@misc{Astsatryan_Hrachya_Performance, author={Astsatryan Hrachya and Kocharyan Aram and Hagimont Daniel and Lalayan Arthur}, howpublished={online}, publisher={De Gruyter}, language={English}, abstract={The optimization of large-scale data sets depends on the technologies and methods used. The MapReduce model, implemented on Apache Hadoop or Spark, allows splitting large data sets into a set of blocks distributed on several machines. Data compression reduces data size and transfer time between disks and memory but requires additional processing. Therefore, finding an optimal tradeoff is a challenge, as a high compression factor may underload Input/Output but overload the processor. The paper aims to present a system enabling the selection of the compression tools and tuning the compression factor to reach the best performance in Apache Hadoop and Spark infrastructures based on simulation analyzes.}, type={article}, title={Performance Optimization System for Hadoop and Spark Frameworks}, }