LAPSO: A Unified Optimization View for Learning-Augmented Power System Operations

2025-05-08

AI Summary

Traditional model-driven power system operations face limitations in economic efficiency, dynamic stability, and robustness under high renewable energy penetration. Method: This paper proposes the Learning-Augmented Power System Operation (LAPSO) framework—the first to enable end-to-end co-design of machine learning and model-based optimization across both training and inference stages. It introduces Stability-Constrained Optimization (SCO) and Objective-Driven Forecasting (ODF), integrating deep learning, differentiable optimization, uncertainty quantification, and convex/non-convex optimization theory. LAPSO supports cross-task objective-consistent modeling and uncertainty溯源 (traceability). Contribution/Results: We release an open-source Python package, *lapso*, enabling automatic embedding of learnable modules into existing optimization models. Extensive evaluations on standard and real-world grids demonstrate significant improvements in operational economy, small-signal stability, and disturbance robustness, alongside end-to-end uncertainty propagation tracking. All code and datasets are publicly available.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

With the high penetration of renewables, traditional model-based power system operation is challenged to deliver economic, stable, and robust decisions. Machine learning has emerged as a powerful modeling tool for capturing complex dynamics to address these challenges. However, its separate design often lacks systematic integration with existing methods. To fill the gap, this paper proposes a holistic framework of Learning-Augmented Power System Operations (LAPSO, pronounced as Lap-So). Adopting a native optimization perspective, LAPSO is centered on the operation stage and aims to break the boundary between temporally siloed power system tasks, such as forecast, operation and control, while unifying the objectives of machine learning and model-based optimizations at both training and inference stages. Systematic analysis and simulations demonstrate the effectiveness of applying LAPSO in designing new integrated algorithms, such as stability-constrained optimization (SCO) and objective-based forecasting (OBF), while enabling end-to-end tracing of different sources of uncertainties. In addition, a dedicated Python package-lapso is introduced to automatically augment existing power system optimization models with learnable components. All code and data are available at https://github.com/xuwkk/lapso_exp.

Problem

• Integrates machine learning with power system operations for better decisions
• Unifies forecast, operation, and control tasks in power systems
• Addresses uncertainties in renewables via end-to-end optimization framework

Innovation

• Unified framework integrating learning and optimization
• End-to-end uncertainty tracing in power systems
• Python package for learnable optimization models