Scheduling data processing flows under budget constraint on the cloud

Directed acyclic graph (DAG) scheduling is a well-known problem, because a DAG can be used to describe a wide range of complex applications, including scientific applications and parallel computing jobs. Most DAG scheduling algorithms were proposed to minimize the job makespan (i.e., execution time) on a multiprocessor computer or cluster. However, as the cost-driven public cloud services have become an attractive and popular platform for providing computing resources, cost minimization emerges as a new critical issue. Therefore, the objective of this work is to propose and solve the cost optimization problem for scheduling DAGs on an IaaS cloud platform where task scheduling must cope with resource provisioning to achieve the optimal solution. In this paper, we proposed both optimal and heuristic scheduling algorithms, and we evaluated them across a variety of DAGs using the price model from EC2. Comparing to other cost-oblivious DAG schedules that aim to minimize makespan or resource usage, the results show that our cost-aware heuristic algorithm can reduce cost by 20---50 % and achieve a cost within x1.16 of the optimal one.

Cloud computing technology is getting more advanced these days. Cloud computing is a pay-as-you-go service since it allows for variable resource allocation for services. Task scheduling and resource allocation are becoming major requirements for efficient and effective load balancing among cloud resources. For scheduling resources in cloud environment, different tasks need to be executed simultaneously by the available resources in order to minimize the completion time. To achieve this, we proposed a new technique called Enhanced Max-Min Algorithm (EMM). This algorithm takes less time to complete all the tasks with minimum completion time. In the proposed algorithm, small size tasks are concurrently executed and resource allocation is done accordingly. When compared to Min-Min algorithm the Enhanced Max-Min algorithm provides high resource utilization and reduces the makespan.

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.

Cloud computing is an information technology paradigm that enables ubiquitous access to shared pools of configurable system resources and higher level services required by modern technology. Task scheduling is an important part in cloud computing for limited number of heterogeneous resources and increasing number of user tasks. Task scheduling is to allocate tasks (cloudlets) to the best suitable resources to increase performance in terms of some parameters, such as makespan and resource utilization. Allocating cloudlets with good load balancing and minimum makespan is an NP-hard optimization problem. Many meta-heuristic and heuristic algorithms have been proposed to solve the said problem, but they lack in considering the completion time of virtual machine and total length of its allocated cloudlets instead of only considering completion time of a cloudlet. This lack leads to decrease the performance of a cloud system in some cases, such as large cloudlets. To address the said problem, in this paper, we propose an optimal heuristic cloudlet allocation algorithm for resource allocation and task scheduling, referred as HCA, to cope with the increasing large number of user cloudlets under minimum resource capacity. So, we devise a new mechanism to combine optimal completion time and earliest finish time to minimize both degree of imbalance and overall completion time. The experimental results show that the proposed HCA can achieve effectively and efficiently good performance, best load balancing, and improve the resource utilization in comparison with the other existing cloudlet allocation methods.

Basic science is becoming ever more computationally intensive, increasing the need for large-scale compute and storage resources, be they within a High Performance Computer cluster, or more recently within the cloud. In most cases, large scale scientific computation is represented as a workflow for scheduling and runtime provisioning. Such scheduling become an even more challenging problem on cloud systems due to the dynamic nature of the cloud, in particular, the elasticity, the pricing models (both static and dynamic), the non-homogeneous resource types, the vast array of services, and virtualization. This mapping of workflow tasks on to a set of provisioned instances is an example of the general scheduling problem and is NP-complete. In addition, we also need to ensure that certain runtime constraints are met - the most typical being the cost of the computation and the time which that computation requires to complete. In this article, we introduce a new heuristic scheduling algorithm, Budget Deadline Aware Scheduling (BDAS), that addresses eScience workflow scheduling under budget and deadline constraints in Infrastructure as a Service (IaaS) clouds. The novelty of our work is satisfying both budget and deadline constraints while introducing a tunable cost-time trade off over heterogeneous instances. In addition, we study the stability and robustness of our algorithm by performing sensitivity analysis. The results demonstrate that overall BDAS finds a viable schedule for more than 40000 test cases accomplishing both defined constraints: budget and deadline. Moreover, our algorithm achieves a 17.0-23.8 percent higher success rate when compared to state of the art algorithms.

In this paper, we first propose a new parallel video coding framework, considering three important factors: parallel strategy, computational complexity and task scheduling. Then combining the characteristics of scalable video coding (SVC), a novel parallel encoding structure for temporal and quality scalabilities is introduced to obtain a high speedup of parallel SVC. Since the data dependencies in SVC are complex and time variant, the scheduling of parallel SVC is extremely difficult. In order to find the optimal scheduling solution, directed acyclic graph (DAG) is exploited to model the dependencies of encoding tasks, and the complexities of the encoding tasks which are accurately estimated by the Kalman filter to weight the scheduling tasks. Finally, two heuristic scheduling algorithms are also proposed to achieve a high encoding speed of parallel SVC. Experimental results show that the speedup of our parallel method was higher (about 60%) than previous work. Using the proposed method, high definition (HD) SVC videos can be encoded in real time.

When the traditional heterogeneous multi-core scheduling algorithm performs tasks with high resource density, a large amount of idle time often occurs on the processor core. Therefore, based on the environment of heterogeneous multi-core processors, this paper studies the static heuristic table scheduling algorithm, and proposes an optimization approach for the problem of single priority assignment and too simple task assignment. We design optimization in the static heuristic scheduling algorithm list generation phase and task allocation phase, and propose a hybrid task allocation method with three strategies to improve the standby time utilization of processor core. Then, DVFS technology is used to optimize the scheduling results, so that the task can run with lower energy consumption without increasing makespan. Finally, the new algorithm is compared with three traditional scheduling algorithms through design experiments, and it is proved that the new algorithm has better performance when executing more tasks.

Distributed computing, grid computing, and virtualization have all resulted in the growth of cloud computing.. The existing research work, introduced a strategic theory (ST) based Improved Elephant Herd Optimization (IEHO) for feasible allotment procedure where the result function confess a straight payment system to meet the users requirements. However total users is huge in cloud computing, total tasks and total data are as well vast. Because the cost of every work on cloud services varies, client task scheduling in the cloud is not like conventional scheduling approaches. In a cloud computing system, it's critical to figure out how to effectively schedule work. As a results, the research proposes an unique Task Scheduling Mechanism (TSM) was proposed, which may suit users' needs while also improving resource usage and so improving the overall performance of the cloud cloud computing. The goal of this project is to plan task groups in a cloud computing platform with varying resource costs and computational performance. The suggested cloud scheduling solution uses an enhanced cost-based scheduling scheme to efficiently map workloads to existing cloud services. The scheduling technique, that is founded on Hybrid Evolutionary (HE)algorithms, increases the computation/communication proportion by combining user jobs as per a cloud resource's processing capacity and sending the aggregated activities to the resource. The simulation experiments show that the proposed Hybrid Evolutionary based Task Scheduling Mechanism (HE-TSM) is efficiently schedule the tasks along with both costs and performance in the cloud computing environment.

WITHDRAWN: Enterprise based data deployment inference methods in cloud infrastructure

Cloud computing(CC), which utilizes massively virtualized data centers to deliver quick and affordable computing solutions, has developed ‎into an established industrial standard that is growing quickly. To handle such a massive amount of data effectively, cloud computing mostly ‎relies on automation and dynamic resource management. In cloud computing, load balancing (LB) is a vital technique for maximizing ‎resource utilization and making sure that no resource is used up. Without the requirement for physical infrastructure, cloud ‎LB allows online platforms to adjust their resources in response to traffic demands. In a cloud environment, workload and resource allocation entail determining the best way to divide up work among several servers. For increasingly severe uncertainty problems, traditional LB ‎approaches are simple but ineffective; for this reason, meta-heuristic methods are employed. This algorithm is heuristic and is independent ‎of the complexity of the challenges. Meta-heuristics approaches based on Artificial Intelligence (AI) are employed to analyze real-time data ‎and intelligently distribute workload among servers. This ensures efficient operations by preventing bottlenecks and enabling proactive LB ‎decisions. The review offers a thorough analysis of meta-heuristics techniques based on artificial intelligence (AI) for static and dynamic LB ‎in both homogeneous and heterogeneous cloud systems.

Cloud computing workflows are collections of interdependent tasks. Workflow scheduling is mainly concerned with cost reduction and overall completion time reduction. Our algorithm devised for workflow scheduling aims to address these two QoS factors. Workflows have many tasks which may require different kinds of execution environment for each task. Supporting all these environment dependencies and task dependencies is really difficult for a cloud scheduling system. Workflows are represented using directed acyclic graph (DAG) which shows the dependencies among tasks. Introducing execution environment dependencies to a DAG will lead to a several combinatorial DAGs. In this paper, our system provides a modified DAG which supports task and execution environment dependency. This paper deals with this time-cost tradeoff and tries to balance both these QoS in compromised way. It compromises the cost when the completion time of tasks is higher and vice versa. Hence, the cost as well as makespan will be as minimum as possible. Experimental results show that our algorithm provides a better time-cost balanced solution in imposing execution environment into task DAG.

Cloud computing is an Internet-based computing and network model, which provides a market for sharing computing and storage resources. To motivate the cloud providers, the allocation of resources and their pricing becomes one of the challenges in this market. In this situation, designing auction-based mechanisms for cloud resource allocation have attracted a wide interest. Most of prior works focus on designing strategy-proof (a.k.a. truthful) cloud auction mechanisms to eliminate market manipulation. Strategy-proof auctions ensure that no bidders can improve their utilities by untruthful bidding. However, these strategy-proof auctions are fragile when false-name-bids are allowed. This is a new type of cheating where a bidder can gain profit by submitting bids using multiple fictitious names, and it is easy to form in cloud environment. Therefore, a new series of auction mechanisms are needed to guarantee the false-name-proofness. To tackle this issue, in this paper, we designed CACC, a combinatorial auction for resource allocation in Cloud Computing. To address the heterogeneity of cloud resource, the combinatorial auction model is adopted. We show CACC is both strategy-proof and false-name-proof. Moreover, CACC is computationally efficient. Through simulation experiments, we show that CACC is effective and efficient.

This paper presents a hybrid approach based discrete Particle Swarm Optimization (PSO) and chaotic strategies for solving multi-objective task scheduling problem in cloud computing. The main purpose is to allocate the summited tasks to the available resources in the cloud environment with minimum makespan (i.e. schedule length) and processing cost while maximizing resource utilization without violating Service Level Agreement (SLA) among users and cloud providers. The main challenges faced by Particle Swarm Optimization (PSO) when used to solve scheduling problems are premature convergence and trapping into local optimum. This paper presents an enhanced Particle Swarm Optimization algorithm hybridized with Chaotic Map strategies. The proposed approach is called Enhanced Particle Swarm Optimization based Chaotic Strategies (EPSOCHO) algorithm. Our proposed approach suggests two Chaotic Map strategies: sinusoidal iterator and Lorenz attractor to enhanced PSO algorithm in order to get good convergence and diversity for optimizing the task scheduling in cloud computing. The proposed approach is simulated and implemented in Cloudsim simulator. The performance of the proposed approach is compared with the standard PSO algorithm, the improved PSO algorithm with Longest job to fastest processor (LJFP-PSO), and the improved PSO algorithm with minimum completion time (MCT-PSO) using different sizes of tasks and various benchmark datasets. The results clearly demonstrate the efficiency of the proposed approach in terms of makespan, processing cost and resources utilization.

Scheduling in workflows plays a crucial role in optimizing task execution and resource utilization in cloud computing systems, particularly when Quality of Service (QoS) requirements, such as deadlines and task priorities, have to be fulfilled. This paper presents a novel, lightweight heuristic scheduling algorithm that incorporates QoS metrics into the heuristic scheduling process using the WorkflowSim simulation framework. The algorithm filters tasks based on the feasibility of deadlines, computes dynamic priority scores based on a blend of urgency and task weight, and employs an earliest-finish-time (EFT) policy for task to VM allocation. To test the proposed approach, simulation experiments were performed with synthetic Directed Acyclic Graph (DAG) workflows in a heterogeneous VM (Virtual Machine) cloud environment. The performance of the algorithm was evaluated relative to traditional baseline approaches, including First-Come-FirstServe (FCFS), Round Robin (RR), and Min-Min, using the metrics makespan, deadline miss rate, workflow success rate, and VM utilization. The results demonstrate the effectiveness of the proposed method in reducing makespan by up to 31.7% and improving workflow success rate to $\mathbf{7 2 \%}$ while achieving $\mathbf{7 9 \%}$ VM utilization, outperforming traditional schedulers. These findings suggest that lightweight heuristics can graciously meet the objectives of QoS without suffering the computational cost of metaheuristics. Enhancements in the future may include energy- and cost-conscious goals, re- scheduling, and predictive models to make it applicable across the various dynamics of a production field.

Cloud computing paradigm provides dynamically scalable resources as a service over the Internet. It promises reduction in capital expenditure as well as operational expenditure. In cloud computing, there are still some challenges need to be solved. Among them, job scheduling is one of the important issues, since the objective of service provider and the cloud user is to utilize the computing resources efficiently. Job scheduling is the process of assigning user jobs to appropriate resources so that it can utilize the cloud resources efficiently. In cloud computing environment, the communication time between the users and resources can have a great impact on job scheduling. The primary objective in cloud environment is to process the tasks provided by user with higher responsiveness. So there is a need of an efficient group-based job scheduling algorithm that assemble the independent fine-grained jobs into groups by taking the communication time into consideration. In this work, we have proposed a group-based scheduling strategy for scheduling fine-grained jobs according to the processing capability and bandwidth of available resources in cloud computing environment.