Building Energy Consumption On-line Forecasting Using System Identification and Data Fusion

Model based control has been proven to have significant building energy saving potentials through operation optimization. Accurate and computationally efficient, and costeffective building energy model are essential for model based control. Existing studies in this area have mostly been focusing on reducing computation burden using simplified physics based modeling approach. However, creating and identification the simplified physics based model is often challenging and requires significant engineering efforts. Therefore, this study proposes a novel methodology to develop building energy estimation models for on-line building control and optimization using an integrated system identification and data fusion approach. System identification model has been developed based on frequency domain spectral density analysis. Eigensystem realization algorithm is used to generate the state space model from the Markov parameters. Kalman filter based data fusion technique has also been implemented to improve the accuracy and robustness of the model by incorporating with real measurements. A systematic analysis of system structure, system excitation selection as well as data fusion implementation is also demonstrated. The developed strategies are evaluated using a simulated testing building (simulated in EnergyPlus environment). The overall building energy estimation accuracy from this proposed model can reach to above 95% within 2 minutes calculation time, when compared against detailed physics based simulation results from the EnergyPlus model. The electricity consumption of the US grew 1.7% annually from 1996 to 2006, and the total growth will reach 26% until 2030 [1]. Among that consumption, buildings are responsible for over 70% of electricity consumption in the US [2]. Studies have shown that most of the commercial and residential buildings have equipment and operational problems that reduce the comfort and waste more energy. Around 4% to 20% of energy used in HVAC and lighting system [3] was wasted due to equipment and operation problems. Moreover, it is estimated by the National Energy Technology Laboratory that more than one-fourth of the 713 GW of U.S. electricity demand in 2010 could be dispatchable if only buildings could respond to that dispatch through advanced building energy control and operation strategies and smart grid infrastructure [4]. Therefore the quality of building control and operation is significant economically and environmentally. The quality of building control and operation is significantly affected by the building energy forecasting models. How to develop accurate, robust, and cost-effective building energy forecasting models is the focus of this study. One of the most comprehensive white box model in the existing building energy modeling tools is EnergyPlus, which is a whole building energy simulation program that engineers, architects, and researchers use to model energy and water use in buildings [5]. Moreover, In order to apply EnergyPlus in modeled based building control and operation, a Building Controls Virtual Test Bed (BCVTB) was developed by Wetter and Haves to link the building models (EnergyPlus) with real control systems [6]. BCVTB can be sued as a middleware tool that allows to data sharing among different simulation programs, such as EnergyPlus, Matlab, Modelica, and etc., for distributed simulation. Therefore, through this test bed different user defined building control and optimization strategies can be applied into different building simulation models. For example, Ma et al. proposed and demonstrated an economic MPC technique to reduce energy and demand cost using EnergyPlus and BCVTB [7]. Even though these elaborate simulation tools are very effective and accurate, they require detailed information and parameters of buildings, energy system and outside weather conditions. Identifying these parameters,