Using Big Data Analytics in Network Management

• Main Authors: TING, WEI-QUAN, 陳威全
• Other Authors: LEE, ZNE-JUNG
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/y2nb5e

碩士 === 華梵大學 === 資訊管理學系碩士班 === 106 === World Customs Organization (WCO) passed the “Framework of Standards to Secure and Facilitate Global Trade (WCO SAFE)”. According to the WCO SAFE, Executive also planed “Ubiquitous Economy and Trade Network Plan”. Customs Administration revised the procedure of customs automation software and Customs broker encountered problems such as network management, information security management and the evaluation of equipment performance in electrization operational procedures. In this thesis, a customs broker network operation center (CBNOC) is built based on software as a service (SaaS), Big Data, simple network management protocol (SNMP) and open-source software to provide equipment management, network topology, multiple regression analysis, and decision tree analysis. In multiple regressions, root mean square error (RMSE) and coefficient of determination (R2) for the flow of upload are 0.03334 and 0.9994, respectively. RMSE and R2 for the flow of download are 0.03334 and 0.9994, respectively. There are three modes, “standby,” “daily operation” and “cpu busy” that are generated from the flow results of decision tree. From the results, CBNOC could generate decision rules and find the problems of security management for users. Moreover, it could provide the decision-making for the evaluation of equipment performance.