Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/243765 
Year of Publication: 
2020
Citation: 
[Journal:] Energy Reports [ISSN:] 2352-4847 [Volume:] 6 [Issue:] 1 [Publisher:] Elsevier [Place:] Amsterdam [Year:] 2020 [Pages:] 409-416
Publisher: 
Elsevier, Amsterdam
Abstract: 
This study addresses a new generation of adaptable intelligent control systems for energy management. The proposed approach consists of a high-level predictive control system based on advanced simulation and optimization algorithms which interact with conventional machine-level controllers of HVAC systems, e.g., PID, in order to define optimized set points considering current and forecasted operation conditions, minimizing a predefined objective cost function, e.g., energy consumption, subjected to maintain predefined levels of comfort. The flexibility of the proposed architecture and the development of reliable surrogate models based on robust machine learning techniques are key features to combine green building requirements while granting or even improving occupant comfort. A first version of the proposed system was developed, and preliminary results emphasize its role in the path of transition to intelligent green buildings as a part of new buildings or, more important, as a retrofit of current buildings, with almost no changes on infrastructures, but promoting them to a smart building level.
Subjects: 
Green buildings
Energy efficiency
Intelligent supervision
Supervised predictive control
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article
Appears in Collections:

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.