Carnival Maritime uses machine learning to optimise cruise operations

Carnival Maritime, the marine service unit for Carnival Corporation’s cruise brands, has harnessed the power of machine learning and Microsoft’s Cortana Intelligence Suite to better predict water consumption onboard the Costa Group’s 26 cruise ships.

Traditionally, cruise operators use experience and simple calculation models to estimate how much water they might need for a particular voyage. However, this often leads to ships producing and carrying excess water while at sea, increasing fuel costs, or carrying too little and having to bunker water in transit.

Carnival Maritime has joined with Arundo Analytics to use its proprietary Microsoft Azure-based big data platform and the machine learning models, APIs and templates in the Microsoft Cortana Intelligence Suite to collect data from thousands of sensors onboard the ships. Arundo analysed historical data sets, as well as data about the speed and position of the ships, the age and nationality of passengers, historical weather data and more, to better understand what drives onboard water consumption.

“Arundo has built a large big data platform that runs on Microsoft Azure, and it was an exciting challenge figuring out what we can do with it for Carnival Maritime,” said Tor Jakob Ramsoy, Arundo’s CEO. “We can very quickly prove a use case or a business case to show the business value that applying advanced analytics and big data can bring—and how it can bring that value in a very short time and make a big impact on operations.”

Costa Group is currently testing the solution on select ships in its fleet. Carnival Maritime expects that Arundo’s solution will enable it to better predict how much water a ship will need for a specific route with a particular set of guests. By producing water via evaporators and reverse osmosis systems rather than bunkering it, each Costa ship could save more than US$$200,000 a year and also reduce carbon dioxide emissions.

“We want to produce our own water and we want to understand when to produce it so that, ideally, we never have to bunker any water,” said Alexander Klingelhoefer, director of Continuous Improvement at Carnival Maritime. “This is not only cost-effective but it also ensures a stable and superior water quality.”

Carnival Maritime is also exploring how it can use Arundo’s solution to implement a predictive maintenance solution for the equipment and systems used onboard ships.

“Arundo’s big data and advanced analytics solution with Cortana Intelligence Suite is very interesting for us to investigate, especially how we can further increase efficiency in our ship operation,” said Klingelhoefer. “We spend a lot of money on maintenance and repair of our ships, so we’re looking forward to doing predictive maintenance, using the data to understand how the machines operating and proactively maintaining them or exchanging parts before something breaks down.”