English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electricity load forecasting is crucial for effectively managing andoptimizing power grids. Over the past few decades, various statistical and deeplearning approaches have been used to develop load forecasting models. Thispaper presents an interpretable machine learning approach that identifies loaddynamics using data-driven methods within an operator-theoretic framework. Werepresent the load data using the Koopman operator, which is inherent to theunderlying dynamics. By computing the corresponding eigenfunctions, wedecompose the load dynamics into coherent spatiotemporal patterns that are themost robust features of the dynamics. Each pattern evolves independentlyaccording to its single frequency, making its predictability based on lineardynamics. We emphasize that the load dynamics are constructed based on coherentspatiotemporal patterns that are intrinsic to the dynamics and are capable ofencoding rich dynamical features at multiple time scales. These features arerelated to complex interactions over interconnected power grids and differentexogenous effects. To implement the Koopman operator approach more efficiently,we cluster the load data using a modern kernel-based clustering approach andidentify power stations with similar load patterns, particularly those withsynchronized dynamics. We evaluate our approach using a large-scale datasetfrom a renewable electric power system within the continental Europeanelectricity system and show that the Koopman-based approach outperforms a deeplearning (LSTM) architecture in terms of accuracy and computational efficiency.The code for this paper has been deposited in a GitHub repository, which can beaccessed at the following address github.com/Shakeri-Lab/Power-Grids.

Characterizing the load profile in power grids by Koopman mode decomposition of interconnected dynamics