Sanjaya Kumar Panda

Efficient task scheduling algorithms for heterogeneous multi-cloud environment

Cloud Computing has grown exponentially in the business and research community over the last few years. It is now an emerging field and becomes more popular due to recent advances in virtualization technology. In Cloud Computing, various applications are submitted to the datacenters to obtain some services on pay-per-use basis. However, due to limited resources, some workloads are transferred to other data centers to handle peak client demands. Therefore, scheduling workloads in heterogeneous multi-cloud environment is a hot topic and very challenging due to heterogeneity of the cloud resources with varying capacities and functionalities. In this paper, we present three task scheduling algorithms, called MCC, MEMAX and CMMN for heterogeneous multi-cloud environment, which aim to minimize the makespan and maximize the average cloud utilization. The proposed MCC algorithm is a single-phase scheduling whereas rests are two-phase scheduling. We perform rigorous experiments on the proposed algorithms using various benchmark as well as synthetic datasets. Their performances are evaluated in terms of makespan and average cloud utilization and experimental results are compared with that of existing single-phase and two-phase scheduling algorithms to demonstrate the efficacy of the proposed algorithms.

A multi-objective task scheduling algorithm for heterogeneous multi-cloud environment

Cloud Computing has become a popular computing paradigm which has gained enormous attention in delivering on-demand services. Task scheduling in cloud computing is an important issue that has been well researched and many algorithms have been developed for the same. However, the goal of most of these algorithms is to minimize the overall completion time (i.e., makespan) without looking into minimization of the overall cost of the service (referred as budget). Moreover, many of them are applicable to single-cloud environment. In this paper, we propose a multi-objective task scheduling algorithm for heterogeneous multi-cloud environment which takes care both these issues. We perform rigorous experiments on some synthetic and benchmark data sets. The experimental results show that the proposed algorithm balances both the makespan and total cost in contrast to two existing task scheduling algorithms in terms of various performance metrics including makespan, total cost and average cloud utilization.

SLA-based task scheduling algorithms for heterogeneous multi-cloud environment

Service-level agreement (SLA) is a major issue in cloud computing because it defines important parameters such as quality of service, uptime, downtime, period of service, pricing, and security. However, the service may vary from one cloud service provider (CSP) to another. The collaboration of the CSPs in the heterogeneous multi-cloud environment is very challenging, and it is not well covered in the recent literatures. In this paper, we present two SLA-based task scheduling algorithms, namely SLA-MCT and SLA-Min-Min for heterogeneous multi-cloud environment. The former algorithm is a single-phase scheduling, whereas the latter one is a two-phase scheduling. The proposed algorithms support three levels of SLA determined by the customers. Furthermore, the algorithms incorporate the SLA gain cost for the successful completion of the service and SLA violation cost for the unsuccessful end of the service. We simulate the proposed algorithms using benchmark and synthetic datasets. The experimental results of the proposed SLA-MCT are compared with three single-phase task scheduling algorithms, namely CLS, Execution-MCT, and Profit-MCT, and the results of the proposed SLA-Min-Min are compared with two-phase scheduling algorithms, namely Execution-Min-Min and Profit-Min-Min in terms of four performance metrics, namely makespan, average cloud utilization, gain, and penalty cost of the services. The results clearly show that the proposed algorithms properly balance between makespan and gain cost of the services in comparison with other algorithms.

Normalization-Based Task Scheduling Algorithms for Heterogeneous Multi-Cloud Environment

Cloud computing is one of the most successful technologies that offer on-demand services through the Internet. However, datacenters of the clouds may not have unlimited capacity which can fulfill the demanded services in peak hours. Therefore, scheduling workloads across multiple clouds in a federated manner has gained a significant attention in the recent years. In this paper, we present four task scheduling algorithms, called CZSN, CDSN, CDN and CNRSN for heterogeneous multi-cloud environment. The first two algorithms are based on traditional normalization techniques, namely z-score and decimal scaling respectively which are hired from data mining. The next two algorithms are based on two newly proposed normalization techniques, called distribution scaling and nearest radix scaling respectively. All the proposed algorithms are shown to work on-line. We perform rigorous experiments on the proposed algorithms using various synthetic as well as benchmark datasets. Their performances are evaluated through simulation run by measuring two performance metrics, namely makespan and average cloud utilization. The experimental results are compared with that of existing algorithms to show the efficacy of the proposed algorithms.

An Efficient Resource Allocation Algorithm for IaaS Cloud

Infrastructure as a Service IaaS cloud provides access to computing resources by forming a virtualized environment. The resources are offered by means of leases. However, it is not possible to satisfy all the leases due to finite capacity of resources or nodes. Mapping between all the leases and the available nodes referred as resource allocation problem is very challenging to IaaS cloud. In this paper, we propose a resource allocation algorithm for IaaS cloud which is based on a novel approach of alert time. First, it uses alert time to assign the leases and then employs swapping to reschedule the already accommodated leases in case a lease is not schedulable by the alert time. This makes resource allocation superior to support the deadline sensitive leases by minimizing the lease rejection in contrast to two existing algorithms by Haizea [3] and Nathani [2]. We perform extensive experiments on several synthetic data sets and the results show that the proposed algorithm outperforms both the algorithms in terms of accepted leases and rejected leases.

A smoothing based task scheduling algorithm for heterogeneous multi-cloud environment

Task scheduling for heterogeneous multi-cloud environment is a well-known NP-complete problem. Due to exponential increase of client applications (i.e., workloads), cloud providers need to adopt an efficient task scheduling algorithm to handle workloads. Furthermore, the cloud provider may require to collaborate with other cloud providers to avoid fluctuation of demands. This workload sharing problem is referred as heterogeneous multi-cloud task scheduling problem. In this paper, we propose a task scheduling algorithm for heterogeneous multi-cloud environment. The algorithm is based on smoothing concept to organize the tasks. We perform rigorous experiments on synthetic and benchmark datasets and compare their results with two well-known multi-cloud algorithms namely, CMMS and CMAXMS. The comparison results show the superiority of the proposed algorithm in terms of two evaluation metrics, makespan and average cloud utilization.

Skewness-Based Min-Min Max-Min Heuristic for Grid Task Scheduling

Skewness plays a very important role in task scheduling. It measures the degree of asymmetry in a data set. Moreover, the data set may be positively skewed or negatively skewed. The quartile coefficient of skewness lies in between -1 to 1. If the quartile coefficient is in between -1 to 0, then the data set is negatively skewed. Otherwise, it is positively skewed. Min-Min and Max-Min heuristic underperforms if the data set is positively skewed and negative skewed respectively. In order to overcome this problem, we have proposed a hybrid heuristic called Skewness-Based Min-Min Max-Min (SBM2). This heuristic selects one of the heuristics (Min-Min or Max-Min) based on the skewness value. It can be calculated using three factors: first quartile, second quartile (or median) and third quartile. Simulation results show that the proposed hybrid heuristic minimizes the make span and handle the skewed data set.

A Group based Time Quantum Round Robin Algorithm using Min-Max Spread Measure

Round Robin (RR) Scheduling is the basis of time sharing environment. It is the combination of First Come First Served (FCFS) scheduling algorithm and preemption among processes. It is basically used in a time sharing operating system. It switches from one process to another process in a time interval. The time interval or Time Quantum (TQ) is fixed for all available processes. So, the larger process suffers from Context Switches (CS). To increase efficiency, we have to select different TQ for processes. The main objective of RR is to reduce the CS, maximize the utilization of CPU and minimize the turn around and the waiting time. In this paper, we have considered different TQ for a group of processes. It reduces CS as well as enhancing the performance of RR algorithm. TQ can be calculated using min-max dispersion measure. Our experimental analysis shows that Group Based Time Quantum (GBTQ) RR algorithm performs better than existing RR algorithm with respect to Average Turn Around Time (ATAT), Average Waiting Time (AWT) and CS.

An Efficient Intra-Server and Inter-Server Load Balancing Algorithm for Internet Distributed Systems

The growing popularity of Internet Distributed System has drawn enormous attention in business and research communities for handling large number of client requests. These requests are managed by a set of servers. However, the requests may not be equally distributed due to their random nature of arrivals. The optimal assignment of the requests to the servers is a well-known NP-hard problem. Therefore, many algorithms have been proposed to address this problem. However, these algorithms suffer from an excessive number of comparisons. In this paper, a Swapping-based Intraand interServer (SIS) load balancing with padding algorithm is proposed for its solution. The algorithm undergoes a three-phase process to balance the loads among the servers. The proposed algorithm is compared with a client-server load balancing algorithm and the performance is measured in terms of the number of load comparisons and load factor. The simulation outcomes show the efficacy of the proposed algorithm. KEywoRDS Client, Internet Distributed System, Load Balancing, Load Factor, Padding, Server, Swapping

FTMXT: Fault-Tolerant Immediate Mode Heuristics in Computational Grid

Fault tolerance plays a key role in computational grid. It enables a system to work smoothly in the presence of one or more failure components. The components are failing due to some unavoidable reasons like power failure, network failure, system failure, etc. In this chapter, we address the problem of machine failure in computational grid. The proposed system model uses the round trip time to detect the failure, and it uses the checkpointing strategy to recover from the failure. This model is applied to the traditional immediate mode heuristics such as minimum execution time (MET) and minimum completion time (MCT) (defined as MXT). The proposed Fault-Tolerant MET (FTMET) and Fault-Tolerant MCT (FTMCT) heuristics (defined as FTMXT) are simulated using MATLAB. The experimental results are discussed and compared with the traditional heuristics. The results show that the proposed approaches bypass the permanent failure and reduce the makespan.