TY - GEN
T1 - DENA
T2 - 44th Annual IEEE Conference on Local Computer Networks, LCN 2019
AU - Zandi, Yasamin
AU - Majidi, Akbar
AU - Ma, Lizhuang
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - We propose DENA as a deep reinforcement learning (DRL) based energy-efficient algorithm in the data center. To achieve the goal, DENA adjusts the transmission rate for each flow with deadlines and reduce the flow completion time (FCT) when the paths of flows are pre-given. Moreover, DENA includes a neural network classifier and a DRL system (DS). Accordingly, classifier separates the mice and elephant flows, then directly transfers the mice flows to avoid latency, while DS detects the interval of the most significant energy consumption density as a critical interval to schedule elephant flows. Besides, we apply deep deterministic policy gradient to DS with the advantage of an optimal base solution to enhance the accuracy of exploration. To the best of our knowledge, we are the first to use DRL for the rate adjustment. Our results show that besides saving energy, DENA reduces FCT for elephant flows workload 4.12%, data mining 1.04% and Hadoop 3.8%.
AB - We propose DENA as a deep reinforcement learning (DRL) based energy-efficient algorithm in the data center. To achieve the goal, DENA adjusts the transmission rate for each flow with deadlines and reduce the flow completion time (FCT) when the paths of flows are pre-given. Moreover, DENA includes a neural network classifier and a DRL system (DS). Accordingly, classifier separates the mice and elephant flows, then directly transfers the mice flows to avoid latency, while DS detects the interval of the most significant energy consumption density as a critical interval to schedule elephant flows. Besides, we apply deep deterministic policy gradient to DS with the advantage of an optimal base solution to enhance the accuracy of exploration. To the best of our knowledge, we are the first to use DRL for the rate adjustment. Our results show that besides saving energy, DENA reduces FCT for elephant flows workload 4.12%, data mining 1.04% and Hadoop 3.8%.
UR - https://www.scopus.com/pages/publications/85080953177
U2 - 10.1109/LCN44214.2019.8990731
DO - 10.1109/LCN44214.2019.8990731
M3 - 会议稿件
AN - SCOPUS:85080953177
T3 - Proceedings - Conference on Local Computer Networks, LCN
SP - 234
EP - 237
BT - Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019
A2 - Andersson, Karl
A2 - Tan, Hwee-Pink
A2 - Oteafy, Sharief
PB - IEEE Computer Society
Y2 - 14 October 2019 through 17 October 2019
ER -
