Driving efficiency with artificial intelligence and machine learning
Melbourne Water is using artificial intelligence and machine learning in a unique approach to driving down electricity use in its water treatment operations.
Winneke treatment plant is one of the major water treatment sites for Melbourne’s potable drinking water. On average approximately 350 ML of water moves through the plant every day before being distributed to millions of homes and business around the city.
The plant has a daily targeted flow rate for water production in order to ensure Melbourne has the right amount of drinking water at all times. The target is different every day, meaning different pumps running at different speeds.
In order to ensure these pumps are operated at maximum efficiency while still achieving the required flow rate, Melbourne Water is using a custom developed artificial intelligence (AI) program which mines historical pump operational data to ‘learn’ the most efficient pump configuration at any given time.
Melbourne Water Automation Team leader Russell Riding said the AI system, developed in house using the “Python” platform was powerful enough to consider a wide range of factors in its decision making.
“The Python program is able to utilise our historical data to determine the most energy efficient combinations of pumps and, the associated speeds to run them at, in order to achieve the necessary flow rate,” he said.
“Because it was developed by one of our experienced data analysts, it is able to understand a range of factors which are very unique to our system, including reservoir level, available pumps and past performance”.
“The program even gives us the ability to switch to a special training mode where our operations team can test a wide range of pump combinations which may not normally be utilised so the program can learn these for future reference”.
“When in operational mode, the Python program determines optimal pump calibrations and sends them directly to the pump system without any human intervention; The AI determines the best settings and then applies them in real time.”
Mr Riding said cybersecurity was an important consideration when trialling the system.
“The AI is stored on a computer which is not connected to the broader Melbourne Water network, or the internet. This is best practice to ensure that cyber security risks are minimised.”
“The local control system also has rules built in to its code to ensure the AI system can only optimise the pump operations within set parameters. This is an important failsafe feature to ensure production can continue if the AI system fails.”
The project is expected to reduce Melbourne Water’s pump station energy costs at the Winneke site by around 20% per year, and is being tested at other locations.
“We’re currently commencing testing with Python on another pump station with different requirements to find out if we can replicate the same kind of results that have been achieved at Winneke.”
“If the success proves to be repeatable it is likely we will implement Python across a range of environments within Melbourne Water’s operations over time.”