LightLearn: An adaptive and occupant centered controller for lighting based on reinforcement learning

Park, June Young; Dougherty, Thomas; Fritz, Hagen; Nagy, Zoltán

doi:10.1016/j.buildenv.2018.10.028

Cited by 165 publications

(56 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 5 summarizes the major machine learning algorithms used in building control stage. MPC [96], [97], [98], [99] Kalman Filter [100], [101] Generic Algorithm [102] RL: value based [103], [104], [105], [106], [107], [108] RL: actor critic [109], [110] Learning building thermal dynamics for building control RC model and regression [97], [111], [112], [113] RC model and Generic Algorithm [114] Lighting control RL: value based [115] Window control RL: value based [116] Thermal Energy Storage control Non-linear programming [117] RL: value based [118] RL: actor critic [119], [120] Hot water control RL: value based [121] RL: actor critic [122] Comfort improvement…”

Section: Machine Learning For Building Controlmentioning

confidence: 99%

“…In the comfort side, thermal comfort is the most frequent control objective. In addition to thermal comfort, visual comfort [115] and indoor air quality [116] have been considered in previous studies. Other similar goals complementary to energy conservation include minimizing carbon emission, minimizing operation costs [117], and enhancing grid interactivity (such as load shifting, or maximizing the self-consumption of the local PV production [121]).…”

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

209

View full text Add to dashboard Cite

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

show abstract

Section: Machine Learning For Building Controlmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

209

View full text Add to dashboard Cite

show abstract

“…Park et al [58] introduced a reinforcement learning-based occupant-centered controller for lighting. LightLearn utilizes occupancy information, switch position, and light information to adjust the lighting according to environmental conditions and user preferences.…”

Section: Algorithms and Techniques Used For The Energy Optimizationmentioning

confidence: 99%

A Review on Energy Consumption Optimization Techniques in IoT Based Smart Building Environments

et al. 2019

View full text Add to dashboard Cite

In recent years, due to the unnecessary wastage of electrical energy in residential buildings, the requirement of energy optimization and user comfort has gained vital importance. In the literature, various techniques have been proposed addressing the energy optimization problem. The goal of each technique is to maintain a balance between user comfort and energy requirements, such that the user can achieve the desired comfort level with the minimum amount of energy consumption. Researchers have addressed the issue with the help of different optimization algorithms and variations in the parameters to reduce energy consumption. To the best of our knowledge, this problem is not solved yet due to its challenging nature. The gaps in the literature are due to advancements in technology, the drawbacks of optimization algorithms, and the introduction of new optimization algorithms. Further, many newly proposed optimization algorithms have produced better accuracy on the benchmark instances but have not been applied yet for the optimization of energy consumption in smart homes. In this paper, we have carried out a detailed literature review of the techniques used for the optimization of energy consumption and scheduling in smart homes. Detailed discussion has been carried out on different factors contributing towards thermal comfort, visual comfort, and air quality comfort. We have also reviewed the fog and edge computing techniques used in smart homes.

show abstract

“…Wang and Shao conducted one 24-h monitoring over 30 days in library and applied a rule mining approach, finding 26.1% of total energy cost can be saved [28]. Since Wi-Fi signals distribute indoor space like air surrounding it and will be reflected by human body, [33]. On the other hand, Manzoor proposed a study for efficient building lighting control by monitoring occupancy with passive RFID technology, which proved 13% of electrical energy savings [34].…”

Section: Occupancy Studies With Single Data Typementioning

confidence: 99%

Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering

Wang

Hong

et al. 2019

Building and Environment

View full text Add to dashboard Cite

Fusing various sensing data sources is able to improve the accuracy and reliability of building occupancy detection. Efficiently fusing environmental sensors and wireless network signals is seldom studied for its computational and technical challenges. This study aims to propose an integrated model that is able to extract critical data features for environmental and Wi-Fi probe dual sensing sources to promote computational efficiency. The adaptive lasso model was introduced for the feature extraction and reduction process. To validate the proposed model, an onsite experiment was conducted and two occupancy resolutions, real-time and four-level occupancy resolutions, were compared. The results suggested that eight features among all twelve features are most relevant. The mean absolute error of the selected data features is about 2.18 for real-time occupancy and F1_accuracy is about 84.36% for four-level occupancy.

show abstract

LightLearn: An adaptive and occupant centered controller for lighting based on reinforcement learning

Cited by 165 publications

References 60 publications

State-of-the-art on research and applications of machine learning in the building life cycle

State-of-the-art on research and applications of machine learning in the building life cycle

A Review on Energy Consumption Optimization Techniques in IoT Based Smart Building Environments

Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering

Contact Info

Product

Resources

About