Data Science Platform
Make the right use of data
Consolidate, visualize and evaluate.

Data

Data Science Practice

Data Science Platform

Pro Data Science Platform
- Central storage of all data
- Effective and high-performance analysis of large amounts of data
- Real-time insights – data-driven descisions
- Increasing performance and competitiveness of your company

Data Science Challenges
- The provision, storage and loading of data are crucial for the implementation and success of data science projects.
- Data pipelines are an appropriate choice as the demands for performance, regularity, and reliability of data delivery grow.

Data Pipeline for your data
- Extraction of data from different sources
- Data validation and quality control
- Data transformation
- Storage of the data in the target system
Case Study Data Science Platform: Windenergie bei WindCores
Making wind farms more efficient and profitable through intelligently used weather and turbine data.
More and more companies in the renewable energy sector rely on Data Science Platforms, including WindCores
We support WindCores in collecting, consolidating and providing data, so that WindCores employees can evaluate the data in real time.
the collected data enables WindCores to predict how turbines can be used most efficiently in the future in order to optimally exploit the potential of their wind turbines.
Platform
The 5 most important components of our Data Science Platform:
- We use Kubernetes for scalability.
- The timeseries database Prometheus is used to store the data.
- We use jupyter notebooks for static analysis.
- For the visualization of the actual data we utilize grafana
- The microservice data science platform is secured by Keycloak.
All used technologies have in common that they are based on open source. This has the advantage that we can adapt our Data Science Platform to specific customer requirements at any time.
Exemplary architecture of our Data Science Platform
Performant and scalable.
