Adaptive Data Replication Optimization Based on Reinforcement Learning
- Resource Type
- Authors
- Richi Nayak; Chee Keong Wee
- Source
- SSCI
- Subject
- business.industry
Adaptive optimization
Computer science
Distributed computing
Information technology
Workload
0102 computer and information sciences
02 engineering and technology
01 natural sciences
Software
010201 computation theory & mathematics
0202 electrical engineering, electronic engineering, information engineering
Reinforcement learning
020201 artificial intelligence & image processing
Enterprise it
business
Metaheuristic
Throughput (business)
- Language
Data replication plays an important role in enterprise IT landscapes, where data is shared among multiple IT systems. IT administrators need to tune the replicating software’s configuration setting for it to perform at its optimum level. It is a challenge to continue optimizing the software’s configuration to keep up with the fluctuating workload in a dynamic business environment. We propose a novel approach of using reinforcement learning with meta-heuristics to create an adaptive optimization method for data replication software. The experimental results show the replicating software managed by the proposed approach can perform at an optimum level despite consistently working under changing workloads.