RL-Storage applies deep Q-learning to storage parameter tuning and claims up to 2.6x throughput gains and 43% latency reduction, but the evidence is not rigorously presented.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.OS 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Dynamic Optimization of Storage Systems Using Reinforcement Learning Techniques
RL-Storage applies deep Q-learning to storage parameter tuning and claims up to 2.6x throughput gains and 43% latency reduction, but the evidence is not rigorously presented.