Intelligent Replication Management for HDFS Using Reinforcement Learning
This work addresses storage system optimization for cloud computing, but it is incremental as it explores reinforcement learning as an alternative to heuristics without full practical implementation.
The paper tackled the problem of block management in HDFS storage systems by applying reinforcement learning, achieving performance comparable to or better than existing heuristics, though scalability and fidelity limitations were noted.
Storage systems for cloud computing merge a large number of commodity computers into a single large storage pool. It provides high-performance storage over an unreliable, and dynamic network at a lower cost than purchasing and maintaining large mainframe. In this paper, we examine whether it is feasible to apply Reinforcement Learning(RL) to system domain problems. Our experiments show that the RL model is comparable, even outperform other heuristics for block management problem. However, our experiments are limited in terms of scalability and fidelity. Even though our formulation is not very practical,applying Reinforcement Learning to system domain could offer good alternatives to existing heuristics.