PFI-TT: Smart Climate Control in Shared Workspaces for More Personalization and Efficiency

这个PFI项目的更广泛的影响/商业潜力是在建筑运营中实现显著的节能，并为居住者创造更舒适和个性化的工作环境。建筑物的节能措施不仅提供了一种降低能源相关成本的手段，而且还提供了减少温室气体排放的巨大机会。此外，该项目旨在开发和评估的技术还可以在共享空间中为人类居住者创造更加个性化的工作空间，从而在室内共享工作场所中提高员工的健康和生产力。该项目的教育和推广目标将通过对一名研究生研究员进行跨学科培训和让本科生参与在RPI的一个智能会议室设施内对蜜蜂系统进行实验评价来加强。项目团队将积极与工业合作伙伴和潜在客户接触，以最大限度地发挥其商业化潜力。我们认为，拟议中的技术在智能建筑、物联网和人工智能等新兴领域具有相当大的未来潜力，可以创造新的就业机会。拟议的项目旨在为共享办公空间中的异构HVAC元件开发数据驱动的学习和集成控制解决方案，旨在为居住者提供更个性化的热环境，并最大限度地减少整体能源使用。即使当前暖通空调系统的运行成本很高，最近的几项研究也强调了居住者对工作场所热环境的不满。该项目旨在通过综合应用i)室内环境的数据驱动学习，以及ii)集成控制这种共享办公空间中通常存在的异构HVAC元素来解决这一问题。首先，它将利用物理环境复杂时空动态的数据驱动建模，以及可用控制与环境变量之间的依赖关系。其次，它将利用数据驱动模型对与空间相关的异质暖通空调元件进行综合控制，以达到使用者所期望的不同空间温度。该项目的产品将是一个软件原型，将与传感器和物联网设备以及联网的暖通空调元件一起运行。将对这种集成的HVAC控制技术在智能会议室中的技术性能和商业可行性进行评估。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this PFI project is in attaining significant energy savings in building operations, and in creating more comfortable and personalized work environments for its occupants. Energy efficiency measures in the buildings not only provides a means to reduce energy related costs, it also provides tremendous opportunity to reduce greenhouse gas emissions. Further, the technology that this project aims to develop and evaluate can also create a more personalized workspace for human occupants in a shared space, leading to better wellness and increased productivity of employees in indoor shared workplaces. The education and outreach goals of the project will be enhanced through cross-disciplinary training of a graduate student researcher, and involvement of undergraduate students in the experimental evaluation of the BEES system in a Smart Conference Room facility at RPI. The project team will actively engage with industrial partners and potential clients towards maximizing its commercialization potential. We believe that the proposed technology has considerable future potential for creating new jobs in emerging areas such as Smart Buildings, Internet-of-Things, and Artificial Intelligence.The proposed project seeks to develop a data-driven learning and integrated control solution for heterogeneous HVAC elements in shared office spaces, with the aim of providing more personalized thermal environments to occupants and minimizing overall energy usage. Even with the high cost of operating the current HVAC systems, occupant dissatisfaction with thermal environments in workplaces have been highlighted by several recent studies. This project seeks to address this issue through the integrated application of i) data-driven learning of the indoor environment, and ii) integrated control of heterogeneous HVAC elements that typically exist in such shared office spaces. Firstly, it will utilize data driven modeling of complex spatiotemporal dynamics of the physical environment, and the dependency between the controls available and the environmental variables. Secondly, it will utilize the data-driven model towards integrated control of the heterogeneous HVAC elements associated with the space to attain differentiated temperatures across the space as desired by the occupants. The product of this project will be a software prototype that will operate in conjunction of sensor and IoT devices, and networked HVAC elements. This integrated HVAC control technology will be evaluated for technical performance and commercial viability in a smart conference room.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.