Treffer: Evaluation of SQL and NoSQL Databases on Parallel Processing

This study performs an independent examination of the performance exhibited by NoSQL and SQL databases regarding key-value stores in parallel processing using a simulation model containing 15 nodes. Specifically, the focus is on comparing the efficiency of read, write, delete, and instantiate operations within the context of key-value stores implemented with both NoSQL (MongoDB, RavenDB, and Cassandra) and SQL (MS-SQL) databases within the average time of three runs. The results show that SQL achieved better read operation times, while NoSQL databases, especially RavenDB, had better results in the other operations.