aiqbench analysis
This research presents a nonparametric machine learning method that improves intraday renewable energy forecasting by fusing deterministic predictions with partial real-time data via functional curve completion. By leveraging nearest-neighbor similarity metrics across diverse assets and locations, the approach effectively quantifies operational uncertainty through calibrated probabilistic distributions. The technique offers a robust framework for grid operators managing the increasing variability of wind and solar generation without relying on heavy parametric assumptions.
Nearest Neighbor Functional Curve Completion for Intraday Probabilistic Revisions of Renewable Generation Forecasts
arXiv:2610.17075v1 Announce Type: new Abstract: We propose a nonparametric approach that fuses deterministic initial forecasts and a partial realization into a probabilistic forecast using the framework of functional curve completion. Our motivation is to construct intra-day forecasts for renewable energy generation, which is a key operational task in modern power grids. The aim is to combine the day-ahead (DA) forecast and the morning realized generation profile to create trajectories for the rest of the day, quantifying operational uncertainty. Starting with a large database of complete forecast-actual pairs across many assets, we adopt a functional point of view and construct a weighted neighborhood based on similarity metrics for the observed partial curve, the DA forecast, the day, and the geographical location. The selected complete nearest-neighbor curves provide a full predictive distribution, including functional focal envelopes and predictive bands based on functional depth. The hyperparameters governing neighborhood size, distances, and fusion rates are tuned across forecast update times and directly target probabilistic calibration in terms of the predictive probability integral transform. Three case studies using synthetic wind and solar assets, as well as real-life regional wind generation, showcase that our algorithm is able to achieve excellent calibration.
Abstract:We propose a nonparametric approach that fuses deterministic initial forecasts and a partial realization into a probabilistic forecast using the framework of functional curve completion. Our motivation is to construct intra-day forecasts for renewable energy generation, which is a key operational task in modern power grids. The aim is to combine the day-ahead (DA) forecast and the morning realized generation profile to create trajectories for the rest of the day, quantifying operational uncertainty. Starting with a large database of complete forecast-actual pairs across many assets, we adopt a functional point of view and construct a weighted neighborhood based on similarity metrics for the observed partial curve, the DA forecast, the day, and the geographical location. The selected complete nearest-neighbor curves provide a full predictive distribution, including functional focal envelopes and predictive bands based on functional depth. The hyperparameters governing neighborhood size, distances, and fusion rates are tuned across forecast update times and directly target probabilistic calibration in terms of the predictive probability integral transform. Three case studies using synthetic wind and solar assets, as well as real-life regional wind generation, showcase that our algorithm is able to achieve excellent calibration.
Machine Learning (cs.LG)
arXiv:2610.17075 [cs.LG]
(or arXiv:2610.17075v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.17075 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 284 words
Related coverage
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · Jul 15, 2026
Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy
LessWrong · Oct 12, 2026