smart.lab.tunisia@gmail.com +216 71 588 443
Connexion

Mouna Karaja

Informations générales

Mouna Karaja
Grade

Maître Assistant

Biographie courte

Mouna Karaja received the B.Sc. (2011), M.Sc. (2014), and Ph.D. (2022) degrees in Business Computing from the Higher Institute of Management of Tunis, University of Tunis, Tunisia. She is currently an assistant professor at the Faculty of Science of Monastir and a research member within the SMART Laboratory (ISG, University of Tunis, Tunisia). Her research interests include scheduling problems, cloud computing, evolutionary computation, and optimization.

Axes de recherche

Bi-level optimization
Cloud computing
Evolutionary optimization
Optimization
Scheduling problems
Metaheuristics

Publications

  • 2023
    Mouna Karaja, Abir Chaabani, Ameni Azzouz, Lamjed Ben Said

    Dynamic bag-of-tasks scheduling problem in a heterogeneous multi-cloud environment: a taxonomy and a new bi-level multi-follower modeling

    Journal of Supercomputing,1-38,, 2023

    Résumé

    Since more and more organizations deploy their applications through the cloud, an increasing demand for using inter-cloud solutions is noticed. Such demands could inherently result in overutilization of resources, which leads to resource starvation that is vital for time-intensive and life-critical applications. In this paper, we are interested in the scheduling problem in such environments. On the one hand, a new taxonomy of criteria to classify task scheduling problems and resolution approaches in inter-cloud environments is introduced. On the other hand, a bi-level multi-follower model is proposed to solve the budget-constrained dynamic Bag-of-Tasks (BoT) scheduling problem in heterogeneous multi-cloud environments. In the proposed model, the upper-level decision maker aims to minimize the BoT’ makespan under budget constraints. While each lower-level decision maker minimizes the completion time of tasks it received. Experimental results demonstrated the outperformance of the proposed bi-level algorithm and revealed the advantages of using a bi-level scheme with an improvement rate of 32%, 29%, and 21% in terms of makespan for the small, medium, and big size instances, respectively.

    Abir Chaabani, Mouna Karaja, Lamjed Ben Said

    An Efficient Non-Dominated Sorting Genetic Algorithm for Multi-objective Optimization

    International Conference on Control Decision and Information Technology Codit’9, Rome, 1565-1570, 2023

    Résumé

    Multi-Objective Evolutionary Algorithms (MOEAs) is actually one of the most attractive and active research field in computer science. Significant research has been conducted in handling complex multi-objective optimization problems within this research area. The Non-Dominated Sorting Genetic Algorithm (NSGA-II) has garnered significant attention in various domains, emphasizing its specific popularity. However, the complexity of this algorithm is found to be O(MN2) with M objectives and N solutions, which is considered computationally demanding. In this paper, we are proposing a new variant of NSGA-II termed (Efficient-NSGA-II) based on our recently proposed quick non-dominated sorting algorithm with quasi-linear average time complexity; thereby making the NSGA-II algorithm efficient from a computational cost viewpoint. Experiments demonstrate that the improved version of the algorithm is indeed much faster than the previous one. Moreover, comparisons results against other multi-objective algorithms on a variety of benchmark problems show the effectiveness and the efficiency of this multi-objective version

    Abir Chaabani, Mouna Karaja, Lamjed Ben Said

    An Efficient Non-dominated Sorting Genetic Algorithm For Multi-objective Optimization.

    9th International Conference on Control, Decision and Information Technologies, CoDIT 2023, Rome, Italy., 2023

    Résumé

    Multi-Objective Evolutionary Algorithms (MOEAs) is actually one of the most attractive and active research field in computer science. Significant research has been conducted in handling complex multi-objective optimization problems within this research area. The Non-Dominated Sorting Genetic Algorithm (NSGA-II) has garnered significant attention in various domains, emphasizing its specific popularity. However, the complexity of this algorithm is found to be O(MN2) with M objectives and N solutions, which is considered computationally demanding. In this paper, we are proposing a new variant of NSGA-II termed (Efficient-NSGA-II) based on our recently proposed quick non-dominated sorting algorithm with quasi-linear average time complexity; thereby making the NSGA-II algorithm efficient from a computational cost viewpoint. Experiments demonstrate that the improved version of the algorithm is indeed much faster than the previous one. Moreover, comparisons results against other multi-objective algorithms on a variety of benchmark problems show the effectiveness and the efficiency of this multi-objective version.

    Mouna Karaja, Abir Chaabani, Ameni Azzouz, Lamjed Ben Said

    Dynamic bag-of-tasks scheduling problem in a heterogeneous multi-cloud environment: a taxonomy and a new bi-level multi-follower modeling

    J Supercomput 79, 17716–17753 (2023), 2023

    Résumé

    Since more and more organizations deploy their applications through the cloud, an increasing demand for using inter-cloud solutions is noticed. Such demands could inherently result in overutilization of resources, which leads to resource starvation that is vital for time-intensive and life-critical applications. In this paper, we are interested in the scheduling problem in such environments. On the one hand, a new taxonomy of criteria to classify task scheduling problems and resolution approaches in inter-cloud environments is introduced. On the other hand, a bi-level multi-follower model is proposed to solve the budget-constrained dynamic Bag-of-Tasks (BoT) scheduling problem in heterogeneous multi-cloud environments. In the proposed model, the upper-level decision maker aims to minimize the BoT’ makespan under budget constraints. While each lower-level decision maker minimizes the completion time of tasks it received. Experimental results demonstrated the outperformance of the proposed bi-level algorithm and revealed the advantages of using a bi-level scheme with an improvement rate of 32%, 29%, and 21% in terms of makespan for the small, medium, and big size instances, respectively.

  • Mouna Karaja, Abir Chaabani, Ameni Azzouz, Lamjed Ben Said

    Efficient bilevel multi-objective approach for budget-constrained dynamic Bag-of-Tasks scheduling problem in heterogeneous multi-cloud environment

    Applied Intelligence, 1-29, 2022

    Résumé

    Bag-of-Tasks is a well-known model that processes big-data applications supporting embarrassingly parallel jobs with independent tasks. Scheduling Bag-of-Tasks in a dynamic multi-cloud environment is an NP-hard problem that has attracted a lot of attention in the last years. Such a problem can be modeled using a bi-level optimization framework due to its hierarchical scheme. Motivated by this issue, in this paper, an efficient bi-level multi-follower algorithm, based on hybrid metaheuristics, is proposed to solve the multi-objective budget-constrained dynamic Bag-of-Tasks scheduling problem in a heterogeneous multi-cloud environment. In our proposed model, the objective function differs depending on the scheduling level: The upper level aims to minimize the makespan of the whole Bag-of-Tasks under budget constraints; while each follower aims to minimize the makespan and the execution cost of tasks belonging to the Bag-of-Tasks. Since multiple conflicting objectives exist in the lower level, we propose an improved variant of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) called Efficient NSGA-II (E-NSGA-II), applying a recently proposed quick non-dominated sorting algorithm (QNDSA) with quasi-linear average time complexity. By performing experiments on proposed synthetic datasets, our algorithm demonstrates high performance in terms of makespan and execution cost while respecting budget constraints. Statistical analysis validates the outperformance of our proposal regarding the considering metrics.

    Mouna Karaja, Abir Chaabani, Ameni Azzouz, Lamjed Ben Said

    Efficient bi-level multi objective approach for budget-constrained dynamic Bag-of-Tasks scheduling problem in heterogeneous multi-cloud environment.

    Appl Intell 53, 9009–9037 (2023), 2022

    Résumé

    Bag-of-Tasks is a well-known model that processes big-data applications supporting embarrassingly parallel jobs with independent tasks. Scheduling Bag-of-Tasks in a dynamic multi-cloud environment is an NP-hard problem that has attracted a lot of attention in the last years. Such a problem can be modeled using a bi-level optimization framework due to its hierarchical scheme. Motivated by this issue, in this paper, an efficient bi-level multi-follower algorithm, based on hybrid metaheuristics, is proposed to solve the multi-objective budget-constrained dynamic Bag-of-Tasks scheduling problem in a heterogeneous multi-cloud environment. In our proposed model, the objective function differs depending on the scheduling level: The upper level aims to minimize the makespan of the whole Bag-of-Tasks under budget constraints; while each follower aims to minimize the makespan and the execution cost of tasks belonging to the Bag-of-Tasks. Since multiple conflicting objectives exist in the lower level, we propose an improved variant of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) called Efficient NSGA-II (E-NSGA-II), applying a recently proposed quick non-dominated sorting algorithm (QNDSA) with quasi-linear average time complexity. By performing experiments on proposed synthetic datasets, our algorithm demonstrates high performance in terms of makespan and execution cost while respecting budget constraints. Statistical analysis validates the outperformance of our proposal regarding the considering metrics.

  • Mouna Karaja, Meriem Ennigrou, Lamjed Ben Said

    Solving Dynamic Bag-of-Tasks Scheduling Problem in Heterogeneous Multi-cloud Environment Using Hybrid Bi-Level Optimization Model.

    In: Abraham A., Hanne T., Castillo O., Gandhi N., Nogueira Rios T., Hong TP. (eds) Hybrid Intelligent Systems. HIS 2020. Advances in Intelligent Systems and Computing, vol 1375. Springer, Cham., 2021

    Résumé

    Task scheduling problem has attracted a lot of attention since it plays a key role to improve the performance of any distributed system. This is again more challenging, especially for multi-cloud computing environment, mainly based on the nature of the multi-cloud to scale dynamically and due to heterogeneity of resources which add more complexity to the scheduling problem. In this paper, we propose, for the first time, a new Hybrid Bi-level optimization model named HB-DBoTSP to solve the Dynamic Bag-of-Tasks Scheduling Problem (DBoTSP) in heterogeneous multi-cloud environment. The proposed model aims to minimize the makespan and the execution cost while taking into consideration budget constraints and guaranteeing load balancing between Cloud’s Virtual Machines. By performing experiments on synthetic data sets that we propose, we demonstrate the effectiveness of the algorithm.

  • Mouna Karaja, Meriem Ennigrou

    Solving Dynamic Bag-of-Tasks Scheduling Problem in Heterogeneous Multi-cloud Environment Using Hybrid Bi-Level Optimization Model

    HIS, 2020

    Résumé

    Task scheduling problem has attracted a lot of attention since it plays a key role to improve the performance of any distributed system. This is again more challenging, especially for multi-cloud computing environment, mainly based on the nature of the multi-cloud to scale dynamically and due to heterogeneity of resources which add more complexity to the scheduling problem. In this paper, we propose, for the first time, a new Hybrid Bi-level optimization model named HB-DBoTSP to solve the Dynamic Bag-of-Tasks Scheduling Problem (DBoTSP) in heterogeneous multi-cloud environment. The proposed model aims to minimize the makespan and the execution cost while taking into consideration budget constraints and guaranteeing load balancing between Cloud’s Virtual Machines. By performing experiments on synthetic data sets that we propose, we demonstrate the effectiveness of the algorithm.

    Mouna Karaja, Meriem Ennigrou, Lamjed Ben Said

    Budget-constrained dynamic Bag-of-Tasks scheduling algorithm for heterogeneous multi-cloud environment

    2020 International Multi-Conference on: “Organization of Knowledge and Advanced Technologies” (OCTA), Tunis, Tunisia, pp. 1-6., 2020

    Résumé

    Cloud computing has reached huge popularity for delivering on-demand services on a pay-per-use basis over the internet. However, since the number of cloud users evolves, multi-cloud environment has been introduced where clouds are interconnected in order to satisfy customers’ requirements. Task scheduling in such environments is very challenging mainly due to the heterogeneity of resources. In this paper, a budget-constrained dynamic Bag-of-Tasks scheduling algorithm for heterogeneous multi-cloud environment is proposed. By performing experiments on synthetic data sets that we propose, we demonstrate the effectiveness of the algorithm in terms of makespan.

    Mouna Karaja, Meriem Ennigrou

    Solving Dynamic Bag-of-Tasks Scheduling Problem in Heterogeneous Multi-cloud Environment Using Hybrid Bi-Level Optimization Model

    20th International Conference on Hybrid Intelligent Systems (HIS 2020), 2020

    Résumé

    Task scheduling problem has attracted a lot of attention since it plays a key role to improve the performance of any distributed system. This is again more challenging, especially for multi-cloud computing environment, mainly based on the nature of the multi-cloud to scale dynamically and due to heterogeneity of resources which add more complexity to the scheduling problem. In this paper, we propose, for the first time, a new Hybrid Bi-level optimization model named HB-DBoTSP to solve the Dynamic Bag-of-Tasks Scheduling Problem (DBoTSP) in heterogeneous multi-cloud environment. The proposed model aims to minimize the makespan and the execution cost while taking into consideration budget constraints and guaranteeing load balancing between Cloud’s Virtual Machines. By performing experiments on synthetic data sets that we propose, we demonstrate the effectiveness of the algorithm.