A data intensive heuristic approach to the two-stage streaming scheduling problem

被引:4
|
作者
Liang, Wei [1 ,2 ]
Hu, Chunhua [1 ,2 ]
Wu, Min [3 ]
Jin, Qun [4 ]
机构
[1] Hunan Univ Commerce, Key Lab Hunan Prov Mobile Business Intelligence, Changsha, Hunan, Peoples R China
[2] Hunan Univ Commerce, Mobile E Busines Collaborat Innovat Ctr Hunan Pro, Changsha, Hunan, Peoples R China
[3] China Univ Geosci, Sch Automat, Wuhan, Hubei, Peoples R China
[4] Waseda Univ, Fac Human Sci, Tokorozawa, Saitama, Japan
关键词
Data intensive computing; Scheduling; Makespan; NP-hard; HYBRID FLOW-SHOPS; MANAGEMENT; ALGORITHM; SYSTEMS;
D O I
10.1016/j.jcss.2017.01.005
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Data intensive computing (DIC) provides a high performance computing approach to process large volume of data. In this study, a new formalization is introduced to present the two-stage DIC task execution in a stream manner. A novel heuristic algorithm is proposed for the scheduling problem due to the NP complexity. The theoretical approximation ratio bounds for the heuristic are analyzed and confirmed by the experimental evaluation. Overall, we observe that the proposed method conducts average 1.2 times makespan than the theoretic bound of the optimal solution. Besides, the proposed method outperforms the GA and FIFO scheduling schemes with overall improvements. (C) 2017 Elsevier Inc. All rights reserved.
引用
收藏
页码:64 / 79
页数:16
相关论文
共 50 条