Ronak Singh Monga, a data science student at Indiana University Bloomington who was a research intern at Berkeley Lab this past summer, was awarded first place in the Association for Computing Machinery’s (ACM) Student Research Competition for Undergraduates during SC23.

While at Berkeley Lab, Monga was mentored by Berkeley Lab Computing Sciences’ Alex Sim and John Wu of the Scientific Data Division, where he researched whether and how in-network regional data caching systems that store scientific data can reduce network traffic and access latency.

Monga’s poster, “Comparative Study of the Cache Utilization Trends for Regional Scientific Data Caches,” built on this work, examining the Southern California Petabyte Scale Cache and the Chicago Regional Cache for a high-energy physics experiment to analyze cache utilization trends and compare regional data access patterns. The results showed that the cache contributed to sharing a majority of data and that regional differences can be explained through comparative study. In addition, predictions of cache behavior show low error values in both regions, providing a useful tool for future data resource planning.

“Ronak is an articulate and enthusiastic young scholar,” Wu said.  “He came to us from Indiana University and worked on a comparative study of in-network data caches.  He worked through terabytes of log files from the cache installations and found practical recommendations that could significantly improve the effectiveness of the cache installation at Chicago.”