Remote Monitoring Integrated State Variables for AR Model Prediction of Daily Total Building Air-Conditioning Power Consumption

It is extremely difficult to predict daily accumulated power consumption of the entire building air-conditioning facilities because of a huge number of variables. We propose new integrated state variables, i.e. the daily operation amount and the daily operation-capacity-weighted average set temperature. Taking advantage of a remote monitoring technology, time series data of the integrated state variables were collected and an autoregressive (AR) model prediction for the daily total power consumption has been tried. (C) 2010 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.