http://isda03.softcomputing.net/fgcs2010_f.pdf

Computational models and heuristic methods for Grid scheduling problems

In this chapter, we review a few important concepts from Grid computing related to scheduling problems and their resolution using heuristic and meta-heuristic approaches. Scheduling problems are at the heart of any Grid-like computational system. Different types of scheduling based on different criteria, such as static vs. dynamic environment, multi-objectivity, adaptivity, etc., are identified. Then, heuristics and meta-heuristics methods for scheduling in Grids are presented. The chapter reveals the complexity of the scheduling problem in Computational Grids when compared to scheduling in classical parallel and distributed systems and shows the usefulness of heuristics and meta-heuristics approaches for the design of efficient Grid schedulers.

/pdf/meta-heuristics-for-grid-scheduling-problems-rd5iwf8cg2.pdf

Meta-heuristics for Grid Scheduling Problems

In this paper we present the implementation of Genetic Algorithms (GA) for job scheduling on computational grids that optimizes the makespan and the total flowtime. Job scheduling on computational grids is a key problem in large scale grid‐based applications for solving complex problems. The aim is to obtain an efficient scheduler able to allocate a large number of jobs originated from large scale applications to grid resources. Several variations for GA operators are examined in order to identify which works best for the problem. To this end we have developed a grid simulator package to generate large and very large size instances of the problem and have used them to study the performance of GA implementation. Through extensive experimenting and fine tuning of parameters we have identified the configuration of operators and parameters that outperforms the existing implementations in the literature for static instances of the problem. The experimental results show the robustness of the implementa...

/pdf/use-of-genetic-algorithms-for-scheduling-jobs-in-large-scale-4we1xgpvdc.pdf

Use of genetic algorithms for scheduling jobs in large scale grid applications

Job Scheduling on Computational Grids is gaining importance due to the need for efficient large-scale Grid-enabled applications. Among different optimization techniques addressed for the problem, Genetic Algorithm (GA) is a popular class of solution methods. As GAs are high level algorithms, specific algorithms can be designed by choosing the genetic operators as well as the evolutionary strategies. In this paper we focus on Struggle GAs and their tuning for the scheduling of independent jobs in computational grids. Our results showed that a careful hash implementation for computing the similarity of solutions was able to alleviate the computational burden of Struggle GA and perform better than standard similarity measures.

Tuning struggle strategy in genetic algorithms for scheduling in computational grids

Providing effective feedback, monitoring and evaluation to on-line collaborative learning discussions

A Parallel Grid-based Implementation for Real Time Processing of Event Log Data in Collaborative Applications.

Collaborative applications usually register user interaction in the form of semi-structured plain text event log data. Extracting and structuring of data is a prerequisite for later key processes such as the analysis of interactions, assessment of group activity, or the provision of awareness and feedback. Yet, in real situations of online collaborative activity, the processing of log data is usually done offline since structuring event log data is, in general, a computationally costly process and the amount of log data tends to be very large. Techniques to speed and scale up the structuring and processing of log data with minimal impact on the performance of the collaborative application are thus desirable to be able to process log data in real time. In this paper, we present a parallel grid-based implementation for processing in real time the event log data generated in collaborative applications. Our results show the feasibility of using grid middleware to speed and scale up the process of structuring and processing semi-structured event log data. The Grid prototype follows the Master Worker (MW) paradigm. It is implemented using the Globus Toolkit (GT) and is tested on the Planetlab platform.

/pdf/a-parallel-grid-based-implementation-for-real-time-3z41ig6rd3.pdf

A parallel grid-based implementation for real-time processing of event log data of collaborative applications

Constantly providing feedback to on-line learning teams is a challenging yet one of the latest and most attractive issues to influence learning experience in a positive manner The possibility to enhance learning group’s participation by means of providing appropriate feedback is rapidly gaining popularity due to its great impact on group performance and outcomes Indeed, by storing parameters of interaction such as participation behaviour and giving constant feedback of these parameters to the group may influence group’s motivation and emotional state resulting in an improvement of the collaboration Furthermore, by feeding back to the group the results of tracking the interaction data may enhance the learners’ and groups’ problem solving abilities In all cases, feedback implies constantly receiving information from the learners’ actions stored in log files since the history information shown is continuously updated Therefore, in order to provide learners with effective feedback, it is necessary to process large and considerably complex event log files from group activity in a constant manner, and thus it may require computational capacity beyond that of a single computer To that end, in this paper we show how a Grid approach can considerably decrease the time of processing group activity log files and thus allow group learners to receive selected feedback even in real time Our approach is based on the master-worker paradigm and is implemented using Globus technology running on the Planetlab platform To test our application, we used event log files from the Basic Support for Collaborative Work (BSCW) system

A grid-aware implementation for providing effective feedback to on-line learning groups

Using Grid services to parallelize IBM's Generic Log Adapter

Providing collaborative learning applications the possibility to offer continuous awareness to on-line collaborative learning teams is a challenging issue since it is essential to keep participants informed of both what is happening and what happened in the learning group. Moreover, awareness is the basis to enhance collaboration and improve the individual and group performance since it allows to track and assess the collaborative learning process more objectively and to model students' behavior more efficiently. In order to provide students and tutors with effective awareness, we consider the collaborative actions registered in log files. It is necessary to process large and considerably complex event log files in a constant manner, and thus it may requires processing capacity beyond that of a single computer. To that end, in this paper we show how a Grid approach can considerably decrease the time of processing group activity log files and thus allow students and tutors to be aware of what is going on in the group activity even in real time. Our approach is based on the master-worker paradigm and is implemented using Globus technology running on the Planetlab platform. To test our application, we used event log files from the Basic Support for Collaborative Work (BSCW) system.

https://telearn.archives-ouvertes.fr/hal-00190583/document

Claudi Paniagua

Papers

A Parallel Grid-based Implementation for Real Time Processing of Event Log Data in Collaborative Applications.

A parallel grid-based implementation for real-time processing of event log data of collaborative applications

A grid-aware implementation for providing effective feedback to on-line learning groups

Using Grid services to parallelize IBM's Generic Log Adapter

A grid approach to provide effective awareness to on-line collaborative learning teams