Universal Differential Equations for Scientific Machine Learning of Node-Wise Battery Dynamics in Smart Grids
This work addresses battery modeling for decentralized energy networks, offering potential improvements in real-time control and optimization for renewable-integrated smart grids, but it is incremental as it applies an existing UDE framework to a specific domain problem.
The authors tackled the challenge of modeling node-wise battery dynamics in smart grids, which is difficult due to stochastic solar input and variable household loads, by proposing a Universal Differential Equations (UDE) approach that embeds a neural residual into a physical battery ODE, achieving close alignment with ground truth trajectories and stable long-term forecasts in synthetic experiments.
Universal Differential Equations (UDEs), which blend neural networks with physical differential equations, have emerged as a powerful framework for scientific machine learning (SciML), enabling data-efficient, interpretable, and physically consistent modeling. In the context of smart grid systems, modeling node-wise battery dynamics remains a challenge due to the stochasticity of solar input and variability in household load profiles. Traditional approaches often struggle with generalization and fail to capture unmodeled residual dynamics. This work proposes a UDE-based approach to learn node-specific battery evolution by embedding a neural residual into a physically inspired battery ODE. Synthetic yet realistic solar generation and load demand data are used to simulate battery dynamics over time. The neural component learns to model unobserved or stochastic corrections arising from heterogeneity in node demand and environmental conditions. Comprehensive experiments reveal that the trained UDE aligns closely with ground truth battery trajectories, exhibits smooth convergence behavior, and maintains stability in long-term forecasts. These findings affirm the viability of UDE-based SciML approaches for battery modeling in decentralized energy networks and suggest broader implications for real-time control and optimization in renewable-integrated smart grids.