Building-level occupancy data to improve ARIMA-based electricity use forecasts

Abstract

The material in this document is covered by the provisions of the Copyright Act, by Canadian laws, policies, regulations and international agreements. Such provisions serve to identify the information source and, in specific instances, to prohibit reproduction of materials without written permission. For more information visit http://laws.justice.gc.ca/en/showtdm/cs/C-42Les renseignements dans ce document sont protégés par la Loi sur le droit d'auteur, par les lois, les politiques et les règlements du Canada et des accords internationaux. Ces dispositions permettent d'identifier la source de l'information et, dans certains cas, d'interdire la copie de documents sans permission écrite. Pour obtenir de plus amples renseignements : http://lois.justice.gc.ca/fr/showtdm/cs/C-42 benjamin.birt@nrc-cnrc.gc.ca ABSTRACTThe 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.

Energy intelligent buildings based on user activity: A survey

“…At the same time, other works tackle the issue of one of the three subsystems. While [52,35], [55,47,36,56,42], and [60] choose to deal with HVAC subsystem, [24,63,62,48], and [59] focus on light subsystem. Last, [58,27,31,23,45,32,28], and [49] save energy for plug loads subsystem.…”

“…To gather data related to total building occupancy, they install wireless sensors in a three-storey building in eastern Ontario, Canada comprising laboratories and 81 individual work spaces [56].…”

“…On the other hand, seven of the works, as illustrated in Fig. 5, namely, [40,73,56,74,61,64], and [49] deal with activity or behaviour patterns recognition for energy savings. Though, they have not shown any evaluation of potential energy savings.…”

“…Instead of using occupant's preference, Newsham and Benjamin [56] use the total number of building occupants 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 total number of building occupants is also used in [75] to apportion the total energy consumption of a building or organisation to individual users.…”

Building Energy Consumption Prediction: An Extreme Deep Learning Approach

“…In [9], Kimbara et al developed an autoregressive integrated moving average (ARIMA) model to implement online building energy consumption prediction. In [10], the ARIMA with external inputs (ARIMAX) model was applied to predict the power demand of the buildings. In [11], a regression-based method-conditional demand analysis (CDA)-was used for predicting the building energy consumption.…”