Flexibility of German gas-fired generation: evidence from clustering empirical operation

2025-04-14

arXiv.org

AI Summary

This study addresses the significant discrepancy between the actual flexibility and nominal technical parameters of gas-fired power units. Leveraging hourly real-world output data from large German gas units (2019–2023), we propose the first deep learning–driven time-series representation and clustering framework to accurately identify unit-level operational flexibility. Results reveal that nearly half of non-peaking units exhibit severely constrained ramping capability yet supply over 83% of must-run generation; clustering identifies two distinct peaking and two non-peaking unit types, with the former exhibiting average ramp rates 1.5–3× higher than the latter. Our approach breaks from conventional flexibility assumptions rooted solely in nameplate parameters, enabling— for the first time—flexibility classification grounded in empirical operational behavior. Based on these findings, we formulate a regulatory optimization pathway to unlock latent flexible capacity.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Optimization

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

A key input to energy models are assumptions about the flexibility of power generation units, i.e., how quickly and often they can start up. These assumptions are usually calibrated on the technical characteristics of the units, such as installed capacity or technology type. However, even if power generation units technically can dispatch flexibly, service obligations and market incentives may constrain their operation. Here, we cluster over 60% of German national gas generation (generation units of 100 MWp or above) based on their empirical flexibility. We process the hourly dispatch of sample units between 2019 and 2023 using a novel deep learning approach, that transforms time series into easy-to-cluster representations. We identify two clusters of peaker units and two clusters of non-peaker units, whose different empirical flexibility is quantified by cluster-level ramp rates. Non-peaker units, around half of the sample, are empirically less flexible than peakers, and make up for more than 83% of sample must-run generation. Regulatory changes addressing the low market responsiveness of non-peakers are needed to unlock their flexibility.

Problem

• Estimating empirical flexibility of gas power units
• Identifying clusters with differing operational flexibility characteristics
• Assessing real-world limitations versus technical assumptions in energy models

Innovation

• Deep clustering for empirical flexibility analysis
• Unsupervised embedding of hourly generation data
• Identified distinct clusters of peaker and non-peaker units