Author:
Overgaard Anders,Skovmose Kallesøe Carsten,Dimon Bendtsen Jan,Kongsgaard Nielsen Brian
Abstract
In hydronic heating systems, a mixing loop is used to control the temperature and pressure. The task of the mixing loop is to provide enough heat power for comfort while minimizing the cost of heating the building. Control strategies for mixing loops are often limited by the fact that they are installed in a wide range of different buildings and locations without being properly tuned. To solve this problem the reinforcement learning method known as Q-learning is investigated. To improve the convergence rate this paper introduces a Gaussian kernel backup method and a generic model for pre-simulation. The method is tested via high-fidelity simulation of different types of residential buildings located in Copenhagen. It is shown that the proposed method performs better than well tuned industrial controllers.
Reference21 articles.
1. Gynther L., Lappillone B., and Pollier K., “Energy efficiency trends and policies in the household and tertiary sectors. An analysis based on the ODYSSEE and MURE databases,” no. June, p. 97, 2015. [Online]. Available: http://www.odyssee-mure.eu/publications/br/energy-efficiencytrends- policies-buildings.pdf
2. Building energy-consumption status worldwide and the state-of-the-art technologies for zero-energy buildings during the past decade
3. A review on optimized control systems for building energy and comfort management of smart sustainable buildings
4. Advanced control systems engineering for energy and comfort management in a building environment—A review
5. Sallent Cuadrado R., “Return temperature influence of a district heating network on the CHP plant production costs,” Ph.D. dissertation, 2009. [Online]. Available: http://hig.divaportal. org/smash/get/diva2:228450/FULLTEXT01
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献