Browsing by Author "Mohd Noor Md Sap"

Now showing 1 - 3 of 3
  • Default Image
    Item
    Meta-scheduler in Grid environment with multiple objectives by using genetic algorithm
    (2006) Siriluck Lorpunmanee; Mohd Noor Md Sap; Abdul Hanan Abdullah; Surat Srinoy; S. Lorpunmanee; Faculty of Science and Technology, Suan Dusit Rajabhat University, Dusit, Bangkok, 295 Rajasrima Rd., Malaysia; email: siriluck_lor@dusit.ac.th
    Grid computing is the principle in utilizing and sharing large-scale resources of heterogeneous computing systems to solve the complex scientific problem. Such flexible resource request could offer the opportunity to optimize several parameters, such as coordinated resource sharing among dynamic collections of individuals, institutions, and resources. However, the major opportunity is in optimal job scheduling, which Grid nodes need to allocate the resources for each job. This paper proposes and evaluates a new method for job scheduling in heterogeneous computing Systems. Its objectives are to minimize the average waiting time and make-span time. The minimization is proposed by using a multiple objective genetic algorithm (GA), because the job scheduling problem is NP-hard problem. Our model presents the strategies of allocating jobs to different nodes. In this preliminary tests we show how the solution founded may minimize the average waiting time and the make-span time in Grid environment. The benefits of the usage of multiple objective genetic algorithm is improving the performance of the scheduling is discussed. The simulation has been obtained using historical information to study the job scheduling in Grid environment. The experimental results have shown that the scheduling system using the multiple objective genetic algorithms can allocate jobs efficiently and effectively.
  • Default Image
    Item
    Optimalisation of a job scheduler in the grid environment by using fuzzy C-mean
    (2007) Siriluck Lorpunmanee; Mohd Noor Md Sap; Abdul Hanan Abdullah; S. Lorpunmanee; Faculty of Science and Technology, Suan Dusit Rajabhat University, Dusit, Bangkok, Thailand; email: siriluck_lor@dusit.ac.th
    Grid computing is the principle in utilizing and sharing large-scale resources to solve complex scientific problems. Under this principle, Grid environment has problems in flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources. However, the major problems include optimal job scheduling, and which grid nodes allocate the resources for each job. This paper proposes the model for optimizing jobs scheduling in Grid environment. The model presents the results of the simulation of the Grid environment of jobs allocation to different nodes. We develop the results of job characteristics to three classifications depending on jobs run time in machines, which have been obtained using the optimization of jobs scheduling. The results prove the model by using Fuzzy c-mean clustering technique for predicting the characterization of jobs and optimization of jobs scheduling in Grid environment. This prediction and optimization engine will provide Jobs scheduling base upon historical information. This paper presents the need for such a prediction and optimization engine that discusses the approach for history-based prediction and optimization. Simulation runs demonstrate that our algorithm leads to better results than the traditional algorithms for scheduling policies used in Grid environment.
  • Default Image
    Item
    To identify suspicious activity in anomaly detection based on soft computing
    (2006) Witcha Chimphlee; Mohd Noor Md Sap; Abdul Hanan Abdullah; Siriporn Chimphlee; Surat Srinoy; W. Chimphlee; Faculty of Science and Technology, Suan Dusit Rajabhat University, Dusit, Bangkok, 295 Rajasrima Road, Thailand; email: witcha_chi@dusit.ac.th
    The Traditional intrusion detection systems (IDS) look for unusual or suspicious activity, such as patterns of network traffic that are likely indicators of unauthorized activity. However, normal operation often produces traffic that matches likely "attack signature", resulting in false alarms. In this paper we propose an intrusion detection method that proposes rough set based feature selection heuristics and using fuzzy c-means for clustering data. Rough set has to decrease the amount of data and get rid of redundancy. Fuzzy Clustering methods allow objects to belong to several clusters simultaneously, with different degrees of membership. Our approach allows us to recognize not only known attacks but also to increase accuracy detection rate for suspicious activity and signature detection. Empirical studies using the network security data set from the DARPA 1998 offline intrusion detection project (KDD 1999 Cup) show the feasibility of misuse and anomaly detection results.