Using Digital Twins for Effective Energy Retrofitting and Performance Optimization of Buildings

The current approach to upgrading building and facilities usually entails retrofitting each building separately without carrying out a thorough assessment. This method uses generic data inputs and static tools with broad assumptions. Because of this, each year only 1% of all the building stock is upgraded with energy-efficient features. To overcome this challenge, it is imperative to embrace innovative techniques and contemporary tools that can streamline and accelerate the process of energy retrofits in existing buildings. With an emphasis on non-residential existing buildings, this article introduces a novel platform based on the idea of digital twins that offers methodical assistance for building energy retrofit decision-making and energy systems performance optimization based on data collected from various meters and sensors. The digital twin leverages operational data collected from buildings and employs advanced machine learning methods to create adaptable data-based models with the goal of enhancing energy efficiency. Furthermore, the solution uses clamp IoT sensors as means to collect data on system level, resulting in an automated and adaptable approach to energy retrofits. The use of the data-driven energy modeling approach to deliver building services is demonstrated with preliminary investigations targeting continuous commissioning and retrofit scenarios evaluation. Owners will expect increased comfort and energy efficiency in their upgraded buildings with the application of the suggested solution. Also, a monitoring system that facilitates the methodical retro-commissioning of buildings will be provided for facility managers. Consultants and urban planners will possess a scalable instrument that will broaden effective and systematic retrofit projects.