Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (8): 2114-2120.DOI: 10.11772/j.issn.1001-9081.2016.08.2114

Previous Articles     Next Articles

Performance optimization of wireless network based on canonical causal inference algorithm

HAO Zhifeng1,2, CHEN Wei1, CAI Ruichu1, HUANG Ruihui3, WEN Wen1, WANG Lijuan1   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou Guangdong 510006, China;
    2. School of Mathematics and Big Data, Foshan University, Foshan Guangdong 528000, China;
    3. Guangdong Southern Communication Construction Company Limited, Guangzhou Guangdong 510630, China
  • Received:2016-01-20 Revised:2016-04-28 Online:2016-08-10 Published:2016-08-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61375039), the Program (135 Program) of Computer Network Information Center, Chinese Academy of Sciences (CNIC_PY_1402).

基于典型因果推断算法的无线网络性能优化

郝志峰1,2, 陈薇1, 蔡瑞初1, 黄瑞慧3, 温雯1, 王丽娟1   

  1. 1. 广东工业大学 计算机学院, 广东 广州 510006;
    2. 佛山科学技术学院 数学与大数据学院, 广东 佛山 528000;
    3. 广东南方通信建设有限公司, 广东 广州 510630
  • 通讯作者: 陈薇
  • 作者简介:郝志峰(1968-),男,江苏苏州人,教授,博士,CCF会员,主要研究方向:机器学习、人工智能;陈薇(1993-),女,广东潮州人,硕士研究生,主要研究方向:机器学习;蔡瑞初(1983-),男,浙江温州人,教授,博士,CCF高级会员,主要研究方向:数据挖掘、机器学习、信息检索;黄瑞慧(1979-),女,广东广州人,硕士研究生,主要研究方向:移动无线网络优化、网络数据挖掘、数据建模;温雯(1981-),女,江西赣州人,副教授,博士,CCF会员,主要研究方向:机器学习、模式识别、信息检索;王丽娟(1978-),女,河北邢台人,讲师,博士,主要研究方向:机器学习、高维数据聚类分析。
  • 基金资助:
    NSFC-广东联合基金资助项目(U1501254);国家自然科学基金资助项目(61472089,61572143);广东省自然科学基金资助项目(2014A030306004,2014A030308008);广东省科技计划项目(2013B051000076,2015B010108006,2015B010131015);河北省高等学校科学技术研究项目(QN2014165)。

Abstract: The existing wireless network performance optimization methods are mainly based on the correlation analysis between indicators, and cannot effectively guide the design of optimization strategies and some other interventions. Thus, a Canonical Causal Inference (CCI) algorithm was proposed and used for wireless network performance optimization. Firstly, concerning that wireless network performance is usually presented by numerous correlated indicators, the Canonical Correlation Analysis (CCA) method was employed to extract atomic events from indicators. Then, typical causal inference method was conducted on the extracted atomic events to find the causality among the atomic events. The above two stages were iterated to determine the causal network of the atomic events and provided a robust and effective basis for wireless network performance optimization. The validity of CCI was indicated by simulation experiments, and some valuable causal relations of wireless network indicators were found on the data of a city's more than 30000 mobile base stations.

Key words: Canonical Correlation Analysis (CCA), causal inference, Linear Non-Gaussian Acyclic Model (LiNGAM), wireless network performance optimization

摘要: 现有的无线网络性能优化方法主要基于指标间的相关关系分析,无法有效指导网络优化等干预行为。为此,提出典型因果推断(CCI)算法,并将其应用于无线网络性能优化。首先,针对无线网络性能由大量相关指标体现这一特性,采用典型相关分析(CCA)方法,提取指标中蕴含的原子事件;然后再采用因果推断方法,构建原子事件间的因果关系网络。通过上述两个阶段反复迭代,确定原子事件间的因果关系网络,为无线网络性能优化提出一个较为可靠和有效的依据。最后通过模拟实验验证了CCI算法的有效性,在某城市3万多个移动基站数据上发现了一批有意义的无线网络指标间的因果关系。

关键词: 典型相关分析, 因果推断, 线性非高斯非循环模型, 无线网络性能优化

CLC Number: