SQC and Schneider Electric Use Hybrid Quantum-Classical Models to Improve Energy Forecasting

Schneider Electric and SQC's partnership moves to Stage 2 of Australia's Critical Technologies Challenge Program (CTCP) following an average 20% accuracy improvement in forecasting grid consumption with SQC's Watermelon™ system

Image credit: Silicon Quantum Computing

Silicon Quantum Computing (SQC) and Schneider Electric, a global energy technology leader, have progressed to Stage 2 of the Australian Governments Critical Technologies Challenge Program (CTCP), receiving A$3.6 million (US$2.5m) in funding to continue their work in partnership with UNSW Sydney.

Energy grids are under increasing pressure and urgent solutions are required for grid resilience. As rooftop solar, home batteries and electric vehicles become widespread, household energy systems have become more dynamic and difficult to predict. Schneider Electric uses advanced forecasting and optimisation technologies to help balance distributed energy resources, including forecasting when to switch back and forth to solar energy deployment.

During Stage 1, the joint team explored whether SQC's atomically engineered, quantum-enhanced Al chip, Watermelon, could improve the accuracy of Schneider Electrics forecasting models. Watermelon generates quantum features that, when used alongside classical features, deliver richer models with greater predictive abilities.

For companies like Schneider Electric, more accurate forecasting can improve the management of distributed energy resources, increase renewable energy utilisation and contribute to lower energy costs for consumers. Even modest improvements in forecasting accuracy can deliver these benefits, and Stage 1 results delivered well beyond that threshold.

By applying Watermelon to next-day forecasting data over a 12-month period, SQC and Schneider Electric achieved an average 20% improvement in forecasting accuracy against the classical benchmark, with gains up to 41%.

Building on these results, Stage 2 funding will expand modelling to hundreds of homes across Australia, with direct integration into Schneider Electric's Al workflows. This work provides a clear pathway for today's quantum computing systems to be used in production environments.