Authors:
Lucas Benevides Dias
1
;
Dennis Sávio Silva
2
;
3
;
Rafael T. de Sousa Junior
4
and
Maristela Holanda
2
Affiliations:
1
Institute for Applied Economic Research, Brasília, Brazil
;
2
Department of Computer Science, University of Brasília, Brasília, Brazil
;
3
Federal University of Piauí, Picos, Piauí, Brazil
;
4
Department of Electrical Engineering, University of Brasília, Brasília, Brazil
Keyword(s):
Databases, NoSQL, Internet of Things, Time Series, Auto-tuning, Cassandra, Compaction Strategies.
Abstract:
Internet of Things environments may generate massive volumes of time series data, with specific characteristics that must be considered to facilitate its storage. The Apache Cassandra NoSQL database provides compaction strategies that improve data pages’ organization, benefiting the storage and query performance for time series data. This study exploits the temporal characteristics of IoT data, and proposes an engine called C*DynaConf based on the TWCS (Time Window Compaction Strategy), which dynamically changes its compaction parameters according to configurations previously defined as optimal, considering current metadata and metrics from the database. The results show that the engine’s use brought a 4.52% average gain in operations performed compared to a test case with optimal initial configuration that changes the scenario’s characteristics change over time.