Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach
One of the most difficult aspects of scheduling operations on virtual machines in a multi-cloud environment is determining a near-optimal permutation. This task requires assigning various computing jobs with competing objectives to a collection of virtual machines. A significant number of NP-hard pr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2023
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/110241/ |
| _version_ | 1848865470972690432 |
|---|---|
| author | Farid, Mazen Heng, Siong Lim Chin, Poo Lee Latip, Rohaya |
| author_facet | Farid, Mazen Heng, Siong Lim Chin, Poo Lee Latip, Rohaya |
| author_sort | Farid, Mazen |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | One of the most difficult aspects of scheduling operations on virtual machines in a multi-cloud environment is determining a near-optimal permutation. This task requires assigning various computing jobs with competing objectives to a collection of virtual machines. A significant number of NP-hard problem optimization methods employ multi-objective algorithms. As a result, one of the most successful criteria for discovering the best Pareto solutions is Pareto dominance. In this study, the Pareto front is calculated using a novel multi-objective minimum weight approach. In particular, we use particle swarm optimization (PSO) to expand the FR-MOS multi-objective scheduling algorithm by using fuzzy resource management to maximize variety and obtain optimal Pareto convergence. The competing objectives include reliability, cost, utilization of resources, risk probability, and time makespan. Most of the previous studies provide numerous symmetry or equivalent solutions as trade-offs for different objectives, and selecting the optimum solution remains an issue. We propose a novel decision-making strategy named minimum weight optimization (MWO). Multi-objective algorithms use this method to select a set of permutations that provide the best trade-off between competing objectives. MWO is a suitable choice for attaining all optimal solutions, where both the needs of consumers and the interests of service providers are taken into consideration. (MWO) aims to find the best solution by comparing alternative weights, narrowing the search for an optimal solution through iterative refinement. We compare our proposed method to five distinct decision-making procedures using common scientific workflows with competing objectives: Pareto dominance, multi-criteria decision-making (MCDM), linear normalization I, linear normalization II, and weighted aggregated sum product assessment (WASPAS). MWO outperforms these strategies according to the results of this study. |
| first_indexed | 2025-11-15T14:05:14Z |
| format | Article |
| id | upm-110241 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T14:05:14Z |
| publishDate | 2023 |
| publisher | Multidisciplinary Digital Publishing Institute |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1102412024-09-04T04:08:39Z http://psasir.upm.edu.my/id/eprint/110241/ Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach Farid, Mazen Heng, Siong Lim Chin, Poo Lee Latip, Rohaya One of the most difficult aspects of scheduling operations on virtual machines in a multi-cloud environment is determining a near-optimal permutation. This task requires assigning various computing jobs with competing objectives to a collection of virtual machines. A significant number of NP-hard problem optimization methods employ multi-objective algorithms. As a result, one of the most successful criteria for discovering the best Pareto solutions is Pareto dominance. In this study, the Pareto front is calculated using a novel multi-objective minimum weight approach. In particular, we use particle swarm optimization (PSO) to expand the FR-MOS multi-objective scheduling algorithm by using fuzzy resource management to maximize variety and obtain optimal Pareto convergence. The competing objectives include reliability, cost, utilization of resources, risk probability, and time makespan. Most of the previous studies provide numerous symmetry or equivalent solutions as trade-offs for different objectives, and selecting the optimum solution remains an issue. We propose a novel decision-making strategy named minimum weight optimization (MWO). Multi-objective algorithms use this method to select a set of permutations that provide the best trade-off between competing objectives. MWO is a suitable choice for attaining all optimal solutions, where both the needs of consumers and the interests of service providers are taken into consideration. (MWO) aims to find the best solution by comparing alternative weights, narrowing the search for an optimal solution through iterative refinement. We compare our proposed method to five distinct decision-making procedures using common scientific workflows with competing objectives: Pareto dominance, multi-criteria decision-making (MCDM), linear normalization I, linear normalization II, and weighted aggregated sum product assessment (WASPAS). MWO outperforms these strategies according to the results of this study. Multidisciplinary Digital Publishing Institute 2023 Article PeerReviewed Farid, Mazen and Heng, Siong Lim and Chin, Poo Lee and Latip, Rohaya (2023) Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach. Symmetry, 15 (11). art. no. 2047. pp. 1-28. ISSN 2073-8994 https://www.mdpi.com/2073-8994/15/11/2047 10.3390/sym15112047 |
| spellingShingle | Farid, Mazen Heng, Siong Lim Chin, Poo Lee Latip, Rohaya Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title | Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title_full | Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title_fullStr | Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title_full_unstemmed | Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title_short | Scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| title_sort | scheduling scientific workflow in multi-cloud: a multi-objective minimum weight optimization decision-making approach |
| url | http://psasir.upm.edu.my/id/eprint/110241/ http://psasir.upm.edu.my/id/eprint/110241/ http://psasir.upm.edu.my/id/eprint/110241/ |