@inproceedings{dey_optimizing_2020,
	title = {Optimizing {Asynchronous} {Multi}-{Level} {Checkpoint}/{Restart} {Configurations} with {Machine} {Learning}},
	doi = {10.1109/IPDPSW50202.2020.00174},
	abstract = {With the emergence of versatile storage systems, multi-level checkpointing (MLC) has become a common approach to gain efficiency. However, multi-level checkpoint/restart can cause enormous I/O traffic on HPC systems. To use multilevel checkpointing efficiently, it is important to optimize check-point/restart configurations. Current approaches, namely modeling and simulation, are either inaccurate or slow in determining the optimal configuration for a large scale system. In this paper, we show that machine learning models can be used in combination with accurate simulation to determine the optimal checkpoint configurations. We also demonstrate that more advanced techniques such as neural networks can further improve the performance in optimizing checkpoint configurations.},
	booktitle = {2020 {IEEE} {International} {Parallel} and {Distributed} {Processing} {Symposium} {Workshops} ({IPDPSW})},
	author = {Dey, Tonmoy and Sato, Kento and Nicolae, Bogdan and Guo, Jian and Domke, Jens and Yu, Weikuan and Cappello, Franck and Mohror, Kathryn},
	month = may,
	year = {2020},
	keywords = {Computational modeling, Large-scale systems, HPC systems, storage management, parallel processing, learning (artificial intelligence), Machine learning, Neural networks, Predictive models, checkpointing, Checkpointing, Forestry, Machine Learning, machine learning models, MultiLevel Checkpointing (MLC), multilevel checkpointing configuration, Neural Network, restart configuration, software fault tolerance, storage systems},
	pages = {1036--1043}
}