Optimal Surrogate and Neural Network Modeling for Day-Ahead Forecasting of the Hourly Energy Consumption of University Buildings. Ghassemi, P., Zhu, K., & Chowdhury, S. In Volume 2B: 43rd Design Automation Conference, pages V02BT03A026, 8, 2017. American Society of Mechanical Engineers.
Optimal Surrogate and Neural Network Modeling for Day-Ahead Forecasting of the Hourly Energy Consumption of University Buildings [link]Website  doi  abstract   bibtex   
This paper presents the development and evaluation of Artificial Neural Networks (ANN) based models and optimally selected surrogate models to provide the day-ahead forecast of the hourly-averaged energy load of buildings, by relating it to eight weather parameters as well as the hour of the day. Although ANN and other surrogate models have been used to predict building energy loads in the past, there is a limited understanding of what type of model prescriptions impact their performance as well as how un-recorded impact factors (e.g., human behavior and building repair work) should be accounted for. Here, the recorded energy data of three university buildings, from 9/2013–12/2015, is cleaned and synchronized with the local weather data. The data is then classified into eight classes; weekends and weekdays of Fall/Winter/Spring/Summer semesters. Both Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) NNs are explored. Differing number of hidden layers and transfer function choices are also explored, leading to the choice of the hyperbolic-tangent-sigmoid transfer function and 60 hidden layers. Similarly, an automated surrogate modeling framework is used to select the best models from among a pool of Kriging, RBF, and SVR models. A baseline concept, that uses energy information from the previous day as an added input to the ANN, helps to account for otherwise unrecorded recent changes in the building behavior, leading to improvement in fidelity of up to 30%.
@inproceedings{
 title = {Optimal Surrogate and Neural Network Modeling for Day-Ahead Forecasting of the Hourly Energy Consumption of University Buildings},
 type = {inproceedings},
 year = {2017},
 pages = {V02BT03A026},
 websites = {https://asmedigitalcollection.asme.org/IDETC-CIE/proceedings/IDETC-CIE2017/58134/Cleveland, Ohio, USA/252375},
 month = {8},
 publisher = {American Society of Mechanical Engineers},
 day = {6},
 city = {Cleveland, Ohio, USA},
 id = {b74d514d-3038-3197-aa98-1cad32734741},
 created = {2019-07-08T20:51:37.509Z},
 accessed = {2019-07-08},
 file_attached = {false},
 profile_id = {0bdc2b56-796f-3d8c-b59b-624a5fa689c3},
 last_modified = {2020-07-10T06:28:06.003Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {ghassemi2017optimal},
 patent_owner = {Ghassemi, Payam},
 private_publication = {false},
 abstract = {This paper presents the development and evaluation of Artificial Neural Networks (ANN) based models and optimally selected surrogate models to provide the day-ahead forecast of the hourly-averaged energy load of buildings, by relating it to eight weather parameters as well as the hour of the day. Although ANN and other surrogate models have been used to predict building energy loads in the past, there is a limited understanding of what type of model prescriptions impact their performance as well as how un-recorded impact factors (e.g., human behavior and building repair work) should be accounted for. Here, the recorded energy data of three university buildings, from 9/2013–12/2015, is cleaned and synchronized with the local weather data. The data is then classified into eight classes; weekends and weekdays of Fall/Winter/Spring/Summer semesters. Both Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) NNs are explored. Differing number of hidden layers and transfer function choices are also explored, leading to the choice of the hyperbolic-tangent-sigmoid transfer function and 60 hidden layers. Similarly, an automated surrogate modeling framework is used to select the best models from among a pool of Kriging, RBF, and SVR models. A baseline concept, that uses energy information from the previous day as an added input to the ANN, helps to account for otherwise unrecorded recent changes in the building behavior, leading to improvement in fidelity of up to 30%.},
 bibtype = {inproceedings},
 author = {Ghassemi, Payam and Zhu, Kaige and Chowdhury, Souma},
 doi = {10.1115/DETC2017-68350},
 booktitle = {Volume 2B: 43rd Design Automation Conference},
 keywords = {ADAMS,SBO}
}

Downloads: 0