Paper Info
Title
Optimizing Concurrent Evacuation Transfers for Geo-Distributed Datacenters in SDN.
Abstract
Disaster evacuation assigns bulk endangered data to geographically distributed datacenters out of disaster zone within acceptable duration. However, previous works overlooked the bandwidth allocation proportion problem and multi-path routing problem for multiple concurrent evacuation transfers (especially with shared links). Therefore they could not guarantee full utilization of network transmission capability in disaster evacuation. In this paper, with flexible traffic scheduling in the Software Defined Network scenarios, we propose a new optimal bandwidth proportion allocation strategy for concurrent evacuation transfers. To maximize disaster evacuation capability, we formulate the bandwidth allocation problem as a new Bandwidth-Proportion-Constrained Multi-Commodity Flow (BPC-MCF) problem. To obtain optimal solution for practical networks of large scale, we propose a Bandwidth-Proportion-Aware Ant Colony Optimization (BPA-ACO) algorithm to achieve maximum evacuation flow matching data amount proportion of concurrent evacuation transfers. We introduce available evacuation capability, bandwidth proportion offset and link sharing degree to guide optimal solution searching. We adjust bandwidth proportion by rearranging flows in shared links and alternate paths. Through extensive simulations we demonstrate that our algorithm has better performance with less total evacuation time and higher network utilization.
Year
Venue
Field
2017
ICA3PP
Ant colony optimization algorithms,Computer science,Scheduling (computing),Bandwidth allocation,Bandwidth (signal processing),Software-defined networking,Offset (computer science),Distributed computing
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
7
6
Name
Order
Citations
PageRank
Xiaole Li194.87
Hua Wang27614.82
Shanwen Yi3166.34
Xibo Yao412.38
Fangjin Zhu501.01
Linbo Zhai6157.01