scholarly journals Weight based Task Assignment Model to Tolerate Faults in Heterogeneous Distributed Systems

2015 ◽  
Vol 125 (9) ◽  
pp. 25-28 ◽  
Author(s):  
Shubhinder Kaur ◽  
Gurpreet Kaur
Keyword(s):  
Distributed Systems ◽  
Task Assignment ◽  
Assignment Model ◽  
Heterogeneous Distributed Systems

Energy-Efficient Scheduling Optimization for Parallel Applications on Heterogeneous Distributed Systems

2020 ◽  
Vol 29 (13) ◽  
pp. 2050203
Author(s):  
Nan Gao ◽  
Cheng Xu ◽  
Xin Peng ◽  
Haibo Luo ◽  
Wufei Wu ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Distributed Systems ◽  
Energy Efficient ◽  
Gaussian Elimination ◽  
Task Assignment ◽  
Computation Time ◽  
Parallel Applications ◽  
Heterogeneous Distributed Systems ◽  
Static Energy ◽  
Energy Efficient Scheduling

Designing energy-efficient scheduling algorithms on heterogeneous distributed systems is increasingly becoming the focus of research. State-of-the-art works have studied scheduling by combining dynamic voltage and frequency scaling (DVFS) technology and turning off the appropriate processors to reduce dynamic and static energy consumptions. However, the methods for turning off processors are ineffective. In this study, we propose a novel method to assign priorities to processors for facilitating effective selection of turned-on processors to decrease static energy consumption. An energy-efficient scheduling algorithm based on bisection (ESAB) is proposed on this basis, and this algorithm directly turns on the most energy-efficient processors depending on the idea of bisection to reduce static energy consumption while dynamic energy consumption is decreased by using DVFS technology. Experiments are performed on fast Fourier transform, Gaussian elimination, and randomly generated parallel applications. Results show that our ESAB algorithm makes a better trade-off between reducing energy consumption and low computation time of task assignment (CTTA) than existing algorithms under different scale conditions, deadline constraints, and degrees of parallelism and heterogeneity.

Adaptive load sharing in heterogeneous distributed systems

1990 ◽  
Vol 9 (4) ◽  
pp. 331-346 ◽  
Author(s):  
Ravi Mirchandaney ◽  
Don Towsley ◽  
John A. Stankovic
Keyword(s):  
Distributed Systems ◽  
Load Sharing ◽  
Heterogeneous Distributed Systems

scholarly journals Combining an Extended SMAA-2 Method with Integer Linear Programming for Task Assignment of Multi-UCAV under Multiple Uncertainties

Symmetry ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 587 ◽  
Author(s):  
Jun Wang ◽  
Pengcheng Luo ◽  
Xinwu Hu ◽  
Xiaonan Zhang
Keyword(s):  
Linear Programming ◽  
Integer Linear Programming ◽  
Programming Model ◽  
Task Assignment ◽  
Target Information ◽  
Interval Numbers ◽  
Weighted Arithmetic ◽  
Assignment Model ◽  
Arithmetic Averaging Operator ◽  
Multiple Uncertainties

Uncertainty should be taken into account when establishing multiobjective task assignment models for multiple unmanned combat aerial vehicles (UCAVs) due to errors in the target information acquired by sensors, implicit preferences of the commander for operational objectives, and partially known weights of sensors. In this paper, we extend the stochastic multicriteria acceptability analysis-2 (SMAA-2) method and combine it with integer linear programming to achieve multiobjective task assignment for multi-UCAV under multiple uncertainties. We first represent the uncertain target information as normal distribution interval numbers so that the values of criteria (operational objectives) concerned can be computed based on the weighted arithmetic averaging operator. Thus, we obtain multiple criteria value matrices for each UCAV. Then, we propose a novel aggregation method to generate the final criteria value matrix based on which the holistic acceptability indices are computed by the extended SMAA-2 method. On this basis, we convert the task assignment model with uncertain parameters into an integer linear programming model without uncertainty so as to implement task assignment using the integer linear programming method. Finally, we conduct a case study and demonstrate the feasibility of the proposed method in solving the multiobjective task assignment problem multi-UCAV under multiple uncertainties.

Sign in / Sign up

Export Citation Format

Share Document