A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Energy-savings predictions for building-equipment retrofits
AbstractEnergy-consumption data collected from two equipment-retrofit projects before and after the retrofits was used to develop a model that estimates energy savings from retrofit projects. The computation method used in the model is based on Artificial Neural Networks (ANN). The model integrates weather variables, specific equipment-usage and occupancy data, and building-operation schedules into the pre-retrofit energy-usage pattern. It then estimates the energy usage of the pre-retrofit equipment in the post-retrofit period by using weather data, occupancy, and building-operation schedules in the post-retrofit period. The difference between the recorded energy usage of the post-retrofit equipment and the predicted energy usage of the pre-retrofit equipment in the post-retrofit period is the estimate of energy savings. For the two retrofit projects used in the ANN model, the coefficient of correlation varied from 0.957 to 0.844; the root mean square error varied from 6.81% to 16.4%; and the mean absolute error varied from 5.31% to 9.95%. Additionally, the sensitivity of the model to the input variables was analyzed with one of the retrofit project data. Dry bulb temperature, wet bulb temperature, and time (representing building-occupancy and equipment-operation schedule) were determined as the most effective variables in the ANN model. The research and findings are presented in this paper.
Energy-savings predictions for building-equipment retrofits
AbstractEnergy-consumption data collected from two equipment-retrofit projects before and after the retrofits was used to develop a model that estimates energy savings from retrofit projects. The computation method used in the model is based on Artificial Neural Networks (ANN). The model integrates weather variables, specific equipment-usage and occupancy data, and building-operation schedules into the pre-retrofit energy-usage pattern. It then estimates the energy usage of the pre-retrofit equipment in the post-retrofit period by using weather data, occupancy, and building-operation schedules in the post-retrofit period. The difference between the recorded energy usage of the post-retrofit equipment and the predicted energy usage of the pre-retrofit equipment in the post-retrofit period is the estimate of energy savings. For the two retrofit projects used in the ANN model, the coefficient of correlation varied from 0.957 to 0.844; the root mean square error varied from 6.81% to 16.4%; and the mean absolute error varied from 5.31% to 9.95%. Additionally, the sensitivity of the model to the input variables was analyzed with one of the retrofit project data. Dry bulb temperature, wet bulb temperature, and time (representing building-occupancy and equipment-operation schedule) were determined as the most effective variables in the ANN model. The research and findings are presented in this paper.
Energy-savings predictions for building-equipment retrofits
Yalcintas, Melek (author)
Energy and Buildings ; 40 ; 2111-2120
2008-06-02
10 pages
Article (Journal)
Electronic Resource
English
Energy-savings predictions for building-equipment retrofits
| Online Contents | 2008
Energy-savings predictions for building-equipment retrofits
| Online Contents | 2008
Lighting retrofits power Minneapolis energy savings
British Library Online Contents | 2018
Long-term savings persistence from existing building commissioning and retrofits
| Taylor & Francis Verlag | 2021
| British Library Online Contents | 2009