用扩散模型扩充小样本数据，提升电力负荷预测精度
Generative Modeling and Data Augmentation for Power System Production Simulation
- 用扩散模型生成新数据扩增训练集
- 预测误差比原始数据降低约200倍
- 适合数据稀缺的电力系统建模场景
负荷预测是电力系统生产仿真中的关键环节，对系统稳定运行至关重要。当前该领域主流采用机器学习方法，但训练数据有限仍是主要挑战。本文提出一种基于生成模型的数据增强方法，分两步进行：首先利用基于扩散的生成模型扩充数据集，然后在扩增后的数据上训练多种机器学习回归器以筛选最优模型。与原始数据相比，扩增后数据显著降低了预测误差；且扩散模型相较生成对抗模型误差缩小约200倍，并在潜在数据分布对齐方面表现更优。
原文摘要 · Abstract (English)
As a key component of power system production simulation, load forecasting is critical for the stable operation of power systems. Machine learning methods prevail in this field. However, the limited training data can be a challenge. This paper proposes a generative model-assisted approach for load forecasting under small sample scenarios, consisting of two steps: expanding the dataset using a diffusion-based generative model and then training various machine learning regressors on the augmented dataset to identify the best performer. The expanded dataset significantly reduces forecasting errors compared to the original dataset, and the diffusion model outperforms the generative adversarial model by achieving about 200 times smaller errors and better alignment in latent data distributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。