Case Study — Commercial Office

Chiller Plant Optimization at 400 George Street, Sydney

AI-driven chiller sequencing and condenser water optimization delivered verified energy savings across a 51,034 m² premium-grade commercial tower in Sydney's CBD.

Location Sydney CBD, Australia
Sector Commercial Office
Plant Capacity 7,480 kWr
Implementation March 2023
10.4%
Annual Energy
Savings
118.4
tCO₂ Reduced
Per Year
$23,680
Annual OPEX
Reduction
7,480
kWr Plant
Capacity

Inefficient Chiller Sequencing in a High-Load Commercial Tower

400 George Street is a 51,034 m² premium-grade office tower in Sydney's CBD operating a 7,480 kWr central chiller plant. The facility's existing building management system (BMS) relied on fixed set-point controls that could not adapt to dynamic load conditions, weather variations, or partial-load operation.

The result was systematic over-cooling, sub-optimal chiller staging, and condenser water temperatures that did not track ambient conditions — all driving avoidable energy spend and unnecessary carbon emissions across the portfolio.

The plant was consuming significantly more energy than required to meet the same cooling demand — a common outcome of static set-point controls in large commercial HVAC systems.

Asset Overview

Building Type Premium-grade commercial office tower
Total Area 51,034 m²
Location Sydney CBD, New South Wales
Chiller Plant Capacity 7,480 kWr
BMS Integration March 2023
M&V Period April 2023 – March 2024
Data Source Building Data Warehouse + FM Team

AI Optimization Without Capital Expenditure

Exergenics deployed its AI Digital Twin platform to model the full chiller plant, identify the optimal operating envelope, and push real-time control signals directly into the existing BMS — with no hardware changes and zero operational disruption.

1

Digital Twin Modelling

Exergenics built a high-fidelity AI model of the chiller plant using 12+ months of historical BMS and energy data. The model captures load profiles, ambient conditions, and equipment performance curves to establish a precise energy baseline.

2

Optimal Set-Point Generation

Machine learning algorithms continuously compute optimal chiller staging sequences, condenser water temperature set-points, and chilled water differential pressure targets — adapting in real time to occupancy, weather, and load demand.

3

BMS Integration & Verification

Control signals were written directly into the existing BMS in March 2023, enabling autonomous operation. A full 12-month IPMVP-aligned M&V period confirmed savings against the independently verified baseline, with a final report issued March 2024.

Independently Verified Performance Outcomes

Following a full 12-month measurement and verification period conducted in accordance with IPMVP principles, the following savings were independently confirmed.

Outcome Verified Result
Annual Energy Savings 10.4% reduction in chiller plant energy consumption
Carbon Reduction 118.4 tCO₂ per annum
OPEX Reduction $23,680 per annum
Plant Capacity 7,480 kWr
M&V Baseline April 2023 (Preliminary) — March 2024 (Final)
Data Sources Building Data Warehouse, FM Team records
Implementation Date March 2023
Capital Expenditure $0 — software-only deployment

Achieve Similar Results at Your Facility

Exergenics delivers verified energy savings for commercial buildings, hospitals, airports, and industrial facilities — with no capital expenditure required.