一种基于SOA和JBPM的工作流引擎模型

工作流技术是实现业务流程自动化的关键技术,但现有的工作流技术已不能满足目前分布式异构和松散耦合的企业信息资源需求。利用SOA技术,结合JBPM,提出了一种基于SOA和JBPM的工作流引擎模型,并对其流程控制与任务管理进行了分析,最后,基于SOAP、WSDL协议和JPDL实现了此工作流引擎,证明了其有效性。     

求解多维背包问题的MapReduce蚁群优化算法

应用MapReduce编程模式实现蚁群优化算法的并行化计算,提出基于MapReduce的改进背包问题蚁群算法.通过改进概率计算时机、轮盘赌、交叉、变异等技术,降低蚁群算法的计算复杂度.在云计算环境中应用该算法分布式并行地求解大规模多维背包问题,仿真实验结果表明,该算法能改善蚁群算法搜索时间长的缺陷,增强对大规模问题的处理能力.     

基于遗传算法的云存储分类规则提取

针对云存储数据源分散、难于集中的特点,根据代理提取分类规则数与每个代理提取误差率以及整体提取误差率之间的关系,提出一种基于遗传算法的云存储分类规则提取方法.在代理端分布式提取分类规则后传输到中心数据库进行归并,从而达到分布式提取分类规则的目的,通过理论推导得出每个代理提取误差率和整体提取误差率的上限随着提取规则数的增加而递减.实验结果证明,在提取规则数足够多的情况下,分布式提取的回归准确率和集中式提取的回归准确率的差值趋于常数,保证了云存储分布式分类规则提取的可行性.     

云计算环境下基于粒子群算法的多目标优化

为了优化资源的部署调度,需要考虑处理费用、传输费用,并提高云计算的性能.对云计算环境下特点进行了研究,把云计算环境下的数据部署和任务调度问题映射为处理交互图,对处理交互图进行分析、提出了多目标优化模型,并通过粒子群算法对多目标模型进行优化.仿真结果表明,该多目标优化模型和算法不但能优化处理时间、传输时间,也能优化处理费用和传输费用.     

基于SVM的并行网络流量分类方法

针对SVM (support vector machine)算法应用到大规模网络流量分类中存在计算复杂度高、训练速度慢等问题,提出一种基于云计算平台进行并行网络流量分类的SVM方法,以提高对大数据集的分类训练速度.该方法是一种采用云计算平台构建多级SVM和映射规约(MapReduce)模型的方法.它将训练数据集划分为多个子训练数据集,通过对所有子训练数据集进行并行训练,得到支持向量集,进而训练出流量分类模型.实验结果表明,与传统的SVM方法相比,并行SVM网络流量分类方法在保持较高分类精度的前提下,有效地减少了训练时间,提高了大规模网络流量分类的速度.     

快速收敛的克隆选择算法

针对克隆选择算法抗体群多样性有限和容易早熟等问题,提出了快速收敛的克隆选择算法.引入新型克隆算子,维持了抗体间促进与抑制的平衡;为了跳出局部最优,结合云模型的特征,给出了云自适应变异算子,与抗体重组算子合作,有效地增加了抗体的多样性,进而增强了算法的全局和局部搜索能力.对标准测试函数进行了仿真实验,并与其它算法进行了比较,比较结果表明,该算法寻优精度高、鲁棒性好、收敛速度快、时间复杂度不高.     

基于工作日历的工作流时间管理的研究与实现

随着企业提出“精细化管理”的需求,企业对工作流平台的时效性、作业管理和时间监控提出了更高的要求.为了提高工作流系统对时间维度的处理能力,借鉴ERP系统的工厂日历思想,提出了基于工作日历的工作流时间模型,基于XML规范定义了5种时间表示方法,实现了基于工作日历的工作流时间管理模块.最后实例结果证明该时间模型易于理解和便于软件实现.     

Partition-Based Online Aggregation with Shared Sampling in the Cloud

Online aggregation is an attractive sampling-based technology to response aggregation queries by an estimate to the final result, with the confidence interval becoming tighter over time. It has been built into a MapReduce-based cloud system for big data analytics, which allows users to monitor the query progress, and save money by killing the computation early once sufficient accuracy has been obtained. However, there are several limitations that restrict the performance of online aggregation generated from the gap between the current mechanism of MapHeduce paradigm and the requirements of online aggregation, such as： 1） the low sampling efficiency due to the lack of consideration of skewed data distribution for online aggregation in MapReduce, and 2） the large redundant I/O cost of online aggregation caused by the independent job execution mechanism of MapReduce. In this paper, we present OLACloud, a MapReduce-based cloud system to well support online aggregation for different data distributions and large-scale concurrent query processing. We propose a content-aware repartition method with a fair-allocation block placement strategy to increase the sampling efficiency and guarantee the storage and computation load balancing simultaneously. We also develop a shared sampling method to share the sampling opportunities among multiple queries to reduce redundant I/O cost. We also implement OLACloud in Hadoop, and conduct an extensive experimental study on the TPC-H benchmark for skewed data distribution. Our results demonstrate the efficiency and effectiveness of OLACloud.     

HEDC＋＋： An Extended Histogram Estimator for Data in the Cloud

With increasing popularity of cloud-based data management, improving the performance of queries in the cloud is an urgent issue to solve. Summary of data distribution and statistical information has been commonly used in traditional databases to support query optimization, and histograms are of particular interest. Naturally, histograms could be used to support query optimization and efficient utilization of computing resources in the cloud. Histograms could provide helpful reference information for generating optimal query plans, and generate basic statistics useful for guaranteeing the load balance of query processing in the cloud. Since it is too expensive to construct an exact histogram on massive data, building an approximate histogram is a more feasible solution. This problem, however, is challenging to solve in the cloud environment because of the special data organization and processing mode in the cloud. In this paper, we present HEDC＋＋, an extended histogram estimator for data in the cloud, which provides efficient approximation approaches for both equi-width and equi-depth histograms. We design the histogram estimate workflow based on an extended MapReduce framework, and propose novel sampling mechanisms to leverage the sampling efficiency and estimate accuracy. We experimentally validate our techniques on Hadoop and the results demonstrate that HEDC＋＋ can provide promising histogram estimate for massive data in the cloud.     

An Energy-Aware Heuristic Scheduling for Data-Intensive Workflows in Virtualized Datacenters

With the development of cloud computing, more and more data-intensive workflows have been deployed on virtualized datacenters. As a result, the energy spent on massive data accessing grows rapidly. In this paper, an energy-aware scheduling algorithm is proposed, which introduces a novel heuristic called Minimal Data-Accessing Energy Path for scheduling data-intensive workflows aiming to reduce the energy consumption of intensive data accessing. Extensive experiments based on both synthetical and real workloads are conducted to investigate the effectiveness and performance of the proposed scheduling approach. The experimental results show that the proposed heuristic scheduling can significantly reduce the energy consumption of storing/retrieving intermediate data generated during the execution of data-intensive workflow. In addition, it exhibits better robustness than existing algorithms when cloud systems are in presence of I/O- intensive workloads.