Balancing comfort and energy consumption of a heat pump using batch reinforcement learning with fitted Q-iteration

被引：39

作者：

Vazquez-Canteli, Jose ^{[1
]}

Kampf, Jerome ^{[2
]}

Nagy, Zoltan ^{[1
]}

机构：

[1] Univ Texas Austin, Dept Civil Architectural & Environm Engn, Intelligent Environm Lab, Austin, TX 78712 USA

[2] Haute Ecole Ingn & Architecture Fribourg HEIA FR, ENERGY Inst, Fribourg, Switzerland

来源：

CISBAT 2017 INTERNATIONAL CONFERENCE FUTURE BUILDINGS & DISTRICTS - ENERGY EFFICIENCY FROM NANO TO URBAN SCALE | 2017年 / 122卷

关键词：

artificial intelligence; energy management; thermal comfort; building simulation; energy storage;

D O I：

10.1016/j.egypro.2017.07.429

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

In this study, a heat pump satisfies the heating and cooling needs of a building, and two water tanks store heat and cold respectively. Reinforcement learning (RL) is a model-free control approach that can learn from the behaviour of the occupants, weather conditions, and the thermal behaviour of the building in order to make near-optimal decisions. In this work we use of a specific RL technique called batch Q-learning, and integrate it into the urban building energy simulator CitySim. The goal of the controller is to reduce the energy consumption while maintaining adequate comfort temperatures. (C) 2017 The Authors. Published by Elsevier Ltd.

引用

页码：415 / 420

页数：6