Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Summary
In the US, commercial buildings use approximately 18 % of primary energy and 35 % of electricity at a cost of around $190 billion. Approximately 35-40 % of that energy is used for the operation of heating, ventilation, and air conditioning (HVAC) equipment. The HVAC industry is also facing a workforce shortage that makes it more difficult to keep up with demand for the maintenance and repair of HVAC systems. Artificial intelligence (AI) is being used to improve the operation of buildings, but challenges to widespread application exist. The challenges include the cost of implementation, a lack of trust, and the lack of building automation systems (BAS) in most commercial buildings in the US. While BAS exist in 60 % of commercial buildings over 4600 m2 (50,000 ft2), only 13 % of smaller commercial buildings have a BAS. The incorporation of AI to reduce operating costs and mitigate the impact of workforce shortages is, therefore, limited. The focus of this project is to demonstrate, develop, and evaluate advanced control approaches for applications in commercial buildings in the US. The results will be shared with the public via publications, software shared on GitHub, and publicly available datasets; laboratory facilities are also available for collaborative research.
Description
Objective
Demonstrate the feasibility of practical AI control techniques for reducing the energy costs of operating HVAC systems in commercial buildings and create a research infrastructure, the Intelligent Building Agents Laboratory (IBAL) and Virtual Cybernetic Building Testbed (VCBT), suitable for ongoing demonstration, development, and evaluation of advanced AI technologies.
Technical Idea
NIST is investigating intelligent agents as a means to make more intelligent control decisions, automatically find and diagnose faults, and allow existing staff to do their jobs more effectively. Intelligent agents are an AI-based approach that can learn the performance and status of the systems and equipment they monitor and can communicate and collaborate with other agents to achieve a common goal, such as minimizing the cost of operations, maximizing occupant comfort, identifying and diagnosing problems, supporting grid flexibility, etc. Intelligent agents can be deployed in a distributed manner, which will decrease the computational requirements of the system. This work requires simulation and prototyping tools for rapid testing of AI approaches as well as a laboratory facility where promising approaches are tested.
Research Plan
The AI-Optimized Building Controls project has two primary components: 1) the development and evaluation of AI-based control algorithms for HVAC operations and 2) support for research efforts that require access to real HVAC systems or controllers.
The Intelligent Building Agent Simulation (IBASIM) program will be used to quickly test and revise new and existing control algorithms and examine their performance under different scenarios, all while comparing them to baseline controllers. IBASIM is a simulation platform that includes a validated and calibrated simulation of the IBAL and a virtual building model. One baseline gaining popularity in industry is ASHRAE Guideline 36, which defines high performance sequences of operation and therefore is an appropriate state-of-the-art baseline. As with all simulations, IBASIM does not capture all of the dynamic, transient, and stochastic behavior of real equipment, so the most promising algorithms will be tested in the IBAL to determine how well they perform in a real system.
Algorithms will be refined based on considerations including the cost of implementing an approach and the savings realized from operating the system more efficiently. In addition, the computational efficiency will be evaluated in order to understand what type of platform (workstation, edge computing, cloud computing, local controller, etc.) is required to run an algorithm.
The IBAL will be used to test algorithms that will enhance the reliability of HVAC systems and in support of the development of a semantic framework for the interoperability of building systems. It provides a flexible platform on which ideas can be tested under repeatable conditions before they are deployed in larger, more complex commercial buildings. Additional opportunities for collaborations that support American commerce continue to be explored.
Major Accomplishments
- The Intelligent Building Agents Laboratory (IBAL) is a unique, flexible laboratory facility consisting of a mixed system of chillers, thermal energy storage, and air distribution components capable of supporting building system optimization research under reproducible operating conditions.
- Over 100, 14-hour tests were completed for the DOE-sponsored Hardware-in-the-loop Load Flexibility Test project and the data are available at https://data.nist.gov/od/id/mds2-3058.
- The IBAL was connected to the Virtual Cybernetic Building Testbed (VCBT), a platform where commercial HVAC control hardware and software are combined with a simulated building to evaluate commercial control systems. The connection between these two labs creates a platform to test the impact of different commercially available or newly developed control algorithms on the performance of HVAC systems.
- Test scripts for ASHRAE Guideline 36 sequences have been developed for the Functional Performance Testing Module (FPTM), which confirms whether a control sequence conforms to a specified standard.