Using AI/ML for sustained energy efficiency in industrial operations (SUS304)

Reducing Energy Consumption and CO2 Emissions with Machine Learning on AWS

Key Takeaways

  • Volkswagen and Amazon are leveraging machine learning on AWS to reduce energy consumption and CO2 emissions in their operations.
  • Volkswagen reduced energy consumption of air compressors in their Poznan factory by 12% using an ML-driven model.
  • Amazon optimized energy usage for heating, ventilation, and air conditioning (HVAC) systems in their warehouses, achieving 25% energy savings and 468 tons of CO2 savings per year.
  • Both companies are taking a systematic and scalable approach to improving sustainability across their entire operations.

Volkswagen's Energy Optimization for Air Compressors

  • Volkswagen has a clear "go to zero" strategy to achieve CO2-neutral production by 2040.
  • The Poznan factory uses a significant amount of compressed air, accounting for over 20% of the plant's total electricity consumption.
  • Volkswagen developed an ML-driven model to predict future air consumption based on production schedules and derive an optimal compressor sequence to minimize energy usage.
  • The solution achieved a 12% improvement in energy usage compared to the manual approach, leading to 1,000 tons of CO2 savings per year and $250,000 in cost savings.
  • Volkswagen plans to expand this solution to its 114 factories worldwide.

Amazon's HVAC Optimization

  • Amazon's retail operations consume a significant amount of energy, with HVAC systems accounting for 20-40% of a site's total energy usage.
  • Amazon developed a prescriptive model that integrates predictive models for photovoltaic energy production, internal temperature, and energy consumption to optimize the HVAC system's operation.
  • The model provides an optimal schedule for the HVAC system, balancing energy consumption and maintaining comfort levels.
  • Preliminary results show 25% energy savings, 468 tons of CO2 savings per year, and $395,000 in cost savings by applying the solution to a fraction of Amazon's sites.
  • Amazon's long-term vision is to optimize energy consumption across its entire network of 2,862 sites, enabling dynamic energy management and leveraging renewable energy sources.

Collaboration and Scalability

  • Both Volkswagen and Amazon emphasized the importance of collaboration, data management, and scalable architectures to drive sustainable impact.
  • Volkswagen and Amazon leveraged AWS services like Amazon SageMaker, AWS Glue, and AWS Lambda to build robust, scalable, and automated ML-powered solutions.
  • The companies' approaches demonstrate how machine learning can be applied systematically across large-scale industrial and retail operations to achieve significant energy and emissions reductions.

Your Digital Journey deserves a great story.

Build one with us.

Cookies Icon

These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.

If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.

Talk to us