Building occupancy profiles are critical in thermal and energy simulations. However, determining an accurate occupancy profile is difficult due to its stochastic nature. In most simulations, the occupant activities are usually represented by fixed yearly schedules, which are often derived from guides and other similar sources and may not represent the simulated building accurately. Therefore, an inaccuracy in defining occupancy profiles can be a source of error in building simulations. Over the past few years machine learning has become very popular due to its ability to reveal hidden patterns and relationships between data and this makes it suitable for investigating patterns in occupancy data. This study proposes a novel hybrid model combining the Graph Neural Network and the Long Short-term Memory neural network (LSTM) to predict the occupancy of individual rooms on a typical office floor. The proposed Graph LSTM model can produce high-resolution occupancy profiles of an office that are in good agreement with the reference occupancy profiles of the same office. The reference occupancy profiles for this office were derived from an agent-based model using AnyLogic and were not used in the training of the neural network. The proposed Graph LSTM model outperformed other neural networks tested such as the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU) and LSTM. When Graph LSTM is compared to the other neural networks tested, there is a range of improvement between 13.5 and 14.6% in the index of agreement, 38.3 and 46.8% in mean absolute error and 34.4 and 40.0% in root mean square error, when averaging the differences over the whole office.

Digital Twins (DT), as one of the emerging trends in digitalisation, have attracted a large amount of research in the past few years due to its ability to provide more accurate models and better predictions for various energy-related applications. In the context of demand response (DR), the real-time bidirectional communication characteristic of DT allows for functions such as real-time energy forecast and decision-making aid, which provided high potential in DR applications due to the nature of DR being highly time-sensitive. The objective of this paper is to explore the concept and application of DT in the domain of DR, as there are currently limited numbers of review on this topic. It was identified that most work in this area shows promising results but is still exploratory. The main application of DT in the domain of DR is using DT as an enabling tool by leveraging the real-time and data processing function of DT for monitoring and decision-making, and providing a medium for better visualisation. Future studies can experiment with applying DT frameworks to larger case studies and apply more elaborate DT with higher maturity levels.