IoT-Enabled Automatic Synthesis of Distributed Feedback Control Schemes in Smart Buildings

There is currently a rapid evolution of technologies enabling the "Internet-of-Things" paradigm, which leads to the design of systems with augmented sensing, analysis, and actuation capabilities. The intelligent control research community is beginning to recognize the challenge of designing flexible and adaptable control systems that will take advantage of the online evolution of the number and types of "things" in a large-scale system. Responding to this challenge, in a previous article, we designed and presented a semantically enhanced control system supervisor that integrates a knowledge graph and deductive inference capabilities, to achieve the online (re)configuration of feedback control schemes. In this article, we show that by exploiting the capabilities of this supervisor, we facilitate the automatic synthesis and plugging of model-based controllers for the space heating problem in multizone buildings. The supervisor retrieves stored knowledge about the building and the available control system components and uses it to configure online a scheme of distributed feedback controllers, one per building zone. The controllers are designed to utilize information online and optimally allocate the control signal to multiple heating devices in each building zone.