Optimal scheduling of renewable energy microgrids: A robust multi-objective approach with machine learning-based probabilistic forecasting

Diego Aguilar, Jhon J. Quinones, Luis R. Pineda, Jason Ostanek and Luciano Castillo

Applied Energy, 2024, vol. 369, issue C, No S0306261924009310

Abstract: Microgrids (MGs) powered by renewable energy sources (RES) like solar and wind face integration and management challenges due to their variability and fluctuating energy prices. Moreover, traditional scheduling strategies often overlook the decay in prediction accuracy over time and lack a mechanism for establishing optimal forecasting horizons. This research addresses this gap by merging machine learning (ML) probabilistic forecasting with robust optimization to create optimal dispatch schedules for RES MGs. It reveals that longer scheduling horizons can reduce dispatch costs but at the expense of forecast accuracy due to increased prediction accuracy decay (PAD). To address this, we propose a novel method that determines how to split the time horizon into timeblocks to minimize dispatch costs and maximize forecast accuracy. This forms the basis of an optimal rolling horizon strategy (ORoHS) which schedules distributed energy resources over varying prediction/execution horizons. The model was evaluated on a simulated renewable microgrid with energy storage. Probabilistic forecasts were generated for wind, solar, and energy prices at different confidence levels. This data fed into a robust optimization model to schedule energy transactions. Results offer Pareto-optimal fronts, showing the trade-offs between cost and accuracy at varying confidence levels. Solar power proved more cost-effective than wind power due to lower variability, despite wind’s higher energy output. The ORoHS strategy outperformed common scheduling methods. In the case study, it achieved a cost of $4.68 compared to $9.89 (greedy policy) and $9.37 (two-hour RoHS).

Keywords: Renewable microgrids; Robust optimization; Machine learning; Rolling horizon strategies; Probabilistic forecasting (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261924009310
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:369:y:2024:i:c:s0306261924009310

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.123548

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().