Huang receives prestigious NSF CAREER award to build a learning-based storage ecosystem
The emergence of the cloud and edge computing combined with new storage hardware like non-volatile memory has made the data storage ecosystem even more complicated than it was before. The entire storage hardware and software stacks are under increasing pressure to adapt instantly to meet performance and efficiency requirements.
According to ECE Assistant Professor Jian Huang, the storage ecosystem could benefit from a whole new design approach. Recently, Huang received a $593,000 NSF CAREER research grant for young faculty to develop systems and architecture techniques to build a learning-based storage ecosystem.
During the five-year grant, Huang and his students will develop learning-based storage devices, storage software optimizations, and storage architecture innovations.
According to Huang, recent advances in machine learning techniques show that the learning-based approach is a promising method to solve system optimization problems. However, it remains unclear how the storage ecosystem will embrace the learning techniques to facilitate its development, deployment, and optimizations across the full stack.
“Our project will intensively explore learning-based techniques to enable automated development, management, and optimizations of storage systems,” Huang said.
Huang’s approach involves four research areas. First, he will develop customized storage devices for specific application types with automated tuning of hardware specifications.
“This will enable developers to identify optimal device specifications with much less time and effort,” he said.
Second, he will develop elastic storage management for multi-tenant applications using reinforcement learning, which will result in improved resource utilization and performance isolation. Third, he will integrate the storage hardware knowledge into the learning procedure to facilitate the development of learning-based storage software.
Fourth, he will revisit the storage hardware architecture for building learning-based storage drives to further enhance the learning-based storage ecosystem.
Another component of NSF CAREER award grants is course and curriculum development. Huang plans to incorporate research results into the ECE522 course, Emerging Memory and Storage Systems. Huang created this course based on material he taught in ECE598, Advanced Memory and Storage Systems.
He also plans to provide undergraduates with research internships and individual study projects.
The NSF CAREER Award is the agency’s most prestigious award in support of early-career faculty who have the potential to serve as academic role models in both research and education and can advance the mission of their respective department or organization.