Methodology for Commercial Buildings Thermal Loads Predictive Models Based on Simulation Performance

Abstract

Commercial buildings incorporate Building Energy Management Systems (BEMS) to monitor indoor environment conditions as well as controlling Heating Ventilation and Air Conditioning (HVAC) systems. Measurements of temperature, humidity and energy consumption are typically stored within BEMS. These measurements include underlying information regarding building thermal response, which is crucial for the calculation of heating and cooling loads. Forecasting of building thermal loads can be achieved using data records from BEMS. Accurate predictions can be produced when introducing these data records to datamining predictive models. Incomplete datasets are often acquired when extracting data from the BEMS; hence detailed representations of commercial buildings can be implemented using EnergyPlus. For the purposes of the research described in this paper, different types of commercial buildings in various climates are examined to investigate the scalability of the predictive models.

Input variable selection for thermal load predictive models of commercial buildings

“…The methodology developed in the current research is based on the filter method to detect interrelationships between variables in order to select the input variables for predictive models capable of forecasting thermal loads of commercial buildings. This methodology is part of the overall research methodology followed by the authors as previously published in [36]. The process of data analysis consists of the investigation of linear and monotonic correlations, to identify the intra-variable relationships and the relative importance therein.…”

Inverse blackbox modeling of the heating and cooling load in office buildings

“…Heating and cooling load modelling approaches used in the reviewed literature can be categorized in three broad groups: (1) the calibrated building performance simulation (BPS) models that blend an expert's knowledge of building systems and the historical metered load data [4,5], (2) the greybox models that blend a generic simplified representation of a building's physical characteristics and the metered load data [6][7][8], and (3) the blackbox models that attempt to find useful statistical input-output relationships between weather/categorical data and metered load patterns [9][10][11][12][13][14][15][16][17][18][19][20][21][22]. Due to their dependence on an expert's building systems knowledge, the models developed in the first category are outside the scope of this study.…”

“…Blackbox models that predict heating/cooling loads have been built by using different statistical methods: linear regression [14,18,19,21], artificial neural networks [10,12,14,[16][17][18][19][20], support vector machines [9,11,15,16], autoregressive integrated moving average [13], gradient boosting regression [14], random forest regression [14], k-nearest neigbours regression [14], kernel ridge regression [14], Bayesian ridge regression [14], and singular value decomposition [22]. They input weather variables such as outdoor temperature [9-12, 14-16, 18-21], humidity [6, 10-12, 14-16, 18, 19], solar irradiance [11,15,16,[18][19][20], wind speed [14,19,20], precipitation [14], sky clearness [19], and categorical indoor variables such as the state of occupancy [13,14,17,19]. In some cases, synthetically generated data from BPS tools were used in lieu of measured data from real buildings [15,16,18,19].…”

“…They input weather variables such as outdoor temperature [9-12, 14-16, 18-21], humidity [6, 10-12, 14-16, 18, 19], solar irradiance [11,15,16,[18][19][20], wind speed [14,19,20], precipitation [14], sky clearness [19], and categorical indoor variables such as the state of occupancy [13,14,17,19]. In some cases, synthetically generated data from BPS tools were used in lieu of measured data from real buildings [15,16,18,19]. The objective of these models is often to forecast heating/cooling loads over a short time horizon at hourly or subhourly intervals [25].…”

Experimental Study of the Thermo-Mechanical Properties of Building Blocks Used in Hot Desert Arid Climate

“…Due to the design deficiencies in the thermal properties of the outer shell of buildings and the leakage of air to and from the interior atmosphere, most of the electrical energy is consumed by air conditioning systems to treat this deficiency [3]. Therefore, the choice and design of the outer shell in terms of its thermal properties, and the control of air leakage contributed effectively in reducing the consumption of electrical energy without negatively affecting the thermal comfort of building users [4][5][6][7][8]. Also, it is noticeable in the Algerian modern desert buildings, the total dependence on concrete and the using of the bearing elements only (columns -tributaries) in its walls and ceilings [9].…”