Minimising the Deviation between Predicted and Actual Building Performance via Use of Neural Networks and BIM

Abstract

Building energy performance tools are widely used to simulate the expected energy consumption of a given building during the operation phase of its life cycle. Deviations between predicted and actual energy consumptions have however been reported as a major limiting factor to the tools adopted in the literature. A significant reason highlighted as greatly influencing the difference in energy performance is related to the occupant behaviour of the building. To enhance the effectiveness of building energy performance tools, this study proposes a method which integrates Building Information Modelling (BIM) with artificial neural network model for limiting the deviation between predicted and actual energy consumption rates. Through training a deep neural network for predicting occupant behaviour that reflects the actual performance of the building under examination, accurate BIM representations are produced which are validated via energy simulations. The proposed method is applied to a realistic case study, which highlights significant improvements when contrasted with a static simulation that does not account for changes in occupant behaviour.

Influence of Occupant Behavior for Building Energy Conservation: A Systematic Review Study of Diverse Modeling and Simulation Approach

“…Moreover, from a detailed survey, one review [41] study offers model categorization in terms of whether the developed model is based on data, and therefore the authors categorized wide-ranging behavior models into data-driven and simulation-based approaches. In brief, modeling using data-driven methods involves an extensive amount of data to build a statistical model for selected occupant behaviors, although simulation-based energy models depend on empirical or pre-defined rules that control the occupant behavior configuration [44,45]. A comprehensive list of quantitative modeling for this review study is shown in Table 1.…”

Towards an Interoperable Approach for Modelling and Managing Smart Building Data: The Case of the CESI Smart Building Demonstrator

“…This process involves a single simulation for all of a home's occupants (instead of a separate one for each user profile), thus minimising HVAC (heating, ventilation and air conditioning) consumption prediction errors. Processes that use ANNs are 72% more accurate than traditional static methods [29]. The forecasting process discussed in [29] was based on three steps: (1) input data related to the building and users collected from IoT sensors was recorded in the BIM model, (2) ANN-based AI statistical data was used to perform a simulation, and (3) the results were compared to reality to obtain new input data if those results were positive.…”

“…Processes that use ANNs are 72% more accurate than traditional static methods [29]. The forecasting process discussed in [29] was based on three steps: (1) input data related to the building and users collected from IoT sensors was recorded in the BIM model, (2) ANN-based AI statistical data was used to perform a simulation, and (3) the results were compared to reality to obtain new input data if those results were positive. Furthermore, existing monitoring approaches are usually simplistic and inappropriate in the way that they try to define then regulate a building's cooling and/or heating based on a fixed indoor temperature.…”

A review of the Digital Twin technology for fault detection in buildings

“…In order to construct the next generation of occupancy models that can reliably anticipate occupants' behavior, new DL approaches are being employed. Hammad (Hammad, 2019) presented a strategy for reducing the difference between expected and real energy consumption rates by merging BIM with an ANN model. A deep neural network training to predict occupant behavior results in accurate BIM representations, further confirmed by energy simulations.…”