9 September 2017 Coflow routing and spectrum assignment in optical orthogonal frequency division multiplexing data center networks
Author Affiliations +
Abstract
The communication between data-intensive applications in data centers often involves a collection of parallel flows, usually referred to as a coflow. A coflow between two groups of machines can capture diverse communication patterns observed in data centers. The static coflow routing and spectrum assignment (CofRSA) problem in optical orthogonal frequency division multiplexed data center networks is investigated, when the coflow traffic demands are given. The static CofRSA problem considers the spectrum constraints of the flows between different coflows and those within the same coflow. We formulate the static CofRSA problem as an integer linear programming (ILP) model. The objective of the ILP model is to minimize the used spectrum slots. However, the ILP model cannot achieve an optimal solution within tolerable time for large networks. To solve the problem, two highly efficient heuristic algorithms, the most cofSize first (MCSF) ordering algorithm and the greedy inserting (GI) algorithm, are proposed to achieve suboptimal solutions. The simulation results indicate that ILP provides an optimal solution for small networks, whereas GI and MCSF yield suboptimal solutions in large networks. The results also show that GI provides more efficient solutions than MCSF.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Aijun Liu, Yongmei Sun, Yuefeng Ji, "Coflow routing and spectrum assignment in optical orthogonal frequency division multiplexing data center networks," Optical Engineering 56(9), 096103 (9 September 2017). https://doi.org/10.1117/1.OE.56.9.096103 . Submission: Received: 26 March 2017; Accepted: 14 August 2017
Received: 26 March 2017; Accepted: 14 August 2017; Published: 9 September 2017
JOURNAL ARTICLE
9 PAGES


SHARE
Back to Top