摘要
2019年是我国5G商用元年,2020年各大运营商发力“新基建”,在全国大规模开展了5G网络建设。网络广覆盖、深覆盖,需要运行商扩建、新建大量的基站网络资源。加速5G站点建设、开通成了主旋律,随之而来的大量工程站入网开通、转维验收扑面而来。5G基站验收转维具有“接收量大”、“质量控制点多”、“调测规范要求高”、“多工种立体化同步展开”、“验收入网周期短”等特点,以现有的维护人力无法应对5G网工程转维的“浪涌”模式,运维人员压力巨大。中国移动适时提出了“推进网络运维的智能化,深化集中运维,完善端到端,自动化,云网一体的运维体系”战略目标。基于遇到的5G基站验收转维工作瓶颈,为提升5G基站验收入网转维工作效率,网络运维向“人工智能化”、“云网一体”的演进势在必行。
2019 is the first year of China’s 5G commercial,In 2020,major operators will build“new infrastructure”and carry out large-scale 5G network construction throughout the country.Network coverage,deep coverage,need to expand the operating company,a large number of new base station network resources.Speed up the construction of 5G site,opening has become the main theme,followed by a large number of project stations into the network opening,the transfer of acceptance came.5G base station acceptance and transfer has the characteristics of“large reception volume”,“many quality control points”,“high specification requirements”,“multi-work threedimensional simultaneous expansion”,“short cycle of income verification network”and so on,with the existing maintenance manpower can not cope with the 5G network project transfer“surge”mode,operation and maintenance personnel pressure is enormous.China Mobile timely put forward the strategic goal of“promoting the intelligent operation and operation of the network,deepening the centralized operation and development,perfecting the end-toend,automation,cloud network integrated operation and operation and development system”.Based on the bottleneck of 5G base station acceptance transfer work encountered,in order to improve the efficiency of 5G base station inspection revenue network transfer,the evolution of network operation and support to“artificial intelligence”and“cloud network as one”is imperative.
作者
施建荣
曹烨辉
施君宇
SHI Jian-rong;CAO Ye-hui;SHI jun-yu(China Mobile Group Jiangsu Co.,Ltd.,Nanjiang 210029,China;China Mobile(Suzhou)Software Technology Co.,Ltd.,Suzhou 215000,China)
出处
《通信电源技术》
2020年第S01期282-287,共6页
Telecom Power Technology
关键词
人工智能
工程转维
效能
artificial intelligence
engineering-to-maintenance
efficiency