求解Web服务组合QoS优化的多属性决策及自适应遗传算法

Multi-attribute Decision Making and Adaptive Genetic Algorithm for Solving QoS Optimization of Web Service Composition

随着面向服务计算(Service-oriented Computing,SOC)的不断发展,基于服务质量(Quality of Service,QoS)的Web服务组合研究成为了必然趋势。鉴于QoS属性的多维性及相互矛盾性,提出将基于QoS的Web服务组合优化问题转化为多属性决策问题进行求解。采用折中系数对每个组合服务实例到正负理想点的距离进行累加求和,最终得到一组最优服务排序结果,用户可以根据自身偏好进行选择。传统的多属性决策方法无法有效地处理大规模的组合服务搜索空间,因此,为了有效地解决Web服务组合优化这一NP难题,提出一种结合多属性决策方法和自适应遗传算法的新型优化算法来解决该问题。实验采用真实的QoS综合服务数据集进行验证,实验结果表明,该方法能够在较短时间内找到全局近似最优解,且解集的排序结果接近于实际的最优服务排序。同时,该方法对于解决大规模的Web服务组合优化问题具有良好的可伸缩性。

With the increasing of service-oriented computing,the research on Web service composition based on quality of service(QoS)becomes an inevitable trend.With respect of the multi-dimensional nature and mutual contradiction,this paper transformed the optimization of Web service composition based on QoS into the problem of multi-attribute decision making to resolve it.The distances of each solution to the positive ideal solution(PIS)and the negative ideal solution(NIS)were summed up by means of a compromise coefficient.Finally,a set of ranked Web services were provided to users for a flexible choice.The traditional multi-attribute decision making method can not effectively solve the large-scale search space of Web service composition.Therefore,in order to solve the NP-hard problem of Web service composition optimization better,this paper developed an approach combining the multi-attribute decision making and adaptive genetic algorithm(MADMAGA).The experiments were conducted on a real and comprehensive QoS dataset.The experimental results indicate that the method can find the globally optimal solution in a short period of time.The ranking result of solutions is close to the true sort.Moreover,the proposed method has better scalability for solving the large-scale problem of Web service composition optimization.