# B-SMART: A Reference Architecture for Artificially Intelligent Autonomic Smart Buildings

arXiv: https://arxiv.org/abs/2211.03219 · HTML: https://mlsanity.com/paper/2211.03219/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 46 references that are in the map.
- First posted on arXiv 6 Nov 2022.

## Builds on (most cited first, 1 of 1)

- [A Reference Architecture for Smart and Software-defined Buildings](https://mlsanity.com/paper/1902.09464/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Transfer Learning Approach to Minimize Reinforcement Learning Risks in Energy Optimization for Smart Buildings](https://mlsanity.com/paper/2305.00365/) (2023)

## Abstract (arXiv)

The pervasive application of artificial intelligence and machine learning algorithms is transforming many industries and aspects of the human experience. One very important industry trend is the move to convert existing human dwellings to smart buildings, and to create new smart buildings. Smart buildings aim to mitigate climate change by reducing energy consumption and associated carbon emissions. To accomplish this, they leverage artificial intelligence, big data, and machine learning algorithms to learn and optimize system performance. These fields of research are currently very rapidly evolving and advancing, but there has been very little guidance to help engineers and architects working on smart buildings apply artificial intelligence algorithms and technologies in a systematic and effective manner. In this paper we present B-SMART: the first reference architecture for autonomic smart buildings. B-SMART facilitates the application of artificial intelligence techniques and technologies to smart buildings by decoupling conceptually distinct layers of functionality and organizing them into an autonomic control loop. We also present a case study illustrating how B-SMART can be applied to accelerate the introduction of artificial intelligence into an existing smart building.