AI Enables Intelligent Networks, Facilitating Efficient Operation of "Autonomous Evolution Networks"
With the virtual cloud transformation of telecommunications networks, the integration of 5G and IoT technologies, and the diversified development of industrial applications, the operation and maintenance of telecommunications networks are facing unprecedented challenges. Artificial Intelligence (AI) technology has natural advantages in solving such problems as high computing data analysis, cross-field feature mining and dynamic strategy generation. New models and capabilities for network operation and maintenance in the 5G era.
Ubiquitous AI Enablement Network Evolution
As a world-leading equipment vendor, ZTE has proposed the uSmartNet "autonomous evolution network" solution, with which the ubiquitous AI can realize the intelligence of the entire 5G network and enabler the comprehensive evolution of the network:
- One unified AI platform: The independently developed uSmartInsight AI platform provides all-round AI capability, supports mainstream in-depth learning and machine learning framework, has built-in 100+ all-domain network AI algorithm, supports visual zero programming AI model development, and makes scenario exploration easier.
- Three types of AI engines: AI engine, lightweight AI engine, and real-time AI engine, which match the full layers of operation, management and control, and NEs. They are embedded with a full range of 5G products in a modular manner to meet the ubiquitous intelligent requirements of the network.
- 60+ AI Scenario: Covers the whole service life cycle of planning, construction, maintenance, optimization and operation, and assists the operator in building efficient operation network.
ZTE uSmartNet Autonomous Evolution Network Solution
In terms of architecture, the uSmartNet "autonomous evolution network" solution adopts the principle of hierarchical and closed loop. Build an NE-level, single-domain, and cross-domain intelligent network architecture. The AI capability is designed in a modular manner, where the NE layer, management and control layer, and operation layer need to be embedded, and an autonomous evolution network with hierarchical evolution of capabilities and continuous superposition of values needs to be built. Through network evolution, O&M evolution, and operation evolution, network operation and O&M can be simplified to facilitate operators' open-source flow and improve efficiency.
- Network evolution: An AI is introduced to the NE layer to generate dynamic policies based on real-time perception and analysis of service scenarios and service operation statuses, so that resources can be scheduled and guaranteed as required to achieve the best match between network capabilities and user requirements.
- O&M evolution: The AI is introduced to the management and control layer to simplify network management and maintenance based on comprehensive information perception, analysis, and decision making. In this way, machines can take repeated work step by step, reduce the workload of O&M personnel, improve O&M efficiency, and reduce O&M costs.
- Operation evolution: AI is introduced at the Operations Management layer to construct the end-to-end intelligent closed loop driven by intention, so as to improve the service capability of the user in an all-round way, implement fast user-oriented service response and intention guarantee, and continuously increase service revenue.
" Autonomous Evolution Network" Boosts Efficient Operation
In terms of application scenarios, the independently-evolved network can provide operators with a series of network AI solutions in more than 60 scenarios, covering the full service lifecycle of network planning, construction, O&M, optimization, and operation.
- Network planning: Rapidly identify valuable areas and areas that users intend to suppress, and release traffic through fast capacity expansion and capacity balancing.
- Network construction: The Automatic Integration Center (AIC) platform implements intelligent design, one-click installation and deployment, and automatic tests, and reduces the skill requirements of personnel by one level.
- Network maintenance: Take work orders as the main line, and use intelligent policies and tools to improve troubleshooting efficiency.
- Network optimization: The LION intelligent network optimization solution is basically implemented without manual intervention. It features fast self-evaluation, efficient self-decision and precise self-optimization, and achieves accurate prediction in advance.
- Network operation: Actively identifies unsatisfied users and cells, provides guidance for active optimization, guarantees VIP care for VAP users, and achieves active O&M of user experience.
- Operation energy saving: Based on AI traffic prediction, smart scenario identification, and smart shutdown, flexible power saving modes, power saving time, and differentiated thresholds can be set. Compared with the traditional manual energy saving method, the application time of the base station power saving function based on AI intelligent algorithm is increased by over 80% on average, and the power consumption is reduced by 10%.
ZTE has worked with domestic and foreign operators to carry out intelligent network verification on more than 20 commercial and pilot sites, and has achieved stage-by-stage results. In the field of network intelligence, ZTE will continue to invest in research and innovation to provide operators with all-round professional support for 5G network construction and intelligent network development, and to help operators build efficient, green, energy-saving, and secure and reliable intelligent networks.