Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: A comparative study

2011 ◽  
Vol 43 (10) ◽  
pp. 2893-2899 ◽  
Author(s):  
Kangji Li ◽  
Hongye Su ◽  
Jian Chu
Teknomekanik ◽  
2021 ◽  
Vol 4 (1) ◽  
pp. 30-35
Author(s):  
Andre Kurniawan ◽  
Nanang Qosim ◽  
Remon Lapisa ◽  
Zainal Abadi ◽  
Jasman Jasman

Energy consumption of a building is one of the biggest sources of energy use today. Green Building Comitte Indonesia (GBCI) has launched a concept of energy consumption saving in a nationally standard building. Audit Building energy audit is the way to know how actual building energy consumption is and find alternative solution to decrease energy consumption in order to fulfill the energy saving building criteria. Two types of HVAC systems will be run in the EnergyPlus simulation, split AC and central AC. The previous research proved that central AC is better than split AC system for energy saving in the building with 20 floors. The simulation results show that by using a certain energy system, a more efficient energy system will be achieved and can still maintain the comfort of the room at a temperature of 24 °C and relative humidity according to the Green Building Indonesia standard reference.


Buildings ◽  
2019 ◽  
Vol 9 (9) ◽  
pp. 204 ◽  
Author(s):  
Yang ◽  
Tan ◽  
Santamouris ◽  
Lee

With the rising focus on building energy big data analysis, there lacks a framework for raw data preprocessing to answer the question of how to handle the missing data in the raw data set. This study presents a methodology and framework for building energy consumption raw data forecasting. A case building is used to forecast the energy consumption by using deep recurrent neural networks. Four different methodologies to impute missing data in the raw data set are compared and implemented. The question of sensitivity of gap size and available data percentage on the imputation accuracy was tested. The cleaned data were then used for building energy forecasting. While the existing studies explored only the use of small recurrent networks of 2 layers and less, the question of whether a deep network of more than 2 layers would be performing better for building energy consumption forecasting should be explored. In addition, the problem of overfitting has been cited as a significant problem in using deep networks. In this study, the deep recurrent neural network is then used to explore the use of deeper networks and their regularization in the context of an energy load forecasting task. The results show a mean absolute error of 2.1 can be achieved through the 2*32 gated neural network model. In applying regularization methods to overcome model overfitting, the study found that weights regularization did indeed delay the onset of overfitting.


2016 ◽  
Vol 53 ◽  
pp. 1520-1528 ◽  
Author(s):  
Sareh Naji ◽  
Shahaboddin Shamshirband ◽  
Hossein Basser ◽  
Afram Keivani ◽  
U. Johnson Alengaram ◽  
...  

2021 ◽  
Vol 13 (19) ◽  
pp. 10607
Author(s):  
Xiaoyue Zhu ◽  
Bo Gao ◽  
Xudong Yang ◽  
Yanping Yuan ◽  
Ji Ni

Human behaviors that greatly influence building energy consumption are stimulated by the indoor environment. However, the relative importance of different environmental factors remains unclear. Previous literature mostly focused on single behavior. Holistic study of multiple energy-related behaviors is scarce. To fill the gap, this study investigated 22 government office buildings in Sichuan using questionnaires and field measurement. Environmental factors were ranked based on the two dimensions of “importance level’level” and “satisfaction level”. The key energy-related behaviors were identified by the comparative study between low- and high-energy-consuming buildings. Lastly, interactions between the building energy consumption, indoor environment quality, occupants’ satisfaction, and human behaviors were analyzed. Questionnaires reveal that most occupants consider indoor air quality as the prior “pain point” while feeling satisfied enough with the thermal environment. Although people attach less importance to the acoustic environment, they manifest evident discontent, suggesting that noise control is an urgent imperative. In contrast, occupants are relatively unconcerned with illuminance, which implies the feasibility of saving energy by reasonably reducing lighting requirements of some non-critical areas. The comparative study indicates that increased energy consumption was attributable to extra personal appliances, wasteful air conditioning habits, and the lack of ventilation in summer. The objective environment of high-energy-consuming buildings is slightly better. However, the difference in perceived satisfaction was not obvious. The findings of this study contribute to determining the most noteworthy environmental factor and the key energy-related behaviors and provide reference information for optimizing energy-saving strategies.


Sign in / Sign up

Export Citation Format

Share Document