#### DMCA

## On The Energy Optimization for Precedence Constrained Applications Using Local Search Algorithms

### Citations

240 | Performance-effective and low-complexity task scheduling for heterogeneous computing
- Topcuoglu, Hariri, et al.
- 2002
(Show Context)
Citation Context ...tant execution time among processors. Since we are interested in heterogenous instances, we have only considered the structure of these applications and we have implemented the procedure described in =-=[9]-=- to consider heterogeneity. We fixed the parameter β to 1. Parameter β is basically the heterogeneity factor for processor speeds. A high percentage value (i.e., a percentage of 1) causes a significan... |

122 | Energy-Efficient Algorithms - Albers |

44 | A cooperative game theoretical technique for joint optimization of energy consumption and response time in computational grids - Khan, Ahmad - 2009 |

36 |
A case study on the use of workflow technologies for scientific analysis: Gravitational wave data analysis,” in Workflows for eScience: Scientific Workflows for Grids
- Brown, Brady, et al.
- 2007
(Show Context)
Citation Context ...ts are the robot control application, a sparse matrix solver, fpppp problem from the Standard Task Graph Set (STG) [17], and the Laser Interferometer Gravitational-Wave Observatory (LIGO) application =-=[16]-=-. Table II summarizes the main characteristics for these applications: instances size, edges amount and the ratio between tasks and edges (ETR). 136 TABLE I VOLTAGE-RELATIVE SPEED PAIRS [6], [8] Pair ... |

30 | Towards Energy Aware Scheduling for Precedence Constrained Parallel Tasks in a Cluster with DVFS
- Laszewski, Wang
(Show Context)
Citation Context ...an be better and use less energy. In the independent mode, which is considered as a twophases optimization technique, a best-effort scheduling algorithm is combined with a slack reclamation technique =-=[4]-=-– [6]. The slack reclamation algorithm is used as a second 978-1-4673-2362-8/12/$31.00 ©2012 IEEE 133 pass to minimize the energy consumption of tasks in a schedule generated by the best-effort schedu... |

21 |
2002), A standard task graph set for fair evaluation of multiprocessor scheduling algorithms
- Tobita, Kasahara
(Show Context)
Citation Context ...uctured realworld parallel applications. The four applications used for our experiments are the robot control application, a sparse matrix solver, fpppp problem from the Standard Task Graph Set (STG) =-=[17]-=-, and the Laser Interferometer Gravitational-Wave Observatory (LIGO) application [16]. Table II summarizes the main characteristics for these applications: instances size, edges amount and the ratio b... |

20 |
An overview of energy efficiency techniques in cluster computing system
- Valentini, Lassonde, et al.
(Show Context)
Citation Context ...ion time, hence makespan. This is the principle of the Dynamic Voltage Scaling (DVS) technique. DVS (equivalently, dynamic voltage frequency scaling, dynamic speed scaling, dynamic frequency scaling) =-=[2]-=- enables processors to dynamically adjust voltage supply levels aiming to reduce power consumption at the expense of performance deterioration. For heterogeneous distributed computing systems, variabl... |

20 |
Energy conscious scheduling for distributed computing systems under different operating conditions
- Lee, Zomaya
- 2011
(Show Context)
Citation Context ...ply voltage vk and its corresponding relative speed msk. We consider that processors consume energy while idling; that is, when a processor is idling it is assumed that the lowest voltage is supplied =-=[8]-=-. A precedence constrained parallel application is represented by a Directed Acyclic Graph (DAG). The DAG is defined as G = (T,E), where T is a finite set of nodes (vertices) and E is a finite set of ... |

18 | Dynamic resource management in energy constrained heterogeneous computing systems using voltage scaling - Kim, Siegel, et al. - 2008 |

15 | Energy optimization of multiprocessor systems on chip by voltage selection
- Andrei, Eles, et al.
- 2007
(Show Context)
Citation Context ...m is further complicated because slack allocation must consider variations in workload and energy consumption among different tasks. Moreover, the discrete voltage scaling problem is strongly NP-hard =-=[3]-=-, the proof is a reduction to the discrete time-cost trade-off problem by restricting the dynamic voltage scaling problem to contain only tasks that requires an execution of one clock cycle. Variable ... |

15 |
Comparison and analysis of eight scheduling heuristics for the optimization of energy consumption and makespan in large-scale distributed systems,” The
- Lindberg, Leingang, et al.
(Show Context)
Citation Context ... to other scheduling algorithms, with a low time complexity (O(nlogn+ (e+ n)m)). An important number of energy conscious scheduling algorithms have been proposed in the literature [2], [5], [7], [8], =-=[10]-=-–[15]. These algorithms mainly differ on the assumptions they consider. However, the most common technique they exploit is DVS. Some energy-aware scheduling algorithms are based on the best-effort ide... |

15 |
A parallel bi-objective hybrid metaheuristic for energy-aware scheduling for cloud computing systems
- Mezmaz, Melab, et al.
- 2011
(Show Context)
Citation Context ...ther scheduling algorithms, with a low time complexity (O(nlogn+ (e+ n)m)). An important number of energy conscious scheduling algorithms have been proposed in the literature [2], [5], [7], [8], [10]–=-=[15]-=-. These algorithms mainly differ on the assumptions they consider. However, the most common technique they exploit is DVS. Some energy-aware scheduling algorithms are based on the best-effort idea. Ba... |

14 |
Some observations on optimal frequency selection in DVFS-based energy consumption minimization
- Rizvandi, Taheri, et al.
- 2011
(Show Context)
Citation Context ... better and use less energy. In the independent mode, which is considered as a twophases optimization technique, a best-effort scheduling algorithm is combined with a slack reclamation technique [4]– =-=[6]-=-. The slack reclamation algorithm is used as a second 978-1-4673-2362-8/12/$31.00 ©2012 IEEE 133 pass to minimize the energy consumption of tasks in a schedule generated by the best-effort scheduling ... |

3 | A Multiobjective GRASP Algorithm for Joint Optimization of Energy Consumption and Schedule Length of Precedence-Constrained Applications
- Pecero, Bouvry, et al.
(Show Context)
Citation Context ...comparable to other scheduling algorithms, with a low time complexity (O(nlogn+ (e+ n)m)). An important number of energy conscious scheduling algorithms have been proposed in the literature [2], [5], =-=[7]-=-, [8], [10]–[15]. These algorithms mainly differ on the assumptions they consider. However, the most common technique they exploit is DVS. Some energy-aware scheduling algorithms are based on the best... |

3 |
Energy aware DAG scheduling on heterogeneous systems
- Baskiyar, Abdel-Kader
(Show Context)
Citation Context ...s mainly differ on the assumptions they consider. However, the most common technique they exploit is DVS. Some energy-aware scheduling algorithms are based on the best-effort idea. Baskiyar and Palli =-=[14]-=- introduces an algorithm that combines Decisive Path Scheduling (DPS) with DVS to minimize both finish time and energy consumption. However, energy consumption due to idle time is not considered in th... |

1 |
Low Energy and High Performance Scheduling
- Pecero, Bouvry, et al.
- 2010
(Show Context)
Citation Context ...ngth comparable to other scheduling algorithms, with a low time complexity (O(nlogn+ (e+ n)m)). An important number of energy conscious scheduling algorithms have been proposed in the literature [2], =-=[5]-=-, [7], [8], [10]–[15]. These algorithms mainly differ on the assumptions they consider. However, the most common technique they exploit is DVS. Some energy-aware scheduling algorithms are based on the... |

1 |
Nonparametric Statistics with Applications to
- Kvam, Vidakovic
- 2007
(Show Context)
Citation Context ... and 32 processors. We have executed each algorithm 15 times on each instance. MAX STEPS is fixed to 100 on the proposed algorithms. B. Results We have first evaluated the algorithms by Friedman test =-=[18]-=-. The Friedman test is a nonparametric statistical tool that allows to compare a set of a non normalized population to verify if exists significant statistical differences in the sample, additionally,... |