Nantum control modeled to save 5% to 11% of building energy

NREL's field study for GSA modeled whole-building energy savings of 5% to 11% from Nantum's control of air handlers. COVID-19 rules kept the controls from running, and payback exceeded five years.

  • Not rated an organization

    The savings are modeled because COVID-19 rules kept the optimized schedules from running, and the subscription cost more than the modeled utility savings.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported and intended benefits.
Evidence

foundstudiedreportedclaimed

Only the evaluators support the benefit.

Compared with

Calibrated energy models of the same buildings under their 2019 operation. Assumed without a measurement.

Without the system
11,270 GJ a year (Terminal Annex Federal Building baseline)
With it
10,699 GJ a year with the software's schedules
The system’s part
Not isolated. NREL modeled each building with and without the schedules that the software would have set, because COVID-19 rules kept them from running. No measured comparison is reported. NREL states that the platform used machine learning and thermal modeling.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Carbon Emissions
System
Nantum energy management information system with automated system optimization
Made by
Prescriptive Data
Used by
U.S. General Services Administration (four federal buildings)
Where
Texas, Maryland and Washington, D.C., United States
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Controlling Machines and Processes, Estimating the Quantifiable Characteristics of Products, Events, or Information
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Evaluation report, by an evaluator that the makers or users commissioned.

    Pachuta S, Dean J, Kandt A, Nguyen Cu K. Field Validation of a Building Operating System Platform. National Renewable Energy Laboratory for the U.S. General Services Administration and the U.S. Department of Energy, NREL/TP-5R00-83236, August 2022. Executive summary and Table 1. GSA, the deployer, funded the work with DOE.

    In the modeled energy savings performance objective, the whole-building energy savings from the baseline ranged from 5% at the Terminal Annex Federal Building to 11% at the Austin Courthouse.

Details

AI system

Workflow

Occupancy counters at building entrances fed occupancy data to the platform. Machine learning algorithms set optimum start times and ramped air handling units down at lunchtime and at the end of the day.

Follow-up

Conditions for replication

Building rules allow the optimized start and ramp-down schedules to run. Utility rates are high enough for the savings to cover the subscription.

Entry details

Sector

Building energy management.

Purpose

Prescriptive Data built Nantum to optimize building operations by setting air handler schedules through the building automation system with machine learning.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Nantum control modeled to save 5% to 11% of building energy (AIBD-0896). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0896.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions