Search

Cloud environment provides a shared pool of resources to various users all around the world. The cloud model has the physical machines and the virtual machines for processing the tasks from the users in a parallel manner. In certain situations, the user's demand may be high, which leads to the overloading of the processing units, and this situation affects the performance of the cloud setup. Several works have introduced the load balancing strategy to balance the load of the cloud environment, but they lack in the ability to reduce the number of task migrations. This paper introduces the load balancing strategy by defining the optimization algorithm and the multi-objective model. This research introduces the Crow search with the integrated Fractional Dragonfly Algorithm (C-FDLA), for load balancing through the hybridization of the Crow Search Algorithm (CSA), Dragonfly Algorithm (DA) and the fractional calculus. Also, the paper uses the multi-objective model based on selection probabilities, the frequency scaling based capacity of the machine and the data length of the task. The performance of the proposed C-FDLA is analyzed under different cloud scenarios, and from the results, it is evident that the proposed work has achieved significant performance with the minimum load of 0.0913 and number of tasks reallocated as 11. [ABSTRACT FROM AUTHOR]

Cloud computing makes scientists to run complex scientific applications. The research community is able to access on-demand compute resources within a short span of time instead of experiencing peak demand bottlenecks. As the demand for cloud resources is dynamic and volatile in nature, this in turn affects the availability of resources during scheduling. In order to allocate sufficient resources for scientific applications with different execution requirements, it is necessary to predict the appropriate set of resources. To attain this objective, a resource prediction–based scheduling technique has been introduced which automates the resource allocation for scientific application in virtualized cloud environment. First, the proposed prediction model is trained on the dataset generated by concurrently deploying tasks of a scientific application on cloud. Then, the resources are scheduled based on the output of proposed prediction technique. The main objective of resource prediction–based scheduling technique is to efficiently handle the resources for virtual machines in order to reduce the execution time, error rate, and improve the accuracy. [ABSTRACT FROM AUTHOR]

To ensure the cloud environment outsourcing data from tampering,and improve the efficiency of data integrity audit, this paper proposed a data audit method based on relative index-Merkle hash lree(RIMHT) . Firstly,it modified each node of the classic MHT to store two information, that was data block hash value and the relative index value of node. To reduce the computation cost of data block search,it integrated the relative index of MHT with the node. Then,by adding the last modification time of the data,it ensured the freshness of the data. The experimental results verify the effectiveness of the proposed method. Compared with other similar methods, the proposed method has some advantages in terms of computational cost, communication cost and storage cost. And it is possible to detect the improper operation of the server with higher probability. [ABSTRACT FROM AUTHOR]

With the increasing availability of large amount of information and the benefits related to data processing, big data have gained large significance in recent years. With scalable nature of data, big data applications are processed using MapReduce programming model. However, the application of rule-based models in datasets is not straightforward and big data are not classified in an efficient manner. To overcome the above-mentioned problems, parallel linguistic fuzzy rule with canopy MapReduce (LFR-CM) framework is introduced. LFR-CM framework classifies big data using canopy MapReduce function for information sharing in cloud with higher classification accuracy and lesser time consumption. It comprises three steps for efficient classification in cloud environment. Initially, it constructs the fuzzy knowledge base (KB) from the big data training set where linguistic fuzzy rules are constructed. The second step in LFR-CM framework has three operations. The first operation is map function used in parallel manner through every cloud user without transmitting any data to other cloud user nodes. The second operation is processing of data through the map function across all additional cloud user nodes. The third operation is reduce function deployed by each cloud user through the partitioned information. Finally, by this way, the data classification is performed with higher classification accuracy and lesser time consumption. LFR-CM framework is implemented and evaluated on Amazon EC2 cloud big data datasets and compared with the other classification system that utilizes MapReduce in terms of the runtime, classification time, classification accuracy and input/output cost. Based on the results observed from the study, LFR-CM framework is more efficient than the existing methods. [ABSTRACT FROM AUTHOR]

In order to reduce the cost of scientific workflow execution in cloud environment, we propose an approach to optimizing the execution plans o£ scientific workflows in cloud environment. It introduces the monkey group algorithm and relies on the intra-level and inter-level optimization of the current execution plan. Under the premise of ensuring the global deadline of the workflow, through the logical aggregation of the same-level tasks and the inter-level adjustment of the tasks, the difference in the number of tasks at each level is minimized to avoid waste of resources and reduce the waiting time of tasks. Experiments show that compared with the BTS algorithm and the SPSWVC algorithm, the proposed method can reduce resource consumption and the total delay time of tasks. [ABSTRACT FROM AUTHOR]

Object tracking is a fundamental problem in Supply Chain Management (SCM). Recent innovations eliminate the difficulties in traditional approach such as manual counting, locating the object, and data management. Radio Frequency Identification (RFID) implementation in SCM improves the visibility of real-time object movement and provide solutions for anti-counterfeiting. RFID is a major prerequisite for the IoT, which connects physical objects to the Internet. Various research works have been carried out to perform object tracking using GPS, video cameras, and wifi technology. These methods just hope to see the actual object, but not the characteristic changes of the object due to environmental changes. After reviewing the implementation of latest technologies in object tracking system, it is expected that the security and privacy risks in large-scale IoT systems are to be eliminated and an efficient IoT services are provided to SCM. In this work, an architecture is proposed for a fine-grained IoT-enabled online object tracking system. Cloud storage used in this architecture enhances the scalability and data management. We propose a novel secure and efficient end to end authentication protocol that is based on a symmetric key cryptosystem and one-way hash function. A new scheme is also proposed to address object tracking communication flow which uses the secret key established in the authentication process. A formal security analysis method, GNY logic is used and proved that the proposed protocol achieves an end to end authentication. Tag/Reader impersonation attack and replay attack are prevented in the proposed scheme. It also preserves forward and backward secrecy. Performance analysis shows that the proposed protocol is not storage and computationally intensive. [ABSTRACT FROM AUTHOR]

With the rapid development of cloud computing technology, more and more users choose to outsource image data to clouds. To protect users' privacy and guarantee data's confidentiality, images need to be encrypted before being outsourced to CSP, but this brings new difficulties to some basic yet important data services, such as content-based image retrieval (CBIR). In this paper, a privacy-preserving image retrieval method based on an improved BoVW model is proposed. An improved BoVW method based on Hamming embedding can provide binary signatures that refine the matching based on visual words; therefore, retrieval precision is improved significantly; orthogonal transformation is utilized to implement privacy-preserving image retrieval, where image features are divided into two different fields with orthogonal decomposition, for which encryption and distance comparison are executed separately, and two kinds of operation results are fused in the final vector with orthogonal composition. As a result, cloud server can extract components from encrypted features directly and compare distance with those of query image, without violating the privacy of images and features. Any algorithm can be used to encrypt features, which enhance the practicability of the proposed method. The security analysis and experimental results prove its security and retrieval performance. [ABSTRACT FROM AUTHOR]

Broker policy is a critical decision factor for the cloud computing environment. During this process, the broker allocates the cloudlets to the different datacenters. In this paper, we have considered four strategies for the allocation of cloudlets to the datacenter. The broker allocation policies under consideration are: round robin, Bee colony optimization, genetic learning and particle swarm algorithm. Finally, the Enhanced genetic learning based Particle swarm optimization technique is designed and tested for performance. The Enhanced genetic learning based particle swarm optimization is found to be fastest in getting the job done whereas the round robin algorithm is slowest among the four algorithms. The Enhanced genetic learning based particle swarm optimization technique shows an improvement of 10% over the other soft computing techniques. [ABSTRACT FROM AUTHOR]

Massive spatiotemporal data scheduling in a cloud environment play a significant role in real-time visualization. Existing methods focus on preloading, prefetching, multithread processing and multilevel cache collaboration, which waste hardware resources and cannot fully meet the different scheduling requirements of diversified tasks. This paper proposes an optimized spatiotemporal data scheduling method based on maximum flow for multilevel visualization tasks. First, the spatiotemporal data scheduling framework is designed based on the analysis of three levels of visualization tasks. Second, the maximum flow model is introduced to construct the spatiotemporal data scheduling topological network, and the calculation algorithm of the maximum data flow is presented in detail. Third, according to the change in the data access hotspot, the adaptive caching algorithm and maximum flow model parameter switching strategy are devised to achieve task-driven spatiotemporal data optimization scheduling. Compared with two typical methods of first come first serve (FCFS) and priority scheduling algorithm (PSA) by simulating visualization tasks at three levels, the proposed maximum flow scheduling (MFS) method has been proven to be more flexible and efficient in adjusting each spatiotemporal data flow type as needed, and the method realizes spatiotemporal data flow global optimization under limited hardware resources in the cloud environment.