Sydney Airport International Terminal T1 Chilled Water Plant Optimisation — 34% Operation Energy Reduction Recognised by AIRAH and CIBSE Awards

Overview

The Chilled Water Plant Optimisation project at Sydney Airport involved using the latest machine learning and simulation techniques to improve the control logic of the Terminal 1 chiller plant and secondary pumping system. The project achieved a 33.4% increase in efficiency, reducing annual energy consumption by 1,742,000 kWh and cutting greenhouse gas (GHG) emissions by 1,377 tCO2.

The project was undertaken in a close partnership between A.G. Coombs Advisory and Exergenics, working with the Sydney Airport team to achieve their ambitious sustainability targets.

The Sydney Airport Chilled Water Plant Optimisation project by A.G. Coombs Advisory and Exergenics exemplifies excellence in innovation through the utilisation and combination of novel techniques in HVAC including machine learning, model predictive control, evolutionary optimisation algorithms and
a purpose-built measurement and verification methodology specific for the chilled water plant.

The project’s success is attributed to its innovative approach that required no equipment upgrades or additional hardware, minimised disruption and delivered rapid implementation and results.

This methodology enabled the development of a ‘generative controls’ approach to the optimisation of this complex plant, whereby efficiency gains that would take years of labor-intensive system tuning to achieve were realised in just 3 months.

Conventional system tuning has typically relied on manufacturers’ data as a proxy for the optimal operational performance of equipment within a chilled water plant system.

This project advances that approach significantly by leveraging the latest machine learning tools to determine the operational efficiency profiles of chillers, pumps and cooling towers which change over time with wear and tear.

As a result, the accuracy of the final control logic that was implemented on-site using this approach is optimal for how the equipment is performing in the field, rather than how it was designed to perform.

Project Drivers

A highly collaborative team approach by Exergenics and A.G. Coombs enabled Sydney Airport to achieve their primary objective of the project which was to enhance energy efficiency and reduce greenhouse gas emissions from the chilled water plant, which is critical for maintaining optimal temperature conditions for millions of passengers annually.

The project aimed to achieve these goals without significant capital expenditure or disruption to airport operations.

Aligning with Sydney Airport’s strict cybersecurity standards, the initiative sought to leverage existing Building Management System (BMS) data in a fully air-gapped fashion and benefit from advanced machine learning algorithms to deliver substantial energy savings and emissions reductions. The optimisation programme was designed to be seamless, cost-effective, and scalable, ensuring that it could be implemented quickly and provide immediate benefits.

The project’s drivers included the need for cost savings, improved operational efficiency, and a commitment to environmental stewardship, all of which were successfully addressed.

Technically, the energy savings were achieved through the implementation of the following optimised controls:

• Secondary pump staging and flow reset
• Update to chiller sequencing strategy
• Update to chiller stage up & down demand setpoints
• Implementation of a stage-based dynamic condenser water temperature reset algorithm.

Project Delivery

The project was led by A.G. Coombs Advisory, with Exergenics providing plant simulation and optimisation and the incumbent Johnson Controls implementing the optimised controls into the existing system.

It kicked off with a comprehensive data collection and validation phase, utilising the airport’s existing data collection and storage ensuring no additional cost. The machine learning engine analysed the historical temperature, pressure, energy and flow data from the existing BMS to model and simulate plant equipment performance and system dynamics under a range of conditions.

Once the model accuracy was validated with sufficient simulation accuracy and energy-mass balance compared with historical data, the project team met to identify which controls would be optimised and then the optimisation loop determined the optimal setpoints and reset algorithms for the site given the equipment performance and load profiles.

Key challenges included integrating the optimisation with the existing BMS and ensuring minimal disruption to airport operations. These were addressed by adopting a software-based approach that required no additional hardware.

The project team collaborated closely with Sydney Airport’s facilities management team to ensure smooth implementation and continuous performance monitoring.

The use of a cloud-based model facilitated seamless data integration, while regular stakeholder engagement ensured that the project met all operational and sustainability objectives.

Importantly once operational stability was achieved, the Measurement & Verification (M&V) of energy savings was continuously monitored throughout the 12-month project duration.

Project Outcomes and Benefits

The project achieved a 33.4% increase in efficiency, reducing energy consumption by 890,094 kWh and cutting GHG emissions by 704 tCO2 over the first nine months.

The overall annual project reduction in energy consumption was 1,742,000 kWh and attributable GHG emissions reduced by 1,377 tCO2.

These benefits were measured through rigorous data analysis and verified by both preliminary and final Measurement and Verification (M&V) processes.
All M&V was conducted following the International Performance Measurement and Verification Protocol Option B (Retrofit Isolation).

The project showcases the enormous opportunity for energy savings in existing HVAC systems that can be optimised for better performance and reduced environmental impact using advanced data analytics, setting a new standard for innovation in the industry.

The substantial improvements in efficiency and cost savings underline the effectiveness and potential of such initiatives to drive significant environmental and financial benefits across the sector.

The project also provides a model for other facilities looking to achieve similar goals, demonstrating the scalability and adaptability of the methodology.
The accuracy that can be accomplished when utilising real-world data to train simulation models and the benefits of evolutionary optimisation algorithms when dealing with complex optimisation problems that are highly dimensional, non-linear and discontinuous, as is the case with chilled water plant, was demonstrated with the quantum of savings that were achieved on an already highly efficient plant with an operating COP of 6.25 prior to the optimisation program.

Regular updates were provided to the Sydney Airport stakeholders to be utilised in wider decarbonisation reporting and for the assessment of the financial performance of the project, which was estimated to have a 2-year payback period but achieved a 12-month payback.