物联网环境下QoS驱动的服务组合能量优化研究  

Research on Service Composition Energy Optimization Method Driven by QoS Within IoT Context

作　　者：付佳 李爱萍 段利国 王舒漫 赵菊敏 FU Jia;LI Ai-ping;DUAN Li-guo;WANG Shu-man;ZHAO Ju-min(College of Information and Computer,Taiyuan University of Technology,Taiyuan 030000,China)

机构地区：[1]太原理工大学信息与计算机学院,太原030000

出　　处：《小型微型计算机系统》2020年第9期1912-1917,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金面上项目(61972273)资助。

摘　　要：物联网设备由于其有限的计算能力和存储能力,单个设备通常不能满足相对复杂的用户需求,集成和组合智能对象、函数或它们的服务是创建和促进具有高级功能的更复杂的物联网应用所必需的,通过组合这些原子服务来提供单一服务所不能提供的新功能.综合以上特点,建立物联网能量优化模型;结合物联网数据信息与地理位置密切相关的特点,利用位置信息进行局部优选,缩小候选服务范围;为解决QoS性能和能源消耗之间的负载均衡问题,本文中提出一种自适应的目标函数值计算方法;考虑到物联网环境下服务组合是一个NP难问题,将此过程简化成为一个多目标优化问题,并利用启发式算法进行求解.实验结果表明,该方法在保持合理的QoS水平的同时,可以获得良好的能耗性能和网络寿命.The Internet of things(IoT)device are resource constrained with very limited computation and storage capacities,and a single device usually cannot meet relatively complex user requirements.Integrating and composing smart objects functions or their services is necessary to create and promote more complex IoT applications with advanced capabilities.Provide a new feature that cannot be provided by a single service through a combination of these atomic services.Based on the above characteristics,an IoT energy optimization model is established.We use location information for local optimization by combining the characteristics of IoT data information related to geographical location to narrowing the scope of candidate services.In order to find a good balance between the QoS and energy consumption,an adaptive objective function value calculation method is proposed in this paper.QoS-aware services composition is known to be an NP-hard problem.In this work,we thought of the process as a multi-objective optimization problem,and used heuristic algorithm to solve the problem.Experimental results show that it can obtain good performance in energy consumption and network lifetime while maintaining a reasonable QoS level.

关 键 词：物联网服务 服务组合 能量优化 多目标优化 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]