Filters








105 Hits in 5.8 sec

Neural network, ARX, and extreme learning machine models for the short-term prediction of temperature in buildings

Primož Potočnik, Boris Vidrih, Andrej Kitanovski, Edvard Govekar
2019 Building Simulation  
), and 0.065°C for the neural network model (in the case of available future weather data).  ...  Autoregressive models with exogenous inputs (ARX), neural network models (NN), and extreme learning machine models (ELM) are considered.  ...  +aMq -M , and B(q) = b1+b2q -1 +...+bMq -M+1 . The linear ARX model can be used to construct a predictive model for the thermal response of a building.  ... 
doi:10.1007/s12273-019-0548-y fatcat:joppjhiorjff7hqj4dwrbewrtm

Models for Prediction of Daily Mean Indoor Temperature and Relative Humidity: Education Building in Izmir, Turkey

Türkan Göksal Özbalta, Alper Sezer, Yusuf Yıldız
2011 Indoor and Built Environment  
In order to forecast the IT and internal relative humidity (IRH) parameters in the building, a number of artificial neural networks (ANN) models were trained and tested with a dataset including outdoor  ...  In this research, several models were developed to forecast the daily mean indoor temperature (IT) and relative humidity values in an education building in Izmir, Turkey.  ...  [14] evaluated the usage of neural network models for estimation of indoor air temperature.  ... 
doi:10.1177/1420326x11422163 fatcat:iwlwrudthbbjvjsnjwy6ejgsdu

Heat demand model for district heating simulation

Viliam Dolinay, Lubomir Vasek, Jakub Novak, Petr Chalupa, Erik Kral, N. Mastorakis, V. Mladenov, A. Bulucea
2018 MATEC Web of Conferences  
It is assumed that the heat demand is the most challenging part of the prediction, and therefore the accuracy and quality of these models will be the most significant to the accuracy of the entire future  ...  The fundamental idea is to build a modular model for specific district heating and start from the endpoints -from the individual consumption objects that will be interconnected through the distribution  ...  Many researchers use neural networks for modelling the nonlinearity of heat demand temperature dependence.  ... 
doi:10.1051/matecconf/201821002044 fatcat:f4t5cxzhpjalfop2wb4p462gci

Learning and training techniques in fuzzy control for energy efficiency in buildings

J. Sedano, J. R. Villar, L. Curiel, E. Corchado, E. A. De La Cal
2011 Logic Journal of the IGPL  
Finally, a supervised dynamic neural network model and identification techniques are applied to FC learning and training.  ...  Firstly, the dynamic thermal performance of different variables is mathematically modelled for each specific building type and climate zone.  ...  Finally, different techniques were applied to obtain a suitable prediction model, which was used for the prediction of indoor temperature. The results show a new promising method for learning FCs.  ... 
doi:10.1093/jigpal/jzr022 fatcat:m55e23dfjbamjppmn6d7prhx34

Simulation of thermal behavior of residential buildings using fuzzy active learning method

Masoud Taheri Shahraein, Hamid Taheri Shahraiyni, Melika Sanaeifar
2015 Journal of Fuzzy Set Valued Analysis  
In addition, it is necessary to predict and control indoor temperature for minimization of energy consumption.  ...  In this paper, a fuzzy modeling technique called Modified Active Learning Method (MALM) was introduced and utilized for fuzzy simulation of indoor and inner surface temperatures in residential buildings  ...  The authors thank Key Laboratory State of Faculty of Architecture (South China University of Technology) for the preparation of inner surface and indoor temperature measurement tools.  ... 
doi:10.5899/2015/jfsva-00208 fatcat:zjybntc74fhxvgqia5xifv5mmq

Can semi-parametric additive models outperform linear models, when forecasting indoor temperatures in free-running buildings?

Matej Gustin, Robert S. McLeod, Kevin J. Lomas
2019 Energy and Buildings  
Whilst, logistic GAMs were shown to adequately predict the window opening state, incorporating knowledge of the window state did not significantly improve the accuracy of the indoor temperature predictions  ...  A novel application combining semi-parametric Generalized Additive Models (GAMs) with logistic GAMs was developed to forecast indoor temperatures and window opening states during prolonged heatwaves.  ...  Acknowledgements This research was made possible by the Engineering and Physical Sciences Research Council (EPSRC) support for the 'London-Loughborough (LoLo) Centre for Doctoral Training in Energy Demand  ... 
doi:10.1016/j.enbuild.2019.03.048 fatcat:rhnhj3d7abevhe7yxxge7tt3mq

Long Term Solar Power Generation Prediction using Adaboost as a Hybrid of Linear and Non-linear Machine Learning Model

Sana Mohsin Babbar, Chee Yong Lau, Ka Fei Thang
2021 International Journal of Advanced Computer Science and Applications  
neural network ARX models applied to a prediction of the indoor statistical methods.  ...  to the Feed-forward Neural Network (FFNN), SVM and There always been a comparison in linear and non-linear regression model. 72 hour ahead prediction was made into the models with respect  ... 
doi:10.14569/ijacsa.2021.0121161 fatcat:arvdoolxhzh6nkwe226vr4pvhi

Performance Assessment of Data-Driven and Physical-Based Models to Predict Building Energy Demand in Model Predictive Controls

Alice Mugnini, Gianluca Coccia, Fabio Polonara, Alessia Arteconi
2020 Energies  
The implementation of model predictive controls (MPCs) in buildings represents an important opportunity to reduce energy consumption and to apply demand side management strategies.  ...  With a maximum deviation of 0.5 °C from the indoor set-point temperature, the physical-based model shows better performance in following the system dynamics, while the value rises to 1.8 °C in presence  ...  The most common black box models are [18] support vector machines (SVM) [19] , statistical regression (e.g., linear auto regressive models with exogenous inputs, ARX [20] ), and artificial neural networks  ... 
doi:10.3390/en13123125 fatcat:hvsiklac3zconex2s5rrdwnopq

Modeling of a Building System and its Parameter Identification

Herie Park, Nadia Martaj, Marie Ruellan, Rachid Bennacer, Eric Monmasson
2013 Journal of Electrical Engineering and Technology  
This study proposes a low order dynamic model of a building system in order to predict thermal behavior within a building and its energy consumption.  ...  This study will permit a further study on Model Predictive Control adapting to the proposed model in order to reduce energy consumption of the building.  ...  Moreover, [14] applied an ARX model and a neural network ARX model to the prediction of indoor temperature and relative humidity of an unoccupied residential building.  ... 
doi:10.5370/jeet.2013.8.5.975 fatcat:xpwus3ldnjgudb7m3phjiu6vdm

Artificial neural networks in energy applications in buildings

S. A. Kalogirou
2006 International Journal of Low-Carbon Technologies  
Results presented in this paper are testimony to the potential of artificial neural networks as a design tool in many areas of building services engineering.  ...  Artificial neural networks (ANNs) are nowadays accepted as an alternative technology offering a way to tackle complex and ill-defined problems.  ...  Prediction of the indoor air temperature Mechaqrane and Zouak [24] used a neural network auto regressive with exogenous input (NNARX) model to predict the indoor temperature of a residential building  ... 
doi:10.1093/ijlct/1.3.201 fatcat:seexwykmtvechnufftapndwvl4

Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression

Yin Guo, Ehsan Nazarian, Jeonghan Ko, Kamlakar Rajurkar
2014 Energy Conversion and Management  
The prediction method includes a combination of two separate time-indexed ARX models to improve prediction accuracy of the cooling load over different forecasting periods.  ...  The numerical case studies show the proposed prediction method performs better than some ANN and ARX forecasting models for the given test data set.  ...  Acknowledgement This study was partially supported by the Nebraska Center for Energy Sciences Research and the New Faculty Research Fund of Ajou University.  ... 
doi:10.1016/j.enconman.2013.12.060 fatcat:ur6gm3ki75gxxm67b4tbhemj6q

Comparison and Simulation of Building Thermal Models for Effective Energy Management

Fatima Amara, Kodjo Agbossou, Alben Cardenas, Yves Dubé, Sousso Kelouwani
2015 Smart Grid and Renewable Energy  
These lead to use inverse models to describe thermal behavior and to evaluate the energy consumption of buildings.  ...  In this paper, we propose a detailed review and simulation of the main thermal building models.  ...  Acknowledgements This work was supported by Laboratoire des technologies de l'énergie (LTE) d'Hydro-Québec, Natural Science and Engineering Research Council of Canada and Fondation UQTR.  ... 
doi:10.4236/sgre.2015.64009 fatcat:awcp52kcv5haxg57trobu3zqtq

Use of Machine Learning Methods for Indoor Temperature Forecasting

Lara Ramadan, Isam Shahrour, Hussein Mroueh, Fadi Hage Chehade
2021 Future Internet  
This paper contributes to this objective by comparing the ability of seven machine learning algorithms (ML) and the thermal gray box model to predict the indoor temperature of a closed room.  ...  The results showed that the best prediction was obtained with the artificial neural network (ANN) and extra trees regressor (ET) methods, which outperformed the thermal gray box model.  ...  Wang and Chen [78] compared three data-driven models, a linear black-box model (ARX), a non-linear black-box model (ANN), and a gray box model in predicting the indoor temperature of a single-zone house  ... 
doi:10.3390/fi13100242 fatcat:ppv3ck46gjgwjoyf7aw3xxwo2e

Improving Energy Efficiency in Buildings Using Machine Intelligence [chapter]

Javier Sedano, José Ramón Villar, Leticia Curiel, Enrique de la Cal, Emilio Corchado
2009 Lecture Notes in Computer Science  
Finally, neural projections and identification techniques are applied, in order to detect fluctuations in room temperatures and, in consequence, thermal insulation failures.  ...  Improving the detection of thermal insulation in buildings -which includes the development of models for heating and ventilation processes and fabric gain -could significantly increase building energy  ...  We would like to extend our thanks to Phd. Magnus Nørgaard for his marvellous freeware version of Matlab Neural Network Based System Identification Toolbox.  ... 
doi:10.1007/978-3-642-04394-9_95 fatcat:qetpeal73fa27cnmlcfj2fimla

WSN BASED THERMAL MODELING: A NEW INDOOR ENERGY EFFICIENT SOLUTION

Yi Zhao, Valentin Gies, Jean-Marc Ginoux
2015 International Journal on Smart Sensing and Intelligent Systems  
A linear approximation of these models makes it possible to estimate the EITTC of building room.  ...  Accordingly, a low cost, energy-efficient, wide-applicable indoor thermal modeling solution is developed by combining Wireless Sensor Network (WSN) and Artificial Neural Network (ANN).  ...  Previous studies outlined that ANN model outperformed Auto-Regressive(ARX) models in predicting the indoor temperature because the ANN models are more sensible to the nonlinearities of the thermal effects  ... 
doi:10.21307/ijssis-2017-787 fatcat:vktsquvwh5gcbcchzbxybecmxa
« Previous Showing results 1 — 15 out of 105 results