4.7 Article

Deep reinforcement learning optimal control strategy for temperature setpoint real-time reset in multi-zone building HVAC system

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Thermodynamics

Integrated optimization of the building envelope and the HVAC system in nZEB refurbishment

Boris Delac et al.

Summary: This research introduces a method for optimizing the heating, ventilation, and air-conditioning (HVAC) system of a hotel building in Croatia to achieve nearly zero energy consumption. By combining dynamic simulation models and genetic algorithms, this method helps minimize costs and energy consumption while considering different design factors and available HVAC systems. The study identifies the most promising solution for the hotel's year-round operation and concludes that a water-to-water heat pump system using seawater as the heat source and sink is the best option.

APPLIED THERMAL ENGINEERING (2022)

Article Energy & Fuels

Towards healthy and cost-effective indoor environment management in smart homes: A deep reinforcement learning approach

Ting Yang et al.

Summary: This paper presents an autonomous indoor environment management approach utilizing a deep reinforcement learning control strategy to optimize the control of ventilation system and heating/cooling system, achieving a healthy indoor environment with minimized energy cost.

APPLIED ENERGY (2021)

Article Energy & Fuels

A clustering-based approach for cross-scale load prediction on building level in HVAC systems

Wenqiang Li et al.

Summary: This paper proposes a new cross-scale load prediction model on the building level based on the k-means clustering method, aiming to quantify the intra-cluster relationships. An ANN logistic regression model is used to investigate the association between each explanatory variable and cluster belongings. The proposed model is validated by real-world data and showed its effectiveness, and the inclusion of accumulative effect leads to better cross-scale prediction accuracy.

APPLIED ENERGY (2021)

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)

Article Construction & Building Technology

An explainable one-dimensional convolutional neural networks based fault diagnosis method for building heating, ventilation and air conditioning systems

Guannan Li et al.

Summary: A novel explainable deep learning based fault diagnosis method is proposed for HVAC systems, with distinctive features including the exclusion of the pooling layer, a convolution filter kernel size of 1, and the use of softsign as an activation function, achieving over 98.5% fault diagnosis accuracy for seven chiller faults and providing fault-discriminative information through the Grad-Absolute-CAM method.

BUILDING AND ENVIRONMENT (2021)

Article Thermodynamics

A hybrid deep transfer learning strategy for short term cross-building energy prediction

Xi Fang et al.

Summary: This study proposes a novel hybrid deep transfer learning strategy for short term cross-building energy prediction, utilizing LSTM and DANN models to enhance energy prediction performance. Experimental results demonstrate significant improvement in building energy prediction compared to other models.

ENERGY (2021)

Article Construction & Building Technology

Data-driven building energy modeling with feature selection and active learning for data predictive control

Liang Zhang

Summary: This paper discusses three main obstacles in the development of data-driven building energy modeling, proposes a framework integrating active learning and feature selection to address these issues, and evaluates the framework in a virtual test platform, demonstrating its effectiveness.

ENERGY AND BUILDINGS (2021)

Article Construction & Building Technology

A general multi-source ensemble transfer learning framework integrate of LSTM-DANN and similarity metric for building energy prediction

Xi Fang et al.

Summary: The study proposes a multi-source ensemble transfer learning framework to enhance building energy prediction performance. Experimental results show that multi-source transfer learning models can improve the prediction performance of target building power consumption compared to single-source models.

ENERGY AND BUILDINGS (2021)

Review Green & Sustainable Science & Technology

Data-driven predictive control for unlocking building energy flexibility: A review

Anjukan Kathirgamanathan et al.

Summary: Managing supply and demand in the electricity grid becomes more challenging with the increasing penetration of variable renewable energy sources. Buildings are expected to have an expanding role in the future smart grid through better grid integration and predictive control. Data-driven predictive control, coupled with the Internet of Things, holds promise for scalable and transferrable approaches in grid integration of buildings.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Computer Science, Artificial Intelligence

A data-efficient goal-directed deep reinforcement learning method for robot visuomotor skill

Rong Jiang et al.

Summary: This study introduces a data-efficient goal-directed deep reinforcement learning method, which achieves human-robot intention transfer and improves data efficiency through novel network designs and auxiliary evaluation.

NEUROCOMPUTING (2021)

Article Energy & Fuels

A real-time optimal control strategy for multi-zone VAV air-conditioning systems adopting a multi-agent based distributed optimization method

Wenzhuo Li et al.

Summary: This study introduces a real-time optimal control strategy for multi-zone VAV air-conditioning systems, utilizing a multi-agent based distributed optimization method to address large-scale mathematics programming challenges. Through schemes like temperature set-point reset, multi-objective optimization, and distributed optimization, it effectively balances thermal comfort, IAQ, and energy use while reducing programming challenges.

APPLIED ENERGY (2021)

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)

Review Green & Sustainable Science & Technology

Intelligent building control systems for thermal comfort and energy-efficiency: A systematic review of artificial intelligence-assisted techniques

Ghezlane Halhoul Merabet et al.

Summary: This paper provides a comprehensive review of AI-based techniques for building control systems, discussing the challenges faced in using AI for energy productivity and comfort improvement. It also outlines the main future directions in relation with AI-based building control systems for human comfort and energy-efficiency management.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Automation & Control Systems

Hybrid autonomous controller for bipedal robot balance with deep reinforcement learning and pattern generators

Christos Kouppas et al.

Summary: The research proposed a hybrid autonomous controller that hierarchically combines two separate systems for bipedal robots to recover in close collaboration with humans in real-world applications. By combining hardcoded and reinforcement learning controllers, a balance of speed and adaptability is achieved, allowing the system to maintain efficient control in new dynamic environments.

ROBOTICS AND AUTONOMOUS SYSTEMS (2021)

Article Construction & Building Technology

Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network

Zhengbo Zou et al.

BUILDING AND ENVIRONMENT (2020)

Article Construction & Building Technology

Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings

Silvio Brandi et al.

ENERGY AND BUILDINGS (2020)

Article Thermodynamics

Multi-objective optimization of a solar assisted heat pump-driven by hybrid PV

Evangelos Bellos et al.

APPLIED THERMAL ENGINEERING (2019)

Article Construction & Building Technology

Fusing TensorFlow with building energy simulation for intelligent energy management in smart cities

Jose R. Vazquez-Canteli et al.

SUSTAINABLE CITIES AND SOCIETY (2019)

Article Construction & Building Technology

Energy optimization associated with thermal comfort and indoor air control via a deep reinforcement learning algorithm

William Valladares et al.

BUILDING AND ENVIRONMENT (2019)

Article Construction & Building Technology

Data-driven model predictive control for building climate control: Three case studies on different buildings

Jiangyu Wang et al.

BUILDING AND ENVIRONMENT (2019)

Article Green & Sustainable Science & Technology

Optimal Control Strategy for Variable Air Volume Air-Conditioning Systems Using Genetic Algorithms

Nam-Chul Seong et al.

SUSTAINABILITY (2019)

Proceedings Paper Energy & Fuels

Advanced Building Control via Deep Reinforcement Learning

Ruoxi Jia et al.

INNOVATIVE SOLUTIONS FOR ENERGY TRANSITIONS (2019)

Article Construction & Building Technology

Optimal control of HVAC and window systems for natural ventilation through reinforcement learning

Yujiao Chen et al.

ENERGY AND BUILDINGS (2018)

Article Construction & Building Technology

Evaluation of a cost-responsive supply air temperature reset strategy in an office building

Paul Raftery et al.

ENERGY AND BUILDINGS (2018)

Review Green & Sustainable Science & Technology

A review of data-driven building energy consumption prediction studies

Kadir Amasyali et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Proceedings Paper Computer Science, Information Systems

Practical Implementation and Evaluation of Deep Reinforcement Learning Control for a Radiant Heating System

Zhiang Zhang et al.

BUILDSYS'18: PROCEEDINGS OF THE 5TH CONFERENCE ON SYSTEMS FOR BUILT ENVIRONMENTS (2018)

Article Construction & Building Technology

Nonlinear model predictive control for a heating and cooling system of a low-energy office building

Alexander Schirrer et al.

ENERGY AND BUILDINGS (2016)

Article Thermodynamics

Grey-box modeling of a low pressure electric boiler for domestic hot water system

Abdul Atisam Farooq et al.

APPLIED THERMAL ENGINEERING (2015)

Article Thermodynamics

Review of modeling methods for HVAC systems

Abdul Afram et al.

APPLIED THERMAL ENGINEERING (2014)

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)

Article Construction & Building Technology

Use of model predictive control and weather forecasts for energy efficient building climate control

Frauke Oldewurtel et al.

ENERGY AND BUILDINGS (2012)

Article Thermodynamics

Modelling and adaptive control of small capacity chillers for HVAC applications

A. Beghi et al.

APPLIED THERMAL ENGINEERING (2011)