Quantum Computing Boosts Solar and Battery Forecasting by 20 Percent
Silicon Quantum Computing and Schneider Electric have advanced their collaboration to stage two of Australia's Critical Technologies Challenge Program, receiving A$3.6 million to expand quantum-enhanced forecasting across hundreds of Australian homes. The partnership achieved a 20 percent average improvement in energy prediction accuracy using quantum-generated features combined with classical algorithms, with some applications reaching 41 percent gains. The enhanced forecasting capabilities will help optimize distributed renewable energy resources and reduce consumer electricity costs.
The collaboration between Silicon Quantum Computing and Schneider Electric represents a significant technical milestone in applying quantum systems to real-world energy challenges. The Watermelon chip, launched in 2025, generates quantum-derived features that enhance traditional machine learning models, enabling more sophisticated pattern recognition in energy data. The 20 percent average accuracy gain—with certain scenarios exceeding 40 percent—emerged from analyzing 12 months of next-day forecasting data, demonstrating measurable performance improvements over conventional approaches. Expanding to hundreds of Australian households in Stage 2 will test whether these laboratory results translate effectively into distributed residential settings, where solar generation, battery storage, and electric vehicle charging create highly variable demand patterns.
If successful at scale, improved energy forecasting could benefit households through reduced electricity costs and grid operators through better integration of distributed renewable resources. Australian consumers with rooftop solar and battery systems may experience more efficient energy allocation and lower peak-demand charges. The work could also influence how energy companies globally approach grid management as residential generation becomes more prevalent. However, realizing these benefits depends on successful deployment across diverse household conditions and on market adoption of the technology, which remain to be demonstrated.