Learning to Optimally Dispatch Power: Performance on a Nation-Wide Real-World Dataset

2025-05-30

AI Summary

This work addresses the optimal reactive power dispatch (ORPD) problem in power grids with high renewable energy penetration, identifying a critical bottleneck: the severe degradation of generalization performance of learning-based optimization methods under real-world conditions. Leveraging Uruguay’s national-scale grid topology and over two years of actual operational data, we construct the first publicly available, spatiotemporally complete national ORPD benchmark dataset—incorporating realistic load profiles and renewable generation patterns. Through systematic evaluation of state-of-the-art approaches—including supervised neural networks and learning-to-optimize frameworks—we observe substantial increases in prediction error on real data. The primary cause is the inability of existing models to jointly capture the complex spatiotemporal statistical dependencies and tightly coupled physical constraints inherent in real power systems. This work establishes a reproducible benchmark, a diagnostic framework, and concrete directions for advancing robust, learning-based power system optimization.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The Optimal Reactive Power Dispatch (ORPD) problem plays a crucial role in power system operations, ensuring voltage stability and minimizing power losses. Recent advances in machine learning, particularly within the ``learning to optimize'' framework, have enabled fast and efficient approximations of ORPD solutions, typically by training models on precomputed optimization results. While these approaches have demonstrated promising performance on synthetic datasets, their effectiveness under real-world grid conditions remains largely unexplored. This paper makes two key contributions. First, we introduce a publicly available power system dataset that includes both the structural characteristics of Uruguay's electrical grid and nearly two years of real-world operational data, encompassing actual demand and generation profiles. Given Uruguay's high penetration of renewable energy, the ORPD problem has become the primary optimization challenge in its power network. Second, we assess the impact of real-world data on learning-based ORPD solutions, revealing a significant increase in prediction errors when transitioning from synthetic to actual demand and generation inputs. Our results highlight the limitations of existing models in learning under the complex statistical properties of real grid conditions and emphasize the need for more expressive architectures. By providing this dataset, we aim to facilitate further research into robust learning-based optimization techniques for power system management.

Problem

• Evaluating machine learning for Optimal Reactive Power Dispatch in real-world grids
• Assessing performance gap between synthetic and real power system data
• Addressing limitations of current models in handling real grid complexities

Innovation

• Uses machine learning for power dispatch optimization
• Introduces real-world Uruguay grid dataset
• Highlights limitations in synthetic-to-real transition