N.A. Ramli, M.F. A. Hamid, H.G. Anak Richard


Buildings consume almost the highest energy in Malaysia, and the highest energy consumption comes from electricity. In order to reduce energy consumption in the commercial buildings, energy efficiency measures need to be done based on factors that affect energy consumption in the building. In this paper, the energy consumption of two commercial buildings are taken as a case study, and a number of energy cost saving measures were proposed based on the energy audit. The primary objective of this study is to obtain the minimum years of return of investment for two different commercial buildings through energy efficiency measures. In this case study, energy prediction is added and its results are used to determine how much saving could be obtained. The methodology used for prediction of energy consumption is autoregressive integrated moving average, and its performance was compared with linear regression and artificial neural network. The results showed that the most accurate method with the highest cost saving is autoregressive integrated moving average. Finally, building energy index was calculated, and the results showed that the minimum years of return on investment is two years if the investment is RM 499,539. For future work, other factors such as the number of equipment should be included in the prediction analysis to obtain more accurate results.   


ARIMA; artificial neural network; building energy index; Energy Cost Saving Measures; energy prediction.

Full Text:



Abdul-Rahman, Hamzah, Chen Wang., Kho, M.Y. (2011). Potentials for sustainable improvement in building energy efficiency: case studies in tropical zone. International Journal of the Physical Sciences, 6 (2): 325-339.

Giovanni Tardioli, Ruth Kerrigan, Mike Oates, James O‘Donnell & Donal Finn (2015). Data Driven Approaches for Prediction of Building Energy Consumption at Urban Level. Energy Procedia. 78: 3378-3383.

Gul, M.S., Patidar, S. (2014). Understanding the energy consumption and occupancy of a multi-purpose academic building. Energy and Building. 87(87): 155-165.

Kumar, R., Aggarwal, R.K., Sharma, J.D. (2013). Energy analysis of a building using artificial neural network: a review. Energy and Buildings. 65: 352 – 358.

Mahusin, N.A., Baharun, R. (2014). Utility consumption among Malaysian electricity users in government buildings. International Symposium on Technology Management and Emerging Technologies. 27-29 May 2014. Bandung, Indonesia. IEEE. 383-387.

Rumelhart, D.E., Hinton, G.E., Williams, R.J. (1986). Learning internal representation by error propagation. In D.E. Rumelhart, J.L. McClelland and PDP Research Group (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition Vol. 1 (pp. 318-362). Cambridge: MIT Press.

Wang, Zeyu & Srinivasan, Ravi. (2015). A review of artificial intelligence based building energy prediction with a focus on ensemble prediction models. Doi: 10.1109/WSC.2015.7408504.

Westphalen, D. (1999). Thermal distribution, auxiliary equipment and ventilation. In A.D. Little (Ed.), Energy Consumption Characteristic of Commercial Building HVAC System (pp. 31-314). United States: National Technical Information Service.

Zainordin, N., Abdullah, S.M. (2012). Users Perception Towards Energy Efficient Building. Faculty of Build Environment, IMPERIA Institute of Technology.

Zeeshan, S. (2014). Case Study Optimization of Energy Management in an Office Building. Mechanical Engineering Department, University of Punjab.


  • There are currently no refbacks.