Variational Digital Twins
Logan A. Burnett, Umme Mahbuba Nabila, Majdi I. Radaideh

TL;DR
This paper introduces a variational digital twin framework that enhances neural models with Bayesian uncertainty estimation, enabling real-time updates and reliable predictions across various energy systems.
Contribution
It proposes a lightweight Bayesian augmentation and a novel update algorithm for digital twins, improving real-time performance and uncertainty quantification in energy applications.
Findings
Active learning reduces experiments by 47% for critical-heat-flux prediction.
Renewable-generation twin maintains R2 > 0.95 over three years with monthly updates.
Li-ion battery twin significantly lowers voltage error and adapts to end-of-life conditions.
Abstract
While digital twins (DT) hold promise for providing real-time insights into complex energy assets, much of the current literature either does not offer a clear framework for information exchange between the model and the asset, lacks key features needed for real-time implementation, or gives limited attention to model uncertainty. Here, we aim to solve these gaps by proposing a variational digital twin (VDT) framework that augments standard neural architectures with a single Bayesian output layer. This lightweight addition, along with a novel VDT updating algorithm, lets a twin update in seconds on commodity GPUs while producing calibrated uncertainty bounds that can inform experiment design, control algorithms, and model reliability. The VDT is evaluated on four energy-sector problems. For critical-heat-flux prediction, uncertainty-driven active learning reaches R2 = 0.98 using 47 %…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsModel Reduction and Neural Networks · Digital Transformation in Industry · Integrated Energy Systems Optimization
