Evaluation of 'Dunkelflaute' event detection methods considering grid operators' needs

TL;DR

This paper reviews and validates methods for detecting 'dunkelflaute' events, which challenge renewable energy supply, comparing their effectiveness against detailed power system simulations to inform grid management.

Contribution

It provides a comparative validation of three dunkelflaute detection methods using real system data, highlighting their strengths and limitations for grid operator needs.

Findings

All methods can identify some energy shortages but miss others.

Residual load input improves detection performance.

Otero'22 method is the most effective and easy to implement.

Abstract

Weather conditions associated with low electricity production from renewable energy sources (RES) can result in challenging 'dunkelflaute' events, where 'dunkel' means dark and 'flaute' refers to low windspeeds. In a power system relying significantly on RES, such events can pose a risk for maintaining resource adequacy, i.e. the balance between generation and demand, particularly if they occur over a large geographical area and for an extended period of time. This risk is further emphasized in periods of cold ('kalte') temperature, known as 'kalte dunkelflaute'. In this paper, we perform a literature review of different methods to identify dunkelflaute events from hourly RES production and load data alone. We then validate three of these methods by comparing their results with periods of shortage identified from a detailed power system simulation model used by grid operators (ERAA2023). Strengths and weaknesses of these methods are discussed in terms of their data requirements, ease of application, and skill in detecting dunkelflaute events. We find that all three 'dunkelflaute' event detection methods have some ability to identify potential energy shortages, but none are able to detect all events. Most likely other factors such as the presence of energy storage capacity, non-weather-dependent outages, and model-related factors limit the skill of these methods. We find that all three methods perform best if the residual load is used as input, rather than hourly RES production or load alone. Overall, we find that Otero'22 is the method that yields the best results while being straightforward to implement and requiring only data with daily resolution. The results hold for countries relying on a small or a large share of RES production in their electricity mix.