To achieve the ultimate success of global collaborative resource sharing in Grid computing, an effective and efficient Grid resource management system is necessary and it is only possible if its core component, the scheduler, can perform scheduling in an efficient manner. Scheduling tasks to resources in Grid computing is a challenging task and known as a NP hard problem. In this paper, we propose a novel hybrid heuristic-based algorithm, which synergised the excellent diversification capability of Great Deluge (GD) algorithm with the powerful systematic multi-neighbourhood search strategy captured in Variable Neighbourhood Descent (VND) algorithm, to efficiently schedule independent tasks in Grid computing environment with an objective of minimising the makespan. Simulation experiments have been conducted to examine the impact of hybridising GD and VND. In addition, the performance of the proposed algorithm has been evaluated and compared with some other recent meta-heuristics in the literature. The experimental simulation results show that our proposed algorithm outperforms the other algorithms in the literature and the performance improvement achieved by this hybrid strategy is effective and efficient with respect to makespan and computational time as it can obtain good quality (makespan) of solutions while obviating the drawback of requiring high computational cost from the VND.

No abstract

Wireless sensor networks operate through commonly self-organized sensor nodes to transfer data in a multi-hop approach to a central sink. In order to support fine-grained diagnostic analysis and optimize the performance level of the networks, the reconstruction of per-packet routing path is essential. However, in large-scale networks, the performance levels of the current path reconstruction method decline rapidly, with loss of links. An efficient approach to fully comprehend the complex internal behavior of network is through the reconstruction of the routing path of each received packet at the sink side. This paper discussed the added of energy efficiency parameter to enhance the inference Path (iPath). Thus, the iPath by added the energy efficiency enables the reconstruction of the per-packet routing paths of large-scale networks, by providing a stable and efficient route to exchange messages between source and destination in a timely manner. This work uses iterative boosting algorithm to find an alternative path with less distance and energy consumption. To achieve energy efficiency, it compresses the packet information by using GZIP tools in JAVA. Energy efficient iPath (E-iPath) is evaluated with several variations of nodes in WSN deployments as well as large-scale simulations. The findings demonstrate that E-iPath surpasses other current approaches such as EEPMM. E-iPath has accomplished low transmission overhead which it has reduced 13% of the energy consumption and has gained significant reconstruction ratio compared with iPath.

To realise the utmost idea of global collaborative resource sharing with Grid computing, the fundamental scheduling process is playing a critical role. However, scheduling in Grid computing environment is a well-known NP-complete problem. In this study, we propose a new extension of Great Deluge algorithm with an effective diversification strategy for the Grid scheduling problem. The proposed approach, namely BiGD, exploits two different decay rates (a linear and a non-linear decay rate of water level) to provide a better diversification strategy for exploring the solution space. The performance of the proposed algorithm has been evaluated and compared with the standard Great Deluge and Extended Great Deluge algorithm, through the GridSim simulation toolkit. Four different scheduling scenarios or cases which comprise different combination of task heterogeneity and resource heterogeneity are considered for the performance evaluation. Moreover, we have adapted all the algorithms to have same total number of evaluation for solution searching in order to ensure a fair comparison is established in the performance evaluation. The experimental simulation results show that the proposed algorithm is superior and able to produce good quality solutions compared to the other algorithms in all the problem instances.

No abstract