IT Science Case Study: Australian Gas Light Gets Its Act Together

Australian Gas Light needed to manage its assets portfolio and cost structure much more effectively. Its data collection and reporting system was slow and paper-driven, and as the company grew, the process became harder to manage.


Here is the latest article in a new eWEEK feature series called IT Science, in which we look at what actually happens at the intersection of new-gen IT and legacy systems.

Unless it’s brand new and right off various assembly lines, servers, storage and networking inside every IT system can be considered “legacy.” This is because the iteration of both hardware and software products is speeding up all the time. It’s not unusual for an app-maker, for example, to update and/or patch for security purposes an application a few times a month, or even a week. Some apps are updated daily! Hardware moves a little slower, but manufacturing cycles are also speeding up.

These articles describe new-gen industry solutions. The idea is to look at real-world examples of how new-gen IT products and services are making a difference in production each day. Most of them are success stories, but there will also be others about projects that blew up. We’ll have IT integrators, system consultants, analysts and other experts helping us with these as needed.

Today’s Topic: Managing the portfolio of Australia’s largest power producer

Name the problem to be solved: Australian Gas Light (AGL) needed to manage its assets portfolio and cost structure much more effectively. Its data collection and reporting system was slow and paper-driven, and as the company grew, the process became harder to manage.

Describe the strategy that went into finding the solution: Australian Gas Light (AGL) is Australia’s oldest and largest power producer and has grown from 300 MW (megawatts) in 2005 to 10,000 MW in 2017 with a growing percentage of wind and solar. Unfortunately, AGL was also “data blind,” said David Bartolo, head of asset performance, who had to rely on print-outs and prepared reports to understand the output of its assets.

In the real-time world that is the power business, that wasn’t adequate. In 2012 (when AGL was at around 5,500 MW) it signed an enterprise agreement with OSIsoft to be able to collect data from all of its assets and synthesize it in a way that employees could understand it and act upon it.

List the key components in the solution:

  • OSIsoft PI System and PI Vision: PI System is a data fabric, which was new to AGL and installed locally. PI Vision is the visualization suite. Employees can act on PI insights directly for further analysis using the cloud. AGL analyzes more than 45,000 data points at 5 minute-or-shorter intervals.
  • Predict-IT: Cloud analytics platform that absorbs PI data and conducts diagnostics.

Describe how the deployment went, perhaps how long it took, and if it came off as planned: AGL steadily rolled the PI system out across various assets and departments. Both engineers and non-engineers relatively quickly began to develop dashboards to analyze various parts of the business. One engineer created a solar power monitoring system to gauge and compare the output from different solar assets. Another (a non-technical employee) created a condition based monitoring system for hydro dams 700 kilometers away. The console showed how pieces of equipment were tripping on and off so he was able to direct on-site subcontractors to the source of the problem. In three months, AGL saw a lift of 7 percent in the availability of those hydro units.

“The next data scientist could be anybody,” Bartolo said. Initial ROI took about nine months.

Describe the result, new efficiencies gained, and what was learned from the project:

  • By 2015, AGL had launched its Operational Diagnostics Center for analyzing assets across the portfolio in a centralized way.
  • During the next three years (2015, 2016, 2017) it saved $18.7 million, with $8.5 million coming in the last year alone. Initial setup costs were $1.2 million and ongoing costs are $620,000.
  • The system also detected an anomaly in a hydrogen stator (a large piece of grid equipment; a hydrogen-cooled turbo generator); it discovered metal inside. Bartolo estimates it could have been days away from a catastrophic fire which could have cost $50 million and caused a shutdown of 12 to 14 weeks This figure is not included in the ROI calculations—it would throw off the ROI calculations from what is being achieved in normal conditions—but is very real.

AGL now has two new projects:

  • Wind Yield Optimization System: This harvests and synthesizes repair data, performance signals and weather data, to increase output by 1 percent to 2 percent.
  • Thermal Performance Optimization System: This reduces fuel burn on its fossil assets by 0.5 percent. This is potentially worth millions in revenue.

Describe ROI, carbon footprint savings, and staff time savings: AGL paid off the project in nine months. The company saved quite a bit by tightening up its operations, but the interesting part is that it was a bottom-up affair. Employees were coming up with solutions on their own and driving improvements.

If you have a suggestion for an eWEEK IT Science article, email [email protected].

Chris Preimesberger

Chris J. Preimesberger

Chris J. Preimesberger is Editor-in-Chief of eWEEK and responsible for all the publication's coverage. In his 15 years and more than 4,000 articles at eWEEK, he has distinguished himself in reporting...