Satisfaction based Q-learning for integrated lighting and blind control

Cheng, Zhiqiang; Zhao, Qianchuan; Wang, Fulin; Jiang, Yi; Xia, Li; Ding, Jinlei

doi:10.1016/j.enbuild.2016.05.067

Cited by 107 publications

(52 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7. The architecture of the proposed control framework and other building energy subsystems (e.g., blind, lighting, and window systems) has great potential of saving energy [70] [71]. For example, HVAC energy consumption can be reduced by 17%-47% if window-based natural ventilation is adopted [71].…”

Section: B Multiple Energy Subsystems In Commercial Buildingsmentioning

confidence: 99%

Deep Reinforcement Learning for Smart Home Energy Management

Xie

et al. 2020

IEEE Internet Things J.

286

View full text Add to dashboard Cite

In this paper, we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, nonshiftable power demand, outdoor temperature, and electricity price) and temporally-coupled operational constraints, it is very challenging to determine the optimal energy management strategy for scheduling Heating, Ventilation, and Air Conditioning (HVAC) systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management strategy based on Deep Deterministic Policy Gradients (DDPG). It is worth mentioning that the proposed strategy does not require the prior knowledge of uncertain parameters and building thermal dynamics model. Simulation results based on real-world traces demonstrate the effectiveness and robustness of the proposed strategy.

show abstract

Section: B Multiple Energy Subsystems In Commercial Buildingsmentioning

confidence: 99%

Deep Reinforcement Learning for Smart Home Energy Management

Xie

et al. 2020

IEEE Internet Things J.

286

View full text Add to dashboard Cite

show abstract

“…In [19], a reinforcement learning control (RLC) approach was presented for optimal control of low exergy buildings. An improved reinforcement learning controller was designed in [20] to obtain an optimal control strategy of blinds and lights, which provided a personalized service via introducing subject perceptions of surroundings gathered by a novel interface as the feedback signal. In [21], a model-free actor-critic reinforcement learning (RL) controller was addressed using a variant of artificial recurrent neural networks called long-short-term memory (LSTM) networks.…”

Section: Background and Motivationmentioning

confidence: 99%

Improvement of Refrigeration Efficiency by Combining Reinforcement Learning with a Coarse Model

Zhang

2019

Processes

View full text Add to dashboard Cite

It is paramount to improve operational conversion efficiency in air-conditioning refrigeration. It is noticed that control efficiency for model-based methods highly relies on the accuracy of the mechanism model, and data-driven methods would face challenges using the limited collected data to identify the information beyond. In this study, a hybrid novel approach is presented, which is to integrate a data-driven method with a coarse model. Specifically, reinforcement learning is used to exploit/explore the conversion efficiency of the refrigeration, and a coarse model is utilized to evaluate the reward, by which the requirement of the model accuracy is reduced and the model information is better used. The proposed approach is implemented based on a hierarchical control strategy which is divided into a process level and a loop level. The simulation of a test bed shows the proposed approach can achieve better conversion efficiency of refrigeration than the conventional methods.

show abstract

“…Kuo et al [17] developed an automatic shading control system using photometer, 3Dprinting component, and support vector machine algorithm for learning an individual's lighting preference. Cheng et al [18] developed a satisfaction based Qlearning system which integrated lighting and blind control by gathering occupants' feedback. Tang et al [19] used smartphone and light sensors to perform daylight harvesting while maintaining occupant desired light color.…”

Section: Literature Reviewmentioning

confidence: 99%

The Design of Building Management Platform Based on Cloud Computing and Low-Cost Devices

Huang¹,

Chiu²,

Chan³

2019

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

Indoor environment monitor and control are important aspects of reducing building energy consumption and maintaining occupants' visual and thermal comforts. Previous research showed that the lots of buildings were not able to provide designed service level in the daily operation and the feedback from occupants showed that the predetermined service level sometimes did not match occupants' desire. However, most of existing buildings and residential buildings did not have building management systems that can systematically monitor the indoor environment, collect occupants' feedback, and fine-tune built-in control logic when the occupants' needs could not be met. An easy-to-build and easy-to-use build management system can help researchers, engineers, and occupants themselves to identify the issue. The goal of this study was to develop a building management platform with the functions of indoor environment data collection (temperature, relative humidity, solar radiation, etc.), remote control (air conditioner, window, shading), occupants' feedback collection (set point, status of building components, etc.), and user interface for retrieving the data and modifying control logic. The platform was developed using Arduino-based and Raspberry Pi-based microcontroller board, low-cost sensors, 3D printing technology, and cloud computing technology. The stored data can serve for personal behavior/comfort analysis, components efficiency analysis, and advanced control logic development. This last part of this paper demonstrated the ability of the developed platform and exhibited the potential application. In the end, we provided further discussion about the potential challenges we might face when developing building management systems in other existing spaces/buildings.

show abstract

Satisfaction based Q-learning for integrated lighting and blind control

Cited by 107 publications

References 25 publications

Deep Reinforcement Learning for Smart Home Energy Management

Deep Reinforcement Learning for Smart Home Energy Management

Improvement of Refrigeration Efficiency by Combining Reinforcement Learning with a Coarse Model

The Design of Building Management Platform Based on Cloud Computing and Low-Cost Devices

Contact Info

Product

Resources

About