Skip to content

Mina Naghshnejad

 

↓

Mina Naghshnejad

Cloud Lab

Electrical Engineering and Computer Science (EECS)

University of California, Merced

California, USA

Email: MNaghshnejad at UCMerced.edu

 

URL: http://cloudlab.ucmerced.edu/mina

I apply machine learning to improve scheduling algorithms in distributed processing systems. More accurate online prediction of resource usages for cloud and cluster workloads improves the scheduling performance, efficiency, and fairness. I am currently designing new online learning algorithms to improve the online prediction accuracy for these workloads. I do data science side projects in my spare time!

  • Research Interests:

Applied Machine Learning,

Time Series Analysis,

Online learning,

Workload Characterization,

Resource management for distributed processing systems

  • Publications:

Naghshnejad, M. & Singhal, M.''A hybrid scheduling platform: a runtime prediction reliability aware scheduling platform to improve HPC scheduling performance" J Supercomput (2019). https://doi.org/10.1007/s11227-019-03004-3  jsc_hybrid.pdf

Mina Naghshnejad, Mukesh Singhal. “Adaptive Online Runtime Prediction to Improve HPC Application Latency in Cloud“, IEEE CLOUD 2018- Cloud Management and Operations -

Mina Naghshnejad, Sungjin Im, Mukesh Singhal. "Scheduling Jobs with Non-uniform Demands on Multiple Servers without Interruption, INFOCOM 2016,  PDF