Dynamic congestion management system for cloud service broker

2013 3rd IEEE International Advance Computing Conference (IACC), 2013

The applications submitted to cloud middle ware have been distributed to the Cloud Service Providers(CSPs) based on the available CSPs in the cloud environment to categorize the service CSP providers with this work we are trying to introduce a concept to find the optimal CSP based on rough set based approach. IaaS provides a large amount of computational capacities to users in a flexible and efficient way. In the market various CSPs are available example Amazons elastic computing cloud offers virtual machine with 0.1 us dollars per hour similarly another cloud Google compute cloud offers virtual machine with 0.5 us dollars per hour then the cloud users need rating among the various CSPs. In this research work we have been proposing an approach to provide the rating of CSPs based on the internal performance of Datacenters and virtual machines. In present situation day-by-day number of cloud service providers have been increasing drastically. In this scenario existing service providers scheduling need a mechanism to find the optimal service providers information to Service request scheduling using this information SRS can allocate the service to the respective optimal service providers. In this paper we studied the problem of dynamic request allocation and scheduling for context aware application deployed in geographically distributed data centers forming a cloud.

2018

Cloud computing system offers reliable services to the users based on their service requests. The users should pay for the amount of resources availed by them. The main goal of the cloud computing system is to minimize the capital and maintenance cost by eliminating the process of the owning the resources. It supports the users by providing the equipment and programming resources required for them. The cloud data centers comprise a group of configurable resources including networks, applications and servers. The data center of the cloud computing system should satisfy the demands of the user to gain reputation and profit. A Service Level Agreement (SLA) should be signed between the cloud users and service providers to enter into an agreed upon business environment. The requirements of the users will be clearly specified in the SLA, which must be strictly followed (Ghosh, 2012). The SLA is necessary to attain the Quality of Service (QoS) and to validate whether the QoS is met. The Qo...

International Journal of Computer Applications, 2012

Cloud computing is one of the newest technology. Today lots of business organizations and educational institutions using Cloud environment, but one of the most important thing is to improve the Quality of Service (QoS) of the Cloud service provider (CSP), there are so many parameters affecting QoS, waiting time is one of them. If waiting time can be optimized QoS may get improved. QoS improvement means how fast it shares the resources for the client machines. There are lots of algorithms available but the waiting time is the important factor in this case. The algorithm is said to be best if it requires very less waiting time to share resources to its client machines. In this paper we propose an algorithm which requires optimum waiting time as well as it does not suffer from starvation in comparison to other algorithms. Here we implement the algorithm in M/M/S queueing model where k number of clients send request to the job scheduler and this scheduler selects resources from the resource pool and using those algorithms job scheduler give permission to the Cloud Users (CU) how they use the resources in less waiting time. In Cloud environment there are numbers of resources present inside CSP in Resource Pool module and there are number of clients send request to the Cloud Service Provider (CSP) and a dedicated Job Scheduler, inside CSP handles those resources in a very efficient manner. In cloud environment cloud user sends the request to cloud service provider which selects the resources for the user using scheduling algorithm. In this paper we describe how the job scheduler handles those resources for the users using our proposed algorithm which is Improved Round Robin scheduling algorithm (IRRA).

Seventh International Conference on Advances in Computing Electronics and Communication ACEC2018

The growing importance of the cloud has attracted many researchers to look for possible improvements and contributions in the field. Their initiations were driven either by personal interests or funded by enterprises. Moreover, Cloud Computing is continuously evolving to meet users' needs and expectations which make it even more attractive. And one of the most interesting research topics is the service brokerage scheduling policy, because of its importance as a routing policy, which could form a bottleneck in the process. This article is a comparative study and analysis on some of the previously done work in the field; it fully explains the role of the service broker scheduling policy in the cloud and summarizes all the work in a single resource for researchers. The advantages and drawbacks are highlighted in terms of factors involved in the decision-making process. By the end of this article, a researcher will be able to formulate own theories about possible areas of improvements, where we have found that having a fully optimized service broker policy is very important in the cloud. Possible research approaches are also suggested in the summary and findings.

2014

We deal with a reservation-based cloud service broker (R-CSB). The main role of the R-CSB is to provide application execution services or Softwareas-a-Service. The R-CSB makes a profit by an arbitrage between cloud service consumers and providers, and service fees from the consumers. In this paper, we first present detail concepts and architecture of the R-CSB. Also, to reduce the VM leasing cost, we discuss two schemes. The VM reservation scheme (C-VMR) makes the R-CSB reduce the VM leasing cost via leasing an appropriate number of reserved VMs. In addition to the C-VMR, we also present the VM allocation scheme (C-VMA) to allocate applications to VMs cost-effectively. Performance evaluation results show that the C-VMR has lower cost than other approaches and the C-VMA shows has higher average VM utilization than the conventional methods in most cases.

Journal of Ambient Intelligence and Humanized Computing, 2020

Cloud computing is the big boom technology in IT industry infrastructure. Many people are moving to cloud computing because of dynamic allocation of resources and reduction in cost. Cloud computing delivers infrastructure, software, and platforms as a service to all consumers. But still, it has numerous issues related to performance unpredictability, resource sharing, security, storage capacity, availability of resources on each requirement, data confidentiality and many more. Load balancing and service brokering are the two main key areas, which ensures reliability, scalability, minimize response time, maximize throughput and cost in the cloud environment. These are the main things we have to focus to improve the performance of the computation. This survey paper presents a comparative and comprehensive study of various load balancing algorithm used in the load balancer and brokering policy used for each service and their scheduling types. The objectives of this survey is to (1) Determine, illustrate, compare and analyze newer methods developed for load balancing and service brokering (the most notable problem) by systematically reviewing papers from the year 2015 to 2018; (2) Classify and analyze techniques based on the key parameters in cloud computing techniques; (3) Ultimately set an updated, thorough and rigorous discussion on load balancing and service broker techniques so as to motivate and direct with valuable references for future research development and direction.

Transactions on Emerging Telecommunications Technologies, 2015

With the increasing digital media content, cloud computing's importance is scaling up very fast. It provides ease of management for the growing media content. Besides this, features like ubiquitous access, service creation, service discovery and resource provisioning play a significant role. Cloud arena is going beyond this now, and the next era is of cloud federation. Services would be brought up together to the user through multiple clouds, known as cloud federation or intercloud computing. Although still in its infancy, intercloud computing is meant to provide more scalable, efficient and better managed services. Cloud broker is an important feature of intercloud computing, which plays its role in terms of resource management, service discovery, service-level agreement negotiation and match making between service provider(s) and customer(s). The already performed studies have trivially addressed brokerage in intercloud environment, and no complete resource management model is presented so far. In this study, we present a detailed service-oriented dynamic resource management model, which covers the issues of resource prediction, customer type-based resource estimation and reservation, advanced reservation, pricing, refunding and acquired quality of service-based refunding. We have implemented our system in Java/NetBeans 8.0 (Oracle Corporation) and evaluated through CloudSim 3.0.3 (The CLOUDS Lab, The University of Melbourne, Australia) toolkit, on 11 parameters. Our methodology was modelled on Google Cluster trace of 12 000 machines. The results and discussion show the validity and performance of our system. This work presents cloud broker resource management model. Implemented on Google Cluster trace of 12 000 machines, the model presents resource allocation, pricing and refunding according to the historical record of cloud customers.

VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE

Cloud computing is a technology in the field of computing which offer services to the customer from anywhere at any time [1]. In the cloud, resources are shared all around the work for quick servicing to the customer. The aggregation of two terms is referred as cloud computing. The term “cloud” is a pool of different resources offers services to the end customers and “computing” is done based on the Service Level Agreement (SLA) to make the resources efficiently to the customers. Load balancing is an important challenge in the environment of the cloud to increase the utilization of resources [3]. Here we proposed an algorithm which is based on load balancing and service broker policy. We user two representative thin the proposed approach local representative and global representative Local user representative is used to predict the parameters of user task and based on priority it allocate the task to the Virtual Machine (VM). Then for scheduling the task and provide the services to ...

Cluster Computing, 2019

Dynamic resource allocation is the key objective of the paper motivated due to a large number of user's service request and increasing network infrastructure complexity. Load balancing and Service Broker Policy are taken as two main key areas for the dynamic provision of resources to the cloud user in order to meet the QoS requirement. While provisioning the resources, the conventional approaches degrade due to QoS performance limits such as time delay, energy, etc. To overcome those problems, we proposed a new approach to provide dynamic provisioning of resources based on load balancing and service brokering. Initially, the Multi-agent Deep Reinforcement Learning-Dynamic Resource Allocation (MADRL-DRA) is used in the Local User Agent (LUA) to predict the environmental activities of user task and allocate the task to the Virtual Machine (VM) based on priority. Next, a Load balancing (LB) is performed in the VM, which increases the throughput and reduces the response time in the resource allocation task. Secondly, the Dynamic Optimal Load-Aware Service Broker (DOLASB) is used in the Global User Agent (GUA) for scheduling the task and provide the services to the users based on the available cloud brokers (CBs). In the global agent, cloud brokers are the mediators between users and providers. The optimization problem in Global Agent (GA) is formulated by the programming of mixed integers, and Bender decomposition algorithm. The result of our proposed method is better as compared with the conventional techniques in terms of Execution Time, Waiting Time, Energy Efficiency, Throughput, Resource Usage, and Makespan.

Cloud is in the air. More and More companies and personals are connecting to cloud with so many variety of offering provided by the companies. The cloud services are based on Internet i.e. TCP/IP. The paper discusses limitations of one of the main existing network management protocol i.e. Simple Network Management Protocol (SNMP) with respect to the current network conditions. The network traffic is growing at a high speed. When we talk about the networked environment of cloud, the monitoring tool should be capable of handling the traffic tribulations efficiently and represent a correct scenario of the network condition. The proposed Model ‘Cloud Network Management Model (CNMM)’ provides a comprehensive solution to manage the growing traffic in cloud and trying to improve communication of manager and agents as in SNMP (the traditional TCP/IP network management protocol). Firstly CNMM concentrates on reduction of packet exchange between manager and agent. Secondly it eliminates the counter problems exist in SNMP by having periodic updates from agent without querying by the manager. For better management we are including managers using virtualized technology. CNMM is a proposed model with efficient communication, secure packet delivery and reduced traffic. Though the proposed model supposed to manage the cloud traffic in a better and efficient way, the model is still a theoretical study, its implementation and results are yet to discover. The model however is the first step towards development of supported algorithms and protocol. Our further study will concentrate on development of supported algorithms.