On-Line Building Energy Optimization Using Deep Reinforcement Learning

By Elena Mocanu, Decebal Constantin Mocanu, Phuong H. Nguyen, Antonio Liotta, Michael E. Webber, Madeleine Gibescu, Johannes G. Slootweg. IEEE Transactions on Smart Grid, 2017

552 citations recorded by the source corpus.

Unprecedented high volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the future power systems and to help customers transition from a passive to an active role. In this paper, we explore for the first time in the smart grid context the benefits of using deep reinforcement learning, a hybrid type of methods that combines reinforcement learning with deep learning, to perform on-line optimization of schedules for building energy management systems. The learning procedure was explored using two methods, Deep Q-learning and deep policy gradient, both of which have been extended to perform multiple actions simultaneously. The proposed approach was validated on the large-scale Pecan Street Inc. database. This highly dimensional database includes information about photovoltaic power generation, electric vehicles and buildings appliances. Moreover, these on-line energy scheduling strategies could be used to provide real-time feedback to consumers to encourage more efficient use of electricity.

Subfields: Building and Construction, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/30741e7e30976f7b482eef3d00295ae4740ec21b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Electrical and Electronic Engineering

Citations in the corpus

Reinforcement learning for building controls: The opportunities and challenges (2020, background): “Mocanu et al. (2018) [63] found both Deep Q-learning and Deep Policy Gradient performs better than the tabular Q-learning, and Deep Policy Gradient is more suited to perform scheduling of energy resources than Deep Q-learning.”
Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges (2021, methodology): “2019 [131] Building energy management Hybrid DPG and DQN ANN Both DPG and DQN are implemented for building energy control and their performances are compared numerically.”
A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management (2020, background): “Reference [20] focuses on the deep RL based on-line optimization of schedules for the building energy management system.”
Applications of reinforcement learning in energy systems (2021, methodology): “Even these few works only utilized the policy-based methods, such as vanilla policy gradient (with and without baseline) [105,108,158] and TRPO [82].”
Intelligent Multi-Microgrid Energy Management Based on Deep Neural Network and Model-Free Reinforcement Learning (2020, background): “In [21], [22], both a deep neural network and reinforcement”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, background): “smart buildings [253], [255] can be regarded as the extension of smart grids AIoT (Section IV-F).”
A Review of Deep Reinforcement Learning for Smart Building Energy Management (2020, methodology): “, peak demand [23], transformer capacity violation [22], and revenue of excess renewable energy [108].”
Tackling Climate Change with Machine Learning (2019, unknown): “ment learning can be used to learn how to optimally schedule household appliances to consume energy more efﬁciently 54See e.g. https://www.tmrow.com/ 55https://www.watttime.org/ 46 and sustainability [627, 628]. Multi-agent learning has also been applied to this problem, to ensure that groups of hom”