International Journal of Web and Grid Services (8 papers in press)
A Service Composition Approach Based on Overall QoS and Modified Graphplan
by Ming Zhu, Guodong Fan, Jing Li, Fengying Wang
Abstract: Increasing emphasis on users preferences and the growth of services on the web make service composition a time consuming and complicated work. In this paper, an approach for web service composition that combines Overall QoS and modified Graphplan is proposed. Fuzzy logic is applied to handle uncertainty and support decision making. Specifically, values of Overall QoS of services are generated by using fuzzy analytical hierarchy process, entropy and users preferences. The Graphplan is modified by pruning services according to the values of Overall QoS of services in forward and backward expansions, while producing solutions of compositions. Furthermore, case studies and experiments are performed and show that our approach has better solutions compared with original Graphplan and some other approaches.
Keywords: web service composition; QoS; fuzzy analytical hierarchy process; entropy.
Natural Parallelization Paradigm on Accelerator Physics Example
by Nataliia Kulabukhova
Abstract: In this paper the problems of using the existing methods and algorithms for applied science with the help of high performance techniques is described. The idea is to provide the scientists with an easy to use tools for constructing the implementation of their research working on heterogeneous systems. Without a doubt the problem-solving environment for these purposes must give the exact solution in a reasonable time. The concept which is described in the article was devised specifically for such kind of tasks. The application of it in terms of high energy physics is given. To illustrate the work of the concept the analysis of the distribution of the particles in the beam under the influence of the space charge is done.
Keywords: Hybrid Systems; General Purpose computations on GPU; Parallelization; Problem-Solving Environment.
WMN-PSOSA: An Intelligent Hybrid Simulation System for WMNs and Its Performance Evaluations
by Shinji Sakamoto, Leonard Barolli, Shusuke Okamoto
Abstract: Networks of today are going through a rapid evolution. Recently, many new networks, especially wireless networks, are appearing. The Wireless Mesh Networks (WMNs) are wireless networks having mesh topology. They have many advantages, such as high robustness and easiness for maintenance. However, WMNs have some problems that need to be solved. One important problem for WMNs is the node placement problem, which is an NP-hard problem. In this work, we propose and implement an intelligent hybrid simulation system based on Particle Swarm Optimization (PSO) and Simulated Annealing (SA) for node placement problem in WMNs, called WMN-PSOSA. We evaluate the performance of WMN-PSOSA system considering different distributions of mesh clients such as Weibull, Chi-square, and Uniform distributions. The simulation results show that the WMN-PSOSA performs better for Weibull distribution compared with the case of Chi-square and Uniform distributions.
Keywords: Wireless Mesh Networks; Node Placement Problem; Particle Swarm Optimization; Simulated Annealing; Intelligent Hybrid System; Weibull Distribution; Chi-square Distribution; Uniform Distribution.
A Dependability and Cost Optimization Method for Private Cloud Infrastructures
by Danilo Oliveira, Jamilson Dantas, Rubens Matos, Nelson Rosa, Paulo Maciel, André Brinkmann
Abstract: Creating a cost-effective and highly available private cloud infrastructure from scratch is challenging. In order to improve availability, system administrators commonly employ redundant hardware, what incurs increased acquisition cost. One question that arises is: among all possible ways to arrange the servers, and considering a set of requirements (e.g., the minimum number of available workers, minimum availability), which configurations are able to sustain a minimal availability level (steady state and capacity oriented)? In this work, we propose an optimization model for private clouds planning supported by analytical modeling for computing the cost of solutions. By combining the optimization model with the bisection method, we can minimize the acquisition cost while maintaining the high availability of the cloud. The proposed method can also be applied to other parallel/distributed systems with the same properties as the private clouds used in our study.
Keywords: Cloud computing; steady-state availability; capacity-oriented
availability; combinatorial optimization.
Staccato: shared-memory work-stealing task scheduler with cache-aware memory management
by Ruslan Kuchumov, Adnrey Sokolov, Korkhov Vladimir
Abstract: Work-stealing is one of the popular ways to schedule near-optimal task distribution across multiple CPU cores with low overheads on time, memory and inter-thread synchronizations. In the work-stealing strategy, workers that run out of tasks for execution start claiming tasks from other workers queues. Double ended queues (deques) based on circular arrays proved to be an effective solution for such scenario. In this paper we investigate ways to improve performance of work-stealing schedulers based on deques by enhancing internal data handling mechanisms. Traditionally, deques are designed with an assumption that task pointers are stored within these data structures, while task objects reside in the heap memory. By modifying task queues so that they can hold task objects instead of pointers we managed to increase the performance more than 2.5 times on CPU-bound applications and decrease last-level cache misses up to 30% compared to Intel TBB and Intel/MIT Cilk work-stealing schedulers.
Keywords: Work-stealing scheduler; work-stealing deques; data structures.
Voting Process with Blockchain Technology: Auditable Blockchain Voting System
by Aneta Poniszewska-Maranda, Micha? Pawlak, Jakub Guziur
Abstract: There exist many different electronic voting solutions and each has its own set of advantages and disadvantages. Most of the existing systems suffer from inadequate transparency and auditability. However, recently introduced blockchain technology may provide a solution to these problems. In this paper the Auditable Blockchain Voting System (ABVS) is presented. It combines existing voting approach and combines it with blockchain technology to create a supervised and remote internet voting system, which is transparent and audit capable. The paper describes the systems processes, components, model and results of initial testing.
Keywords: e-voting; blockchain; e-voting system; audit; verification.
Real-time Disease Detection and Analysis System using Social Media Contents
by Ok-Ran Jeong
Abstract: With the growth of social media, research that makes use of social media has become active. In particular, there are many studies that try to use social media as a sensor, because social media can generate information in real time from daily life to social issues such as disasters. Social media is also being used as a sensor for infectious disease surveillance in public health. However, there are challenges like efficient processing of large amounts of social media contents in real time and detecting disease accurately. We have developed a system that collects and processes social media contents in real time, detects and analyzes disease and visualizes the results. We build a workflow that enables real-time processing by efficiently gathering and building a model that can manage data and accurately detect disease. The system also provides intuitive and useful information to people by analyzing their opinions about diseases and visualizing the detected and analyzed information in real time. We have verified the effectiveness of the system.
Keywords: disease analysis; disease surveillance; real-time detection; social media contents.
Special Issue on: Security for Cloud Computing
Searchable Symmetric Encryption Based on the
Inner Product for Cloud Storage
by Jun Yang, Shujuan Li, Xiaodan Yan, Baihui Zhang, Baojiang Cui
Abstract: Searchable encryption enables the data owner to store their own data after
encrypting them in the cloud. Searchable encryption also allows the client to search over
the data without leaking any information about it. In this paper, we rst introduce a
searchable symmetric encryption scheme based on the inner product: it is more ecient
to compute the inner product of two vectors. In our construction, the parties can be Data
Owners, Clients or the Cloud Server. The three parties communicate with each other
through the inner product to achieve the goal that the client can search the data in the
cloud without leaking any information on the data the owner stored in the cloud. We then
perform a security analysis and performance evaluation, which show that our algorithm
and construction are secure and ecient.
Keywords: Searchable Encryption; Searchable Symmetric Encryption; Inner Product;
the Cloud Server; Security.