Dataiku > Case Studies > Vestas: Leveraging Dataiku for Sustainable Energy Solutions and Cost Reduction

Vestas: Leveraging Dataiku for Sustainable Energy Solutions and Cost Reduction

Technology Category

Analytics & Modeling - Machine Learning
Platform as a Service (PaaS) - Application Development Platforms

Applicable Industries

Equipment & Machinery
Transportation

Applicable Functions

Logistics & Transportation
Maintenance

Use Cases

Building Automation & Control
Inventory Management

Services

Data Science Services
System Integration

About The Customer

Vestas is a global leader in sustainable energy solutions, with 29,000 employees working to design, manufacture, install, develop, and service wind energy and hybrid projects all over the world. With over 160 GW of wind turbines installed in 88 countries, Vestas has already prevented 1.5 billion tons of CO₂ being emitted into the atmosphere. The Service Analytics team at Vestas plays a key role in keeping the company at the forefront of a sustainable future, enabling business decisions and processes with data products and insights across the entire value chain.

The Challenge

Vestas, a global leader in sustainable energy solutions, faced a complex challenge in optimizing their shipment patterns to save costs. The Service Analytics team at Vestas had to consider not only external, customer-facing products, but also internal stakeholders across the Operations, Finance, Supply Chain, and Commercial teams. All of these teams worked together to answer big questions for the company such as how and when to deliver a turbine part from point A to point B. The team recognized that a more robust data operation could help them simplify and improve logistical challenges. They understood that data science-based solutions in predictive asset maintenance, field capacity planning, inventory management, demand and supply forecasting, and price planning would provide critical support to the internal customers of Vestas. However, until that point, the data team ran a traditional business intelligence (BI) based analytics operation, querying BI-dashboards, deriving insights, and building data products in a less automated manner.

The Solution

The Service Analytics team at Vestas decided to upgrade their team’s maturity, with an eye toward building solutions that used machine learning and advanced analytics. As part of this transition, a Center of Excellence (CoE) for advanced analytics was put together with the aim of identifying transitional areas within Service Analytics. This involved building proof of concepts (PoCs) to showcase their machine-learning capabilities, upskilling the team, and identifying tools and a technology ecosystem that would support their journey over the long run. Dataiku served as the cornerstone platform for Service Analytics’ CoE. After conducting an internal study of available data science platforms, the team was drawn to Dataiku for its simplicity, support for citizen data scientists, increased time-to-market, agnostic toolset, and good integration with cloud services. The team onboarded the Dataiku instance and began working on use cases and PoCs that could demonstrate the power of Dataiku and the improved time-to-value it enabled.

Operational Impact

The collaboration with Dataiku has resulted in a fruitful partnership that has upskilled the Vestas team, enabling them to drive and deliver powerful projects independently. The most impactful use case that the Service Analytics team has built with Dataiku has been its express shipment recommendation model. This model helps dispatchers and planners know whether, for a given request, express shipping should be used. The model was built as a stand-alone web application within the Dataiku ecosystem. The close collaboration with the Dataiku data science team allowed Vestas to enhance the technical skills of its existing team, improve data access and data quality for the business, and become independent when delivering future projects on the platform. The team was able to deliver the project as desired, with a deployed machine learning model, APIs, and a stand-alone application for end-users within about one month.

Quantitative Benefit

Estimated cost reduction on express shipments by 11-36%
Improved time-to-market for Vestas’ industry- and function-specific analytic solutions
52% of express-shipped materials were not being put to use for at least 4 months, indicating potential for significant cost savings