QoS-aware Service Composition Problem Research Articles

A Diffraction Service Composition Approach Based on S-ABCPC

In recent years, research on the QoS-aware service composition problem often assumes that each component service in the process to be solved is equally essential. They do not consider the impact of core component services and other component services on problem-solving, or even though their impact is considered, they are not fully considered. So this paper first proposes a diffractive method based on them. Considering the advantages of artificial bee colony (ABC) such as simplicity, this paper chooses it as the basic algorithm. In addition, with the continuous development of service ecosystem, it gradually formed a variety of domain features. They have an important influence on problem-solving, but the existing research has not explored this influence in-depth. Therefore, this paper digs deep into this influence. Given the characteristics of the problem to be solved in this paper, the S-ABCPC algorithm is designed. At last, experiments have proved the effectiveness of the method proposed in this paper. The impact factors of this method have been studied.

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.

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.

Parameter Tuning for S-ABCPK

QoS-aware service composition problem has been drawn great attention in recent years. As an NP-hard problem, high time complexity is inevitable if global optimization algorithms (such as integer programming) are adopted. Researchers applied various evolutionary algorithms to decrease the time complexity by looking for a near-optimum solution. However, each evolutionary algorithm has two or more parameters, the values of which are to be assigned by algorithm designers and likely have impacts on the optimization results (primarily time complexity and optimality). The authors' experiments show that there are some dependencies between the features of a service composition problem, the values of an evolutionary algorithm's parameters, and the optimization results. In this article, the authors propose an improved algorithm called Service-Oriented Artificial Bee Colony algorithm considering Priori Knowledge (S-ABCPK) to solve service composition problem and focus on the S-ABCPK's parameter turning issue. The objective is to identify the potential dependency for designers of a service composition algorithm easily setting up the values of S-ABCPK parameters to obtain a preferable composition solution without many times of tedious attempts. Eight features of the service composition problem and the priori knowledge, five S-ABCPK parameters and two metrics of the final solution are identified. Based on a large volume of experiment data, S-ABCPK parameter tuning for a given service composition problem is conducted using C4.5 algorithm and the dependency between problem features and S-ABCPK parameters are established using the neural network method. An experiment on a validation dataset shows the feasibility of the approach.

An interval-based multi-objective artificial bee colony algorithm for solving the web service composition under uncertain QoS

Most of the existing works addressing the QoS-aware service composition problem (QoSSCP) are based on the assumption of fixed quality of service (QoS) characteristics of elementary web services. However, in the real world, some QoS criteria may be imprecise for many unexpected factors and conditions. Therefore, when dealing with QoSSCP, we must consider the uncertain proprieties of QoS. Moreover, very few studies propose multi-objective solutions for solving the QoSSCP, and there is no multi-objective algorithm solving the QoSSCP under uncertain QoS, in which the non-deterministic values of the QoS attributes are expressed as interval numbers. To resolve this issue, we formulate an interval-constrained multi-objective optimization model to the QoSSCP, and we propose a novel interval-based multi-objective artificial bee colony algorithm (IM_ABC) to solve the suggested model. To deal with the interval-valued of objective functions, we define an uncertain constrained dominance relation for ordering solutions in which the performance and stability are simultaneously considered. As inspired by Deb’s feasibility handling constraints, a new interval-based feasibility technique is proposed to deal with interval constraints. In order to control the diversity of the non-dominated solutions obtained by IM_ABC, the original crowding distance of NSGA-II is extended and adopted to the uncertain QoSSCP by incorporating to it a new interval distance definition. Based on real-world and random datasets, the effectiveness of the proposed IM_ABC has been verified through multiple experiments, where the comparison results demonstrates the superiority of IM_ABC compared to the recently proposed interval-based multi-objective optimization algorithms IPMOPSO, IPMOEOA, and MIIGA as well as a recently introduced interval-based fuzzy ranking single-objective GAP approach.

Optimising web service composition based on differential fruit fly optimisation algorithm

With the emergence of a large number of web services with similar functional but different non-functional attributes, how to select appropriate web services from massive candidate services and assemble them into service composition which can complete the complex value-added business process is of great concern. The problem of QoS-aware service composition belongs to the multi-objective decision optimisation problem. Its goal is to optimise QoS of the entire service composition. To solve this problem, this paper presents a differential fruit fly optimisation algorithm DFOA. Firstly, make fast global optimisation through FOA. Then, perform the local search in the neighbourhoods of global optimisation solution based on fruit fly swarm differential mutation and crossover operation. Finally, update the global optimal solution according to the two optimisation results, thereby obtaining the optimal service composition. The experiment verifies the feasibility of the algorithm.

An efficient and reliable approach for quality-of-service-aware service composition

With the rapidly increasing number of independently developed Web services that provide similar functionalities with varied quality of service (QoS), service composition is considered as a problem in the selection of component services that are in accordance with users’ QoS requirements; a practice known as the QoS-aware service composition problem. However, current solutions are unsuitable for most real-time decision-making service composition applications required to obtain a relatively optimal result within a reasonable amount of time. These services are also unreliable (or even risky) given the open service-oriented environment. In this paper, we address these problems and propose a novel heuristic algorithm for an efficient and reliable selection of trustworthy services in a service composition. The proposed algorithm consists of three steps. First, a trust-based selection method is used to filter untrustworthy component services. Second, convex hulls are constructed to reduce the search space in the process of service composition. Finally, a heuristic global optimization approach is used to obtain the near-optimal solution. The results demonstrate that our approach obtains a close-to-optimal and reliable solution within a reasonable computation time.

E³: A Multiobjective Optimization Framework for SLA-Aware Service Composition

In Service-Oriented Architecture, each application is often designed as a set of abstract services, which defines its functions. A concrete service(s) is selected at runtime for each abstract service to fulfill its function. Since different concrete services may operate at different quality of service (QoS) measures, application developers are required to select an appropriate set of concrete services that satisfies a given Service-Level Agreement (SLA) when a number of concrete services are available for each abstract service. This problem, the QoS-aware service composition problem, is known NP-hard, which takes a significant amount of time and costs to find optimal solutions (optimal combinations of concrete services) from a huge number of possible solutions. This paper proposes an optimization framework, called E^3, to address the issue. By leveraging a multiobjective genetic algorithm, E^3 heuristically solves the QoS-aware service composition problem in a reasonably short time. The algorithm E^3 proposes can consider multiple SLAs simultaneously and produce a set of Pareto solutions, which have the equivalent quality to satisfy multiple SLAs.