Current research on Digital Twin (DT) is largely focused on the performance of built assets in their operational phases as well as on urban environment. However, Digital Twin has not been given enough attention to construction phases, for which this paper proposes a Digital Twin framework for the construction phase, develops a DT prototype and tests it for the use case of measuring the productivity and monitoring of earthwork operation. The DT framework and its prototype are underpinned by the principles of versatility, scalability, usability and automation to enable the DT to fulfil the requirements of large-sized earthwork projects and the dynamic nature of their operation. Cloud computing and dashboard visualisation were deployed to enable automated and repeatable data pipelines and data analytics at scale and to provide insights in near-real time. The testing of the DT prototype in a motorway project in the Northeast of England successfully demonstrated its ability to produce key insights by using the following approaches: (i) To predict equipment utilisation ratios and productivities; (ii) To detect the percentage of time spent on different tasks (i.e., loading, hauling, dumping, returning or idling), the distance travelled by equipment over time and the speed distribution; and (iii) To visualise certain earthwork operations.

Digital Twins (DTs) of buildings can generate large volumes of dynamic data from various sources (e.g., sensors and IoT devices), enabling real-time representation of physical building states in a digital environment. Although machine learning (ML) techniques are increasingly used to predict building energy consumption from this DT data, existing approaches often lack scalability in handling data growth (data scalability) and/or adapting to evolving data patterns (model scalability). This study aims to address both drawbacks by developing a scalable cloud-based framework for the prediction of the building energy consumption. A key contribution to the field is the inclusion of a “monitoring and maintenance” module, which continuously evaluates model performance and triggers retraining only when needed. This enables timely adaptation of the ML model while avoiding unnecessary retraining and the associated computational costs. The framework was implemented and tested in a case study of a commercial building for 90 days, demonstrating its applicability. In a practical setting, the developed model could detect anomalies in time when the accuracy declined below the set threshold (70%) for five days and prevented unnecessary retraining of ML models. The findings support the feasibility of using cloud-based approaches to implement scalable ML models for energy prediction in buildings.

Data scarcity is one of the major barriers to using Machine Learning (ML) techniques for building energy predictions. Transfer Learning (TL) has proven to be an effective approach to address this issue. However, most TL approaches have not considered scalability, which is an important factor when using Digital Twin (DT) data for predictions. To bridge this gap, this research aims to develop a scalable TL approach for predicting building energy consumption from limited DT data using cloud computing. Two frameworks, using Microsoft Azure and Amazon AWS, are developed and implemented in a case study to demonstrate their applicability and practicality. The findings show that both frameworks possess unique strengths in terms of scalability and improving accuracy. Azure performed better in training time and resource efficiency, while AWS excelled in data preprocessing speed and prediction accuracy. This paper supports researchers and practitioners in developing a scalable model (i.e., cloud-based TL) for predicting building energy consumption with limited DT data. Future research can explore the cost of using cloud platforms for building energy prediction and expand the list of decision factors for platform selection.