Novel efficient particle swarm optimization algorithms for solving QoS‐demanded bag‐of‐tasks scheduling problems with profit maximization on hybrid clouds

Zhang, Yi; Sun, Jin

doi:10.1002/cpe.4249

Cited by 24 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abdi et al [28] considered BoT scheduling on a hybrid cloud platform and employed CPLEX solver to solve the problem. The authors in [29] and [30] employed particle swarm optimization algorithms to schedule BoT applications on hybrid clouds under deadline constraints.…”

Section: Related Workmentioning

confidence: 99%

A Novel Firefly Algorithm for Scheduling Bag-of-Tasks Applications Under Budget Constraints on Hybrid Clouds

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper aims at scheduling bag-of-tasks (BoT) applications under budget constraints on hybrid clouds for minimizing the makespan. To solve this NP-hard problem, we propose a novel firefly algorithm (NFA) in which the evaluation of a firefly consists of two steps: (1) mapping a firefly to a scheduling solution (a task sequence); (2) calculating the solution's objective (its corresponding makespan). In the first step, different from the well-known ranked-order value (ROV) rule, we propose a distancebased mapping operator that relies on the distance between a firefly and the brightest one to determine the mapping relationship between a firefly and a solution. We use a probability model in which solutions corresponding to fireflies closer to the brightest one would have higher probabilities to inherit tasks from the current best solution. In this manner, these solutions can inherit more ''good genes'' hidden inside the current best solution to evolve into more high-quality solutions. In the second step, we employ an effective heuristic to evaluate solution objectives. We further develop a composite heuristic to generate the initial best solution, providing the proposed NFA with a good start. We also establish a new movement scheme such that fireflies distant from the brightest one can explore a wide range in the search space, whereas fireflies nearby the brightest one can search in a small neighborhood. Experimental results show that, by employing the above-mentioned strategies, NFA outperforms the standard firefly algorithm and the existing best algorithm, in terms of scheduling effectiveness and computational efficiency. Specifically, the distance-based mapping operator is verified to be both more effective and more efficient than the ROV rule. The composite heuristic is capable of generating a good initial solution, leading to the high quality of the final schedule. The movement scheme can further reduce the makespan of BoT applications.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Firefly Algorithm for Scheduling Bag-of-Tasks Applications Under Budget Constraints on Hybrid Clouds

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Service guarantees on hybrid clouds are much more complicated than single cloud. More research on data center performance optimization problems can be found in [12] and [32]- [34].…”

Section: B In Terms Of the Qosmentioning

confidence: 99%

“…A service level agreement (SLA) is a mutually agreed agreement between service providers and users to guarantee the performance and availability of services under certain overhead. Usually this overhead is a major factor to drive cloud providers to provide the QoS [8], [11], [12]. The optimal operating state of a service with a clear SLA is: adding additional resources to improve the system brings less revenue than the benefits of investing the resource in other services.…”

Section: Introduction a Motivationmentioning

confidence: 99%

An Experience-Based Scheme for Energy-SLA Balance in Cloud Data Centers

Zhou

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The proliferation of cloud computing has resulted in the establishment of large-scale data centers containing thousands of computing nodes and consuming enormous amounts of electrical energy. However, the low-cost and high-efficiency slogans are getting louder and louder, and the IT industry is also striving for this pursuit. Therefore, it is vital to minimizing the energy consumption for cloud providers while ensuring the quality of service for cloud users. In this paper, we propose several heuristic strategies to optimize these two metrics based on a two-level management model under a heterogeneous cloud environment. First, to detect whether a physical node is continuously overloaded, we propose an empirical forecast algorithm, which predicts the future state of the host by statistically analyzing the historical utilization data of the host. Second, we propose a weighted priority virtual machine (VM) selection algorithm. For each VM on the overloaded host, we weight several utilization factors and calculate its migration priority. Then, we simulate the proposed approach and compare it with the existing overloaded hosts detection algorithms with different VM selection policies under different workloads.

show abstract

“…The CPLEX was used to solve the problem with the results showing that the cloud federations benefit customers, compared with single cloud provider. Different from the three aforementioned works assuming that each task can be executed in an instance of any VM type, [29,30] considered computation-intensive BTSP with resource demands and deadline constraints on hybrid clouds from the perspective of cloud providers with an objective of maximizing profit. Both papers employed Particle Swarm Optimization algorithms to solve the considered problems.…”

Section: Related Workmentioning

confidence: 99%

Scheduling Parallel Intrusion Detecting Applications on Hybrid Clouds

Zhang

Sun

et al. 2018

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

Recently, Parallel Intrusion Detection (PID) becomes very popular and its procedure of the parallel processing is called a PID application (PIDA). This PIDA can be regarded as a Bag-of-Tasks (BoT) application, consisting of multiple tasks that can be processed in parallel. Given multiple PIDAs (i.e., BoT applications) to be handled, when the private cloud has insufficiently available resources to afford all tasks, some tasks have to be outsourced to public clouds with resource-used costs. The key challenge here is how to schedule tasks on hybrid clouds to minimize makespan given a limited budget. This problem can be formulated as an Integer Programming model, which is generally NP-Hard. Accordingly, in this paper, we construct an Iterated Local Search (ILS) algorithm, which employs an effective heuristic to obtain the initial task sequence and utilizes an insertion-neighbourhood-based local search method to explore better task sequences with lower makespans. A swap-based perturbation operator is adopted to avoid local optimum. With the objective of improving the proposal’s efficiency without loss of any effectiveness, to calculate task sequences’ objectives, we construct a Fast Task Assignment (FTA) method by integrating an existing Task Assignment (TA) method with an acceleration mechanism designed through theoretical analysis. Accordingly, the proposed ILS is named FILS. Experimental results show that FILS outperforms the existing best algorithm for the considered problem, considerably and significantly. More importantly, compared with TA, FTA achieves a 2.42x speedup, which verifies that the acceleration mechanism employed by FTA is able to remarkably improve the efficiency. Finally, impacts of key factors are also evaluated and analyzed, exhaustively.

show abstract

Novel efficient particle swarm optimization algorithms for solving QoS‐demanded bag‐of‐tasks scheduling problems with profit maximization on hybrid clouds

Cited by 24 publications

References 29 publications

A Novel Firefly Algorithm for Scheduling Bag-of-Tasks Applications Under Budget Constraints on Hybrid Clouds

A Novel Firefly Algorithm for Scheduling Bag-of-Tasks Applications Under Budget Constraints on Hybrid Clouds

An Experience-Based Scheme for Energy-SLA Balance in Cloud Data Centers

Scheduling Parallel Intrusion Detecting Applications on Hybrid Clouds

Contact Info

Product

Resources

About