A Sarsa-based adaptive controller for building energy conservation

被引：6

作者：

Fu, Qiming ^{[1
,2
,3
]}

Hu, Lingyao ^{[1
,2
,3
]}

Wu, Hongjie ^{[1
,2
,3
]}

Hu, Fuyuan ^{[1
,2
,3
]}

Hu, Wen ^{[1
,2
,3
]}

Chen, Jianping ^{[1
,2
,3
]}

机构：

[1] Suzhou Univ Sci & Technol, Inst Elect & Informat Engn, Suzhou 215009, Jiangsu, Peoples R China

[2] Suzhou Univ Sci & Technol, Jiangsu Key Lab Intelligent Bldg Energy Efficienc, Suzhou 215009, Jiangsu, Peoples R China

[3] Suzhou Univ Sci & Technol, Suzhou Key Lab Mobile Networking & Appl Technol, Suzhou 215009, Jiangsu, Peoples R China

来源：

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING | 2018年 / 18卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Energy conservation; Reinforcement learning; Sarsa algorithm; adaptive controller;

D O I：

10.3233/JCM-180792

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In the field of building equipment control, the traditional methods have some problems - instability and slow convergence. To deal with these problems, a new Sarsa-based adaptive controller, SAC (Sarsa-based adaptive controller) was proposed. Based on the model of the exchange mechanism about the building energy consumption, the proposed method with Sarsa algorithm models the exchange mechanism of the building energy consumption, and tries to find the best control policy, which can decrease the energy consumption without losing the performance of good comfort of the building occupants. Compared with the PID method, the proposed SAC has better convergence performance and robustness.

引用

页码：329 / 338

页数：10

共 13 条

[1] Energy consumption and efficiency in buildings: current status and future trends
Allouhi, A.
El Fouih, Y.
Kousksou, T.
Jamil, A.
Zeraouli, Y.
Mourad, Y.
[J]. JOURNAL OF CLEANER PRODUCTION, 2015, 109 : 118 - 130
[2] Energy conservation in buildings through efficient A/C control using neural networks
Ben-Nakhi, AE
Mahmoud, MA
[J]. APPLIED ENERGY, 2002, 73 (01) : 5 - 23
[3] Birchall S., 2016, P 12 REHVA WORLD C C
[4] Trasmission amplitude management in power line communications through a fuzzy logic controller: A real case study
Collotta, Mario
Tirrito, Salvatore
Bobovich, Aleksandr V.
[J]. JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2016, 16 (01) : 3 - 19
[5] Reinforcement learning for energy conservation and comfort in buildings
Dalamagkidis, K.
Kolokotsa, D.
Kalaitzakis, K.
Stavrakakis, G. S.
[J]. BUILDING AND ENVIRONMENT, 2007, 42 (07) : 2686 - 2698
[6] Egilegor B., 1997, 5 INT IBPSAN C, VII, P87
[7] Using reinforcement learning to optimize occupant comfort and energy usage in HVAC systems
Fazenda, Pedro
Veeramachaneni, Kalyan
Lima, Pedro
O'Reilly, Una-May
[J]. JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, 2014, 6 (06) : 675 - 690
[8] Advanced fuzzy logic controllers design and evaluation for buildings' occupants thermal-visual comfort and indoor air quality satisfaction
Kolokotsa, D
Tsiavos, D
Stavrakakis, GS
Kalaitzakis, K
Antonidakis, E
[J]. ENERGY AND BUILDINGS, 2001, 33 (06) : 531 - 543
[9] Chaotic time series prediction by artificial neural networks
Rafsanjani, Marjan Kuchaki
Samareh, Meysam
[J]. JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2016, 16 (03) : 599 - 615
[10] Sutton R.S., 2017, REINFORCEMENT LEARNI, V2, DOI DOI 10.1093/cercor/bhw013

← 1 2 →