Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection
This work addresses data scarcity for residential sector decarbonization and grid planning, offering a novel method for generating diverse and realistic load patterns, though it is incremental in improving upon existing GAN-based approaches.
The paper tackled the problem of generating synthetic residential load data to address data scarcity for decarbonization and grid planning, proposing RLP-GAN, a weakly-supervised GAN framework that outperformed state-of-the-art models in capturing temporal dependencies and similarity, with results validated on real-world data from 417 households and a released dataset of one million synthetic profiles.
The scarcity of high-quality residential load data can pose obstacles for decarbonizing the residential sector as well as effective grid planning and operation. The above challenges have motivated research into generating synthetic load data, but existing methods faced limitations in terms of scalability, diversity, and similarity. This paper proposes a Generative Adversarial Network-based Synthetic Residential Load Pattern (RLP-GAN) generation model, a novel weakly-supervised GAN framework, leveraging an over-complete autoencoder to capture dependencies within complex and diverse load patterns and learn household-level data distribution at scale. We incorporate a model weight selection method to address the mode collapse problem and generate load patterns with high diversity. We develop a holistic evaluation method to validate the effectiveness of RLP-GAN using real-world data of 417 households. 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. Furthermore, we have publicly released the RLP-GAN generated synthetic dataset, which comprises one million synthetic residential load pattern profiles.