Abstract
With the rapid development of data centers, the energy consumption brought by more and more data centers cannot be underestimated. How to intelligently manage software-defined data center networks to reduce network energy consumption and improve network performance is becoming an important research subject. In this paper, for the flows with deadline requirements, we study how to design the rate-variable flow scheduling scheme to realize energy-saving and minimize the mean completion time (MCT) of flows based on meeting the deadline requirement. The flow scheduling optimization problem can be modeled as a Markov decision process (MDP). To cope with a large solution space, we design a DDPG-EEFS algorithm to find the optimal scheduling scheme for flows. The simulation result reveals that the DDPG-EEFS algorithm only trains part of the states and gets a good energy-saving effect and network performance. When the traffic intensity is small, the transmission time performance can be improved by sacrificing a little energy efficiency.
Highlights
With the development of 5G technology [1,2,3,4], more and more data centers as important carriers of data storage and processing will be established [5,6,7]
To verify the effectiveness of the proposed deep deterministic policy gradient (DDPG)-EEFS algorithm, simulation is conducted in the SDN-enabled data center network with Fat-Tree topology
This work selects the commonly used Fat-Tree data center network topology, which is set to consist of 20 four-point switches, 16 hosts, and 48 links
Summary
With the development of 5G technology [1,2,3,4], more and more data centers as important carriers of data storage and processing will be established [5,6,7]. (1) When the network topology and the routes of flows are determined, to further reduce the energy consumption and improve the QoS requirement, based on the ALR energy cost model, the energy-saving QoS flow scheduling problem and the dual optimization objective of minimum energy consumption and mean completion time of flows are proposed. The dual optimal problem is a continual control problem, and it has a large solution space, which can be modeled as a Markov decision process (2) Based on the advantages of DDPG in solving continuous control problems, and the problem of scalability, the DDPG Energy-Efficient Flow Scheduling (DDPG-EEFS) Algorithm is proposed to obtain the optimal scheduling scheme (3) Based on the ALR energy cost model, a rate variable flow transmission mechanism is proposed to flexibly scheduling flow and to balance the flow transmission on the link in time and space and improve the energy-saving effectively.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
