用扩散模型生成可配置、逼真的多设备存储访问记录
A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation
- 基于扩散模型构建可调节的多设备存储痕迹生成框架
- 生成痕迹与设定配置误差仅8%，保真度和多样性高
- 适合存储系统仿真与性能评估的研究者使用
我们提出DiTTO，一种基于扩散的新型框架，用于生成精确可配置、高度逼真且多样化的多设备存储访问痕迹。借助先进的扩散技术，DiTTO能够合成高保真连续痕迹，准确捕捉时间动态及设备间的依赖关系，并支持用户自定义配置。实验结果表明，DiTTO生成的痕迹在保真度与多样性方面表现优异，且与预设配置的偏差仅8%。
原文摘要 · Abstract (English)
We propose DiTTO, a novel diffusion-based framework for generating realistic, precisely configurable, and diverse multi-device storage traces. Leveraging advanced diffusion techniques, DiTTO enables the synthesis of high-fidelity continuous traces that capture temporal dynamics and inter-device dependencies with user-defined configurations. Our experimental results demonstrate that DiTTO can generate traces with high fidelity and diversity while aligning closely with guided configurations with only 8% errors.
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。