Reconfiguration decision making in cognitive wireless network  

作　　者：ZHANG Ping HE Qian FENG ZhiYong ZHANG QiXun 

机构地区：[1]Wireless Technology Innovation Institute(WTI),Key Laboratory of Universal Wireless Communications of Ministry of Education Beijing University of Posts and Telecommunications,Beijing 100876,China

出　　处：《Chinese Science Bulletin》2012年第28期3713-3722,共10页

基　　金：supported by the National Basic Research Program of China (2009CB320400);the National Natural Science Foundation of China(60832009,61121001);the National Science and Technology Major Project of China (2012ZX03003006)

摘　　要：Facing the challenges of dynamic adaptation capabilities in the time-varying environment of cognitive wireless networks(CWNs),we introduce reconfiguration capabilities that flexibly and dynamically adapt to changing wireless environments and service requirements.As an essential characteristic of CWNs,the cognitive reconfiguration can meet user requirements,realize interoperability between heterogeneous networks,make full use of radio resources and adapt to time-varying environments to achieve end-to-end requirements.However,the reconfiguration implementation is still challenging due to the need for complex environment cognition,multi-objective optimization,autonomic decision-making and end-to-end requirement extraction.As an intelligent technology for solving complex issues,we apply adaptive neuro-fuzzy inference system(ANFIS) techniques in this paper to address these challenges in cognitive reconfiguration for self-learning and optimal decision making based on multi-domain cognition results.Moreover,this paper designs a generic ANFIS cognitive reconfiguration system including three functional entities,which are the context management module,multi-domain database and ANFIS optimization module.Finally,numerous results prove the effective performance improvements of the ANFIS based reconfiguration solution in CWN for global end-to-end goals.Facing the challenges of dynamic adaptation capabilities in the time-varying environment of cognitive wireless networks （CWNs）, we introduce reconfiguration capabilities that flexibly and dynamically adapt to changing wireless environments and service re- quirements. As an essential characteristic of CWNs, the cognitive reconfiguration can meet user requirements, realize interopera- bility between heterogeneous networks, make full use of radio resources and adapt to time-varying environments to achieve end-to-end requirements. However, the reconfiguration implementation is still challenging due to the need for complex environ- ment cognition, multi-objective optimization, autonomic decision-making and end-to-end requirement extraction. As an intelli- gent technology for solving complex issues, we apply adaptive neuro-fuzzy inference system （ANFIS） techniques in this paper to address these challenges in cognitive reconfiguration for self-learning and optimal decision making based on multi-domain cogni- tion results. Moreover, this paper designs a generic ANFIS cognitive reconfiguration system including three functional entities, which are the context management module, multi-domain database and ANFIS optimization module. Finally, numerous results prove the effective performance improvements of the ANFIS based reconfiguration solution in CWN for global end-to-end goals.

关 键 词：配置系统 优化决策 无线网络 自适应神经模糊推理系统 ANFIS 适应能力 时间变化 网络环境 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TN92[自动化与计算机技术—控制科学与工程]