facil.ai / California State University Dominquez Hills

Project Overview

The facility management team at California State University Dominguez Hills (CSUDH) is driven by a core commitment to continually reduce campus energy usage through modern technology. To this end, they have partnered with facil.ai to improve their chiller performance.

Before facil.ai’s involvement, the three chillers operating in the CSUDH central plant were achieving roughly 0.7 kW/ton energy efficiency. After a two-week ramp-up period for facil.ai, CSUDH started consistently seeing chiller energy efficiency of approximately 0.3 kW/ton, while improving zone temperature comfort in the spaces and equipment served by the chillers.

Nine months later, the chillers are performing better than imagined at record lows of 0.19 kW/ton (almost 20 Coefficient of performance). These results happened while Kenny Seeton, the Director of Central Plant Operations at CSUDH was on vacation, because facil.ai runs quietly in the background with little to no facility intervention required.

For reference, ASHRAE 90.1 standards define “best performance” at 0.45 kW/ton --- beyond that was previously unheard of.

Project Scope

The facil.ai AI Optimization (Advanced Supervisory Control) solution was deployed at the CSUDH campus in DEC 2023.

The Central Plant contains three, one-thousand ton, JCI/York YMC2 Electric, water-cooled chillers, four Towertech cooling towers, each with eight cells of variable-speed fans, associated pumps, valves, and other supporting equipment. The central plant is controlled by the Johnson Controls Inc. Metasys Building Management System (BMS). One dedicated Network Supervisory Master (NAE4) supervises and controls the central plant/Chillers.

The facil.ai AI Optimization solution was deployed using a software interface gateway running on an existing server at the campus. There was no additional hardware installed by facil.ai. The points in the JCI NAE were automatically discovered, classified and tagged by the facil.ai interface. The first AI application implemented was the condenser water temperature reset process. Typically, this is hard-coded in the BMS as outside air wet bulb temperature + 5 degrees F. The AI applications enabled what facil.ai refers to as Adaptive and Autonomous "AI Experimentation Learning".

Initially, the system starts in "AI Experimentation" mode. This is the first step, where the AI agent safely experiments with the various settings in the central plant and learns over time how best to dynamically configure and adjust the system precisely to increase energy efficiency. Within a couple of weeks of training, the AI agent had learned how to run the CP much better, resulting in a 19.5% energy efficiency gain. (From 0.72 kW/ton down to 0.58 kW/ton).

Eventually, the AI and Machine Learning solution increased the energy efficiency of the central plant/chillers by fifty percent (50%)! The kW/ton reading went as low as 0.36 kW/ton. This reduction continued through the peak summer-time operation as well, which was unexpected. 

It is significant to note that although the energy use was reduced by 50%, the output (production) of the chillers was increased by 30-40%. The AI-enabled the 1,000-ton chiller to put out 1,300 to 1,4000 tons of cooling (that’s an additional 300-400 tons over the rated cooling capacity).

‍Why It's Important

There is generally a distrust of true AI capabilities in facility operations. But examples like this prove it can achieve significant energy-saving results.

The facil.ai team prides itself on questioning the status quo.

The Nexus Labs audience is full of FM rebels just like facil.ai, and facil.ai aims to arm them with information to spread the word that technology isn't hard to use, it isn't scary, it doesn't "break your system," and it most certainly is not going away.

The future of buildings is technology.

The Future

Now that the condenser water temperature (and flow) has been optimized, the next step is to address the chilled water supply temperature control. After that, facil.ai will move to the Air Handling Units (AHUs) distributed throughout the campus. 

CSUDH also has one of the largest "Heat Pump" installations in the United States. facil.ai will deploy AI-agents to optimize the run-time efficiency of those units, plus the boilers and other HVAC/mechanical equipment on the campus.

‍
Learn more about facil.ai.