QoS-aware service composition in cloud computing using data mining techniques and genetic algorithm

One of the requirements of QoS-aware service composition in cloud computing environment is that it should be executed on-the-fly. It requires a trade-off between optimality and the execution speed of service composition. In line with this purpose, many researchers used combinatorial methods in previous works to achieve optimality within the shortest possible time. However, due to the ever-increasing number of services which leads to the enlargement of the search space of the problem, previous methods do not have adequate efficiency in composing the required services within reasonable time. In this paper, genetic algorithm was used to achieve global optimization with regard to service level agreement. Moreover, service clustering was used for reducing the search space of the problem, and association rules were used for a composite service based on their histories to enhance service composition efficiency. The conducted experiments acknowledged the higher efficiency of the proposed method in comparison with similar related works.     

QoS感知的云服务优化组合研究

为了更好地解决服务质量感知的云服务优化组合问题,首先对社会认知算法进行了改进,提出了面向离散型优化问题的模仿学习方法以及基于多次变异的观察学习方法。然后使用改进的社会认知算法对服务质量感知的云服务优化组合问题进行了求解。实验结果表明,改进的社会认知算法具有较强的搜索能力和较快的收敛速度,并且具有较强的推广性,可以用来求解其他离散型优化问题。     

基于时间序列的感知QoS的云服务组合

研究基于时间序列的感知QoS的云服务组合,将服务的QoS偏好随时间不断变化的过程纳入云服务组合的研究范围,将云服务组合建模成时间序列的相似度对比问题。分别用欧几里得距离和扩展Frobenius范数距离度量二维时间序列的相似度,继而用基于主成分分析的扩展Frobenius范数距离和欧几里得距离、Brute Force等方法度量多维时间序列的相似度,通过实验对比验证扩展Frobenius范数距离度量相似度在时间和准确性上的优越性。关     

A QoS-aware composition method supporting cross-platform service invocation in cloud environment

With the increasing popularity of cloud computing technologies, more and more service composition processes are enacted and executed in could environment. Compared with the various and approximately infinite application requirements from end users, the web services held by a cloud platform are usually limited. Therefore, it is often a challenging effort to develop a service composition, in such a situation that only part of the functional qualified candidate services could be found inside a cloud platform. In this situation, the absent services will be invocated in a cross-platform way outside the cloud platform. In view of this challenge, a QoS-aware composition method is investigated for supporting cross-platform service invocation in cloud environment. Furthermore, some experiments are deployed to evaluate the method presented in this paper.     

果蝇优化算法研究进展

作为一种新颖的群智能优化方法,受基于视觉和嗅觉的觅食行为的启发而提出的果蝇优化算法具有易理解和实现、控制参数少的特点.近年来果蝇优化算法的研究受到了广泛关注,果蝇优化算法及其变种在诸多工程优化领域得到了成功应用.阐述果蝇优化算法的设计思想与机制,重点综述果蝇优化算法的研究进展,包括维持种群多样性、知识驱动策略与协同机制的设计等方面的改进工作.同时,介绍果蝇优化算法在离散优化、多目标优化、不确定优化等方面的扩展性研究工作,并总结果蝇优化算法的代表性应用研究成果,最后指出在理论、设计、扩展、应用等方面未来进一步的研究方向和内容.     

Comparative analysis of multi-objective evolutionary algorithms for QoS-aware web service composition

Web service composition combines available services to provide new functionality. The various available services have different quality-of-service (QoS) attributes. Building a QoS-optimal web service composition is a multi-criteria NP-hard problem. Most of the existing approaches reduce this problem to a single-criterion problem by aggregating different criteria into a unique global score (scalarization). However, scalarization has some significant drawbacks: the end user is supposed to have a complete a priori knowledge of its preferences/constraints about the desired solutions and there is no guarantee that the aggregated results match it. Moreover, non-convex parts of the Pareto set cannot be reached by optimizing a convex weighted sum. An alternative is to use Pareto-based approaches that enable a more accurate selection of the end-user solution. However, so far, only few solutions based on these approaches have been proposed and there exists no comparative study published to date. This motivated us to perform an analysis of several state-of-the-art multi-objective evolutionary algorithms. Multiple scenarios with different complexities are considered. Performance metrics are used to compare several evolutionary algorithms. Results indicate that GDE3 algorithm yields the best performances on this problem, also with the lowest time complexity.     

一种用于PID控制参数优化的混合果蝇算法

针对果蝇优化算法（ FOA）收敛速度快但寻优精度低的缺点,为了改善果蝇算法的优化性能,提出一种混合果蝇优化算法（ HFOA）。HFOA采用分段优化的思想,在优化过程后期采用收敛稳定性较好的粒子群优化（ PSO）算法优化果蝇算法中果蝇个体飞行距离和味道浓度的判定值,采用误差性能指标积分准则ITAE作为适应度函数,并将优化方案应用于一类不稳定系统的PID控制。Matlab仿真验证表明：HFOA计算高效,具有良好的稳定性,收敛精度高,进而验证了HFOA应用于PID控制参数优化是可行而有效的。     

QoS-aware and multi-granularity service composition

Composition of Web services can be very complex, and usually involves multiple atomic services and varieties of message exchange patterns. Worst still, with the increasing amount of available services with varying granularity and quality, selecting the best combination of services becomes very challenging. This paper addresses the issues on multi-granularity service composition with awareness of the service quality. In particular, we consider how a new service composition plan is produced, while preserving its original observable behaviors of a service that are shown to the service user, by substituting the service with another service or a set of services of finer or coarser grain. The new plan aims to have services of better quality (if the corresponding underlying services are available). To achieve this, we firstly define a behavioral signature model to capture observable behaviors of services. We then present that two service composition plans are choreography equivalent if they comply with the same behavioral signature model. We then propose a behavioral extracting algorithm to obtain the behavioral signature model from a service composition plan. We also present a method to determine choreography equivalence. Finally we briefly describe our prototype implementation that captures all these proposed algorithms.     

Logistics-involved QoS-aware service composition in cloud manufacturing with deep reinforcement learning

Cloud manufacturing is a new manufacturing model that aims to provide on-demand manufacturing services to consumers over the Internet. Service composition is an essential issue as well as an important technique in cloud manufacturing (CMfg) that supports construction of larger-granularity, value-added services by combining a number of smaller-granularity services to satisfy consumers’ complex requirements. Meta-heuristics algorithms such as genetic algorithm, particle swarm optimization, and ant colony algorithm are frequently employed for addressing service composition issues in cloud manufacturing. These algorithms, however, require complex design flows and painstaking parameter tuning, and lack adaptability to dynamic environment. Deep reinforcement learning (DRL) provides an alternative approach for solving cloud manufacturing service composition (CMfg-SC) issues. DRL as model-free artificial intelligent methods enables a system to learn optimal service composition solutions through training, which can therefore circumvent the aforementioned problems with meta-heuristics algorithms. This paper is dedicated to exploring possible applications of DRL in CMfg-SC. A logistics-involved QoS-aware DRL-based CMfg-SC is proposed. A dueling Deep Q-Network (DQN) with prioritized replay named PD-DQN is designed as the DRL algorithm. Effectiveness, robustness, adaptability, and scalability of PD-DQN are investigated, and compared with that of the basic DQN and Q-learning. Experimental results indicate that PD-DQN is able to effectively address the CMfg-SC problem.     

A hybrid approach to vehicle routing using neural networks and genetic algorithms

A competitive neural network model and a genetic algorithm are used to improve the initialization and construction phase of a parallel insertion heuristic for the vehicle routing problem with time windows. The neural network identifies seed customers that are distributed over the entire geographic area during the initialization phase, while the genetic algorithm finds good parameter settings in the route construction phase that follows. Computational results on a standard set of problems are also reported.     

基于遗传模拟退火混合算法的矩形包络求解

介绍了一种利用遗传模拟退火混合算法求解矩形包络的方法,该算法在优化搜索中能自适应地控制变异率,使得优化高效地逼近全局最优.矩形包络是将不规则多边形用它们的最小外接矩形来代替,就是求解该多边形的最佳包络矩形.实验结果表明,在解决矩形包络问题中,遗传模拟退火混合算法是一种高效的,可靠的优化算法,具有一定的实用价值.     

QoS感知的语义服务组合搜索算法

针对如何在海量Web服务中进行快速的服务自动组合、以满足客户复杂需求的问题,提出一种基于规划图思想的搜索组合算法,该算法在正向扩展阶段除了依据所选取服务的功能与非功能属性进行有效剪枝外,还实时级联更新已驱动服务的QoS信息并有效记录所操作服务的前驱服务,通过前驱索引集合,确保逆向求解阶段的效率并满足了QoS最优的约束。在实验环节证明了注册服务数量与求解效率的线性关系,以及与其他算法相比较所体现出来的性能优势。     

A novel heuristic algorithm for QoS-aware end-to-end service composition

Many works have been carried out to find the efficient algorithms for QoS-aware service composition in recent years. Nevertheless, on one hand, some of these works only consider the local QoS attributes in Web services composition; on the other hand, some ideas derived from QoS selection algorithms for network routing are directly applied in service composition without any adaption. A service composition model with end-to-end QoS constraints has been presented in this paper. An improved heuristics HCE based on the observation of characteristic of end-to-end service composition is proposed as a novel solution. Simulation results reveal the better performance of proposed heuristic compared to the other two heuristics, HMCOP and generic CE algorithm.     

基于混合果蝇优化算法的现场服务调度问题

员工技能熟练程度对现场服务调度问题（FSSP）的执行效率有极大影响,现有研究中未考虑员工技能因素。针对上述问题,首先以员工的旅行时间、服务时间和等待时间为优化目标,建立考虑员工技能熟练程度的FSSP模型;然后,提出混合果蝇优化算法（HFOA）对该模型进行优化求解,根据问题特征和算法特点,设计了基于矩阵的编码方法;定义了两类矩阵操作,提出了3种搜索算子,重构了果蝇优化算法（FOA）的嗅觉搜索和视觉搜索过程;为了提升算法性能,构造了基于最邻近插入启发式算法的初始化算子;最后,通过典型实例对算法进行了仿真实验,并与遗传算法（GA）、贪婪随机自适应搜索过程（GRASP）算法进行了比较。实验数据显示,与其他两种算法相比,HFOA在均值和最优值方面表现更优秀。结果表明改进初始化方法和搜索策略后,HFOA在优化的精度和稳定性上优于其他算法。     

一种高效的服务组合优化算法

随着功能性属性相同而非功能性属性各异的Web服务的大量涌现,如何在服务组合业务流程中为各个任务选择相应的组件服务以达到组合服务的QoS(quality of service)最大化,并在此基础上满足不同用户的需求,已成为了国内外研究的热点.由于该问题的复杂性(NP-hard),目前存在的大多数方法都并不十分适合需要相对精确、实时决策的Web服务组合系统.因此,本文提出了一种基于凸包构建的组合服务优化算法(CM-HEU)用以解决QoS感知的服务组合优化问题.CM-HEU首先通过对组合服务中的每组任务进行凸包构建,以减少搜索空间.然后通过对初始解向量的多次升级和一次降级操作以达到全局优化的目标.实验表明:相对于现阶段存在的一些主流方法,CM-HEU不仅能得到一个比较理想的结果,并且具有良好的效率.     

QoS-aware service composition for distributed video surveillance

Quality of Service (QoS) is essential for the ubiquitous access of media services in real-time distributed video surveillance applications. To have ubiquitous access of desired media with emergency officials’ handheld devices, appropriate media transcoding services are required. Currently, it is challenging to select and compose these services for each of the devices to satisfy the desired QoS demand. To compose these media services so that video stream is available for target pervasive and smart devices, a composition algorithm is required. Thus, this paper presents a QoS-aware service composition algorithm to select the best composition for the target ubiquitous client so that it can optimally provide QoS to heterogeneous users. We have implemented a video surveillance prototype to demonstrate the performance of the proposed QoS-aware composition algorithm. Results from this prototype reveal that the approach is suitable for real-time video surveillance.     

求解置换流水线调度问题的混合离散果蝇算法

针对置换流水线调度问题,提出了一种新颖的混合离散果蝇算法.算法每一代进化包括4个搜索阶段:嗅觉搜索、视觉搜索、协作进化和退火过程.在嗅觉搜索阶段,采用插入方式生成邻域解;在视觉搜索阶段,选择最优邻域解更新个体;在协作进化阶段,基于果蝇个体间的差分信息产生引导个体;在退火操作阶段,以一定概率接受最优引导个体从而更新种群.同时,通过试验设计方法对算法参数设置进行了分析,并确定了合适的参数组合.最后,通过基于标准测试集的仿真结果和算法比较验证了所提算法的有效性和鲁棒性.     

A tuned hybrid intelligent fruit fly optimization algorithm for fuzzy rule generation and classification

Fuzzy rule-based systems (FRBSs) are well-known soft computing methods commonly used to tackle classification problems characterized by uncertainties and imprecisions. We propose a hybrid intelligent fruit fly optimization algorithm (FOA) to generate and classify fuzzy rules and select the best rules in a fuzzy if–then rule system. We combine a FOA and a heuristic algorithm in a hybrid intelligent algorithm. The FOA is used to create, evaluate and update triangular fuzzy rule-based and orthogonal fuzzy rule-based systems. The heuristic algorithm is used to calculate the certainty grade of the rules. The parameters in the proposed hybrid algorithm are tuned using the Taguchi method. An experiment with 27 benchmark datasets and a tenfold cross-validation strategy is designed and carried out to compare the proposed hybrid algorithm with nine different FRBSs. The results show that the hybrid algorithm proposed in this study is significantly more accurate than the nine competing FRBSs.

     

基于混合果蝇优化算法的选址-库存联合优化策略

针对装备维修保障仓库系统运营费用高、仓库点位布局不合理、备件库存结构不合理等问题,建立以多品种联合补货问题为基础的装备维修备件仓库选址-库存控制决策联合优化模型,模型可用于求解仓库的开设位置、维修活动需求点的指派情况、仓库补货时间以及库存水平等.根据模型的结构特点,利用多种群协同进化的方法改进传统果蝇优化算法的位置更新方式,设计一种内外两层搜索策略的混合果蝇优化算法,外层搜索策略作为算法的主程序用于搜索仓库选址决策变量,内层搜索策略采用改进的RAND算法用于搜索库存控制决策变量.仿真结果表明,混合果蝇优化算法具有良好的求解效率,能够确保库存系统在一定服务水平的基础上有效降低库存运营总成本.