Abstract Cloud computing will be basic utility computing an important future. Governments and businesses recognize that foreigners are significantly increasing the cloud with minimal costs and maximum flexibility in infrastructure services or existing applications. But the clouds the privacy of users and management of digital assets, to ensure in the cloud has become a serious challenge to customers. Cloud security must always take into... Cloud computing will be basic utility computing an important future. Governments and businesses recognize that foreigners are significantly increasing the cloud with minimal costs and maximum flexibility in infrastructure services or existing applications. But the clouds the privacy of users and management of digital assets, to ensure in the cloud has become a serious challenge to customers. Cloud security must always take into account the performance. The large complex is a safe method of high service overall at this problem, which in this study a security architecture in two levels before. This architecture with multiple levels of security mode will reduce the best for your health and the cost of the security guard and the security of the hypervisor layer to ensure that you avoid false alarms. Read More Read Less

Abstract Influence maximization aims to seek k nodes from a social network such that the expected number of activated nodes by these k nodes is maximized. However, influence maximization is different from profit maximization for a real marketing campaign. Moreover, we observe that when promotion time increases, the number of activated nodes tends to be stable eventually. In this paper, we first use real... Influence maximization aims to seek k nodes from a social network such that the expected number of activated nodes by these k nodes is maximized. However, influence maximization is different from profit maximization for a real marketing campaign. Moreover, we observe that when promotion time increases, the number of activated nodes tends to be stable eventually. In this paper, we first use real action log to propose a novel influence power allocation model with time span called IPA-T, and then present time optimal profit maximization problem called TOPM based on IPA-T. To address this problem, we propose an effective approximation algorithm called Profit-Max. Experimental results on real datasets verify the effectiveness and efficiency of Profit-Max. Read More Read Less

Abstract Infrastructure-as-a-Service cloud reduces the investment cost of using computing resources when compared with the complicated and expensive traditional business applications. Software-as-a-Service providers, who rent the infrastructure resources to run their applications and serve their customers, are influenced by a variety of characteristics and capabilities of the available resources. As a result, the decision made by business service owners to lease and use... Infrastructure-as-a-Service cloud reduces the investment cost of using computing resources when compared with the complicated and expensive traditional business applications. Software-as-a-Service providers, who rent the infrastructure resources to run their applications and serve their customers, are influenced by a variety of characteristics and capabilities of the available resources. As a result, the decision made by business service owners to lease and use certain cloud resources is an important one in order to achieve the planned outcome i.e. service value. In this paper, we use a value based approach to develop a new model for measuring the benefits of providing computing services in cloud. Based on our approach, customer satisfaction is modeled not only based on the response time offered by the application provider, but also based on the allotted budget. The profit of the service owner is determined according to the revenue generated by serving the customer. Using our model, the application owner is able to direct and control the decision of renting cloud resources as per the current strategy. This strategy is led by a set of defined key performance indicators. In addition, we present a scheduling algorithm that can bid for different types of virtual machines to achieve the target value. We conduct extensive simulations using different types of Amazon EC2 instances with dynamic prices. The results show how the model presents an effective tool for the application owners to control, quantify and reach the needed value of their services per customer request. Read More Read Less