¹û¶³´«Ã½

In the evolving field of modern open offices, control over building facilities such as shading, lighting, heating, ventilation, and air conditioning systems is essential for creating sustainable, productive, and comfortable work environments. Decreased sensor costs have made them more accessible, allowing for real-time data collection on temperature, humidity, lighting, occupancy, and energy use. This data collection supports the development of data-driven control algorithms that adapt the indoor environment to specific needs, balancing reduced energy and operational costs with increased comfort and productivity.

Next Sense, an Amsterdam-based tech firm, focuses on decarbonizing real estate. It leverages data-driven insights and artificial intelligence to meet environmental sustainability goals. The firm has developed the Next Sense platform, an intelligent system for building monitoring and control. This platform integrates sensors and actuators with a digital twin, providing a comprehensive overview of building performance. It aims to enhance productivity and comfort while minimizing energy consumption. It supports the EU's shift towards a net-zero carbon economy through compliance with the Corporate Sustainability Reporting Directive (CSRD) and the Sustainable Finance Disclosure Regulation (SFDR).

The project associated with this platform is split into two phases:

1. Simulation Component: This phase evaluates existing and future control algorithms, assessing their impact on energy use and users’ comfort. It can also identify discrepancies between actual and simulated energy data, clarifying areas for potential energy savings. Furthermore, It also generates synthetic datasets for any data-driven model development.
2. Control Component: This involves developing model-based controllers for lighting systems and the timing of heating and cooling systems.

The project's outputs include a simulation tool using EnergyPlus and Radiance that can be integrated into a building's digital twin. Additionally, a tool has been developed to train machine learning and resistance-capacitor models, which are essential for developing control algorithms for lighting systems and optimizing the operation of heating and cooling systems.

This research offers a scalable, efficient solution for real estate developers and managers to meet energy and emission standards. Accurate simulation can identify and address energy performance gaps, and effective control can reduce consumption and operational costs while enhancing occupant health and productivity.