基于PROMETHEE的云服务推荐:一种多目标决策方法

Service recommendation in cloud:multi-criteria decision making approach based on PROMETHEE

在开放的云计算背景下,面对众多功能相同或相近但QoS属性不同的服务,用户需要有效的推荐方法支持其对服务的选择和决策。针对面向SLA的云服务推荐问题以及传统方法的不足,提出了一个二级服务评价模型,其中在帕累托优化的基础上引入PROMETHEE方法,针对帕累托最优解实现更为精确的量化评价。根据所提出的二级评价模型,提出并实现了一个基于BNL的服务推荐算法,高效地返回PROMETHEE意义上的Topk帕累托最优解,从而为用户的最终优选和决策提供有效的支持。最后,通过一组实验验证了算法的效率和有效性。

This paper addressed the SLA oriented service recommendation problem in cloud computing environment. Considering main drawbacks of traditional approaches,this paper presented a novel hybrid service ranking model,in which the PROMETHEE method was leveraged on the basis of Pareto optimization,to implement further ranking and selection of Pareto optimal solutions. Based on the proposed hybrid ranking model,it proposed a service recommendation algorithm to efficiently find Top-k Pareto optimal solutions according to their PROMETHEE ranking values. A set of experimental studies evaluate the effectiveness and efficiency of our proposed algorithm.