Predictive Uncertainty in Short-Term PV Forecasting under Missing Data: A Multiple Imputation Approach

TL;DR

This paper introduces a model-agnostic framework that incorporates missing-data uncertainty into short-term photovoltaic power forecasts, improving the calibration of prediction intervals by combining stochastic multiple imputation with Rubin's rule.

Contribution

It presents a novel approach to propagate missing-data uncertainty into PV forecasting, enhancing interval calibration without sacrificing point prediction accuracy.

Findings

Ignoring missing-data uncertainty results in overly narrow prediction intervals.

Accounting for imputation uncertainty improves interval calibration.

The method maintains comparable point prediction accuracy.

Abstract

Missing values are common in photovoltaic (PV) power data, yet the uncertainty they induce is not propagated into predictive distributions. We develop a framework that incorporates missing-data uncertainty into short-term PV forecasting by combining stochastic multiple imputation with Rubin's rule. The approach is model-agnostic and can be integrated with standard machine-learning predictors. Empirical results show that ignoring missing-data uncertainty leads to overly narrow prediction intervals. Accounting for this uncertainty improves interval calibration while maintaining comparable point prediction accuracy. These results demonstrate the importance of propagating imputation uncertainty in data-driven PV forecasting.