Sites Inria

Version française

POLARIS Research team

Performance analysis and optimization of LARge Infrastructures and Systems

Team presentation

The goal of the POLARIS project is to contribute to the understanding (from the observation, modeling and analysis to the actual optimization through adapted algorithms) of the performance of very large scale distributed systems by applying original ideas from various research fields and application  domains. Studying all these different aspects at once without restricting to specific systems is the key to push forward our understanding of such challenges and propose innovative solutions. If large computing infrastructures are naturally among our targets, the synergies with other data intensive sciences leads us to consider other kind of big data processing infrastructures as well. This is why we investigate problems arising from application domains as varied as large computing infrastructures, wireless networks, smart grids or transportation systems. The POLARIS team works in close cooperation with other research teams on a continuum of five research themes including measurement and experimentation, statistical trace analysis and visualization, discrete-event and perfect simulation, asymptotic modeling, stochastic optimization and game theory.

Research themes

  1. Measurement: Sound and Reproducible Experimental Methodology
  2. Analysis: Multi-Scale Analysis and Visualization
  3. Simulation: Fast and Faithful Performance Prediction of Very Large Systems
  4. Asymptotic Models: Local Interactions and Transient Analysis in Adaptive Dynamic Systems
  5. Distributed Optimization: Continuous Game Theory and On-line Distributed Optimization

 

From our past experience, we gather skills in:

  • Experiment design: experimental methodology, measuring/monitoring/tracing tools, experiment control, design of experiments, reproducible research, in particular in the context of large computing infrastructures (grid, HPC, volunteer computing, embedded systems, …).
  • Trace Analysis: parallel application visualization (paje, triva/viva, framesoc/ocelotl, …), characterization of failures in large distributed systems, visualization and analysis for geographical information system, spatio-temporal analysis of media events in RSS flows from newspapers, …
  • Modeling and Simulation: emulation, discrete event simulation, perfect sampling, Markov chains, Monte Carlo methods, …
  • Optimization: stochastic approximations, mean field limits, game theory, mean field games, primal dual optimization, learning, information theory.

Keywords: Performance evaluation Simulation Experimental methodology Distributed optimization Game theory Asymptotic models Large scale infrastructures