2011)

Add to Collection

Article Construction & Building Technology

A review on buildings energy consumption information

Luis Perez-Lombard et al.

ENERGY AND BUILDINGS (2008)

Add to Collection

Article Thermodynamics

Dynamic model of an HVAC system for control analysis

B Tashtoush et al.

ENERGY (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.