Journal article Open Access

Towards plug&play smart thermostats inspired by reinforcement learning

Marantos, Charalampos; Lamparkos, Christos; Tsoutsouras, Vasileios; Siozios, Kostas; Soudris, Dimitrios


Citation Style Language JSON Export

{
  "DOI": "10.1145/3285017.3285024", 
  "author": [
    {
      "family": "Marantos, Charalampos"
    }, 
    {
      "family": "Lamparkos, Christos"
    }, 
    {
      "family": "Tsoutsouras, Vasileios"
    }, 
    {
      "family": "Siozios, Kostas"
    }, 
    {
      "family": "Soudris, Dimitrios"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2018, 
        11, 
        1
      ]
    ]
  }, 
  "abstract": "<p>Buildings are immensely energy-demanding and this fact is enhanced by the expectation of even more increment of energy consumption in the future. In order to mitigate this problem, a low-cost, flexible and high-quality Decision-Making Mechanism for supporting the tasks of a Smart Thermostat is proposed. Energy efficiency and thermal comfort are the two primary quantities regarding control performance of a building&#39;s HVAC system. Apart from demonstrating a conflicting relationship, they depend not only on the building&#39;s dynamics, but also on the surrounding climate and weather, thus rendering the problem of finding a long-term control scheme hard, and of stochastic nature. The introduced mechanism is inspired by Reinforcement Learning techniques and aims at satisfying both occupants&#39; thermal comfort and limiting energy consumption. In contrast to to existing methods, this approach focuses on a plug&amp;play solution, that does not require detailed building models and is applicable to a wide variety of buildings as it learns the dynamics using gathered information from the environment. The proposed control mechanisms were evaluated via a well-known building simulation framework and implemented on ARM-based, low-cost embedded devices.</p>", 
  "title": "Towards plug&play smart thermostats inspired by reinforcement learning", 
  "type": "article-journal", 
  "id": "3380093"
}
48
204
views
downloads
Views 48
Downloads 204
Data volume 345.3 MB
Unique views 47
Unique downloads 198

Share

Cite as