International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
214
Comparative Study of Resource Managing Algorithms in Cloud
Computing
P. K. Suri
1, Sunita Rani
2 1Former Dean (Sc. /E&T) and Professor & Chairman (Department of Computer Science and Applications), Kurukshetra University, Kurukshetra, Haryana, India
2Assistant Professor, Department of CSE & IT, B.P.S.M.V., Khanpurkalan, Sonepat, Haryana, India
Abstract—A cloud computing is a very large scale network
computing system that scales to internet size environments with machines distributed across multiple organizations and administrative domains. Cloud computing is a type of parallel and distributed computing consisting of a collection of inter-connected and virtualized computers that are dynamically provisioned. The resource management system is the central component of cloud computing system. A resource management system matches requests to resources, schedules the matched resources, and executes the requests using scheduled resources. This paper provides a brief overview of resource management in cloud computing considering important factors such as resource management models in cloud computing, various job scheduling algorithms and various resource allocation strategies are presented. A comparison of various job scheduling algorithm and various resource allocation strategies in cloud computing have performed.
Keywords—cloud computing, resource management,
resource allocation, scheduling algorithms, scheduling models.
I. INTRODUCTION
Cloud computing is parallel and distributed computing that is collection of inter-connected, dynamic and virtualized resources [1]. National Institute of Standards and Technology (NIST) [2] defines Cloud computing as a model for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction.
Cloud computing has various characteristics like virtualization, service orientation, elasticity, dynamicity, distributed environment, sharing, economic, market oriented, pay as you go, autonomic [3], reduced cost and energy, on demand facility of resources, flexibility for customers, reliability, enhanced security, dynamicity [33] etc. Virtualization is very important characteristic which makes cloud computing different from the others distributed computing.
Resources (i.e. compute, storage, and network capacity) in Clouds are virtualized and virtualization is achieved at various levels including Virtual Machine and Platform levels.
The most basic one is at Virtual Machine (VM) level where different applications can be executed within their containers or operating systems running on the same physical machine. Platform level enables seamless mapping of applications to one or more resources offered by different Cloud infrastructure providers.
Cloud computing is mainly composed of three layers services which cover all the computing stack of a system: Iaas, Paas, Saas. Infrastructure-as-a-Service (IaaS) consists of virtual machines or physical machines, storage, and clusters. Cloud infrastructures can also be heterogeneous, integrating clusters, PCs and workstations. Platform as a Service (PaaS), cloud providers deliver a computing platform, typically including operating system, programming language execution environment, database, and web server. Software as a Service (SaaS) is a software delivery model providing on-demand access to applications. The most common examples of such service are CRM (Customer Relationship Management) and ERP (Enterprise Resource Planning) applications that are commonly used in almost all the enterprises from small, to large business.
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
215
(iii) Hybrid Clouds is the deployment which emerged due to diffusion of both public and private Clouds advantages. In this model, organizations outsource non-critical information and processing to the public Cloud, while keeping critical services and data in their control. (iv) Cloud computing also have Community cloud which shares infrastructure between several organizations from a specific community with common concerns (security, compliance, jurisdiction, etc.), whether managed internally or by a third-party, and either hosted internally or externally, distributed cloud which includes a distributed set of machines that are running at different locations, while still connected to a single network or hub service. (v) Inter cloud which is an interconnected global "cloud of clouds" and an extension of the Internet "network of networks" on which it is based and Multi cloud which use is the use of multiple cloud computing services in a single heterogeneous architecture to reduce reliance on single vendors, increase flexibility through choice, mitigate against disasters, etc. and it differs from hybrid cloud.
Efficiently and effectively management of resources, security, reliability and privacy protection [33] are various challenges faced in cloud computing environment.
In this paper, review of resource management in cloud computing is presented, Firstly various resource and job scheduling algorithm briefly explained and a comparative view is presented on various parameters.
II. CLOUD COMPUTING RESOURCE MANAGEMENT MODELS
There is various cloud computing resource management models like Market Model, Resource Service Model, Application Model [4], Parallel Programming Model [5], Resource Provisioning Model [6], Hierarchical Resource Management Model [7].
A.Cloud Computing Market Model consist two economic agent types, one is resource service agent type and another one is task agents [4]. Cloud Computing market has information about the locations of current resource service providers in the cloud and their prices.
B.Cloud resource service model consist system resource and communication resource. System resources implement specific functions for jobs and belong to a node or cluster which may provide several resources for the cloud and communication resources are used to transfer data.
C.Cloud Application Model [4] is described as undirected graph between job and communication relationship, in this model resource scheduling can be represented as a mapping function from application graph to the resource graph.
D.Parallel Programming Model [5] ensures that the background of complex parallel and task scheduling is transparent to users and programmers. Cloud Computing uses Map Reduce programming model to divide the task automatically into multiple sub-tasks, achieve the scheduling and allocation that task is in large-scale computing nodes.
E. A cloud resource provisioning model [6] uses statistical analysis of job history. A statistical technique, PCA (Principal Component Analysis), is used to analyze execution history of applications and to extract the factors which contribute much to execution time. The effective factors are used for selecting reference job profile and then VM is deployed on the selected node based on the reference profile. An application is executed on chosen nodes and its performance result is incorporated into job history with the purpose of evaluating profile’s credit.
F.Hierarchical Resource Management Model [7] is implemented as hierarchy, its first layer is Master, second layer is Cluster and third layer is group of virtual machines. Master layer is to receive the service requests of external users when regarding the group as a unit. If the resources cannot meet the demands within the group, the cluster layer asks the master for resources. It manages the group of the Virtual Machines. It receives the task of the "master" and the request of the virtual machine. It manages the resource allocation and scheduling within the group. The third layer is divided into groups, and the size of the group is depends on the number of VMs or the physical machines.
III. RESOURCE MANAGEMENT IN CLOUD COMPUTING
Resource management is very important issue in cloud computing. Resource management is efficient and effective management of resources, resource allocation and job scheduling for various applications. Performance, functionality and cost are the three basic factors that are affected by resource management of system. Cloud computing is a large geographically distributed complex system and computing resources, the availability of resources can be increased or decreased as per the resource consumption rate.
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
216
Hence after allocating the resources, an efficient scheduling strategy is required to schedule these jobs to allocated resources so as to provide high resource utilization and to achieve best system throughput.
Resource Allocation (RA) is the process of allocating resources which are available to the needed applications. An efficient and optimized allocation strategy is required to allocate resources and to utilize them within the limit of cloud environment so as to meet QoS requirements of cloud applications. The type and amount of requested resources is decided by the user [8] and then providers place the requested resources, according to their availability. The type and amount of requested resource should be sufficient so as to match the workload characteristics and to meet the constraints respectively
An application may consist of multiple jobs to which resources are allocated. Once the resources (virtual machines) are allocated to the user, procedure is required to schedule tasks or jobs on the resources to achieve maximum profit and efficient resource utilization. In cloud computing resources are allocated to the user on pay-as-per-use basis, hence job scheduling is an important task in cloud environment. Job scheduling strategy is responsible for scheduling jobs on allocated resources so that resource utilization effectively increases. The objectives of job scheduling strategy are: first, to maximize the profit second, to meet user’s QoS requirements third, efficient resource utilization. Forth, high performance computing and fifth, increase in throughput.
IV. RESOURCE ALLOCATION AND JOB SCHEDULING
ALGORITHMS
A.Optimized Resource Scheduling Algorithm for Open-source Cloud Systems (OSCS): This scheduling algorithm is based on Infrastructure as a Service (IaaS) cloud systems of open-source [9] to optimize the cloud scheduling problems. An Improved Genetic Algorithm (IGA) is used to implement this resource scheduling which uses minimal genes and Dividend Policy in Economics to choose a finest allocation for the VMs demand.
B.Optimized scheduling algorithm for cloud computing resource services (CCRS): This scheduling model is for Software as a Service (SaaS) platform and, is based on Buffer-Pool Agent that is used in the failure management due to the concurrency resource service [10].
This model can solve effectively the failure management during online parallel processing data under the SaaS platform, and improved service quality of SaaS platform, and decrease energy loss because of repeat computing. C.Load-Adaptive Cloud Resource Scheduling Model
(LACRS): A load-adaptive cloud resource scheduling model is based on ant colony algorithm [11]. When performance parameters of virtual machines in real time exceeded the threshold, overloading is easily detected and it schedules fast cloud resources using ant colony algorithm to bear some load on the load-free node. This model achieved requirements of self-adaptive cloud resources scheduling and improved the efficiency of the resource utilization.
D.Cost-based Resource Scheduling (CBRS): A cost-based resource scheduling paradigm is for Infrastructure as a Service (IaaS) in cloud computing and based upon market theory to schedule compute resources to meet user’s requirement [12]. The set of computing resources with the lowest price are assigned to the users according to current suppliers’ resource availability and price. This scheduling algorithm has three-tiered hierarchical and extensible architecture.
E.Scheduling Parallel Tasks onto Opportunistically Available Cloud Resources: This scheduling algorithm considered the problem of low-priority tasks onto underutilized computation resources in the cloud left by high-priority tasks and that servers’ availability to low-priority tasks is modeled as ON/OFF Markov chains [13]. This opportunistic scheduling schedules the low-priority tasks onto intermittently available server resources while minimizing the combined cost of waiting and migration and give good performance. F. Energy Efficient Optimization Scheduling Algorithm
(EEOS): This resource scheduling algorithm of cloud computing environment is based on energy efficient optimization methods and used the relationship between infrastructure components and power consumption of the cloud computing environment [14]. In this energy consumption model is presented for computing resources such that CPU, memory, storage and network and showed that, jobs that not fully utilized the hardware environment significantly reduce energy consumption. G.Idle Resource Cached Dynamic Scheduling Algorithm
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
217
This scheduling focused on large idle resources in Cloud and used these idle VMs as cached resources and schedules these idle resources that can quickly meet tasks resource demands and minimize users’ service cost and system energy-consumption.
H.Cloud Backup Scheduling Algorithm (CBS): Cloud Backup Scheduling Algorithm is based on Cloud State Table and Cloud Resources Table. Cloud State Table (CST) describes the state information of each storage nodes in cloud such as IP address, total storage capacity, free storage room, data access speed, network latency, number of I/O task in the queen, etc. Cloud Resource Table (CRT) is to record how data are stored [16]. Cloud backup scheduling algorithm considered both backup time and backup reliability comprehensively and showed good data access performance but did not consider the data redundancy reduction. Cloud backup is effective, reliable, extensible, cost-effective and usable.
I. Cloud Computing Resource Scheduling Policy Based on Genetic Algorithm with Multiple Fitness (MFCCS): This cloud computing resource scheduling policy is based on genetic algorithm with multiple fitnesses, which raised the resource utilization and saved energy cost under a cloud computing environment [17]. A pre-migration strategy which is based on three load dimensions: CPU utilization, network throughput, disk I/O rate, is used in this algorithm.
J. Cloud Computing Resource Scheduling Method Based on Time-Cost-Trust Model (TCTM): This scheduling algorithm is based on the model of the time-cost-trust cloud computing resources, which is based on the subset tree algorithm [18]. This algorithm has a higher efficiency, and is more suitable for large-scale cloud computing resource. This algorithm has good resource optimization, reliability of resources and high efficiency. K.Budget-Driven Scheduling Algorithm (BDS): This scheduling algorithm designed two heuristic algorithms Global Greedy Budget (GGB) and Gradual Refinement (GR), which are based on different greedy strategies to reduce the time complexity in minimizing the scheduling lengths of the workflows without breaking the budget [19]. This is optimal algorithms and showed the efficiencies of the greedy algorithms in cost-effectiveness to distribute the budget for performance optimizations of the MapReduce workflows.
L.Virtual Machine Scheduling for Improving Energy Efficiency in IaaS Cloud (IEES): This scheduling algorithm is used for Iaas to reduce energy consumption [20].
This scheduling problem is a combination of bin packing problem and quadratic assignment problem, which is also known as a classic combinatorial optimization and NP-hard problem and used to solve problem and gave optimization solutions.
M. Adaptive Task Scheduling Strategy (ATS): This adaptive task scheduling strategy is based on dynamic workload adjustment and it is highly efficient, reliable, stable, scalable, and load balancing for heterogeneous Hadoop clusters [21]. Adaptive Task Scheduling Strategy Based on Dynamic Workload Adjustment for Heterogeneous Hadoop Clusters (ATSDWA) significantly benefits both tasktrackers and jobtracker. On the taskertracker’s side, task execution time is reduced, node performance is more stable, task failure rate is obviously decreased, and both hunger and saturation are avoided at the same time. On the jobtracker’s side, the failure of jobtracker due to overloading can be avoided. ATSDWA is applicable to both homogeneous and heterogeneous clusters and can improve the overall task throughput rate of cluster without bringing extra load to tasktrackers.
N.Synchronization-Aware Scheduling (SAS): Synchronization-Aware Scheduling algorithm is for virtual clusters [22] and this scheduling algorithm attains better performance for tightly-coupled parallel applications than the state-of-the-art approaches like Xen’s Credit scheduler, balance scheduling, and hybrid scheduling and no extra communication cost is introduced in schedulers because of our synchronization-aware design.
O.Partial Utility-driven Scheduling for Flexible SLA and Pricing Arbitration in Clouds: This scheduling model takes into account the user’s partial utility specification when the provider needs to transfer resources between virtual machines [23]. It brings benefits to both providers regarding revenue and resource utilization, and client by improving workloads’ execution time.
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
218
Q.Rule Based Resource allocation model (RBRAM): RuleBased Resource allocation model (RBRAM) is based upon Supply-Demand analysis of the resources in a time marching paradigm. Here, queuing system is used to manage jobs and resources within the cloud and for efficient allocation of the resources in M-P-S (Memory-Processor-Storage) matrix model is used [25]. Within the framework of this approach, the analysis shows an improved performance of the system, achieved through efficiently allocating the resources to the jobs submitted to the cloud.
R.Utility-based Resource Allocation for Virtual Machines in Cloud Computing (UBRAVM): This algorithm is presented for dynamically allocating CPU resources to Virtual Machines in Infrastructure-as-a-Service (IaaS) Clouds, taking into account QoS objectives and operating costs [26]. In this a two-tier resource management approach based on adequate utility functions is presented, consisting of local controllers that dynamically allocate CPU shares to virtual machines to maximize a local node utility function and a global controller that initiates live migrations of virtual machines to other physical nodes to maximize a global system utility function. This algorithm improved the global system utility using Virtual Machine live migration, and maintained the performance at acceptable levels while reducing costs.
S. Dynamic Resource Allocation in Cloud Environment Under Time-variant Job Requests (DRATV): Cloud services are based on computing, storage, and networking resources provisioning, to satisfy remote end-users. In the dynamic resource allocation problem computing requests are characterized by their arrival and teardown times, as well as a prediction of their required computing power during their activity period [27]. T.Minimum Cost Maximum Flow Algorithm for Dynamic
Resource Allocation in Clouds (MCMF): A directed graph is used to model the allocation problem for cloud resources organized in a finite number of resource types [28]. Providers can use the minimum cost maximum flow algorithm to opportunistically select the most appropriate physical resources to serve applications or to ensure elastic platform provisioning. The MCMF algorithm uses this time-series model to forecast future requests and exhibits very good performance and scalability properties. The complexity of MCMF is low and prices are lower for resources.
U.Resources allocation and scheduling approaches for business process applications in Cloud contexts: In this allocation and scheduling workflow tasks strategy in Cloud contexts, is used for scheduling business process on distributed Cloud resources [29]. In this three approaches is used that is based on the overall execution time, on the cost incurred using a set of resources (i.e. virtual machines and human resources) and on the both criterion, respectively.
V.Priority Based Dynamic Resource Allocation in Cloud Computing with Modified Waiting Queue (PBDRA): Priority based algorithm is dynamic resource allocation mechanism for preempt-able jobs in cloud [30]. In order to attain the agreed SLA objective this algorithm dynamically responds to fluctuating work load by preempting the current executing task having low priority with high priority task and if preemption is not possible due same priority then by creating the new VM form globally available resources. If global resources are not available, task will be placed in waiting queue. When an appropriate VM become free that advanced reservation task will be selected from waiting queue and allocated for execution to that VM.
W. Resource allocation using Scalable computing (RASC): In this scheduling method, resources are allocated for the real-time tasks using IaaS model. The Real-Time tasks have to be completed before deadlines [31]. Here, the resources can be scaled up based on the necessities this is called Elasticity or Scalable Computing. The resources are scalable and can be used by the user in large number. The user can select any number of VMs based on rapidity and rate to complete the real-time tasks before deadlines. The VMs are leased by the client and hence the charge is fixed only for the rental period.
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
219
V. COMPARATIVE STUDY OF SCHEDULING ALGORITHMS
The comparison of various resource allocation and job scheduling algorithms is given in detail at Annexure-I.
VI. CONCLUSION
In this paper, a review of resource management system in cloud computing is presented. Various types of resource management models in cloud computing and various resource scheduling algorithm in cloud computing and various resource allocation strategies are discussed. A comparison on various parameters like platform, energy consumption, cost, resource utilization is done on different types of job scheduling. A comparison is also made for resource allocation strategies considering various parameters such as QoS, cost, scalability, bandwidth, resource allocation, congestion control and other live applications in IT industry.
REFERENCES
[1] Buyya R, Yeo CS, Venugopal S, Broberg J, Brandic I. “Cloud
computing and emerging IT platforms: Vision, type, and reality for delivering computing as the 5th utility”, Future Generation Computer Systems, 599–616, 2009.
[2] Mell, P. and Grance, T., “The NIST Definition of Cloud computing,
National Institute of Standards and Technology”, 2009.
[3] Saurabh Kumar Garg, Rajkumar Buyya, “Green Cloud computing
and Environmental Sustainability”,
[4] Mengkun Li, Ming Chen, lun Xie, “Cloud Computing: A Synthesis
Models for Resource Service Management”, Second International
Conference on Communication Systems, Networks and
Applications, IEEE, pp. 208-211, 2010.
[5] Liu xuning, Song hongwei, He dongbin, Yang hao, “Research of
Campus Resource Management Based on Cloud Computing”, The 5th International Conference on Computer Science & Education Hefei, China, pp. 1407-1409, August 24–27, 2010.
[6] Seoyoung Kim, Jung-in Koh, Yoonhee Kim, Chongam Kim, “A
Science Cloud Resource Provisioning Model using Statistical Analysis of Job History”, Ninth IEEE International Conference on Dependable, Autonomic and Secure Computing, IEEE Computer Society, IEEE,pp. 792-793, 2011.
[7] Ping Guo, Ling-ling Bu, “The Hierarchical Resource Management
Model Based on Cloud Computing”, IEEE Symposium on Electrical & Electronics Engineering (EEESYM), IEEE, pp. 471-474, 2012.
[8] V.Vinothina, Dr.R.Sridaran, and Dr. Padmavathi Ganapathi, “A
Survey on Resource Allocation Strategies in Cloud Computing”, International Journal of Advanced Computer Science and Applications, Vol. 3, No. 6, 2012.
[9] Hai Zhong, Kun Tao, Xuejie Zhang, “An Approach to Optimized
Resource Scheduling Algorithm for Open-source Cloud Systems”, The Fifth Annual ChinaGrid Conference, IEEE Computer Society , IEEE, pp.124-129, 2010.
[10] Chen Ming, Li Mengkun,Cai Fuqin, “A model of scheduling
optimizing for cloud computing resource sevices based on Buffer-pool Agent”, IEEE International Conference on Granular Computing, IEEE Computer Society, IEEE ,pp.107-110, 2010.
[11] Xin Lu, Zilong Gu, “A LOAD-ADAPATIVE CLOUD RESOURCE
SCHEDULING MODEL BASED ON ANT COLONY
ALGORITHM”, Proceedings of IEEE CCIS2011, IEEE, pp. 296-300, 2011.
[12] Zhi Yang, Changqin Yin, Yan Liu, “A Cost-based Resource
Scheduling Paradigm in Cloud Computing”, 2011 12th International Conference on Parallel and Distributed Computing, Applications and Technologies, IEEE Computer Society, pp. 417-422, 2011.
[13] Ting He, Shiyao Chen, Hyoil Kim, Lang Tong, and Kang-Won Lee,
“Scheduling Parallel Tasks onto Opportunistically Available Cloud Resources”, 2012 IEEE Fifth International Conference on Cloud Computing, IEEE Computer Society, IEEE, pp. 180-187, 2012.
[14] Liang Luo, Wenjun Wu, Dichen Di,Fei Zhang,Yizhou Yan,Yaokuan
Mao, “A Resource Scheduling Algorithm of Cloud Computing based on Energy Efficient Optimization Methods”, 2012 IEEE.
[15] Hu Song, Jing Li, Xinchun Liu, “IdleCached: An Idle Resource
Cached Dynamic Scheduling Algorithm in Cloud Computing”, 2012 9th International Conference on Ubiquitous Intelligence and Computing and 9th International Conference on Autonomic and Trusted Computing, IEEE Computer Society, IEEE, pp.912-917, 2012.
[16] GE Liang, YANG Junduo, ZHU Qingsheng, LV Kang, WANG
Qianqian, LUO Xin, CHEN Qiang, PEI Jie, “Cloud Backup Scheduling Algorithm Based on Cloud State Table and Cloud Resources Table”, 2012 Ninth Web Information Systems and Applications Conference, IEEE Computer Society, IEEE pp.189-192, 2012.
[17] Shi Chen, Jie Wu, Zhihui Lu,” A Cloud Computing Resource
Scheduling Policy Based on Genetic Algorithm with Multiple Fitness”, 2012 IEEE 12th International Conference on Computer and Information Technology, IEEE Computer Society, IEEE, pp.177-184, 2012.
[18] GAO Zhong-wen, ZHANG Kai, “The Research on Cloud
Computing Resource Scheduling Method Based on Time-Cost-Trust Model”, 2012 2nd International Conference on Computer Science and Network Technology, CHANGCHUN, CHINA, IEEE, pp.939-942,2012.
[19] Yang Wang and Wei Shi, “Budget-Driven Scheduling Algorithms for Batches of MapReduce Jobs in Heterogeneous Clouds”, IEEE TRANSACTIONS ON CLOUD COMPUTING, VOL. 2, NO. 3, pp.306-319, JULY-SEPTEMBER 2014.
[20] DONG Jiankang, WANG Hongbo, LI Yangyang, CHENG Shiduan,
“Virtual Machine Scheduling for Improving Energy Efficiency in IaaS Cloud”, ENERGY CONSERVATION AND HARVESTING FOR GREEN COMMUNICATIONS, China Communications , pp. 1-12, March 2014.
[21] Xiaolong Xu, Lingling Cao, and Xinheng Wang, “Adaptive Task
Scheduling Strategy Based on Dynamic Workload Adjustment for Heterogeneous Hadoop Clusters”, IEEE SYSTEMS JOURNAL, IEEE, pp.1-12, 2014.
[22] Song Wu, Haibao Chen, Sheng Di, Bingbing Zhou, Zhenjiang Xie,
Hai Jin, and Xuanhua Shi, “Synchronization-Aware Scheduling for Virtual Clusters in Cloud”, TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, IEEE, pp.1-14, 2013.
[23] Jose Simao, Luıs Veiga, “Partial Utility-driven Scheduling for
International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 6, Issue 6, June 2016)
220
[24] Xindong YOU, Xianghua XU, Jian Wan, Dongjin YU,
“RAS-M:Resource Allocation Strategy based on Market Mechanism in Cloud”, 2009 Fourth ChinaGrid Annual Conference, 2009 , IEEE Computer Societry,IEEE, pp. 256-263.
[25] T.R. Gopalakrishnan Nair, Vaidehi M, “EFFICIENT RESOURCE
ARBITRATION AND ALLOCATION STRATEGIES IN CLOUD COMPUTING THROUGH VIRTUALIZATION”, Proceedings of IEEE CCIS2011, 2011 IEEE, pp.397-401.
[26] Dorian Minarolli and Bernd Freisleben, “Utility-based Resource
Allocation for Virtual Machines in Cloud Computing”,2011 IEEE, pp. 410-417.
[27] Davide Tammaro, Elias A. Doumith, Sawsan Al Zahr, Jean-Paul
Smets, Maurice Gagnaire and Nexedi SA, “Dynamic Resource Allocation in Cloud Environment Under Time-variant Job Requests”, 2011 Third IEEE International Conference on Coud Computing Technology and Science, 2011 IEEE, pp. 592-598.
[28] Makhlouf Hadji, Djamal Zeghlache, “Minimum Cost Maximum
Flow Algorithm for Dynamic Resource Allocation in Clouds”, 2012 IEEE Fifth International Conference on Cloud Computing, 2012 IEEE, IEEE Computer Societry, pp.876-882.
[29] Kahina Bessai, Samir Youcef, Ammar Oulamara, Claude Godart and
Selmin Nurcan∗, “Resources allocation and scheduling approaches
for business process applications in Cloud contexts”, 2012 IEEE 4th International Conference on Cloud Computing Technology and Science, 2012 IEEE, IEEE Computer Societry, pp.496-503.
[30] Chandrashekhar S. Pawar, Rajnikant B. Wagh, “Priority Based
Dynamic Resource Allocation in Cloud Computing with Modified Waiting Queue”, 2013 International Conference on Intelligent Systems and Signal Processing (ISSP), 2013 IEEE, pp.311-316.
[31] Karthik Kumar, Jing Feng, Yamini Nimmagadda, and Yung- Hsiang
Lu,” Resource Allocation for Real-Time Tasks using Cloud Computing”, IEEE (2011), pp.1-7.
[32] Jianfeng Yan, Wen-Syan Li, “Calibrating Resource Allocation for
Parallel Processing of Analytic Tasks”, IEEE International Conference on e-Business Engineering, IEEE (2009), pp.327-332.
[33] Chunlan Li, Zhonghua Deng, “Value of Cloud Computing by the
View of Information Resources”, International Conference on Network Computing and Information Security, IEEE Computer Society, IEEE, 2011,pp.108-112.
Annexure-I
Comparison of Various Resource Allocation and Job Scheduling Algorithm
Features
PBDRA RAS-M MCMF RBRAM UBRAVM RASC Time Variant
Fair Resource Allocation
OSCS CCRS CBRS IRCDS MFCCS IEES SAS
Platform Used IaaS SaaS SaaS IaaS IaaS IaaS SaaS IaaS SaaS IaaS SaaS IaaS IaaS IaaS
QoS Medium High Medium Medium High Low High Medium Low Medium High Low Medium High Medium
Cost Low Medium Low Medium Low Medium Medium Medium Medium Medium Low Low Low Medium Low
Scalability High Low High High Medium High Medium Low High Medium High High Medium High High
Bandwidth Medium Low High Low Medium High Medium Medium Low Medium High Low Medium High Medium
Optimal Resource Allocation/Utilization
Medium Medium High High High Medium High High High High Medium Medium High High High
Congestion Control Medium High Medium Medium Low Medium Medium High Low Medium High Low Medium High Medium
Energy Conservation Low High Medium Low Medium Medium High High High High Medium High High High High
Prohibition of SLA violation