CloudGPS: a scalable and ISP-friendly server selection scheme in cloud computing environments

Cloud computing is one of the most emerging technologies which has created a revolution in the High performance Computing (HPC) domain. The term Quality of Service (QoS) plays a vital role in the formation of more flexible integration of various technologies. The Waiting Time (WT), Turnaround Time (TAT), Context Switching (CS) and Makespan (MS) are the primary parameter that has great impact on the scheduling of cloudlets. The Proposed algorithm has improved the resource utilization system of the existing Round Robin Algorithm (RRA) and Improved Round Robin Cloudlet Scheduling Algorithm (IRRCSA) by introducing the concept of dynamically calculated Time Quantum (TQ) for each virtual machine (VM) according to the allocated cloudlets. This new approach in cloudlet scheduling drastically reduced average WT, average TAT and Number of CS of the VMs, which further enhanced the capability of cloud service providers (CSPs) to provide better QoS.

Cloud environment uses virtualization technology to increase the resource utilization and scalability. Due to the concurrent running of co-allocated tasks with virtual machines on top a physical machine, performance of some tasks suffers significantly because of interference. To improve the quality of service and reduce the service level agreement violation between user and cloud service provider, we presented an interference aware scheduling approach. Interference aware scheduling approach predicts the effect of interference for execution of a task with respect to the resource usage by co-scheduled tasks in a virtualized environment. This prediction model is being used to schedule tasks to achieve better quality of service in term of task guarantee ratio and priority guarantee ratio. We implemented and validated our approach and the results show that our approach performs significantly better than other approaches.

Cloud Computing is known as a provider of dynamic services. It utilizes a very large, scalable and virtualized resource over the Internet. So many industries have joined this bandwagon nowadays. One of the major research issues is to maintain good Quality of Service (QoS) of a Cloud Service Provider (CSP). The QoS encompasses different parameters, like, smart job allocation strategy, efficient load balancing, response time optimization, reduction in wastage of bandwidth, accountability of the overall system, etc. The efficient allocation strategy of the independent computational jobs among different Virtual Machines (VM) in a Datacenter (DC) is a distinguishable challenge in the Cloud Computing domain and finding out an optimal job allocation strategy guided by a good scheduling heuristic for such an environment is an NP-complete problem. So different heuristic approaches may be used for better result. The related works with other NP- complete problems have shown that solutions guided by heuristic approaches can often be improved by applying local scheduling procedure for allocating independent jobs in the virtual machines (VM) inside a Datacenter (DC), which, when combined with fast construction heuristics, can find out the shorter schedules on benchmark problems than the other solution methodologies found in different literatures, and in significant less time. This paper highlights a smart job allocation strategy for a CSP by applying Round-Robin (RR) scheduling policy.

This paper studies economic utilities and quality of service (QoS) in a two-sided non-neutral market where Internet service providers (ISPs) charge content providers (CPs) for the content delivery. We propose new models that involve a CP, an ISP, end users and advertisers. The CP may have either a subscription revenue model (charging end users) or an advertisement revenue model (charging advertisers). We formulate the interactions between the ISP and the CP as a noncooperative game for the former and an optimization problem for the latter. Our analysis shows that the revenue model of the CP plays a significant role in a non-neutral Internet. With the subscription model, both the ISP and the CP receive better (or worse) utilities as well as QoS in the presence of the side payment at the same time. With the advertisement model, the side payment impedes the CP from investing on its contents.

Cloud computing has emerged as a new computing paradigm, with provisioning model generally consisting of cloud service providers (CSPs), network service providers (NSPs), and end users. The associated economics has opened up a new research area; and with the expansion of the cloud computing market, the relationship between CSPs and NSPs, is changing profoundly. In addition to providing the default network services, traditional NSPs, in attempt to compete with CSPs, have started offering cloud services to end users. Though much progress has been made toward addressing competitions among CSPs themselves or among NSPs themselves, few studies have focused on the competition between CSPs and NSPs. In this paper, we investigate the problem of insufficient studies on the competition between CSPs and NSPs by presenting a new economic model to characterize the competition between CSPs and NSPs, and by conducting thorough theoretical analysis as well as numeric experiments to validate the proposed model. We believe, based on results, that the proposed economic model is general and feasible, and thus is applicable to modeling the competition among service providers in cloud computing market.

<span>In this paper, a modification model for single-link reverse charging of internet is formed on a multi-link wireless network. The pricing scheme also takes into account the base costs and quality of services provided by the service provider. Bit error rate (BER) was utilized as one of the well-known quality of service (QoS) attribute that can guarantee best performance for internet service provider (ISP) and users. The base price is determined as a decision variable to help ISP to maximize profit. This optimization model can be solved using the LINGO 13.0 program to gain optimal values. The computational results show that by setting costs as constants and service quality as variables, optimal results are obtained for ISPs. This can make ISP considerations in determining the base price that can benefit the ISP and according to the services provided</span>.

An internet service provider (ISP) tries to maximize profit by choosing an appropriate price for an offered service. In this paper, a system of two identical ISPs is considered. When ISPs independently choose a price to charge to maximize profit and each ISP repeatedly tries to improve profit by changing the price till no further improvements are possible, they may reach an equilibrium called the Nash equilibrium. Another strategy is that one ISP announces an appropriate price in advance and the other ISP chooses the best response strategy. This leads to Stackelberg competition. Both these strategies are compared in the paper. In this paper, it is assumed that few clients have access to multiple ISPs by using multi-SIM handheld devices such as smartphones and tablets. The clients who have access to multiple-ISPs choose an appropriate ISP for service based on the price of the service. The clients who have access to only one ISP, have no choice but to take service from the ISP. Simulations show that the ISP who announces an appropriate price in advance is likely to do better as compared to the ISP who decides the price later after observing the price of the announcer. Simulations also show that announcing an appropriate price in advance is better instead of independently deciding the price which may lead to a Nash equilibrium in terms of profit of the ISPs and quality of service provided to the clients.

Cloud federation is introduced to eliminate the resource limitation problem of individual Cloud Service Provider (CSP). In a federation, one CSP can outsource their overhead requests by hiring unused resources from other CSPs in the federation and CSPs cash greater revenue. In this paper, we propose a system that maximizes this revenue while putting some factor constraints in satisfactory standard. Factors include response time of instances that is analogous to Quality of Service (QoS), and profit that maintains a certain reputation. Response time is reduced by considering geographical location of the user and the data center of desired resources. In this system, CSPs choose suitable resources from resource pool of cloud federation that maximizes the profit while preserving Quality of Service (QoS) high and minimizing the rejection rate of user requests. We map factor constraints to MMKP (Multi-choice Multidimensional Knapsack Problem) algorithm and define objective function for revenue maximization. We calculate response time by Cloud Analyst to measure the QoS. Experimental results show that the proposed system can effectively increases QoS level by reducing response time and rejection requests in a cloud federation that eventually increases the revenue of the CSP.

This paper analyses wireline broadband Quality of Service (QoS) metrics of India’s small and medium Internet Service Providers (ISPs). Key Performance Indicators (KPIs) used in this analysis are – Fault repair (>90% in 1 working day and >=99% in 3 working days), Response time to customer for voice-to-voice operator assistance (in 60 sec. >60% and in 90 sec. >90%), Broadband connection speed from ISP to node (Download speed) and Service availability/uptime. Benchmarks are arrived at, using the Slack Based Measure (SBM) in Data Envelopment Analysis (DEA). Twenty Decision Making Units (DMUs – ISPs) were used in the analysis with eight of them needing to improve their QoS on some of the mentioned parameters. Relative benchmark providers for all providers needing improvement with their weightage are found and optimal targets by each QOS metric is mathematically arrived at.

Multi objective trust aware task scheduling algorithm in cloud computing using whale optimization

Long Term Evolution (LTE) was developed by 3GPP to cope with the increasing demand for better Quality of service (QoS) and the emergence of bandwidth-consuming multimedia applications. Today's data transmission networks face extreme challenges in providing high data rate and low latency. Scheduling paradigms such as Round Robin, Best Channel Quality Condition and Proportional Fair are commonly adopted in current LTE downlink scheduling algorithms, but they are far from optimal for satisfying latency requirements. In this paper, we first survey the state of the art downlink scheduling algorithms in LTE and identify their main challenges. We then formulate the LTE downlink scheduling problem as an optimization problem in order to meet the flow deadlines, then incorporate the formulation within the surveyed scheduling algorithms, to produce better performance. We consider strict deadlines for different types of packets with the goal of maximizing resource distribution. Additionally, in our formulation the buffer state for each user is taken into consideration in order to minimize the packet loss. We evaluate the proposed formulation using LTE-Sim and study its positive impact on the existing LTE downlink scheduling algorithms; the performance in terms of QoS, packet loss and fairness is improved throughout all evaluations.

Cloud computing provides distributed computing resources such as servers, storage and applications to the end users through data centers. The data centers are geographically located at different locations. The client applications or requests being serviced by cloud service providers on “pay per use”. So, different pricing models are adapted to compute the cost and revenue of the data centers. The cost of VM is computed depending on its placement in the data centers through broker policies. So, the broker policies have a significant role in evaluating the cost of the VM which directly impacts on revenue of the service provider. In the computing competition, the VM cost should be minimized by which service demand will be maximized. Moreover, the response time and processing time of the data centers need to be minimized to posses commendatory Quality of Service. In this work, we propose a new service broker policy to minimize the total cost. The total cost considers the VM cost and the data transfer cost. The proposed mechanism also reduces the response time and data processing time of the data centers. The proposed policy is simulated in Cloud Analyst. We examine the performance of the proposed mechanism with ten different scenarios. Finally, we compare performance results with respect to VM cost, data transfer cost, total cost, processing time and response time of data centers with the existing policies and observe better than these.

The subject of research in the article is the processes of fast rerouting with the protection of the Quality of Service level in infocommunication networks. The aim of the work is the development of a mathematical model of Fast ReRouting with the protection of the Quality of Service level by the bandwidth and probability of packet loss for data traffic. The following tasks are solved in the article: development and research of a fast rerouting flow-based model with the protection of the Quality of Service level of data traffic in the infocommunication network. The following methods are used: the graph theory, the teletraffic theory, the queuing theory, and mathematical programming methods. The following results were obtained: the fast rerouting flow-based model was developed and investigated, which, due to the introduced protection conditions on indicators of bandwidth and packet loss probability, allows providing the Quality of Service along both the primary and backup multipath. Conclusions: Within the framework of the proposed flow-based model, the fast rerouting technological task was formulated as an optimization problem with the constraints of the conditions of implementation of the multipath routing strategy, conditions of flow conservation, and conditions of protection of the link, node, and level of Quality of Service in terms of bandwidth and packet loss probability. The application of this solution contributes to the optimal use of the available network resource while providing the specified level of Quality of Service in terms of bandwidth and probability of packet loss along both the primary and backup routes in the case of a failure of the infocommunication network elements. The proposed flow-based model can be used as the basis of the algorithmic software of existing routers and/or controllers of Software-Defined Networks, which are responsible for the calculation of the primary and backup paths in the fast rerouting of data traffic sensitive to such Quality of Service indicators as bandwidth and packet loss probability.

Der Ausdruck Quality of Service (QoS) beschreibt die Güte eines erbrachten Dienstes. QoS beschreibt Eigenschaften wie Antwortzeit, Verfügbarkeit, den Grad der Nachrichten-Verschlüsselung oder den Durchsatz. QoS ist sowohl für Multi-Media Anwendungen (Audio- und Video-Übertragung) als auch für Geschäftsanwendungen wichtig. Die vorgelegte Arbeit konzentriert sich dabei auf das Feld der Geschäftsanwendungen. Solche Anwendungen arbeiten mit Transaktionen wie etwa dem Bestellen eines Produkts oder der Überweisung von Geld zwischen Konten. QoS Eigenschaften solcher Anwendungen sind beispielsweise die Anzahl an Transaktionen während eines Zeitintervalls, die maximale Anzahl gleichzeitig mit dem System arbeitender Nutzer, oder die zu erwartende Verfügbarkeit. Durch Middleware kann die Realisierung von Verteilung vor dem Programmierer verborgen werden. In einer idealen Welt würde Middleware dasselbe für QoS leisten. Das heißt, der Entwickler spezifiziert nur die gewünschte Dienstgüte und kümmert sich nicht darum, wie sie realisiert wird. Das ist so aber nicht möglich, denn die zu erbringende Dienstgüte hat massive Auswirkungen auf das Design einer Applikation. Daher muss QoS schon in der Design-Phase angegangen werden, was mit einer rein Middleware-gestützten Herangehensweise nicht möglich ist. Die vorgelegte Arbeit zeigt, wie dieses Problem durch einen modellgetriebenen Ansatz behoben werden kann. Die Entwicklung beginnt dann mit einem Plattform-unabhängigen Modell (PIM), welches das Verhalten und die QoS Eigenschaften der Applikation beschreibt. Dieses Modell wird automatisch durch eine Modell-Transformation in ein Plattform-spezifisches Modell (PSM) umgewandelt. Das PSM beschreibt das Design einer Implementierung für eine spezifische Plattform und berücksichtigt dabei die im PIM beschriebenen QoS-Eigenschaften. Um dieses Szenario in der Praxis anwenden zu können, müssen zwei Probleme gelöst werden: das Modellieren von QoS Eigenschaften und die Modell-Transformation. Gegenwärtig erfordert das Erstellen einer Modell-Transformation detailliertes Wissen über die Modellierungssprache und ihre Interna. Um das zu vereinfachen, wurde im Rahmen dieser Arbeit die visuelle Regelbasierte Transformationssprache Kafka entwickelt. Kafka und die zugehörigen Werkzeuge bauen auf Graphtransformations-Theorie auf. Kafka vereinfacht das Erstellen von Transformationen weil es auf der Notation des PIM und PSM aufbaut. Daher muss der Entwickler nichts von den Interna (etwa dem Meta-Modell) verstehen. Um PIMs von QoS-fähigen Applikationen zu erstellen, wurde die Modellierungssprache PIQML entwickelt, welche auf UML 2.0 Komponenten, Hierarchischen Nachrichten Sequenz Diagrammen (HMSCs) und einer neuen Meta-Modell Erweiterung für QoS Verträge basiert. Die vorgelegte Arbeit zeigt, wie PIQML Modelle auf verschiedene Zielplattformen (Programmiersprachen und Middleware Produkte) abgebildet werden können. Basierend auf PIQML und Kafka wurde das Werkzeug Kase entwickelt, welches das Editieren von PIQML Modellen (PIMs), UML Modellen (PSMs) und Kafka Transformationen integriert. Das Ergebnis ist eine integrierte Werkzeug-Kette für das modellgetriebene Entwickeln QoS-fähiger verteilter Applikationen.

Technological Innovation and Quality Improvement in U.S. Broadband