Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Neuro-fuzzy model based predictivealgorithm for environmental management of buildings

Sotirios Papantoniou, Kolokotsa Dionysia, Pouliezos Anastasios

Full record


URI: http://purl.tuc.gr/dl/dias/286B50BD-E3C5-421A-AB35-E7B8E34888BE
Year 2012
Type of Item Conference Full Paper
License
Details
Bibliographic Citation S. Papantoniou, D. Kolokotsa, A. Pouliezos," Neuro-fuzzy model based predictive algorithm for environmental management of buildings," in Proceedings of 3rd International Conference on Industrial and Hazardous Waste Management,2012.
Appears in Collections

Summary

This paper presents an algorithm used for predicting indoor environmentalconditions in buildings considering outdoor conditions such as outdoor temperature and humidityas well as window position and operating conditions of an air conditioning unit. Sensors whichare part of an existing Building Energy Management System (BEMS) read necessary data in realtime and the values are also stored in database for further analysis. The pre-mentionedalgorithms are based on an Adaptive-Network-Based Fuzzy Inference System (ANFIS) whichare trained and validated with historical data stored in the database. The results of predictingindoor environmental conditions over a considerable predictive horizon are presented anddiscussed. Further development is planned on the development of smaller systems based onmicrocomputers to store data from sensors, run the main control algorithms and actuate thenecessary components

Services

Statistics