Development of Hybrid Artificial Neural Network for Quantifying Energy Saving using Measurement and Verification
| Autor: | Wan Nazirah Wan Md Adnan, Nofri Yenita Dahlan, Ismail Musirin |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Control and Optimization
Artificial neural network Computer Networks and Communications Computer science 020209 energy Control engineering 02 engineering and technology Development (topology) Hardware and Architecture Signal Processing 0202 electrical engineering electronic engineering information engineering Measurement and Verification Electrical and Electronic Engineering Energy (signal processing) Information Systems |
| Zdroj: | Indonesian Journal of Electrical Engineering and Computer Science. 8:137 |
| ISSN: | 2502-4760 2502-4752 |
| DOI: | 10.11591/ijeecs.v8.i1.pp137-145 |
| Popis: | This paper presents a Hybrid Artificial Neural Network (HANN) for chiller system Measurement and Verification (M&V) model development. In this work, hybridization of Evolutionary Programming (EP) and Artificial Neural Network (ANN) are considered in modeling the baseline electrical energy consumption for a chiller system hence quantifying saving. EP with coefficient of correlation (R) objective function is used in optimizing the neural network training process and selecting the optimal values of ANN initial weights and biases. Three inputs that are affecting energy use of the chiller system are selected; 1) operating time, 2) refrigerant tonnage and 3) differential temperature. The output is hourly energy use of building air-conditioning system. The HANN model is simulated with 16 different structures and the results reveal that all HANN structures produce higher prediction performance with R is above 0.977. The best structure with the highest value of R is selected as the baseline model hence is used to determine the saving. The avoided energy calculated from this model is 132944.59 kWh that contributes to 1.38% of saving percentage. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|