2021
DOI: 10.1016/j.egyai.2020.100043
|View full text |Cite
|
Sign up to set email alerts
|

Deep reinforcement learning for home energy management system control

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
51
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 135 publications
(51 citation statements)
references
References 16 publications
0
51
0
Order By: Relevance
“…For each successful reduction of consumption, the agent received a reward aimed at maximizing the amount of energy saved. Lissa et al (2021) developed such a model, based on Markov Decision Processes (MDP) to control the temperature of domestic hot water. Their goal was to reduce the consumption by optimizing the usage of energy produced by photo-voltaic panels.…”
Section: Deep Learningmentioning
confidence: 99%
“…For each successful reduction of consumption, the agent received a reward aimed at maximizing the amount of energy saved. Lissa et al (2021) developed such a model, based on Markov Decision Processes (MDP) to control the temperature of domestic hot water. Their goal was to reduce the consumption by optimizing the usage of energy produced by photo-voltaic panels.…”
Section: Deep Learningmentioning
confidence: 99%
“…The saving was greater when a neural network was trained for each zone of the building. Lissa et al [27] relied on that same neural network to estimate the Q-values of their deep reinforcement learning algorithm model to manage and control the heating system and the domestic hot water. They proposed a new methodology to define the threshold of indoor temperature comfort, based on the historical temperature of the building.…”
Section: B Reinforcement Learning and Its Growthmentioning
confidence: 99%
“…Several studies have shown that RL-based EMSs can be successfully implemented in various microgrid topologies, either as a single agent [19][20][21] or as a multiagent [22,23]. Nonetheless, the most basic and widely used RL approaches, namely Q-learning [24], suffer from several challenges, including inefficient data utilization, inability to handle continuous/large statespace, and curse of dimensionality, which cause the method to fail for large-scale tasks.…”
Section: Introductionmentioning
confidence: 99%