Optimal Service Composition Research Articles

Optimal web service composition using hybrid optimization algorithm in cloud environment

In recent years, service-based applications are deemed to be one of the new solutions to build an enterpriseapplication system. In order to answer the most demandingneeds or adaptations to the needs of changed servicesquickly, service composition is currently used to exploitthe multi-service capabilities in the Information Technologyorganizations. While web services, which have been independently developed, may not always be compatible with each other, the selection of optimal services and compositionof these services are seen as a challenging issue. In this paper we propose optimal web service composition (OWSC) model, we introduce an improved Dragonfly Algorithm (IDA) to compute services whose network positions are closer to each other and to the users, which ensures the QoS of web service and network. The rule search swarm searcher (RSSA) is used to obtain the desirable characteristics from composite web services for further optimal selection of service composition set in composite planner. Then, we propose optimal tree based replanning mechanism to adapt the execution plan to the actual behavior of already executed services by a dynamic service selection at runtime.Finally, the proposed OWSC model is going to develop by cloudsim toolkit and the performance is compared with the existing models similar to our contributions in terms of QoS parameters.

Multi-task service composition model considering competitive resource constraint in cloud manufacturing

Service composition optimization is one of the core issues of cloud manufacturing research. At present, relevant researches mostly focus on single-task service composition, and there are few reports on the problem of multi-task service composition considering resource competition. However, in the real cloud manufacturing environment, multi-task service composition is common, so how to formulate a robust multi-task service composition model is a meaningful research direction. This paper first proposes a multi-task service composition optimization model considering resource competition constraints (MTSCOM-RCC) in the cloud manufacturing environment to fill the above-mentioned gap. The MTSCOM-RCC model considers the conflicts of interest and time between parallel subtasks and proposes an important service evaluation indicator. Secondly, a two-layer coding method, including task layer and subtask, is proposed based on studying the MTSCOM-RCC’s competition mechanism and characteristics. An improved hybrid genetic artificial bee colony algorithm model is proposed to solve the multi-task model. The model is combined with the global optimization method and task queue optimization method. Experimental results prove that the two-layer task optimization method model is more feasible and effective than the other two solution models.

An efficient two-phase approach for reliable collaboration-aware service composition in cloud manufacturing

Composing existing services into one value-added composite service for a cooperative business process is especially attended by both academia and industry in the cloud manufacturing (CMF) environment from the perspective of industrial information integration. Various service composition methods based on the QoS have been proposed to satisfy the user's requirement. However, the traditional methods fail to consider interrelation among various services and change in QoS. The unstable QoS may affect the reliability of service composition, which may also affect reliable collaboration as cloud services need to cooperate with each other to accomplish the business process efficiently. In this paper, we propose an efficient two-phase approach by integrating clustering and Chaos-Gauss-based PSO to solve the above problem. In phase one, the K-means clustering algorithm is adopted to improve the quality of candidate services with the consideration of QoS stability for reducing the search space. In phase two, a novel multi-objective PSO algorithm based on Chaos-Gauss named CGPSO is proposed to find the optimal service composition. The Two-Phase approach considers both the QoS stability and service collaboration ability to reduce the probability of service composition failure. Further, we conduct a comprehensive analytical and experimental study to show that our approach has better performance and effectiveness for service composition than other approaches in the CMF environment.

Research on 3D Printing Resource cloud Platform Technology based on dynamic Service Composition

To improve the improve the management and matching of 3D printing resources, a 3Dprinting cloud platform based on dynamic service composition technology is established, and the 3D printing composite service is optimized. First, cloud computing is combined with 3D printing to establish cloud manufacturing mode. According to the characteristics of each stage, the dynamic service composition technology under cloud manufacturing mode is divided into three stages. Then, dynamic service composition technology of 3D printing resource is established. Based on the logical relationship between services, breadth algorithm and depth algorithm are used to find the optimal service composition path in the search graph to meet the different needs of users. The experimental results show that the relationship between user requirements and services can be obtained by calculating the quality of service. In the case, the service quality required by users is less than 20, and service 1 and 3 can meet the needs of users. This exploration provides a reference for the study of 3D printing resources dynamic service composition.

Method towards reconstructing collaborative business processes with cloud services using evolutionary deep Q-learning

Service-oriented architecture (SOA) is a significant framework that enables intelligent information systems to offer business process-based services, namely Business Process as a Service (BPaaS). Cloud service-based business model reconstruction within and across enterprises has become an important issue to obtain competitive advantages. Finding appropriate service component is a critical phase in enterprise collaboration, to improve the quality and correlations among collaborative service-providers. Existed methods for business processes reconstruction have not systematically and fully considered the quality correlations in finer-grain, i.e. task-level or activity-level, and temporal performance in a process model optimization. Moreover, the existed approaches might fail to work in an uncertain cloud environment where the quality parameters are unknown in advance. Q-learning has proven its worth in an uncertain cloud environment. However, advances in Q-learning are challenges to leverage in collaborative business process reconstruction. The reconstruction algorithms based on Q-learning suffered from the two core drawbacks: lack of effective exploration and extremely slow convergence property. A hybrid Evolutionary Deep Q-Learning-based BPaaS reconstruction algorithm, named as EDQL-BPR, is proposed by leveraging Particle Swarm Optimization to improve Deep Q-Learning algorithm for systematically optimizing collaborative business processes reconstruction. In order to verify the effectiveness of the proposed algorithm, an annotated transition system has been developed supporting for all possible behaviors state convention from heterogeneous initial states to the target with several collaborative information at activity level, and encoding annotated BP representation matrix automatically. Then, an autonomous three-layer framework has been built to facilitate business process discovery and service reconstruction. In this framework, our optimal collaborative services composition is treated as a multi-objective constraint optimization problem via Evolutionary Deep Q-learning with updated strategy of Q-value, and each annotated component launch a service discovery by service agent. Extensive evaluation results show that EDQL-BPR can outperform several representative business process reconstructions in terms of model optimal convergence, QoS optimality, effectiveness and efficiency under heterogeneous service selection workloads in an uncertain Cloud environment.

Web Service Composition Optimization Based on Adaptive Mutant Beetle Swarm

with the continuous development of cloud computing technology and big data, web services are widely used in intelligent information processing in all walks of life, when facing a large number of services with similar functions and quality, web service composition technology is a crucial technology in web services, which enable common services to be combined and select the optimal service combination to meet the wide range of users’ needs. Aiming at the problems of algorithm accuracy and stability of existing service composition technologies, the penalty function is used to construct the fitness function in this paper, which transforms the constrained optimization problem into an unconstrained optimization problem, and realizes the global optimization. Traditional web service composition models are aimed at QoS attribute perception. This paper establishes a QoE model that focuses on user experience, which can better meet the needs of users. An adaptive mutant beetle herd algorithm was proposed in this paper, the author introduced Beetle Antennae Searching Algorithm into the common particle swarm optimization algorithm, and added an adaptive mutation factor to enhance the searching ability of the algorithm; The use of dynamic learning factors allows the algorithm to have better population diversity and enhanced convergence. The experimental results that the algorithm proposed in this paper has higher algorithm accuracy, comparatively faster convergence speed and stability.

Multiobjective Optimization of Cloud Manufacturing Service Composition with Improved Particle Swarm Optimization Algorithm

Aiming at the problems of low search efficiency and inaccurate optimization of existing service composition optimization methods, a new multiobjective optimization model of cloud manufacturing service composition was constructed, which took service matching degree, composition synergy degree, cloud entropy, execution time, and execution cost as optimization objectives, and an improved particle swarm optimization algorithm (IPSOA) was proposed. In the IPSOA, the integer encoding method was used for particle encoding. The inertia coefficient and two acceleration coefficients were improved by introducing the normal cloud model, sine function, and cosine function. The global search ability of IPSOA in the early stage was improved, and its prematurity was restrained to form a more comprehensive solution space. In the later stage, IPSOA focused on the local fine search and improved the optimization precision. Taking automatic guided forklift manufacturing task as an example, the correctness of the proposed multiobjective optimization model of cloud manufacturing service composition and the effectiveness of its solution algorithm were verified. The performance of IPSOA was analyzed and compared with standard genetic algorithm (SGA) and traditional particle swarm optimization (PSO). Under the same conditions, IPSOA had a faster convergence speed than PSO and SGA and had better performance than PSO.

A Novel Service Composition Optimization Strategy

In order to cope with the increasingly complex application requirements, sensors work in a cooperative and collective manner. Service-oriented Wireless Sensor Networks (WSNs)frameworkbecomes an effective strategy to solve the cooperative work of sensors. Aiming at the key service composition optimization problem under this framework, this paper proposes a novel multi-channel directed harmony search algorithm (MDHS) algorithm after analyzing the performance of ant colony optimization (ACO), genetic algorithm (GA) and particle swarm optimization (PSO) algorithms on this problem. Based on harmony search algorithm (HS) algorithm, this algorithm adopts multi-channel, dynamic parameters, directional perturbation and other technologies, which greatly improves the excellence of service composition and solution efficiency. Extensive experiments have been carried out and the results show that our technique performs better than GA and PSO on reducing energy consumption and extending the life of the wireless sensor network.

Optimization of complex part-machining services based on feature decomposition in cloud manufacturing

ABSTRACT Cloud manufacturing (CM) is a new service-oriented networked manufacturing mode. The optimal configuration of manufacturing services is one of most challenging topics in CM. Most research focuses on service composition optimization algorithms. However, for different manufacturing tasks, the configuration mode of the manufacturing services is different. For complex parts, effectively using the appropriate optimization strategy to solve the optimization of machining services is still rare in CM. To solve the above problem, a new machining task decomposition and service optimization strategy is proposed. Under this mode, the features of the complex part are defined as the basic task granularity. Four machining service optimization modes are constructed, and a mathematical model of machining service optimization under the four modes is established. Subsequently, a particle swarm optimization algorithm based on simulated annealing (PSOBSA) is designed by combining the particle swarm optimization (PSO) and simulated annealing (SA). Finally, three groups of simulation experiments are conducted to simulate the optimization mode of complex parts machining services based on feature decomposition. The simulation results demonstrate the feasibility of the service optimization mode and the effectiveness of the PSOBSA. The research results presented in this paper provide an machining service outsourcing method for complex parts.

The Design of Correlation-aware Service Composition System

A correlation-aware service composition system is designed in this paper. The involving key modules in this system are introduced including service description, service request submission, service composition construction, service composition instantiation, service composition optimization, and service correlation extraction. The feasibility of the system is verified and analyzed based on the example of “online purchasing automobiles parts”.

Reinforcement Learning for Interactive QoS-Aware Services Composition

An important and challenging research problem in web of things is how to select an appropriate composition of concrete services in a dynamic and unpredictable environment. The main goal of this article is to select from all possible compositions the optimal one without knowing a priori the users' quality of service (QoS) preferences. From a theoretical point of view, we give bounds on the problem search space. As the QoS user's preferences are unknown, we propose a vector-valued MDP approach for finding the optimal QoS-aware services composition. The algorithm alternatively solves MDP with dynamic programming and learns the preferences via direct queries to the user. An important feature of the proposed algorithm is that it is able to get the optimal composition and, at the same time, limits the number of interactions with the user. Experiments on a real-world large size dataset with more than 3500 web services show that our algorithm finds the optimal composite services with around 50 interactions with the user.

A preference-based multi-objective algorithm for optimal service composition selection in cloud manufacturing

ABSTRACT Aiming at addressing several conflicting criteria of quality of service (QoS) that should be trade-off optimized during service composition and optimal selection (SCOS) in cloud manufacturing (CMfg), the improved non-dominated sorting genetic algorithm III (NSGA-III) is proposed and employed to address the SCOS issue. This is the first time that a preference-based multi-objective algorithm has been used to address the SCOS problem. In this paper, a novel K-layer preference reference point set approach is proposed for generating a reference point set with this algorithm to guide the search towards the interesting parts of the Pareto optimal region based on customer preferences, which improves the efficiency of the algorithm and the convergence of the obtained solution. A new fitness assignment strategy and environment selection scheme is developed accordingly to balance the relationship of diversity and convergence of preserved individuals in each generation. Additionally, the memetic algorithm is integrated into the evolutionary mechanism of the algorithm to address the insufficiency of local search. To validate the performance of the proposed algorithm, several test cases are conducted. The results demonstrate that the proposed algorithm is more competitive than other considered algorithms.

A nonlinear service composition method based on the Skyline operator

The concept of service composition can provide the complex functionality for users. As the widespread application of cloud computing, the number of services grows exponentially. It becomes more difficult to find out the optimal service composition solution quickly. This paper proposes a nonlinear service composition method based on the Skyline operator. The Skyline operator is to find a collection of data that cannot be dominated by others, which is used to prune the redundant services to reduce the search space. Then the service composition problem is formulated as a nonlinear integer programming model by a mathematical programming language (AMPL), and solved by the existing nonlinear solvers Bonmin. The experiments show that the proposed method can effectively improve the efficiency of service composition, while ensuring the quality of solution.

Personalized manufacturing service composition recommendation: combining combinatorial optimization and collaborative filtering

Owing to the rapid proliferation of service technologies in cross-enterprise manufacturing collaborations, manufacturing service composition (MSC) has attracted much attention from both academia and industries. However, the existing service composition is often constructed by the combination of off-line and on-line services, quality of service (QoS) attributes are not appropriate for satisfying the specific demands of MSC. Moreover, there are very few historical QoS invocations of manufacturing service, leading to difficulty in recommending appropriate service composition to a target user. In order to find the personalized MSC mode from a complex service network more accurately, we combine combinatorial optimization with collaborative filtering in this paper to figure out two questions: (1) how to construct a QoS description model of manufacturing service composition; (2) how to enhance the effectiveness of personalized QoS-aware service composition recommendations. First, the new QoS model of MSC is proposed by considering both traditional characteristics (e.g. availability, performance and reliability), variability of service composition and enterprise dimensional QoS attributes. Second, the service combination optimization is constructed based on combinatorial optimization method. Third, the collaborative filtering is employed to calculate the missing QoS values of the candidate manufacturing services. Finally, with both available objective functions and predicted QoS values, optimal service composition recommendation can be generated by using combinatorial optimization model with QoS constraints.

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

• Deep reinforcement learning is used to solve the QoS-aware service composition problem in cloud manufacturing with the consideration of logistics. • A DRL algorithm that combines the basic DQN algorithm, the dueling architecture, and the prioritized replay mechanism is proposed. • Experimental results demonstrate the effectiveness, high efficiency, adaptability, and scalability of the proposed DRL algorithm. 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 classification-based approach for integrated service matching and composition in cloud manufacturing

Cloud manufacturing has been acknowledged as a transformative manufacturing paradigm aiming towards producing highly customized products via sharing distributed manufacturing resources and capabilities. One of the pivotal challenges regarding the practical realization of this idea is the process of matching manufacturing resources with personalized service demands. This problem contains two main steps: (1) retrieval of functionally similar services through assessing semantic similarity between resources’ and subtasks’ descriptions and (2) optimal composition of subtasks according to non-functional quality of service (QoS) indexes. However, almost all the research work in the field so far has focused on tackling each of these dimensions individually which barely represents actual conditions of the cloud manufacturing paradigm. To this end, this paper aims towards a novel integrated approach that first, successfully retrieves candidate sets for each corresponding subtask via implementing five classification algorithms and using TF-IDF (term frequency–inverse document frequency) vectors extracted from the manufacturing capability data. Then, optimal composite services are obtained for each scenario by using two well-known metaheuristic algorithms. Results obtained from the experiments have proven the advantages of this method resulting in a more comprehensive and realistic way for dealing with the service composition problems.

Simulation and modeling of an improved multi-verse optimization algorithm for QoS-aware web service composition with service level agreements in the cloud environments

Cloud computing is a new trend in information technology that provides resources and shares services by web services over the internet for users. Many web services have similar functionality with different quality of service (QoS) in the cloud. Thus, an appropriate service composition method is needed to assign an optimal composition of services to the users. Furthermore, service level agreement (SLA) which is the level of service expected from the service provider should be satisfied by the service composition method that less considered in previous studies. Introducing an appropriate algorithm for web service composition that could achieve high QoS while satisfying SLA constrains is one of the main issues in the cloud computing area. In this study, an improved multi-verse optimization algorithm for web service composition that is called IMVO algorithm is proposed to improve QoS while satisfying SLA. The simulation results show increasing of normalized QoS up to 57% in comparison with the other approaches, especially for service composition problems with SLA.

IBGSS: An Improved Binary Gravitational Search Algorithm based search strategy for QoS and ranking prediction in cloud environments

Quality of Service (QoS) value prediction and QoS ranking prediction have their significance in optimal service selection and service composition problems. QoS based service ranking prediction is an NP-Complete problem which examines the order of ranked service sequence with respect to the unique QoS requirements. To address the NP-Complete problem, greedy and optimization-based strategies such as CloudRank and PSO have been widely employed in service oriented environments. However, they pose several challenges with respect to the similarity measure based QoS prediction, trap at local optima, and near optimal solution. Hence, this paper presents Improved Binary Gravitational Search Strategy (IBGSS), an optimization based search strategy to address the challenges in the state-of-the-art QoS value prediction and service ranking prediction techniques. IBGSS employs improved cosine similarity measure, and Newton–Raphson inspired Binary Gravitational Search Algorithm (NR-BGSA) for accurate QoS value prediction and optimal service ranking prediction respectively. The effectiveness of IBGSS over the state-of-the-art QoS value prediction and ranking prediction techniques was validated using two real world QoS datasets, namely WSDream#1 and web service QoS dataset in terms of various statistical measures (Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Average Precision Correlation (APC)).

Evolutionary algorithms for many-objective cloud service composition: Performance assessments and comparisons

Service composition and optimal selection (SCOS) concerns the building of optimal composite service by integrating existing services with the aim of performing complex task. Due to a plethora of affordable cloud services providing similar functionalities while differing in quality of service (QoS), how to determine suitable candidates to orchestrate the best composite service, also known as QoS-aware SCOS problem, becomes more complicated. A number of evolutionary optimizers have been developed to resolve SCOS. Unfortunately, a large majority of these optimizers carry out the optimization by aggregating many diverse QoS attributes into a single objective or simply considering two or three representative QoS attributes. SCOS, particularly, from the perspective of many-objective optimization, has not received an appropriate attention. As more factors come into play, SCOS is strictly a many-objective problem. This study explores the scalability of recently state-of-the-art evolutionary many-objective optimization (EMaO) algorithms in addressing SCOS. Comparative results reveal that these EMaO algorithms, never before applied to many-objective SCOS, exhibit distinct search abilities with respect to the objective space dimensionality and problem scale. Based on the empirical observation, useful suggestions and insights for choosing suitable EMaO algorithms pertaining to different SCOS problems are given.

Large-scale and adaptive service composition based on deep reinforcement learning

Service composition is a research hotspot with practical value. With the development of Web service, many Web services with the same functional attributes emerge. However, service composition optimization is still a big challenge since the complex and unstable composition environment. To solve this problem, we propose an adaptive service composition based on deep reinforcement learning, where recurrent neural network (RNN) is utilized for predicting the objective function, improving its expression and generalization ability, and effectively solving the shortcomings of traditional reinforcement learning in the face of large-scale or continuous state space problems. We leverage heuristic behavior selection strategy to divide the state set into hidden state and fully visible state. Effective simulation of hidden state space and fully visible state of the evaluation function can further improve the accuracy and efficiency of the combined results. We conduct comprehensive experiment and experimental results have shown the effectiveness of our method.