Service Composition Problem Research Articles

Composition of construction services with hierarchical planning on digital platform

The digital platform business model offers opportunities for the construction industry to address the problem of extensive development by elaborately orchestrating a range of construction services to meet complex construction requirements. The presence of isomeric and coupling relationships between two construction services leads to alternative execution paths in the service network. However, the problem of generating a service network with alternative branches has been scarcely investigated. This study proposes a hierarchical task network (HTN) approach to address the service composition problem. Specifically, the approach performs a depth-first traversal search to address the isomeric and coupling relationships. A branch merging mechanism is integrated to eliminate repeated planning caused by equivalent planning nodes. The experimental studies demonstrate that the approach can generate valid and correct branches in the construction service network and that the devised branch merging mechanism can significantly improve the efficiency of the approach.

PPDRL: A Pretraining-and-Policy-Based Deep Reinforcement Learning Approach for QoS-Aware Service Composition

Service composition is a mainstream paradigm for rapidly constructing large-scale distributed applications. QoS-aware service composition, i.e., selection of the optimal execution plan that maximizes the composition’s end-to-end QoS properties, is an active area of research and development endeavors in service composition. In this paper, we propose PPDRL, a pretraining-and-policy-based deep reinforcement learning approach, to solve the QoS-aware service composition problem. Its significant feature is to incorporate a maximum likelihood estimate and a policy scoring mechanism into a deep reinforcement learning framework. As a result, our approach can balance the exploitation and exploration efforts adaptively and can search for the solution space in a robust and efficient manner. We have executed our approach to solve 6 randomly generated QoS-aware service composition problems with different sizes and structures based on QWS data set including 2,507 real Web services classified into 233 categories. The results indicate that our approach can find near-optimal solutions within moderate numbers of iteration and has performance superiority in comparison with five state-of-the-art algorithms.

Local Consistency Reinforcement for Enhancing Web Service Composition

Composing Web services to fulfill a user query remains one of the most challenging research problems due to its importance to the world economy. Several composition techniques have been proposed, but these techniques are becoming more and more expensive due to the tremendous growth of data over the internet, the intensive use of services, and the continuous changes of available services. The workflow-based Web service composition problem is an NP-complete problem, due mainly to the property of the workflow structuring the composition and the diversity of underlying constraints. Reinforcing local consistency is one of the well-known pre-processing techniques to reduce the complexity of most NP-complete problems. These techniques are mainly dedicated to binary constraint satisfaction problems. Therefore, only few researchers devoted their efforts toward reinforcing some level of local consistency on Web service composition problems that can be semantically defined in the Ontology Web Language for Web Services (OWL-S) control structure based constraints. The main goal of this paper is to propose a novel approach for reinforcing a reasonable level of local consistency, node and arc-consistency on any Web service composition problems. It is expected to provide a more up-to-date and realistic representation of any Web service composition problems without any user interactions, but with the ability to cope with any types of user’s query, such as incomplete, ambiguous, and others. This is due to the existence of several novel rules for reinforcing node and arc-consistency on all types of control structure constraints. Experiments were performed on random problems of different levels of complexity to evaluate the performance of the proposed approach.

An extended artificial bee colony with local search for solving the Skyline-based web services composition under interval QoS properties

In this paper, we introduce an extended version of artificial bee colony with a local search method (EABC) for solving the QoS uncertainty-aware web service composition (IQSC) problem, where the ambiguity of the QoS properties are represented using the interval-number model. At first, we formulate the addressed problem as an interval constrained single-objective optimization model. Then, we use the skyline operator to prune the redundant and dominated web services from their sets of functionally equivalent ones. Whereas, EABC is employed to solve the IQSC problem in a reduced search space more effectively and more efficiently. For the purpose of validation of the performance and the efficiency of the proposed approach, we present the experimental comparisons to an existing skyline-based PSO, an efficient discrete gbest-guided artificial bee colony and a recently provided Harris Hawks optimization with an elite evolutionary strategy algorithms on an interval extended version of the public QWS dataset.

Improved Eagle Strategy Algorithm for Dynamic Web Service Composition in the IoT: A Conceptual Approach

The Internet of Things (IoT) is now expanding and becoming more popular in most industries, which leads to vast growth in cloud computing. The architecture of IoT is integrated with cloud computing through web services. Recently, Dynamic Web Service Composition (DWSC) has been implemented to fulfill the IoT and business processes. In recent years, the number of cloud services has multiplied, resulting in cloud services providing similar services with similar functionality but varying in Quality of Services (QoS), for instance, on the response time of web services; however, existing methods are insufficient in solving large-scale repository issues. Bio-inspired algorithm methods have shown better performance in solving the large-scale service composition problems, unlike deterministic algorithms, which are restricted. Thus, an improved eagle strategy algorithm method is proposed to increase the performance that directly indicates an improvement in computation time in large-scale DWSC in a cloud-based platform and on both functional and non-functional attributes of services. By proposing the improved bio-inspired method, the computation time can be improved, especially in a large-scale repository of IoT.

Multi-objective metaheuristic search algorithms for service composition in IoT

The basic idea behind the Internet of Things (IoT) is to connect every physical Thing to the Internet. IoT adds ability in Things to sense and communicate with other Things. One of the main concerns in IoT is forming an optimal service composition to fulfil the user requirements while balancing the quality of service (QoS) parameters. So, in this paper, the service composition problem in IoT has been addressed using multi-objective optimisation. An optimal solution to this problem has been provided through proposed novel hybrid and proposed algorithm Multi-Objective Hybrid Hyper-Heuristic Flower Pollination Algorithm (MOHHFPA). The superiority of this algorithm is proved by empirically and statistically comparing it with existing multi-objective algorithms, namely the Non-dominated Sorting Genetic Algorithm II (NSGA II), Multi-Objective Flower Pollination Algorithm (MOFPA), and the Multi-Objective Hyper-Heuristic Search Algorithm (MOHypEA). The proposed algorithm is empirically evaluated using a real-world case study.

Hybrid Metaheuristics Using Rough Sets for QoS-Aware Service Composition

Quality of Service (QoS)-aware service composition plays an increasingly important role in various computational paradigms and delivery models, predominantly cloud computing. The proliferation of services with expanding quality attributes navigates this problem towards big service compositions, which fall under the umbrella of NP-hard. Within the realm of big services, performing composition also became a computationally expensive and challenging task. Since service composition is an NP-hard problem, numerous research aimed to determine optimal or near-optimal solutions within a reasonable budget. A large body of evidence suggests that metaheuristics could realize this goal to some extent. However, the proliferation of services with expanding quality attributes (search dimensions) may fail the most efficient techniques. In order to deal with the problem of big service composition, one trending approach has been devising hybrid metaheuristics methods by incorporating clustering techniques to minimize search space. This paper proposes a hybrid metaheuristic incorporated with a maximal discernibility heuristic based on rough set theory to perform composition in the subset of search space. Moreover, it introduces a parallel architecture and monitoring mechanism to provide immunity against premature convergence when the search space is minimized. The experiment was conducted for 25 datasets generated incrementally from a real-world QWS dataset, where the proposed hybrid solution effectively improves solution quality and reduces execution time with a statistical significance of 99 % confidence interval across diverse metaheuristics and datasets.

Eagle strategy using uniform mutation and modified whale optimization algorithm for QoS-aware cloud service composition

Cloud manufacturing (CMfg) has received increasingly attention from both academia and industry. Cloud service composition is a critical technique in CMfg that connects different available manufacturing cloud services (MCSs) to generate a composite manufacturing cloud service (CMCS) to satisfy users’ requirements. Many available MCSs with the same or similar functionality but different QoS attributes are deployed in the CMfg platform. So it is challenging to obtain an optimal CMCS to satisfy the users’ complex requirements. Considerable numbers of approaches have been proposed to solve this problem. However, most of them often fall in a local optimum instead of the global one. In this paper, a novel eagle strategy using uniform Mutation and modified Whale Optimization Algorithm (MWOA) is proposed to maintain a balance between the global and local search abilities. In this approach, the uniform mutation is applied to perform the global search to preserve the diversification of the population, and a modified whale optimization algorithm is designed to perform the local search. The performance of the new approach is verified on various benchmark functions and different scales of QoS-aware cloud service composition problems. The experimental results demonstrate that the proposed MWOA has superior performance over the other methods.

A Hybrid Hyper-Heuristic Flower Pollination Algorithm for Service Composition Problem in IoT

Objectives: The modern science applications have non-continuous and multivariate nature due to which the traditional optimization methods suffer a lack of efficiency. Flower pollination is a natural interesting procedure in the real world. The novel optimization algorithms can be designed by employing the evolutionary capability of the flower pollination to optimize resources. Methods: This paper introduces the hybrid algorithm named Hybrid Hyper-Heuristic Flower Pollination Algorithm, HHFPA. It uses a combination of Flower Pollination Algorithm (FPA) and Hyper- Heuristic Evolutionary Algorithm (HypEA). This paper compares the basic FPA with the proposed algorithm named HHFPA. FPA is inspired by the pollination process of flowers whereas the hyper-heuristic evolutionary algorithm operates on the heuristics search space that contains all the heuristics to find a solution for a given problem. The proposed algorithm is implemented to solve the Quality of Service (QoS) based Service Composition Problem (SCoP) in Internet of Things (IoT). With increasing services with same functionality on the web, selecting a suitable candidate service based on non-functional characteristics such as QoS has become an inspiration for optimization. Results: This paper includes experimental results showing better outcomes to find the best solution using the proposed algorithm as compared to Basic FPA. Conclusion: The empirical analysis also reveals that HHFPA outperformed basic FPA in solving the SCoP with more convergence rates.

Optimized Artificial Bee Colony Algorithm for Web Service Composition Problem

Optimized Artificial Bee Colony Algorithm for Web Service Composition Problem

An Intelligent Web Service Composition and Resource-Optimization Method Using K-Means Clustering and Knapsack Algorithms

Service-oriented architecture (SOA) has emerged as a flexible software design style. SOA focuses on the development, use, and reuse of small, self-contained, independent blocks of code called web services that communicate over the network to perform a certain set of simple tasks. Web services are integrated as composite services to offer complex tasks and to provide the expected services and behavior in addition to fulfilling the clients’ requests according to the service-level agreement (SLA). Web service selection and composition problems have been a significant area of research to provide the expected quality of service (QoS) and to meet the clients’ expectations. This research paper presents a hybrid web service composition model to solve web service selection and composition problems and to optimize web services’ resource utilization using k-means clustering and knapsack algorithms. The proposed model aims to maximize the service compositions’ QoS and minimize the number of web services integrated within the service composition using the knapsack algorithm. Additionally, this paper aims to track the service compositions’ QoS attributes by evaluating and tracking the web services’ QoS using the reward function and, accordingly, use the k-means algorithm to decide to which cluster the web service belongs. The experimental results on a real dataset show the superiority and effectiveness of the proposed algorithm in comparison with the results of the state–action–reward–state–action (SARSA) and multistage forward search (MFS) algorithms. The experimental results show that the proposed model reduces the average time of the web service selection and composition processes to 37.02 s in comparison to 47.03 s for the SARSA algorithm and 42.72 s for the MFS algorithm. Furthermore, the average of web services’ resource utilization results increased by 4.68% using the proposed model in comparison to the resource utilization by the SARSA and MFS algorithms. In addition, the experimental results showed that the average number of service compositions using the proposed model improved by 26.04% compared with the SARSA and MFS algorithms.

Improved Hunting Search Algorithm for Web Service Composition Optimization

With the rapid development and application of Web services, the problem of Web service composition optimization based on Quality of Service (QoS) has become a research hotspot in the field of service computing. There are many researches on hunting search algorithm in continuous optimization problems, however, there are few researches using it to solve Web service composition optimization. In this paper, we propose an improvement on the hunting search algorithm (IHuS). It introduces an elite guidance strategy to accelerate the convergence of the algorithm, and at the same time it learns from the mutation strategy in the GA algorithm to improve the diversity of combined services. Compared with the standard HuS and GA algorithms, the experimental results demonstrate that IHuS has faster convergence speed and better optimization performance in solving large-scale Web service composition problems.

A novel hybrid algorithm for large-scale composition optimization problems in cloud manufacturing

ABSTRACT At present, with the emergence and development of cloud manufacturing (CMfg), the scale of services in CMfg platforms increases rapidly which provide the same or familiar functionality but different performance. Large-scale cloud service composition and optimization (CSCO) problems is one of the key issues for the implementation of CMfg. To deal with this NP-hard problem, a novel hybrid algorithm called Bee-Colony Simplex method hybrid Algorithm (ABCSA) for CSCO problems is proposed in this paper, which employs both the Simplex method and chaotic and global best guided strategy. The random-evolve Simplex method is proposed to maintain the algorithm work efficiently to keep the population diversity and avoid premature convergence. The global best guided and chaos searching strategy is proposed to avoid local optimization. To evaluate the effectiveness and efficiency, simulation and analysis of the experiments are carried out, and the results clearly prove the superior performance of ABCSA over existing intelligent optimization algorithms in the CSCO problems.

A fog‐based fault‐tolerant and QoE‐aware service composition in smart cities

AbstractNowadays, the smart city trend has attracted an important number of municipalities, enabling to control and manage smartly the city environment and provide the citizens with value‐added urban services. In this regard, Internet of Things and fog computing play a key role in providing smart city services, simplifying the decision making for city authorities and improving the quality of experience (QoE) for citizens. In this article, we address the problem of selecting appropriate urban service providers and their sequencing given the citizen request for a set of urban services (eg, banks, laundries, carwashes, gas stations, bakeries) considering a number of quality metrics. This latter can be translated into a service composition problem with the aim of optimizing the QoE of citizens, the load of service providers and the roads traffic. In such a context, the first contribution of this article consists of proposing a fog‐based fault‐tolerant architecture capable to address the scalability and reliability issues of smart cities, while processing efficiently and reactively the service composition requests of citizens. In addition, we map the QoE‐aware service composition problem in smart cities to a generalized traveling salesman problem and propose three metaheuristics based on genetic algorithms, particle swarm optimization, and artificial bee colony to solve this problem in a timely manner. The results obtained based on the developed prototype of our proposal demonstrate the superiority of our proposed approach compared with other existing service composition alternatives.

Defining IoT Orchestrations with Security and Privacy by Design: A Gap Analysis

Structured approaches to the definition of service orchestrations facilitate the composition of components and services and allow for more capable and powerful applications, while introducing many advantages such as service reusability, cost reduction, and simplification of organization alliances. A variety of such approaches exist in the literature, with more recent approcahes focusing on the IoT. Nevertheless, oftentimes security and privacy aspects are not adequately considered, which constitutes a significant barrier to the deployment of IoT applications and services with security and privacy built-in by design. The objective of this work is to provide an overview of service composition approaches, highlighting how the scientific community approaches the IoT service composition problem, while identifying the limitations of the current solutions in terms of catering to the security and privacy challenges. Furthermore, a novel approach for composing IoT systems with proven security and privacy properties is proposed.

Dynamic mutual manufacturing and transportation routing service selection for cloud manufacturing with multi-period service-demand matching.

Recently, manufacturing firms and logistics service providers have been encouraged to deploy the most recent features of Information Technology (IT) to prevail in the competitive circumstances of manufacturing industries. Industry 4.0 and Cloud manufacturing (CMfg), accompanied by a service-oriented architecture model, have been regarded as renowned approaches to enable and facilitate the transition of conventional manufacturing business models into more efficient and productive ones. Furthermore, there is an aptness among the manufacturing and logistics businesses as service providers to synergize and cut down the investment and operational costs via sharing logistics fleet and production facilities in the form of outsourcing and consequently increase their profitability. Therefore, due to the Everything as a Service (XaaS) paradigm, efficient service composition is known to be a remarkable issue in the cloud manufacturing paradigm. This issue is challenging due to the service composition problem’s large size and complicated computational characteristics. This paper has focused on the considerable number of continually received service requests, which must be prioritized and handled in the minimum possible time while fulfilling the Quality of Service (QoS) parameters. Considering the NP-hard nature and dynamicity of the allocation problem in the Cloud composition problem, heuristic and metaheuristic solving approaches are strongly preferred to obtain optimal or nearly optimal solutions. This study has presented an innovative, time-efficient approach for mutual manufacturing and logistical service composition with the QoS considerations. The method presented in this paper is highly competent in solving large-scale service composition problems time-efficiently while satisfying the optimality gap. A sample dataset has been synthesized to evaluate the outcomes of the developed model compared to earlier research studies. The results show the proposed algorithm can be applied to fulfill the dynamic behavior of manufacturing and logistics service composition due to its efficiency in solving time. The paper has embedded the relation of task and logistic services for cloud service composition in solving algorithm and enhanced the efficiency of resulted matched services. Moreover, considering the possibility of arrival of new services and demands into cloud, the proposed algorithm adapts the service composition algorithm.

A QoS-Aware Service Composition Mechanism in the Internet of Things Using a Hidden-Markov-Model-Based Optimization Algorithm

Recently, a new technology topic has been known as the Internet of Things (IoT), where all devices like smartphones, smart TVs, medical and healthcare ones, and home appliances have been applied for data generating. Due to the variety of services, the numerous service composition problems, mostly related to the Quality-of-Service (QoS) parameters, are recognized in the IoT domain. Since this issue is an NP-hard obstacle, different metaheuristic approaches have been utilized up until now to solve it. Many varieties of services can be brought into the IoT, depending on users’ demands. In this research, we have proposed an effective way based on a hidden Markov model (HMM) and an ant colony optimization (ACO) to answer the service composition issue by enhancing the QoS. The HMM has been trained to predict QoS. The emission and transition matrices have been improved using the Viterbi algorithm. We have executed the QoS estimation using the ACO algorithm and found a suitable path. The outcomes have illustrated the efficacy of the introduced method regarding availability, response time, cost, reliability, and energy consumption compared to the previous methods.

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.

SAIoT: Scalable Anomaly-Aware Services Composition in CloudIoT Environments

Among the novel IT paradigms, cloud computing and the Internet of Things (CloudIoT) are two complementary areas designed to support the creation of smart cities and application services. The CloudIoT not only presents ubiquitous services through IoT nodes but it also provides virtually unlimited resources through services composition. The services composition problem aims to find a set of services among functionally equivalent services with different Quality of Service (QoS) concerning users’ constraints. To this aim, previous studies calculate QoS values through service logs without considering the presence of anomalies in the existing QoS values; however, the dynamicity of distributed service environments and communication networks in CloudIoT environments causes anomalies in the QoS values. Therefore, existing approaches fail to model QoS values accurately that leads to service-level agreement (SLA) violation and penalties for service broker. To address this challenge, we propose a scalable anomaly-aware approach (SAIoT) including two main components: the first component models QoS values based on a machine learning anomaly detection technique, to remove the existing abnormal QoS records, and the second component finds a near-optimal composition by using an effective and efficient metaheuristic algorithm. The experimental results based on real-world data sets show that our approach achieves 30.64% of the average improvement in the QoS value of a composite plan with equal or even less price compared to the previous works, such as information theory-based and advertised QoS-based methods.

Color Revolution: A Novel Operator for Imperialist Competitive Algorithm in Solving Cloud Computing Service Composition Problem

In this paper, a novel high-performance and low-cost operator is proposed for the imperialist competitive algorithm (ICA). The operator, inspired by a sociopolitical movement called the color revolution that has recently arisen in some countries, is referred to as the color revolution operator (CRO). The improved ICA with CRO, denoted as ICACRO, is significantly more efficient than the ICA. On the other hand, cloud computing service composition is a high-dimensional optimization problem that has become more prominent in recent years due to the unprecedented increase in both the number of services in the service pool and the number of service providers. In this study, two different types of ICACRO, one that applies the CRO to all countries of the world (ICACRO-C) and one that applies the CRO solely to imperialist countries (ICACRO-I), were used for service time-cost optimization in cloud computing service composition. The ICACRO was evaluated using a large-scale dataset and five service time-cost optimization problems with different difficulty levels. Compared to the basic ICA and niching PSO, the experimental and statistical tests demonstrate that the ability of the ICACRO to approach an optimal solution is considerably higher and that the ICACRO can be considered an efficient and scalable approach. Furthermore, the ICACRO-C is stronger than the ICACRO-I in terms of the solution quality with respect to execution time. However, the differences are negligible when solving large-scale problems.