RPMSP: A Novel Replica Placement Method Inspired by Self-Similarity Propagation of Plants
- Resource Type
- Conference
- Authors
- Yuan, Xingjia; Zhao, Yuelong
- Source
- 2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 2019 IEEE Intl Conf on. :596-601 Dec, 2019
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
General Topics for Engineers
Layout
Cloud computing
Time factors
Linear programming
Soil
Computer science
Animals
Cloud storage
Replica layout
Plants
Self-similarity propagation
Replica placement
- Language
Replica placement method determines replica layout directly and affects resource management of cloud storage indirectly. Since the imbalance of performance indicators in the issue of replica placement, this paper proposes a novel replica placement method inspired by self-similarity propagation of plants (RPMSP). Firstly, the issue of replica placement affected by multiple performance indicators is modeled as the objective space. Then, the method simulates the self-similarity propagation of plants to find the most profitable area and selects the optimal individual from it as the most suitable replica layout. Finally, it conducted several simulation experiments to evaluate the proposed method. The experimental results show that RPMSP can effectively find a suitable replica layout and balance the relationship among multiple performance indicators.