WISER and E.ON Benchmark Quantum Machine Learning for Smart Grid Energy Forecasting

Researchers from the Washington Institute for STEM, Entrepreneurship and Research and E.ON have successfully benchmarked hybrid quantum-classical machine learning for predicting electricity demand in smart grids, utilizing IBM Quantum hardware with over 100 qubits¹. This collaboration, published on arXiv, explored the potential of Noisy Intermediate-Scale Quantum technology for multi-output time-series forecasting. By leveraging quantum machine learning, the team aimed to improve the accuracy of energy forecasting, which is crucial for optimizing energy distribution and reducing waste. The experiment demonstrated the feasibility of running complex quantum algorithms on current-generation quantum hardware, narrowing the gap between theoretical models and practical applications. This breakthrough has significant implications for the energy sector, as it could enable more efficient and reliable energy forecasting, ultimately leading to better grid management and reduced energy costs. The success of this project underscores the growing importance of quantum computing in addressing real-world challenges, so what matters most to practitioners is the accelerating pace of quantum advancements and their potential to disrupt traditional approaches to energy forecasting.