Workflow Scheduling in Cloud Computing: A Survey

In the last few decades, a novel branch of intelligent computation algorithms has been inspired by a swarm intelligence theory which imitates the behavior of animals. These algorithms are successfully applied to solve many kinds of simple and complex problems in several fields such as optimization problems, pattern recognition, image processing, features section, and task scheduling in cloud and parallel computing. Cloud computing has not only become the preferred environment for several companies, but also helps others to overcome many server-related issues by utilizing characteristics such as reliability, flexibility, high scalability, and security. Therefore, many intelligent computation algorithms are used to improve this environment. In this chapter, an overview of swarm intelligence for solving the scheduling problems of tasks in cloud computing is presented, including particle swarm optimization, cat optimization algorithm, artificial bee colony, lion optimization algorithm, whale optimization algorithm, bat algorithm, gray wolf optimizer, cuckoo search algorithm, hybrid swarm algorithms, and multi-objective swarm optimization. All these algorithms are described and presented with their achievements in solving task scheduling issues in cloud computing.

Cloud computing is a platform that hosts applications and services for businesses and users to accesses computing as a service. In this paper, we identify two scheduling and resource allocation problems in cloud computing. We describe Hadoop MapReduce and its schedulers, and present recent research efforts in this area including alternative schedulers and enhancements to existing schedulers. The second scheduling problem is the provisioning of virtual machines to resources in the cloud. We present a survey of the different approaches to solve this resource allocation problem. We also include recent research and standards for inter-connecting clouds and discuss the suitability of running scientific applications in the cloud.

Dynamic Multi-workflow Scheduling (DMWS) in cloud computing is a well-known combinatorial optimisation problem. It is a great challenge to tackle this problem by scheduling multiple workflows submitted at different times and meet user-defined quality of service objectives. Scheduling with user-defined budget constraints is becoming increasingly important due to cloud dynamics associated with on-demand provisioning, instance types, and pricing. To address the Budget-Constrained Dynamic Multi-workflow Scheduling (BC-DMWS) problem, a novel Cooperative Coevolution Genetic Programming (CCGP) approach is proposed. Two heuristic rules, namely VM Selection/Creation Rule (VMR) and Budget Alert Rule (BAR), are learned automatically by CCGP. VMR is used to allocate ready tasks to either existing or newly rented VM instances, while BAR makes decisions to downgrade VM instances so as to meet the budget constraint. Experiments show significant performance and success rate improvement compared to state-of-the-art algorithms.

<p>Cloud computing is a model for delivering, hosting and accessing shared pool of resources and services over the internet in on-demand, self-service, dynamically scalable and metered manner. Scheduling access to cloud resources is a topic of interest to both researchers and IT community. Several approaches have been proposed from the traditional methods to those that are exhaustive in nature. However, Cloud task scheduling is an NP-hard optimization problem, and can break down deterministic or exhaustive approaches with the increase in the number of variables to be optimized. Recently there is has been attempt to use meta-heuristic algorithm for scheduling in cloud computing. These include Genetic Algorithms (GA), Particle Swamp Optimization (PSO), Ant Colony Optimization Algorithm (ACO) and other nature inspired algorithms. The algorithms offer NP-hard problems global solutions acceptable in time frame proportional to the number of variables to be optimized. We use ACO algorithm for scheduling in cloud computing environment. Load balancing is added into the algorithm to prevent the algorithm from falling into local minima. A comparison with (43) shows that the proposed algorithm achieved 51.95% in makespan. However, the compared work is better than this work in the average running time by 86.50%.</p>

Task scheduling in cloud computing based on grey wolf optimization with a new encoding mechanism

In the research of cloud computing, the advantages and disadvantages of cloud task scheduling algorithm will affect the operation efficiency and service quality of the whole cloud computing system. Evolutionary algorithm is the sum of a series of specific algorithms inspired by the phenomenon of biological evolution in nature. One of the common points of these algorithms is that individuals must be mutated according to certain rules in the running process, so as to avoid falling into local optimum. In order to improve the efficiency of cloud task scheduling in cloud computing, this paper proposes a new mutation strategy which changes the genetic algorithm in evolutionary algorithm. It uses cloudsim platform to simulate cloud task scheduling in cloud computing, and uses particle swarm optimization algorithm to optimize its parameters. The experimental results show that the proposed evolutionary algorithm with improved mutation strategy has the function of cloud task scheduling, and its performance is also improved after the parameters are optimized by particle swarm optimization algorithm. The proposed algorithm improves the mutation step and explores the essence of mutation in evolutionary algorithm, which provides a reference for other research.

Task scheduling is an essential component of any distributed system because it routes tasks to appropriate resources for execution, such as grids, clouds, and peer-to-peer networks. Common scheduling algorithms include downsides, such as high temporal complexity, non-simultaneous processing of input tasks, and longer program execution times. Exploration-based scheduling algorithms prioritize tasks using a variety of methods, resulting in long execution times on heterogeneous distributed computing systems. As a result, task prioritization becomes a bottleneck in such systems. It is appropriate to prioritize tasks with the shortest execution time using faster algorithms. The genetic algorithm (GA) is one of the evolutionary approaches used to solve complex problems quickly. This paper proposes a parallel GA with a MapReduce architecture for scheduling jobs on cloud computing with various priority queues. The fundamental aim of this study is to employ a MapReduce architecture to minimize the total execution time of the task scheduling process in the cloud computing environment. The proposed method accomplishes task scheduling in two stages: first, the GA was used in conjunction with heuristic techniques to assign tasks to processors, and then the GA was used in conjunction with the MapReduce framework to assign jobs to processors. In our experiments, we consider heterogeneous resources that differ in their ability to execute various tasks, as well as running a job on different resources with varying execution durations. The results show that the proposed method outperforms other algorithms such as particle swarm optimization, whale optimization algorithm, moth-flame optimization, and intelligent water drops.

Interest in cloud computing has grown considerably over recent years, primarily due to scalable virtualized resources. So, cloud computing has contributed to the advancement of real-time applications such as signal processing, environment surveillance and weather forecast where time and energy considerations to perform the tasks are critical. In real-time applications, missing the deadlines for the tasks will cause catastrophic consequences; thus, real-time task scheduling in cloud computing environment is an important and essential issue. Furthermore, energy-saving in cloud data center, regarding the benefits such as reduction of system operating costs and environmental protection is an important concern that is considered during recent years and is reducible with appropriate task scheduling. In this paper, we present an energy-aware task scheduling approach, namely EaRTs for real-time applications. We employ the virtualization and consolidation technique subject to minimizing the energy consumptions, improve resource utilization and meeting the deadlines of tasks. In the consolidation technique, scale up and scale down of virtualized resources could improve the performance of task execution. The proposed approach comprises four algorithms, namely Energy-aware Task Scheduling in Cloud Computing(ETC), Vertical VM Scale Up(V2S), Horizontal VM Scale up(HVS) and Physical Machine Scale Down(PSD). We present the formal model of the proposed approach using Timed Automata to prove precisely the schedulability feature and correctness of EaRTs. We show that our proposed approach is more efficient in terms of deadline hit ratio, resource utilization and energy consumption compared to other energy-aware real-time tasks scheduling algorithms.

The prime motive of this work is to develop an efficacious system for workflow scheduling in the cloud using optimized deep learning. Initially, the incoming tasks are fed into a multi-objective task scheduling module where the workflow is scheduled using proposed HMLO by considering the fitness, such as cost, predicted energy, reliability and make span. Here, the energy is predicted using DRN. The HMLO is obtained by the consolidation of Mutated Leader Optimization (MLO), and Hybrid Leader Optimization (HLBO). On the other hand, the deep learning-based task scheduling process is performed by getting the incoming tasks and it is given to DLSTM for workflow scheduling by assuming the live parameters of Virtual Machine (VM) and task. Finally, both outputs are fused to schedule the tasks in the VM. The proposed HMLO[Formula: see text]DLSTM has delivered superior results in terms of minimum make span of 0.499, maximum energy of 0.947 and minimum resource utilization of 0.079.

Cloud computing is a new development in the world of Information Technology (IT) infrastructure and it has brought could of challenges. Task scheduling is one of the main features that allows to be efficient in cloud-computing to guarantee the effectiveness of work with the resources and make the completion time as short as possible. It should, however, be pointed out that the task scheduling in cloud computing belongs to the NP-complete optimization problems. In order to eliminate the difficulties related to task scheduling in cloud computing, a number of algorithms have been presented. One of them is also an original version of the list scheduling scheduling technique, but its implementation is specifically aimed at efficient schedules of tasks execution and load balancing in a cloud environment. This method is based on the Heterogeneous Earliest Finish Time (HEFT) strategy but with some modifications that enhance its efficiency as compared to keeping a similar level of algorithm complexity. I carried out experiments on randomly created Directed Acyclic Graphs (DAGs) with a view to testing the usefulness of the algorithm. The test done on the WorkFlowSim simulator involves testing the real and synthetic workflows. The experiments point out the difference in the effectiveness of the offered mechanism compared to the existing algorithms. As demonstrated by the experiments, the suggested would outperform the current scheduling algorithms by efficiency and use of resources. This algorithm has potential of providing improved results than any prior solutions to the task scheduling problem in computer computing although the task problem is a complex one.

The rapid growth of cloud computing environment with many clients ranging from personal users to big corporate or business houses has become a challenge for cloud organizations to handle the massive volume of data and various resources in the cloud. Inefficient management of resources can degrade the performance of cloud computing. Therefore, resources must be evenly allocated to different stakeholders without compromising the organization’s profit as well as users’ satisfaction. A customer’s request cannot be withheld indefinitely just because the fundamental resources are not free on the board. In this paper, a combined resource allocation security with efficient task scheduling in cloud computing using a hybrid machine learning (RATS-HM) technique is proposed to overcome those problems. The proposed RATS-HM techniques are given as follows: First, an improved cat swarm optimization algorithm-based short scheduler for task scheduling (ICS-TS) minimizes the make-span time and maximizes throughput. Second, a group optimization-based deep neural network (GO-DNN) for efficient resource allocation using different design constraints includes bandwidth and resource load. Third, a lightweight authentication scheme, i.e., NSUPREME is proposed for data encryption to provide security to data storage. Finally, the proposed RATS-HM technique is simulated with a different simulation setup, and the results are compared with state-of-art techniques to prove the effectiveness. The results regarding resource utilization, energy consumption, response time, etc., show that the proposed technique is superior to the existing one.

WITHDRAWN: Efficient Secure Aware Scheduling Model for Enhancing Security and Workflow Model in Cloud Computing

Cloud computing has become biggest buzz in the computer era these days. It runs entire operating systems on the cloud and do everything on cloud to store data off-site. Cloud computing is primarily based on grid computing, but it’s a new computational model. Cloud computing has emerged into a new opportunity to further enhance way of hosting data centre and provide services. The primary substance of cloud computing is to deal the computing power, storage, different sort of stages and services which assigned to the external users on demand through the internet. Task scheduling in cloud computing is vital role optimisation and effective dynamic resource allocation for load balancing. In cloud, the issue focused is under utilisation and over utilisation of the resources to distribute workload of multiple network links for example, when cloud clients try to access and send request to the same cloud server while the other cloud server remain idle at that moment, leads to the unbalanced of workload on cloud data centers. Thus, load balancing is to assign tasks to the individual cloud data centers of the shared system so that no single cloud data centers is overloaded or under loaded. A Hybrid approach of Honey Bee (HB) and Particle Swarm Optimisation (PSO) load balancing algorithm is combined in order to get effective response time. The proposed hybrid algorithm has been experimented by using CloudSim simulator. The result shows that the hybrid load balancing algorithm improves the cloud system performance by reducing the response time compared to the Honey Bee (HB) and Particle Swarm Optimisation (PSO) load balancing algorithm. Â

Task scheduling optimization in heterogeneous cloud computing environments: A hybrid GA-GWO approach

The flexibility of cloud computing to provide a dynamic and adaptable infrastructure in the context of information technology and service quality has made it one of the most challenging issues in the computer industry. Task scheduling is a major challenge in cloud computing. Scheduling tasks so that they may be processed by the most effective cloud network resources has been identified as a critical challenge for maximizing cloud computing’s performance. Due to the complexity of the issue and the size of the search space, random search techniques are often used to find a solution. Several algorithms have been offered as possible solutions to this issue. In this study, we employ a combination of the genetic algorithm (GA) and the gravitational emulation local search (GELS) algorithm to overcome the task scheduling issue in cloud computing. GA and the particle swarm optimization (PSO) algorithms are compared to the suggested algorithm to demonstrate its efficacy. The suggested algorithm outperforms the GA and PSO, as shown by the experiments.