A Data Processing and Distribution System Based on Apache Nifi

被引:2
作者
Wnek, Karol [1 ]
Borylo, Piotr [1 ]
机构
[1] AGH Univ Sci & Technol, Inst Telecomunicat, PL-30059 Krakow, Poland
关键词
Apache NiFi; big data; data processing; ETL;
D O I
10.3390/photonics10020210
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
The monitoring of physical and logical networks is essential for the high availability of 5G/6G networks. This could become a challenge in 5G/6G deployments due to the heterogeneity of the optical layer. It uses equipment from multiple vendors, and, as a result, the protocols and methods for gathering monitoring data usually differ. Simultaneously, to effectively support 5G/6G networks, the optical infrastructure should also be dense and ensure high throughput. Thus, vast numbers of photonic transceivers operating at up to 400 Gbps are needed to interconnect network components. In demanding optical solutions for 5G and beyond, enterprise-class equipment will be used-for example, high-capacity and high-density optical switches based on the SONiC distribution. These emerging devices produce vast amounts of data on the operational parameters of each optical transceiver, which should be effectively collected, processed, and analyzed. The aforementioned circumstances may lead to the necessity of using multiple independent monitoring systems dedicated to specific optical hardware. Apache NiFi can be used to address these potential issues. Its high configurability enables the aggregation of unstandardized log files collected from heterogenous devices. Furthermore, it is possible to configure Apache NiFi to absorb huge data streams about each of the thousands of transceivers comprising high-density optical switches. In this way, data can be preprocessed by using Apache NiFi and later uploaded to a dedicated system. In this paper, we focus on presenting the tool, its capabilities, and how it scales horizontally. The proven scalability is essential for making it usable in optical networks that support 5G/6G networks. Finally, we propose a unique optimization process that can greatly improve the performance and make Apache NiFi suitable for high-throughput and high-density photonic devices and optical networks. We also present some insider information on real-life implementations of Apache NiFi in commercial 5G networks that fully rely on optical networks.
引用
收藏
页数:19
相关论文
共 21 条
[1]  
Alvaro G., 2021, 5G FACILITY VALIDATI
[2]  
[Anonymous], 2010, TOT DAT VOL WORLDW 2
[3]   Big Data and Personalisation for Non-Intrusive Smart Home Automation [J].
Asaithambi, Suriya Priya R. ;
Venkatraman, Sitalakshmi ;
Venkatraman, Ramanathan .
BIG DATA AND COGNITIVE COMPUTING, 2021, 5 (01) :1-21
[4]  
Chanthakit S., 2019, 2019 RES INV INN C R, P1, DOI [10.1109/RI2C48728.2019.8999968, DOI 10.1109/RI2C48728.2019.8999968]
[5]  
Christo Petrov, 25 IMPRESSIVE BIG DA
[6]  
Cisco Annual Internet Report, 2018, White Paper
[7]   Stream Processing on Clustered Edge Devices [J].
Dautov, Rustem ;
Distefano, Salvatore .
IEEE TRANSACTIONS ON CLOUD COMPUTING, 2022, 10 (02) :885-898
[8]  
Gonzalez D, 2019, MEDD C EMBED COMPUT, P75
[9]  
Goscien R., 2022, PROC INT C OPT NETW, P1
[10]  
Haapalainen N., 2021, THESIS METROPOLIA U