Tesco uses big data to cut cooling costs by up to €20m

Tesco is aiming to save over €20m a year by using sophisticated analytical technology to ensure its chillers work at optimum temperature

Supermarket chain Tesco aims to save over €20m a year by using sophisticated business intelligence technology to ensure its refrigerators operate at the right temperature.

The move will help the retailer cut its refrigeration energy costs by up to 20% across 3000 stores in the UK and Ireland.

An experimental research project between Tesco in Ireland and IBM Dublin’s research laboratories has shown the retailer can save a significant part of its total energy costs by optimising the performance of its in-store refrigerators.

Analysing gigabytes of data

The project, which used sophisticated computer systems to analyse gigabytes of refrigeration data, revealed that, without realising it, many Tesco stores in Ireland were running their refrigerators at a lower temperature than necessary.

“Ideally, we keep our refrigerators at between -21°C and -23°C, but in reality we found were keeping them colder. That came as a surprise to us,” said John Walsh, Tesco's energy and carbon manager for Ireland, in an interview with Computer Weekly.

Three years ago, the company began work with its refrigerator manufacturers to collect refrigeration data from in-store controllers and deliver it over the internet to a dedicated data warehouse.

The data warehouse takes readings every three seconds from in-store sensors, processes the data in real time, and displays the results on a Google map which shows the performance of refrigerators in more than 120 Irish stores. It is also able to monitor and control the performance of  Tesco's heating and lighting systems (see "How Tesco uses big data to manage lighting and heating costs" below).

Tesco was able to identify the potential savings in its refrigeration costs after it teamed up with IBM last year to look at the data in more depth.

There is a potential saving of €20m if we deliver the same savings that we’ve seen in the trial stores across our full estate

John Walsh, Tesco

70 million data points 

Researchers collected and analysed refrigerator data from a single store in Ireland over the course of a year – equivalent to 70 million data points. They were able to analyse the data using standard blade servers running IBM's SPSS statistical software package.

“We developed a set of key performance indicators [KPIs] that looked at data aggregated every month over a year,” said Niall Brady, IBM's research engineer for intelligent buildings and energy analytics. “Without knowing anything about how the refrigerators should perform, we could identify when they were behaving in an anomalous way.” 

The six-month project helped the company make immediate savings in the trial store by identifying refrigerators that were operating at a lower temperature than they should, Walsh revealed.

“We spend €10m keeping our fridges cold in Ireland, and if you can save 20% of that, it’s a prize worth taking,” he says.

€20m potential saving 

Walsh plans a six-month trial with a larger number of stores. If that is successful, he plans to roll the energy-saving project out across more than 3,000 Tesco outlets in the UK and Ireland within 18 months.

“There is a potential saving of €20m if we deliver the same savings that we’ve seen in the trial stores across our full estate in the UK and Ireland,” he says.

The project is also helping Tesco to reduce its maintenance costs. The Google map can help engineers to identify refrigerators that are not working at the optimum temperature before store managers become aware of them.

Maintenance teams can interrogate the refrigerators remotely, diagnose the problem, and turn up with the right part.

Previously, engineers would turn up to the store, diagnose the problem, and have to return to the depot to collect the equipment they needed.

The limits of big data

Tesco plans to work with IBM to develop techniques to analyse greater volumes of data, but Walsh said the company's IT systems have reached the limit of their capacity for now.

“We have got so much data. It's way too much to handle. So we are a victim of our own success,” he said.

More on big data analytics

How Tesco uses big data to manage lighting and heating costs 

Tesco is using data feeds from more than 120 stores in Ireland to cut lighting and heating costs.

The retailer has worked with its suppliers to link heating and lighting controllers from its Irish stores over the internet to a dedicated data warehouse.

The three-year project has enabled Tesco to view the energy performance of each store in Ireland on a Google map.

“We found there was a huge variation across the stores – some were being run quite coolly, others were being overheated – and there was not a constant policy being applied across the estate,” said John Walsh,  energy and carbon manager for Tesco in Ireland.

Tesco has discovered it can turn the heating on three hours later, in some stores, and still have the store at the right temperature for opening time.

Now Walsh is looking to make further savings by reducing lighting and air-conditioning levels when there are fewer customers in the store.

“We are trying to make sure we have got great lighting when we have customers in the store, and when we don’t have customers in the store, we can let the lighting systems dim down,” he said.

The project has helped Tesco reduce its maintenance costs and speed up the time taken to respond to technical failures, said Walsh.

Each morning, at 7am, he receives a report showing which stores have not reached the right temperature. By 8am, Tesco can have maintenance teams going out to the stores to fix the problems.

Previously it could take hours, or even days, before store managers would report a heating problem, said Walsh.

More on energy efficiency

  • Green computing energy efficiency guide
  • Green cloud computing quiz: Raise your energy efficiency grade
  • Energy efficiency is top datacentre priority for IT, shows study
  • Saving money through an energy-efficient UPS

Tesco's carbon targets

Tesco has set itself a target to reduce its carbon footprint in Ireland by 50% by 2020.

In practice, this means that each year the company aims to cut its energy costs by 5% to 10% each year, said Walsh.

Tesco is replacing fluorescent tubes with energy-efficient LED lighting to reduce its power costs.

At the same time, it is reducing its carbon footprint by replacing traditional refrigerants, with carbon dioxide, which has a lower impact on global warming.

“By the end of 2014, we should be producing half the CO2 emissions per square foot that we were producing in 2006 in our Irish stores,” said  John Walsh, energy and carbon manager for Tesco in Ireland.

But longer term, cutting energy consumption will mean developing analytical technologies that can manage and control buildings more effectively.

“We are still very much in the infancy,” he said.

Read more on Big data analytics

Data Center
Data Management