Cloud Job Research Articles

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

Task scheduling in the cloud computing still remains challenging in terms of performance. Several evolutionary-derived algorithms have been proposed to solve or alleviate this problem. However, evolutionary algorithms have good exploration ability, but the performance drops significantly in high dimensions. To address this issue, considering the characteristic of task scheduling in cloud computing (i.e. all task-VM mappings are 1-dimensional and have the same search range), we propose a task scheduling algorithm based on grey wolf optimization using a new encoding mechanism (GWOEM) in this work. Through this new encoding mechanism, greedy and evolutionary algorithms are rationally integrated in GWOEM. Besides, based on the new mechanism, the dimension of search space is reduced to 1 and the key parameter (i.e., the population size) is eliminated. We apply the proposed GWOEM to the Google Cloud Jobs dataset (GoCJ) and demonstrate better performance than the prior state of the art in terms of makespan.

A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling

A Deep Reinforcement Learning-Based Preemptive Approach for Cost-Aware Cloud Job Scheduling

Reinforcement Learning Based Metaheuristic Algorithm For Optimized Load Balancing In Cloud Environment

In cloud computing, workload balancing remains a difficult issue, as overburdened or underburdened servers are capable of causing issues with computation speed or even cause an entire network to collapse, subsequently this is a scenario that is never supposed to occur when using the cloud. Therefore, in order to avoid these issues, the system should be load balanced—that is, allocate job across each of the accessible computing assets by taking into account an acceptable schedule of utilization. The Virtual Machines are supposed to be used effectively, in response to the distributed load mechanism. In this work, a multifaceted load balancing optimization based on the Enhanced Firefly algorithm (EFA) with a Partial Order Markov Decision (POMD) process algorithm is proposed as an autonomous job allocation strategy in cloud computing. In order to overcome the limits of concurrent considerations, the suggested solution seeks to maximise VM productivity, streamline task allocation and the use of resources, and provide load balancing amongst virtual machines based on Time to Finish, expenditure, and consumption of resources. Using CloudSim, the performance study of the suggested approach was contrasted with the load balancing algorithms now in use in datasets like Google Cloud Jobs (GoCJ). According to the trial results, the suggested POMD-EFA strategy performed better than the other algorithms in terms of decreasing the Time to Finish, minimizing expenses, and increasing the efficiency in the application of resources.

Optimizing Cloud-Fog-Edge Job Scheduling Using Catastrophic Genetic Algorithm and Block Chain-Based Trust: A Collaborative Approach

Collaborative edge-cloud features improve job scheduling. Cloud job scheduling is crucial. Pending delay completion. A cloud-edge mixed system replaced centralized cloud computing. Combining resource levels reduces terminal user service call latency. Decentralization, regionalization, and node dispersal autonomy increase ambiguity, unreliability, and instability. This paper will plan cloud-migrating tasks on edge devices or the cloud to achieve a global optimum. The objective of this research is to enhance the efficiency of job scheduling in cloud-fog edge environments through the integration of the Catastrophic Genetic Algorithm (CGA), a genetic algorithm inspired by natural evolution. Additionally, Berger's theory will be employed to develop a trust-enabled interaction framework based on blockchain technology. The CGA fitness function incorporates load balancing and reasonability in the coordination of services and scheduling of tasks, with the goal of maximizing performance. This article presents proposed improvements to the CGA, which involve the incorporation of mutation and crossover operators, roulette selection, and cataclysm. These changes aim to expand the search area and potentially discover schedules that are more optimal. The approach also effectively deals with the problem of premature convergence, guaranteeing ample time for the algorithm to comprehensively explore the solution space prior to reaching a final solution. The experimental findings indicate that the strategy put forward in this study yields a substantial reduction in task completion time, surpassing 97%. Furthermore, it effectively addresses the best local problem, hence showcasing competing options.

Priority based job scheduling technique that utilizes gaps to increase the efficiency of job distribution in cloud computing

A growing number of services, accessible and usable by individuals and businesses on a pay-as-you-go basis, are being made available via cloud computing platforms. The business services paradigm in cloud computing encounters several quality of service (QoS) challenges, such as flow time, makespan time, reliability, and delay. To overcome these obstacles, we first designed a resource management framework for cloud computing systems. This framework elucidates the methodology of resource management in the context of cloud job scheduling. Then, we study the impact of a Virtual Machine’s (VM’s) physical resources on the consistency with which cloud services are executed. After that, we developed a priority-based fair scheduling (PBFS) algorithm to schedule jobs so that they have access to the required resources at optimal times. The algorithm has been devised utilizing three key characteristics, namely CPU time, arrival time, and job length. For optimal scheduling of cloud jobs, we also devised a backfilling technique called Earliest Gap Shortest Job First (EG-SJF), which prioritizes filling in schedule gaps in a specific order. The simulation was carried out with the help of the CloudSim framework. Finally, we compare our proposed PBFS algorithm to LJF, FCFS, and MAX–MIN and find that it achieves better results in terms of overall delay, makespan time, and flow time.

Internet of Things Data Cloud Jobs Scheduling Using Modified Distance Cat Swarm Optimization

IoT cloud computing provides all functions of traditional computing as services through the Internet for the users. Big data processing is one of the most crucial advantages of IoT cloud computing. However, IoT cloud job scheduling is considered an NP-hard problem due to the hardness of allocating the clients’ jobs to suitable IoT cloud provider resources. Previous work on job scheduling tried to minimize the execution time of the job scheduling in the IoT cloud, but it still needs improvement. This paper proposes an enhanced job scheduling mechanism using cat swarm optimization (CSO) with modified distance to minimize the execution time. The proposed job scheduling mechanism first creates a set of jobs and resources to generate the population by randomly assigning the jobs to resources. Then, it evaluates the population using the fitness value, which represents the execution time of the jobs. In addition, we use iterations to regenerate populations based on the cat’s behaviour to produce the best job schedule that gives the minimum execution time for the jobs. We evaluated the proposed mechanism by implementing an initial simulation using Java Language and then conducted a complete simulation using the CloudSim simulator. We ran several experimentation scenarios using different numbers of jobs and resources to evaluate the proposed mechanism regarding the execution time. The proposed mechanism significantly reduces the execution time when we compare the proposed mechanism against the firefly algorithm and glowworm swarm optimization. The average execution time of the proposed cat swarm optimization was 131, while the average execution times for the firefly algorithm and glowworm optimization were 237 and 220, respectively. Hence, the experimental findings demonstrated that the proposed mechanism performs better than the firefly algorithm and glowworm swarm optimization in reducing the execution time of the jobs.

A Novel Fault-Tolerant Aware Task Scheduler Using Deep Reinforcement Learning in Cloud Computing

Task scheduling poses a wide variety of challenges in the cloud computing paradigm, as heterogeneous tasks from a variety of resources come onto cloud platforms. The most important challenge in this paradigm is to avoid single points of failure, as tasks of various users are running at the cloud provider, and it is very important to improve fault tolerance and maintain negligible downtime in order to render services to a wide range of customers around the world. In this paper, to tackle this challenge, we precisely calculated priorities of tasks for virtual machines (VMs) based on unit electricity cost and these priorities are fed to the scheduler. This scheduler is modeled using a deep reinforcement learning technique which is known as the DQN model to make decisions and generate schedules optimally for VMs based on priorities fed to the scheduler. This research is extensively conducted on Cloudsim. In this research, a real-time dataset known as Google Cloud Jobs is used and is given as input to the algorithm. This research is carried out in two phases by categorizing the dataset as a regular or large dataset with real-time tasks with fixed and varied VMs in both datasets. Our proposed DRFTSA is compared to existing state-of-the-art approaches, i.e., PSO, ACO, and GA algorithms, and results reveal that the proposed DRFTSA minimizes makespan compared to PSO, GA, and ACO by 30.97%, 35.1%, and 37.12%, rates of failure by 39.4%, 44.13%, and 46.19%, and energy consumption by 18.81%, 23.07%, and 28.8%, respectively, for both regular and large datasets for both fixed and varied VMs.

DPS: Dynamic Pricing and Scheduling for Distributed Machine Learning Jobs in Edge-Cloud Networks

5G and Internet of Things stimulate smart applications of edge computing, such as autonomous driving and smart city. As edge computing power increases, more and more machine learning (ML) jobs will be trained in the edge-cloud network, adopting the parameter server (PS) architecture. Due to the distinct features of the edge (low-latency and the scarcity of resources), the cloud (high delay and rich computing capacity) and ML jobs (frequent communication between workers and PSs and unfixed runtime), existing cloud job pricing and scheduling algorithms are not applicable. Therefore, how to price, deploy and schedule ML jobs in the edge-cloud network becomes a challenging problem. To solve it, we propose an auction-based online framework DPS. DPS consists of three major parts: job admission control, price function design and scheduling orchestrator. DPS dynamically prices workers and PSs based on historical job information and real-time system status, and decides whether to accept the job according to the deployment cost. DPS then deploys and schedules accepted ML jobs to pursue the maximum social welfare. Through theoretical analysis, we prove that DPS can achieve a good competition ratio and truthfulness in polynomial time. Large-scale simulations and testbed experiments show that DPS can improve social welfare by at least <inline-formula><tex-math notation="LaTeX">$95\%$</tex-math></inline-formula>, compared with benchmark algorithms in today&#x0027;s cloud system.

SG-PBFS: Shortest Gap-Priority Based Fair Scheduling technique for job scheduling in cloud environment

Job scheduling in cloud computing plays a crucial role in optimizing resource utilization and ensuring efficient job allocation. But cloud resources may be wasted, or service performance may suffer because of under-utilization or over-utilization because of poor scheduling. Existing approaches often overlook the dynamic nature of cloud environments, resulting in issues like missed deadlines, prolonged flowtime, extended makespan, and unacceptable total tardiness. To address this issue, the main objective of this research is to improve the existing Priority Rules (PR) cloud schedulers by developing a new dynamic scheduling algorithm by manipulating the gaps in the cloud job schedule. Firstly, a Priority-Based Fair Scheduling (PBFS) algorithm has been introduced to schedule jobs so that jobs can access the required resources at optimal times. Then, a backfilling strategy called Shortest Gap - Priority-Based Fair Scheduling (SG-PBFS) is developed that attempts to manipulate the gaps in the schedule of cloud jobs. Finally, the performance evaluation demonstrates that the proposed SG-PBFS algorithm outperforms SG-SJF, SG-LJF, SG-FCFS, SG-EDF, and SG-(MAX-MIN) regarding flow time, makespan time, and total tardiness, which conclusively demonstrates its effectiveness. To conduct this experiment, we employed the CloudSim simulator, which is implemented using the Java programming language.

Deep Adversarial Imitation Reinforcement Learning for QoS-Aware Cloud Job Scheduling

Although cloud computing is one of the promising technologies for online business services, how to schedule real-time cloud jobs with high quality of service (QoS) is still challenging current techniques. With the advancing of machine learning, deep reinforcement learning (DRL) has demonstrated its outstanding capability in dispatching time-sensitive tasks. However, the reinforced rewards in DRL are typically unavailable until the completion of the scheduling for all the jobs. Considering the fact that the trajectory of jobs in cloud is always long, current DRL-based solutions will meet challenges in finding the trajectories with high rewards, and thus would have issues such that the finally trained scheduling policy is suboptimal. To improve the problem, in this article, we propose a more advanced approach called a deep adversarial imitation reinforcement learning (AIRL) framework for scheduling time-sensitive cloud jobs. Specifically, we focus on scheduling user requests in a way to maximize job successful rate along with a significant reduction on job response time. We present the detailed design of our method, and our experimental results demonstrate that AIRL can generally outperform the existing cloud job scheduling approaches, including the DRL-based method, in the presence of different real-time workload and computing resource configurations.

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Task scheduling and load balancing problem of heterogeneous computing environment (HCE) is getting more and more attention these days and has become a research hotspot in this field. The task scheduling and load balancing problem of heterogeneous environment, which refers to assigning a set of tasks to a specific set of machines with different hardware and different computing performance with the goal of minimizing task processing time and keeping load balance among machines, has been proved to be an NP-complete problem. The development of artificial intelligence provides new ideas to solve this problem. In this paper, we propose a novel task scheduling and load balancing method based on optimized deep reinforcement learning in HCE. First, we formulate task scheduling problem as a Markov decision process and then adopt a dueling double deep Q-learning network to search the optimal task allocation solution. Then we use two well-known large-scale cluster data sets Google Cloud Jobs data set and Alibaba Cluster Trace data set to validate our approach. The experimental results show that compared with other existing solutions, our proposed method can achieve much shorter task response time and better load balancing effect.

Multi-Objective Task Scheduling Optimization for Load Balancing in Cloud Computing Environment Using Hybrid Artificial Bee Colony Algorithm With Reinforcement Learning

Workload balancing in cloud computing is still challenging problem, especially in Infrastructure as a Service (IaaS) in the cloud model. A problem that should not occur during cloud access is a host or server being overloaded or underloaded, which may affect the processing time or may result in a system crash. Therefore, to prevent these problems, an appropriate schedule of access should be considered so that the system can distribute tasks across all available resources, which is called load balancing. The load balancing technique should ensure that all Virtual Machines (VMs) are used appropriately. In this paper, an independent task scheduling approach in cloud computing is proposed using a Multi-objective task scheduling optimization based on the Artificial Bee Colony Algorithm (ABC) with a Q-learning algorithm,which is a reinforcement learning technique that helps the ABC algorithm work faster, called the MOABCQ method. The proposed method aims to optimize scheduling and resource utilization, maximize VM throughput, and create load balancing between VMs based on makespan, cost, and resource utilization, which are limitations of concurrent considerations. Performance analysis of the proposed method was compared using CloudSim with the existing load balancing and scheduling algorithms: Max-Min, FCFS, HABC_LJF, Q-learning, MOPSO, and MOCS algorithms in three datasets: Random, Google Cloud Jobs (GoCJ), and Synthetic workload. The experimental results indicated that the algorithms used MOABCQ approach outperformed the other algorithms in terms of reducing makespan, reducing cost, reducing degree of imbalance, increasing throughput and average resource utilization.

Power- and QoS-Aware Job Assignment With Dynamic Speed Scaling for Cloud Data Center Computing

As the usage of mission-critical mobile applications increases in Industry 4.0, such as smart manufacturing and self-driving cars, the cloud computing paradigm and its supporting data centers have become more crucial. However, a common practice in the cloud data center computing industry tends to supply a surfeit of computing resources mainly for a robust quality-of-service (QoS). In this paper, we propose a simple real-time algorithm which combines a power-aware job assignment policy for a centralized job dispatcher and a power- and QoS-aware dynamic speed scaling policy for each physical machine (PM). The job assignment policy is called “Join the Least Power Consuming (LPC) Server” that routes an incoming cloud job to a server spending minimum power upon request. The server-side adaptive speed scaling policy expedites energy efficiency and satisfies response time-associated QoS condition. We call this policy “Minimizing Earliness (ME)” since it manages the server speed towards finishing jobs at their deadlines as precisely as possible, reducing the earliness of job completion. The design principle of LPC-ME combination supports both energy efficiency and service quality required in cloud data centers. Numerical experiments compare the proposed algorithm’s power consumption and response time with those of existing popular policies and demonstrate better energy efficiency with negligible degradation of service quality.

Secure and Consistent Job Administration Using Encrypted Data Access Policies in Cloud Systems

Cloud services are provided to individuals or particular communities and groups. The data produced or communicated are expected to be more secure in the cloud environment, which requires the continuous services of Cloud Service Provider (CSP). In this article, Securely Encrypted Data Access Policies (SEDAP) are configured in the cloud platform. The proposed SEDAP helps to understand the cloud services and accesses in different perspectives such as user actions, jobs initiated from users and the batches evolved from the dependent jobs. The boundary between these perspectives is used in SEDAP for providing encrypted and authenticated job administration in cloud services. In this work, efficient fast processing Advanced Encryption Standard (AES), Secure Hashing Algorithm (SHA-3) and other session key distribution mechanisms are used. The results of SEDAP are compared with the other existing cloud security schemes, which shows that SEDAP has 20% more stability and ensures multilevel security in cloud job administration process.

Machine learning based deep job exploration and secure transactions in virtual private cloud systems

Virtual Private Cloud (VPC) is an emerging cloud environment used to provide more secure data communication. VPC provides authentic communication channel for secure communication between the cloud participants. The cloud jobs and the description of the runtime cloud events must be evaluated to provide flawless VPC service. Although VPC provides security in network services, it has to be enriched with internal and external platform level security features. In this regard, secure job service schemes ensure elimination of attacks, unauthorized jobs, improper accesses and intrusions in VPC. These irrelevant tasks (activities) can be isolated before initiating job scheduling process. Particularly, providing security for zero-trust cloud environment is more challenging task. Zero-trust cloud environment has completely vulnerable trust model on both internal and external circumstances. The proposed Machine Learning Based Secure Cloud Job Services (MLSCS) is implemented to provide multi-level security in this zero-trust cloud job servicing system. The proposed MLSCS develops Multi-Server Queue Management techniques, Reinforcement Learning based deep Q Matrix (RL-Q Matrix) techniques, Authentic VPC configuration and VPC Genetic Algorithm Network (VGAN) for establishing security practices in complex job handling system. MLSCS applies effective techniques for eliminating irrelevant cloud jobs to reduce the scheduler complexity and processor utilization. In this work, irrelevant jobs are considered as the jobs that are not appropriate for particular VPC scheduling policies and security principles (attacks). These jobs are identified through various key validation procedures and VPC policy determination procedures. These jobs are eliminated and prohibited in to job scheduler. Consequently, the legitimate jobs are securely forwarded in to job scheduler through multi-server queues. In the experimental setup, the proposed MLSCS is compared with existing schemes such as Reinforcement Learning Based Distributed Heterogeneous Servicing technique (RLDH), Cat Swarm Optimization Based Job Servicing technique (CSOS) and Fuzzy Based Security-Driven Servicing technique (FSDS). The results show the MLSCS delivers 5% to 8% optimal results than existing schemes.

Batch Auction Design for Cloud Container Services

Cloud containers represent a new, light-weight alternative to virtual machines in cloud computing. A user job may be described by a container graph that specifies the resource profile of each container and container dependence relations. This work is the first in the cloud computing literature that designs efficient market mechanisms for container based cloud jobs. Our design targets simultaneously incentive compatibility, computational efficiency, and economic efficiency. It further adapts the idea of batch online optimization into the paradigm of mechanism design, leveraging agile creation of cloud containers and exploiting delay tolerance of elastic cloud jobs. The new and classic techniques we employ include: (i) compact exponential optimization for expressing and handling non-traditional constraints that arise from container dependence and job deadlines; (ii) the primal-dual schema for designing efficient approximation algorithms for social welfare maximization; and (iii) posted price mechanisms for batch decision making and truthful payment design. Theoretical analysis and trace-driven empirical evaluation verify the efficacy of our container auction algorithms.

Integrating clustering and regression for workload estimation in the cloud

AbstractWorkload prediction has been widely researched in the literature. However, existing techniques are per‐job based and useful for service‐like tasks whose workloads exhibit seasonality and trend. But cloud jobs have many different workload patterns and some do not exhibit recurring workload patterns. We consider job‐pool‐based workload estimation, which analyzes the characteristics of existing tasks' workloads to estimate the currently running tasks' workload. First cluster existing tasks based on their workloads. For a new task J, collect the initial workload of J and determine which cluster J may belong to, then use the cluster's characteristics to estimate J′s workload. Based on the Google dataset, the algorithm is experimentally evaluated and its effectiveness is confirmed. However, the workload patterns of some tasks do have seasonality and trend, and conventional per‐job‐based regression methods may yield better workload prediction results. Also, in some cases, some new tasks may not follow the workload patterns of existing tasks in the pool. Thus, develop an integrated scheme which combines clustering and regression and utilize the best of them for workload prediction. Experimental study shows that the combined approach can further improve the accuracy of workload prediction.

An Approach to Optimise Resource Provision with Energy-Awareness in Datacentres by Combating Task Heterogeneity

Cloud workloads are increasingly heterogeneous such that a single Cloud job may encompass one to several tasks, and tasks belonging to the same job may behave distinctively during their actual execution. This inherent task heterogeneity imposes increased complexities in achieving an energy efficient management of the Cloud jobs. The phenomenon of a few proportions of tasks characterising increased resource intensity within a given job usually lead the providers to over-provision all the encompassed tasks, resulting in majority of the tasks incurring an increased proportions of resource idleness. To this end, this paper proposes a novel analytics framework which integrates a resource estimation module to estimate the resource requirements of tasks a priori, a straggler classification module to classify tasks based on their resource intensity, and a resource optimisation module to optimise the level of resource provision depending on the task nature and various runtime factors. Performance evaluations conducted both theoretically and through practical experiments prove that the proposed methodology performs better than the compared statistical resource estimation methods and existing models of straggler mitigation, and further demonstrate the effectiveness of the proposed methodology in achieving energy conservation by postulating appropriate level of resource provisioning for task execution.

Cloud Job ‎Scheduling with‎ Ions Motion Optimization Algorithm

Cloud Job ‎Scheduling with‎ Ions Motion Optimization Algorithm

Job Scheduling in Cloud Computing Using a Modified Harris Hawks Optimization and Simulated Annealing Algorithm.

In recent years, cloud computing technology has attracted extensive attention from both academia and industry. The popularity of cloud computing was originated from its ability to deliver global IT services such as core infrastructure, platforms, and applications to cloud customers over the web. Furthermore, it promises on-demand services with new forms of the pricing package. However, cloud job scheduling is still NP-complete and became more complicated due to some factors such as resource dynamicity and on-demand consumer application requirements. To fill this gap, this paper presents a modified Harris hawks optimization (HHO) algorithm based on the simulated annealing (SA) for scheduling jobs in the cloud environment. In the proposed HHOSA approach, SA is employed as a local search algorithm to improve the rate of convergence and quality of solution generated by the standard HHO algorithm. The performance of the HHOSA method is compared with that of state-of-the-art job scheduling algorithms, by having them all implemented on the CloudSim toolkit. Both standard and synthetic workloads are employed to analyze the performance of the proposed HHOSA algorithm. The obtained results demonstrate that HHOSA can achieve significant reductions in makespan of the job scheduling problem as compared to the standard HHO and other existing scheduling algorithms. Moreover, it converges faster when the search space becomes larger which makes it appropriate for large-scale scheduling problems.