Earticle

Service-oriented software is composed of a combination of services. Because of the dynamic nature of the Web service environment, the QoS often fluctuates with inherent uncertainty and therefore needs to be dynamically replaced. Based on the changes in the QoS of the software itself and users’ requirements for the software, this paper proposes a dynamic replacement approach based on the cloud model. It adopts the cloud model to transform the quantitative QoS to qualitative QoS for the uncertainty computation and judges the uncertainty level by setting the corresponding service QoS parameters. When a member service with unstable QoS is found, it will be replaced with the candidate service with the same or better QoS to stabilize the QoS of the entire software. Both theoretical analysis and experiment results have proven the feasibility and effectiveness of this approach.

K-nearest-neighbor query is an important query in uncertain network, which is finding the k close nodes to a specific node. We first put forward the concept of the credible nearest neighbor query in uncertain network, and give credible k-nearest-neighbor query algorithm. Credible distance is used to describe the distance between nodes in uncertain network. Fuzzy simulation is adopted to decrease the problem difficulty. Network distance constraint is used to reduce the searching space. Priority queue is used to fast find k-nearest-neighbor query result. Theoretical analysis and experimental results show that our approximation algorithm can well solve k-nearest- neighbor query problem under the uncertain network.

In cloud computing model, virtualized resources is provided to customers as a service over the Internet with reasonable price. This model eectively helps customers focus on their creative business because computing resources are provided on demand by cloud provider. Because of the convenient for cloud customers, the demand for cloud resource grows, thus make cloud data center enlarge and energy consumption becomes a critical issue for cloud provider as well as the carbon dioxide emission. In order to save energy, virtual machines are consolidated to reduce the number of servers required to host them. However, for appli- cations that require communication among services, this migration can increase the latency which causes bad eect on their performance. This paper presents an algorithm that im- prove communication performance by reducing overall trac cost of virtual machines and while energy by increasing CPU utilization.

Traditional scheduling algorithms typically aim to minimize the total time cost for processing all tasks. However, in cloud computing environments, computing capability differs for different resources, and so does the cost of resource usage. Therefore, it is vital to take into consideration the usage cost of resources. Along this line, in this paper, we proposed a modified algorithm based on PSO to solve the task scheduling problem in cloud computing environments. Specifically, by adding a cost-aware fitness function to quantify the cost of resource usage, along with the fitness function for time cost, our method can achieve the goal of minimizing both the processing time and resource usage, and therefore reach a global optimal solution. Besides, our experiment on a simulated cloud computing environment proves the efficiency of our proposed algorithm.

Traditional resources allocation in port usually use queuing model and has deviations between model and actual situation. In this paper, focus on loadometers allocation in bulk port, we propose an optimization solution with Internet of Things. Primary method of this solution is upgrading devices with RFID technology. This solution provides more efficiencies and accuracies cause of reducing manual works and collecting dynamic parameters for queuing model. This paper also shows a simple case study of bulk port in southern China.

One major problem in the area of wireless sensor networks is the coverage problem. The coverage problem deals with the ability of the network to cover a certain area or some certain events. In this paper, we focus on the area coverage problem. We use a cluster-based coverage control scheme and propose HSSAC protocol to maintain sensing coverage by keeping a small number of active sensor nodes and a small amount of energy consumption in a wireless sensor network. In this protocol, proper active sensor set can be determined using the harmony search algorithm. Due to the proposed protocol accuracy in selecting the active sensor set, it is able to provide the acceptable coverage rate in sparse deployment. As the result of increasing nodes density, the proposed protocol decreases the number of active nodes in the sensor networks. Thus, the proposed protocol decreases the energy consumption of the networks and prolongs the network lifetime. We have simulated our protocol and simulation results show high efficiency of the proposed protocol.

The theoretical upper bound of generalization error for ECOC SVMs is derived based on Fat-Shattering dimensionality and covering number. The factors affecting the generalization performance of ECOC SVMs are analyzed. From the analysis, it is believed that in real classification tasks, the performance of ECOC depends on the performance of the classifiers corresponding to its coding columns, which is irrelevant to the mathematical characteristics of the ECOC itself. The essence of ECOC SVMs is how to construct an optimal voting machine consisting of a number of SVMs, how to choose Sub-SVMs which have better generalization ability, and how to determine the number of Sub-SVMs taking part in voting, that is the most important issue. Data sets including “Segment” are selected for test. All the ECOC code columns are constructed using an exhaustive technique. A Sub-SVM is trained for each code column, and the generalization ability of each Sub-SVM is evaluated by classification intervals and error rates estimated by cross validation. Then, all the ECOC code columns are sorted by the generalization performance of Sub-SVMs. Three categories of ECOC SVMs, including superior, inferior and ordinary categories, are constructed from the sorted ECOC code columns, by using forward, backward and original sequences. Experimental results show that the performance of ECOC SVMs which consist of Sub-SVMs with better generalization ability is better and vice versa, which validates our view and points out the direction for improving ECOC SVMs.

In an open and dynamic cloud computing environment, the randomness of cloud services with unreliable quality leads to low accuracy in service composition. To address the above problem, this paper proposes a global trust service composition approach based on random QoS and trust evaluation, considering the multi-criteria assessment of service quality. Firstly, statistical test is employed to remove the uncertain outliers and to estimate the ideal value of the collected objective QoS data. Secondly, subjective QoS evaluations of providers and users are aggregated according to direct trust and recommended trust. Finally, services are composed through global QoS optimization. Experiments for each stage show that the approach improves the accuracy and precision of service composition.

This article proposes a design and implementation of a low cost two-tier architecture model for high availability cluster combined with load-balancing and shared storage technology to achieve desired scale of three-tier architecture for application load balancing e.g. web servers. The research work proposes a design that physically omits Network File System (NFS) server nodes and implements NFS server functionalities within the cluster nodes, through Red Hat Cluster Suite (RHCS) with High Availability (HA) proxy load balancing technologies. In order to achieve a low-cost implementation in terms of investment in hardware and computing solutions, the proposed architecture will be beneficial. This system intends to provide steady service despite any system components fails due to uncertainly such as network system, storage and applications.

With widely used at present, web service can enhance not only the reusability of code, but also the utilization rate of the service resources shared on the web services composition. To solve the difficulty in the communication and expression of the requirement information in complex web service composition, this study proposed a visualization method to describe service composition models through animation. This method employed the requirement behavior model established by the behavioral description language as the research object. In the execution mechanism of the animation, state machine and state block were utilized as the execution model and description model respectively. Each state migration was corresponded to a behavior that calls for visualized description. The motion of figure was controlled by associating each migration in the state block model with an action primitive through an association element. The visualization of the requirement behavior model was thereby realized. The advantages of the method lie in that the requirement changes are avoided. This attributes to that the missing and incorrect potential requirements are observable for the users with different backgrounds owning to the intuition of animation. Moreover, the correctness of the requirement animation is ensured through a series of detection on the BDL model. Finally, this study empirically analyzed the method using a travel system and introduced the modeling and animation tools it realized.

Based on Passive Clustering protocol in this paper, a new type of suitable for large-scale wireless sensor network routing protocol, called RBPC protocol, which USES the Passive Clustering routing Reply Broadcast routing protocol, the purpose is to make full use of the routing Reply (the Route Reply, RREP) group, the RREP Reply when routing requests in Broadcast way, a lot of CH nodes by receiving the grouping and routing are cached in the local, thereby reducing the Route setup times throughout the network, and reduces the source node due to establish routing packet delay.

Connected dominating set (CDS) problem is a promising approach for backbone formation in wireless sensor networks. Selecting proper nodes to construct the CDS in order to prolong the network lifetime is an important issue when designing connected dominating set algorithms in wireless sensor networks. In this paper, we propose an energy efficient connected dominating set (CDS) scheme in wireless sensor networks which prolongs the network lifetime. In proposed algorithm, we use an optimal weight based on the minimum residual energy and maximum effective degree of nodes for backbone formation to prolong the network lifetime. The optimal weight coefficients are determined using particle swarm optimization (PSO) algorithm. Then, when selecting nodes for dominating set (DS) formation, these coefficients will be used. If the degree of a node is more than coefficient of degree constraint and energy of a node is less than coefficient of energy constraint, the node won't be selected for DS formation. The message and time complexity of the proposed algorithm is O(n). Simulation results show that proposed algorithm outperforms the other methods in terms of network lifetime.

Internet-based virtual computing environments (iVCE) are open, anonymous and dynamic in nature. Such characteristics bring about threats and vulnerabilities in providing trusted services and improving resource utilization. Therefore, a dynamic trust model for distinguishing service and recommendation is proposed. In this paper, we analyze multidimensional decision factors related to the evaluation of autonomous node, such as user satisfaction, reward function, punishment function and time decay function. According to the network connection degree of node, our model assigns a new trust weight that specifically describes the relationship between network and trust in iVCE. We then propose a dynamic quantitative model for measuring different kinds of trust. Simulation results indicate that our model can effectively cope with malicious behavior and exhibits evident advantages in resource utilization compared with existing models.

As computers are pervading in all aspects of life with advancement of technology, a growing demand is being felt for low-cost, huge computational need. Grid computing paradigm provides an attractive alternative where enormous computational and data processing and management power can be generated at a much cheaper budget by means of large scale sharing of resources. However, the efficacy of such systems largely depends on the efficacy of scheduling policies employed. In the past few years, myriad, novel scheduling algorithms have been proposed. Besides, for long running and similar types of applications the performance of grid systems can be improved further if the scheduled jobs can be tuned at run time. It is a very important aspect for enhancing performance, considering the drastic fluctuation of resources availability, variations in communications bandwidth, fluctuations in job submission frequency etc that characterize a grid scenario. In this paper, the design and implementation of a Comprehensive Performance Tuning Framework (CPTF) is reported that initially schedules jobs to resources, mines all such job-to-resource mapping information and thereafter tunes certain parameters for subsequent scheduling of submitted jobs. CPTF aims to minimize the overall throughput of the system instead of minimizing single job execution time. Experiments result shows the efficacy of the proposed framework under varying load conditions.

In order to study the effect of the internet of things (IOT) on the architecture of logistics service supply chain (LSSC), this paper summarizes the application of IOT in related fields on the basis of the theories of IOT, analyzes the effect of IOT on logistics/service flow, information flow and fund flow in LSSC and the effect on the structure of LSSC, builds the architecture of LSSC based on IOT, and finally forecasts the application prospect of IOT in LSSC.

Mobile cloud computing, which comes up in recent years, is a new computing paradigm. It enables people to access remote clouds by mobile device, even to build mobile micro-cloud(MuCloud) with mobile device to provide lightweight service. Despite extensive studies of task scheduling in wired cloud, effective scheduling in mobile cloud still remains challenges:1) Unreliable wireless connection and dynamic join and quit of MuCloud often result in decreased reliability of scheduling; 2) As the process capacities of wired clouds and MuClouds vary greatly, it is hard to achieve load balancing; 3) During moving, tasks, such as traffic navigation, may be scheduled consecutively by mobile users as space-time changes. Such application scenarios often incur makespan accumulation which impairs user experience, even causes system crash. Our work aims at such problems. We firstly illustrate the reason for selection of makespan and load balancing as two key performance indicators for task scheduling in the proposed architecture of mobile cloud which integrates MuClouds. Then after introduction to Monte Carlo method, degenerated Monte Carlo estimate is defined and a scheduling algorithm based on degenerated Monte Carlo estimate (DMCE) is presented. With extensive simulation experiments, the two above-mentioned indicators of task scheduling using different algorithms including DMCE, Max-Min, Min-Min and IGA are compared and evaluated. Accumulative effect and relative load are introduced to measure scheduling performance. The experimental results show that: 1)Compared with other algorithms, DMCE achieves smallest makespan on average when scheduled respectively; 2) DMCE has least accumulative effect when task sets scheduled consecutively, which makes makespan of a task set hardly relevant to the order of scheduling; 3)Among these algorithms, DMCE outperforms others in keeping relative load balancing by assigning tasks to clouds in proportion to each cloud’s process capacity.