Search

Among the various factors that affect building performance, occupant behavior (OB) has received more and more attention and has become a research hotspot in building design and operation in recent years. However, due to the remarkable randomness and diversity of OB in buildings, it is difficult to accurately describe its characteristics using a fixed schedule, which is a normal approach of most energy simulation tools. DeST, a whole building energy simulation tool offers the function of stochastic OB simulation so that the simulation results can be more in line with the actual situation. In the newly released DeST 3.0, the OB modules are developed based on the actual observed OB data and are divided into two parts: occupancy and occupant action modules. The occupancy module is based on the Markov chain, which simulates the occupant movements among the spaces inside and outside the buildings. The occupant action modules are proposed with an environment and event-driven stochastic infrastructure based on a three-parameter Weibull distribution, such as occupant shading, window, and air-conditioning (AC)/heating control behavior modules. This paper presents the OB modules development for coupled simulation in DeST 3.0 and discusses the effects of integrated simulation of occupant behavior on building energy consumption. Firstly, an overview of the current modelling efforts of OB is given, from the trend to the existing foundation. Secondly, the development of OB modules for coupled simulation in DeST 3.0 is introduced in-depth, including co-simulation of AC/heating control behavior, window behavior and shading behavior. Lastly, two case studies that realize coupled simulation using the developed modules are shown, one is the comparison between existing occupancy schedules from GB standards and the developed occupancy simulation, and the other is the comparison between the result of simulating with or without using AC/heating control behavior modules in two bedrooms of the residential building. [ABSTRACT FROM AUTHOR]

In recent years, a large number of building energy consumption prediction models, with various intended uses, have been proposed. The majority of these models have either taken a data-driven or a physical modeling approach, with each approach having its own strengths and limitations. Towards leveraging the strengths and reducing the limitations of each approach for improved prediction performance, this paper presents a hybrid machine-learning approach for occupant-behavior-sensitive energy consumption prediction. The proposed approach is composed of three constituent models: (1) a machine-learning model that learns the impact of outdoor weather conditions from simulation-generated data, (2) a machine-learning model that learns the impact of occupant behavior from real data, and (3) an ensemble model that predicts cooling energy consumption based on the outputs of the first two models. The simulation-generated data were created through simulating a set of reference buildings in EnergyPlus. The real data were collected from an office building in Pennsylvania. The proposed hybrid model was validated on an unseen real dataset. It achieved 0.73 kWh RMSE and 9.07% CV in hourly cooling energy consumption prediction, which indicates that the proposed approach is promising. [ABSTRACT FROM AUTHOR]