Experimental analysis of simulated reinforcement learning control for active and passive building thermal storage inventory

Liu, Simeng; Henze, Gregor P.

doi:10.1016/j.enbuild.2005.06.002

Cited by 103 publications

(63 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Gregor. P et al [28,29] investigated the use of Q-learning for optimizing thermal energy storage systems in a building. They developed a building simulation platform utilizing MATLAB and EnergyPlus and investigated the use of the tabular Q-learning algorithm.…”

Section: Previous Workmentioning

confidence: 99%

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

2017

View full text Add to dashboard Cite

Energy optimization in buildings by controlling the Heating Ventilation and Air Conditioning (HVAC) system is being researched extensively. In this paper, a model-free actor-critic Reinforcement Learning (RL) controller is designed using a variant of artificial recurrent neural networks called Long-Short-Term Memory (LSTM) networks. Optimization of thermal comfort alongside energy consumption is the goal in tuning this RL controller. The test platform, our office space, is designed using SketchUp. Using OpenStudio, the HVAC system is installed in the office. The control schemes (ideal thermal comfort, a traditional control and the RL control) are implemented in MATLAB. Using the Building Control Virtual Test Bed (BCVTB), the control of the thermostat schedule during each sample time is implemented for the office in EnergyPlus alongside local weather data. Results from training and validation indicate that the RL controller improves thermal comfort by an average of 15% and energy efficiency by an average of 2.5% as compared to other strategies mentioned.

show abstract

Section: Previous Workmentioning

confidence: 99%

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

2017

View full text Add to dashboard Cite

show abstract

“…It is also concluded that this is achievable with high performance in terms of thermal comfort both in summer and winter for the houses in the project. In Liu and Henze (2006b) an experimental analysis of simulated learning control for active and passive building thermal storage is reported. In Liu and Henze (2006a) the theoretical foundation is presented and in Liu and Henze (2006b) the results and analysis are found.…”

Section: Measurementsmentioning

confidence: 99%

“…In Liu and Henze (2006b) an experimental analysis of simulated learning control for active and passive building thermal storage is reported. In Liu and Henze (2006a) the theoretical foundation is presented and in Liu and Henze (2006b) the results and analysis are found. The work was conducted at the Energy Resource Center Station in Iowa.…”

Section: Measurementsmentioning

confidence: 99%

The energy efficiency of onboard hydrogen storage

Jensen

Vestbø

et al. 2007

Journal of Alloys and Compounds

133

View full text Add to dashboard Cite

“…Thus, a long time is necessary to finish the learning, or equipment to be controlled may not endure the trials if it is composed of mechanical parts, like a robot is. Hybrid learning solves this problem [9], [10]. An approach to hybrid learning first makes a control function using a non-linear control theory [11], [12], next the control function is approximated using linear function approximation, and the approximated control function is finally improved using reinforcement learning.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

Satoh

2008

IEICE Transactions on Fundamentals of Electronics, Communicatio

View full text Add to dashboard Cite

SUMMARY An orthonormal basis adaptation method for function approximation was developed and applied to reinforcement learning with multi-dimensional continuous state space. First, a basis used for linear function approximation of a control function is set to an orthonormal basis. Next, basis elements with small activities are replaced with other candidate elements as learning progresses. As this replacement is repeated, the number of basis elements with large activities increases. Example chaos control problems for multiple logistic maps were solved, demonstrating that the method for adapting an orthonormal basis can modify a basis while holding the orthonormality in accordance with changes in the environment to improve the performance of reinforcement learning and to eliminate the adverse effects of redundant noisy states.

show abstract

Experimental analysis of simulated reinforcement learning control for active and passive building thermal storage inventory

Cited by 103 publications

References 11 publications

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

The energy efficiency of onboard hydrogen storage

Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

Contact Info

Product

Resources

About