(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 12, No. 5, 2021 Improved Trust Model to Enhance Availability in Private Cloud Vijay Kumar Damera 1 Research Scholar, Department of CSE JNTU Hyderabad, Telangana, India A Nagesh 2 Professor, Department of CSE MGIT Hyderabad, Telangana, India M Nagaratna 3 Professor, Department of CSE JNTUCEH Hyderabad, Telangana, India Abstract—In the process of cloud service selection, it is difficult for users to choose trusted, available, and reliable cloud services. A trust model is a perfect solution for this service selection problem. In cloud computing, data availability and reliability have always been major concerns. According to research, around $285 million is lost per year due to cloud service failures, with a 99.91 percent availability rate. Replication has long been used to improve the data availability of large-scale cloud storage systems where errors are anticipated. As compared to a small-scale environment, where each data node can have different capabilities and can only accept a limited number of requests, replica place- ment in cloud storage systems becomes more complicated. As a result, deciding where to keep replicas in the system to meet the availability criteria is an issue. To address above issue this paper proposes a trust model which helps in selecting appropriate node for replica placement. This trust model generates comprehensive trust value of the data center node based on dynamic trust value combined with QoS parameters. Simulation experiments show that the model can reflect the dynamic change of data center node subject trust, enhance the predictability of node selection, and effectively decreases the failure rate of node. Keywords—Trust; trust model; cloud; availability; reliability I. I NTRODUCTION Cloud computing provides usable, convenient, and on- demand cloud services in the form of shared computing resource sharing pools. It includes three levels of services: Infrastructure as a service (IaaS), Platform as a service (PaaS), and Software as a service (SaaS), where IaaS provides con- sumers with comprehensive computer infrastructure services, such as hardware server rental, PaaS is to provide software development platform as a service to consumers, SaaS is to provide software to consumers through the network mode. It is a general practice to choose cloud service providers based on a comprehensive evaluation of QoS metrics [1]. The same is considered here in this work to evaluate the trust value of data center nodes. High availability and high-performance are essential features user expects from cloud service providers[3]. Replication plays an important role for any system to improve availability, throughput and response time for user [24]. In fact, replication is an essential corner stone in data storage not only for cloud computing but also for traditional storage systems [12], [13], [14], [15], because it can relatively impact the performance of cloud storage in terms of storage cost, network usage, response time, etc. [22], [23], [24], [25]. Therefore, maintaining static number of replicas in cloud storage for every data file would be inefficient for storage cost and data availability [16], [17], [18]. As a consequence, the determination of the optimum number of replicas and the suitable nodes for replicas has become a key issue in the cloud computing [19], [20], [21]. To address the above issue this paper proposes a node selection model based on the dynamic trust. The trust value is calculated by direct and recommended trust. In order to reflect trust value more comprehensively the concept of Dynamic Trust Value (DTV) is introduced in this model. Further the con- cept of information entropy is introduced to solve the problem of weighting of trusted parameters, so that the comprehensive trust value and QoS value are weighted to obtain the optimal node selection for replica placement. II. RELATED WORKS For the study of cloud service selection, many scholars at home and abroad have done a lot of work. For example works such as multi-objective genetic algorithm, particle swarm op- timization PSO [1], artificial neural network algorithm [2].The application of these methods are generally aimed at a relatively static scenarios. The generation and disappearance of network services in a cloud computing environment are often dynamic, so it is necessary to solve the authenticity judgment of services in a cloud computing environment. Further it is important to solve the problem of degree of understanding of service quality when selecting a service algorithm [3], the trust of cloud services and other problems. In response to the above problems, at the same time, in order to ensure the success of the service selection algorithm, the research based on the trust degree of the service subject is particularly important. Ma You et al. [4] proposed a new ESOW algorithm for QoS measurement. The ESOW algorithm is based on the user’s subjective trust. The two parts of preference weight and objective weight are synthesized. The calculation of user’s subjective weight is based on the adaptive SWDM algorithm, and the objective weight is calculated according to the OWDM algorithm. Sarbjeet [5] proposed a method based on the past experience and third-party service recommendation trust evaluation mechanism. DASA et al. [6] proposed a dynamic trust calculation model that can effectively evaluate the behavior of malicious agent strategies. It mainly analyzes and evaluates all relevant elements to make correct decision. Zhouao et al. [7] proposed a dynamic virtual resource lease method from the perspective of service provider’s benefit maximization, from the perspective of price allocation and request urgency. Cao Jie et al. [8] based on the interpersonal relationship in sociology relationship www.ijacsa.thesai.org 856 | Page