Asset Bundling for Wind Power Forecasting

TL;DR

This paper introduces a novel Bundle-Predict-Reconcile framework that enhances wind power forecasting accuracy by integrating asset bundling, machine learning, and forecast reconciliation, validated on a large industry dataset.

Contribution

It proposes a new hierarchical forecasting approach with asset bundling and reconciliation, improving wind power forecast accuracy at multiple levels.

Findings

BPR significantly outperforms baseline models in forecast accuracy.

Asset bundling criteria effectively capture spatio-temporal wind dynamics.

Framework improves fleet-level forecasts in industry-scale data.

Abstract

The growing penetration of intermittent, renewable generation in US power grids, especially wind and solar generation, results in increased operational uncertainty. In that context, accurate forecasts are critical, especially for wind generation, which exhibits large variability and is historically harder to predict. To overcome this challenge, this work proposes a novel Bundle-Predict-Reconcile (BPR) framework that integrates asset bundling, machine learning, and forecast reconciliation techniques. The BPR framework first learns an intermediate hierarchy level (the bundles), then predicts wind power at the asset, bundle, and fleet level, and finally reconciles all forecasts to ensure consistency. This approach effectively introduces an auxiliary learning task (predicting the bundle-level time series) to help the main learning tasks. The paper also introduces new asset-bundling criteria that capture the spatio-temporal dynamics of wind power time series. Extensive numerical experiments are conducted on an industry-size dataset of 283 wind farms in the MISO footprint. The experiments consider short-term and day-ahead forecasts, and evaluates a large variety of forecasting models that include weather predictions as covariates. The results demonstrate the benefits of BPR, which consistently and significantly improves forecast accuracy over baselines, especially at the fleet level.