ABSTRACT
The energy use of an office building is likely to correlate with the number of occupants, and thus knowing occupancy levels should improve energy use forecasts. To gather data related to total building occupancy, wireless sensors were installed in a three-storey building in eastern Ontario, Canada comprising laboratories and 81 individual work spaces. Contact closure sensors were placed on various doors, PIR motion sensors were placed in the main corridor on each floor, and a carbon-dioxide sensor was positioned in a circulation area. In addition, we collected data on the number of people who had logged in to the network on each day, network activity, electrical energy use (total building, and chilling plant only), and outdoor temperature. We developed an ARIMAX model to forecast the power demand of the building in which a measure of building occupancy was a significant independent variable and increased the model accuracy. The results are promising, and suggest that further work on a larger and more typical office building would be beneficial. If building operators have a tool that can accurately forecast the energy use of their building several hours ahead they can better respond to utility price signals, and play a fuller role in the coming Smart Grid.
- N. Gershenfeld, S. Samouhos, and B. Nordman. Intelligent infrastructure for energy efficiency. Science, pages 1086--1088, February 2010.Google Scholar
- Q. Zhou, S. Wang, and F. Xiao X. Xu. A grey-box model of next-day building thermal load prediction for energy-efficient control. International Journal of Energy Research, 32:1418--1431, December 2008.Google ScholarCross Ref
- A. H. Neto and F. A. S. Fiorellia. Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption. Energy and Buildings, 40:2169--2176, 2008.Google ScholarCross Ref
- A. J. Hoffman. Peak demand control in commercial buildings with target peak adjustment based on load forecasting. In Proceedings of the 1998 IEEE International Conference on Control Applications, volume 2, pages 1292--1296, September 1998.Google ScholarCross Ref
- M. A. Piette, D. S. Watson, N. Motegi, and N. Bourassa. Findings from the 2004 fully automated demand response tests in large facilities. Technical Report LBNL Report Number 58178, 2004. Report for the PIER Demand Response Research Center.Google Scholar
- G. R. Newsham and B. Birt. Demand-responsive lighting: a field study. Leukos, 6(3):203--225, 2010.Google ScholarCross Ref
- D. C. Montgomery, C. L. Jennings, and M. Kulahci. Introduction to Time Series Analysis and Forecasting. John Wiley & Sons, Inc., 2008.Google Scholar
- UC 2010. Notation for ARIMA models. http://www.uc.edu/sashtml/ets/chap30/sect13.htm.Google Scholar
- D. L. Loveday and C. Craggs. Stochastic modelling of temperatures for a full-scale occupied building zone subject to natural random influences. Applied Energy, 45:295--312, 1993.Google ScholarCross Ref
- G. J. Rios-Moreno, M. Trejo-Perea, R. Castaneda-Miranda, V. M. Hernandez-Guzman, and G. Herrera-Ruiz. Modelling temperature in intelligent buildings by means of autoregressive models. Automation in Construction, 16:713--722, 2007.Google ScholarCross Ref
- G. Lowry, F. U. Bianeyin, and N. Shah. Seasonal autoregressive modelling of water and fuel consumptions in buildings. Applied Energy, 84:542--552, 2007.Google ScholarCross Ref
- A. Kimabra, S. Kuroso, R. Endo, K. Kamimura, T. Matsuba, and A. Yamada. On-line prediction for load profile of an air-conditioning system. ASHRAE Transactions, 101(2):198--207, 1995.Google Scholar
- G. R. Newsham and B. Birt. Detecting total building occupancy for more efficient operation. Technical Report RR-304, National Research Council - Institute for Research in Construction, 2010.Google Scholar
- M. Kawashima, C. E. Dorgan, and J. W. Mitchell. Hourly thermal load prediction for the next 24 hours by arima, ewma, lr, and an artificial neural network. ASHRAE Transactions, 101(1):186--200, 1995.Google Scholar
- S. Hay and A. Rice. The case for apportionment. In BuildSys '09: Proceedings of the First ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, pages 13--18, 2009. Google ScholarDigital Library
Index Terms
Building-level occupancy data to improve ARIMA-based electricity use forecasts
Recommendations
Occupancy Detection from Electricity Consumption Data
BuildSys '13: Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient BuildingsDetecting when a household is occupied by its residents is fundamental to enable a number of home automation applications. Current systems for occupancy detection usually require the installation of dedicated sensors, like passive infrared sensors, ...
Estimating Whole Building Occupancy from Transportation Simulations
UrbSys'19: Proceedings of the 1st ACM International Workshop on Urban Building Energy Sensing, Controls, Big Data Analysis, and VisualizationThis paper demonstrates the use of traffic modeling software to estimate the transport of people to-and-from buildings and the whole building occupancy and related building operations. The methods and procedures of the estimation are explained. A ...
Electricity demand forecasting in buildings based on ARIMA and ARX models
IEEA '19: Proceedings of the 8th International Conference on Informatics, Environment, Energy and ApplicationsThe Accuracy of electricity demand forecasting is a key success factor of the organizational operation since energy is the crucial driven force of all activities. As a result, if executives in any organizations can accurately predict the future demand ...
Comments