By Richard Humphreys |
The energy landscape is changing rapidly. With climate volatility growing and demand for electricity rising, the sector is increasingly using renewable sources to generate energy, which is forcing providers to rethink how they manage infrastructure and deliver services.
Renewable energy sources, such as wind and solar, are inherently weather-dependent. Consequently, providers must now be able to accurately predict weather forecasts at greater speed and scale to continue delivering reliable services to customers. To analyse vast volumes of complex environmental and geospatial data, they need to move away from traditional numerical forecasting methods. Instead, they are turning to AI-powered models that can be embedded in modern data platforms and are available to various teams.
BKW, an energy group based in Switzerland, has partnered with Microsoft Energy & Resources Industry to build a cloud-based data and AI platform capable of ingesting, processing and operationalising weather, environmental and geospatial data at scale without relying on custom systems or niche tools.
Built on a Microsoft Azure-native operational infrastructure, BKW’s platform combines Aurora, an AI weather foundation model developed by Microsoft Research and Microsoft AI Weather, with the Microsoft Planetary Computer Pro geospatial intelligence platform. Aurora uses a large-scale AI model trained on decades of atmospheric data to quickly generate accurate ensemble weather forecasts. Its outputs are stored in Microsoft Planetary Computer Pro, which uses two specialised data catalogues – Microsoft AI Weather Grid HD EU and Grid HD EU Solar – to deliver precise, high-resolution regional weather and solar generation forecasting data at scale. Grid HD is particularly useful for energy use cases such as solar generation and residual load modelling, where hourly temporal resolution and improved local accuracy are critical for back testing, diagnostics and operational decision-making.
BKW has collaborated with Microsoft to build an AI-powered weather forecasting platform to deliver reliable energy services (Photo: BKW)
The integration of Aurora and Planetary Computer Pro into Azure-native workflows gives BKW’s data scientists, domain experts and technology teams easy access to geospatial and atmospheric data from a shared, governed environment. In addition, BKW uses a model context protocol server built on Azure-native services to unlock insights from agentic workflows and convert them into coordinated actions for humans to review. Crucially, BKW maintains governance, domain expertise and control over how insights are applied.
BKW now has a clearer understanding of how AI driven weather models can complement traditional numerical forecasting to improve decision-making across its energy and infrastructure portfolio and allow multidisciplinary teams to test and iterate ideas more quickly.
Having validated the technology, BKW will now evolve the platform and embed it into its operational workflows to empower its multidisciplinary team with the insights they need to quickly and precisely forecast weather and solar generation at scale. This will enable it to deliver reliable energy services and move closer to achieving its long-term renewable energy and net-zero goals.
“At BKW, our purpose is to make living spaces worth living in,” says Yamshid Farhat, lead for AI and technology at BKW. “Collaborating with Microsoft helps us translate advanced AI and data capabilities into trusted, scalable foundations for better decisions. This is how we want to use technology: not as a standalone experiment, but as an enabler for sustainable infrastructure, renewable energy growth and our path towards net zero.”
Discover more real-world examples of Microsoft implementation in the Summer 2026 issue of Technology Record. To get content like this on a regular basis, subscribe to the print edition or free digital edition of the quarterly Technology Record magazine.