Informatica

The brokering of the best Cloud proposals that optimizes the application requirements allows to exploit the flexibility of the Cloud programming paradigm by a dynamically selection of the best SLA, which is available into the market. We present in this paper ascalable multi-users version of a Broker As A Service solution that uses the available resources of a distributed environment, and addresses related issues. The brokering problem is divided into simpler tasks, which are distributed among independent agents, whose population dynamically scales together the computing infrastructure, to support unforeseeable workloads produced by the interactions with large groups of users. The brokering model and its implementation, which adopts Cloud technologies itself, are described. Performance results and effectiveness of the first prototype implementation are discussed.

In several areas like Global Optimization using branch-and-bound methods, the unit n-simplex is refined by bisecting the longest edge such that a binary search tree appears. This process generates simplices belonging to different shape classes. Having less simplex shapes facilitates the prediction of the further workload from a node in the binary tree, because the same shape leads to the same sub-tree. Irregular sub-simplices generated in the refinement process may have more than one longest edge when $\mathit{n}\ge 3$ . The question is how to choose the longest edge to be bisected such that the number of shape classes is as small as possible. We develop a Branch-and-Bound (B&B) algorithm to find the minimum number of classes in the refinement process. The developed B&B algorithm provides a minimum number of eight classes for a regular 3-simplex. Due to the high computational cost of solving this combinatorial problem, future research focuses on using high performance computing to derive the minimum number of shapes in higher dimensions.

Classical evolutionary multi-objective optimization algorithms aim at finding an approximation of the entire set of Pareto optimal solutions. By considering the preferences of a decision maker within evolutionary multi-objective optimization algorithms, it is possible to focus the search only on those parts of the Pareto front that satisfy his/her preferences. In this paper, an extended preference-based evolutionary algorithm has been proposed for solving multi-objective optimization problems. Here, concepts from an interactive synchronous NIMBUS method are borrowed and combined with the R-NSGA-II algorithm. The proposed synchronous R-NSGA-II algorithm uses preference information provided by the decision maker to find only desirable solutions satisfying his/her preferences on the Pareto front. Several scalarizing functions are used simultaneously so the several sets of solutions are obtained from the same preference information. In this paper, the experimental-comparative investigation of the proposed synchronous R-NSGA-II and original R-NSGA-II has been carried out. The results obtained are promising.

A nonlinear substitution operation of bytes is the main strength factor of the Advanced Encryption Standard (AES) and other modern cipher systems. In this paper we have presented a new simple algorithm to generate key-dependent S-boxes and inverse S-boxes for block cipher systems. The quality of this algorithm was tested by using NIST tests, and changing only one bit of the secret key to generate new key-dependent S-boxes. The fact that the S-boxes are key-dependent and unknown is the main strength of the algorithm, since the linear and differential cryptanalysis require known S-boxes. In the second section of the paper, we analyze S-boxes. In the third section we describe the key-dependent S-boxes and inverse S-boxes generation algorithm. Afterwards, we experimentally investigate the quality of the generated key-dependent S-boxes. Comparison results suggest that the key-dependent S-boxes have good performance and can be applied to AES.

Poisson conditional autoregressive model of spatio-temporal data is proposed. Markov property and probabilistic characteristics of this model are presented. Algorithms for maximum likelihood estimation of the model parameters are constructed. Optimal forecasting statistic minimizing probability of forecast error is given. The “plug-in” principle based on ML-estimators is used for forecasting in the case of unknown parameters. The results of computer experiments on simulated and real medical data are presented.

Mobile cloud computing has emerged aiming at assisting mobile devices in processing computationally or data intensive tasks using cloud resources. This paper presents an optimization approach for utilizing cloud services for mobile client in mobile cloud, which considers the benefit of both mobile device users and cloud datacenters. The mobile cloud service provisioning optimization is conducted in parallel under the deadline, budget and energy expenditure constraint. Mobile cloud provider runs multiple VMs to execute the jobs for mobile device users, the cloud providers want to maximize the revenue and minimize theelectrical cost. The mobile device user gives the suitable payment to the cloud datacenter provider for available cloud resources for optimize the benefit. The paper proposes a distributed optimization algorithm for utilizing cloud services for mobile devices. The experiment is to test convergence of the proposed algorithm and also compare it with other related work. The experiments study the impacts of job arrival rate, deadline and mobility speeds on energy consumption ratio, execution success ratio, resource allocation efficiency and cost. The experiment shows that the proposed algorithm outperforms other related work in terms of some performance metrics such as allocation efficiency.

P2P systems enable decentralised applications for supporting collaborating groups and communities, where the collaboration may involve both sharing of data and sharing of group processes among group members. In such applications, monitoring and awareness are critical functionalities required for an effective collaboration. However, to date there has been little research into providing generic, application-independent awareness in P2P groupware systems. We present a distributed event-based awareness approach for such systems that provides different forms of awareness through a set of interoperating, low-level awareness services. The user and technical requirements for the approach are motivated with reference to Project-Based Learning in a P2P environment. We describe the implementation of a superpeer P2P network on a Cloud platform and the provision of reliable awareness services (AaaS – Awareness as a Service) from the Cloud. We report on the outcomes of an empirical evaluation of the performance and scalability of the approach.

Traditional researches on scheduling of cloud workflow applications were mainly focused on time and cost. However, security and reliability have become the key factors of cloud workflow scheduling. Taking time, cost, security and reliability into account, we present a trust-based scheduling strategy. We firstly formulate the cloud workflow scheduling and then propose the corresponding algorithm, in which the trustful computation service and storage service are selected according to the set-based particle swarm optimization (S-PSO) method and set covering problem (SCP) tree search heuristic method, respectively. Finally, experimental results show that, compared with traditional methods, the proposed algorithm has better performance.