<ul><li>The paper proposes a Generative Adversarial Network-based Synthetic Residential Load Pattern (RLP-GAN) generation model.</li><li>RLP-GAN leverages an over-complete autoencoder to capture dependencies within complex and diverse load patterns.</li><li>A model weight selection method is incorporated to address the mode collapse problem and generate load patterns with high diversity.</li><li>The results demonstrate that RLP-GAN outperforms state-of-the-art models in capturing temporal dependencies and generating load patterns with higher similarity to real data.</li></ul>

Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection

Discover more