If you need help, please click here:

Why Do We Need Intelligent IP Networks?

Predicted by Huawei's Global Industry Vision 2025

Over the last 30 years, Internet Protocol (IP) networks have evolved, significantly improving bandwidth, the overall experience, and the efficiency of Operations and Maintenance (O&M). Indeed, a suite of new service applications has ushered in a new generation of technology.

If the 1990s marked the beginning of the Internet IP era — when the World Wide Web first emerged — a good service experience for the earliest Internet users simply meant being able to stably connect to the network. To be globally reachable, networks of the period only needed basic interconnection.

Move forward to 2005 and video services — such as Internet Protocol Television (IPTV) — began developing rapidly. Raw IP-based networks were no longer able to carry these considerably more demanding services. Coupled with a gradual increase in network scale, manual O&M methods desperately needed a revamp. Additionally, driven by the IP-based development of various new services, networks were gradually becoming fully IP-based, marking the start of the all-IP era for the industry.

Today, the arrival of 5G and the cloud has accelerated enterprise digitalization and intelligentization, gradually converging office and production services. As networks carry more applications, both network scale and complexity are increasing, leading to more challenges in terms of network planning, construction, maintenance, and optimization.

But the era of intelligent IP networks has only just begun.

What Is an Intelligent IP Network?

Huawei is a leader in introducing big data, Artificial Intelligence (AI), and next generation protocols to IP networks, redefining data analytics and closed-loop optimization to enable the leap to intelligent IP networks.

For Huawei, intelligent IP networks have three key characteristics.

Super capacity is the ultimate goal of intelligent IP network development, with a range of applications — from video and remote working solutions to cloud computing, and AI —driving a new wave of growth in network bandwidth. Campus networks are upgrading to Wi-Fi 6 and 100 GE switches, while data centers and IP backbone networks are already heading towards 400 GE. With advancement in physical layer performance, and emerging network slicing technologies — such as FlexE — enterprises are able to use bandwidth more flexibly and efficiently. This makes it feasible to enjoy multiple services — including office, production, and computing — on one physical network. Moreover, hard bandwidth isolation between different service traffic provides 100% committed bandwidth for key services in vertical industries, enterprise production networks, and carrier IP private lines. The ability to intelligently adjust slice bandwidth enables flexible adjustment of ultra-broadband networks based on service changes, better meeting service requirements.

If an intelligent experience is the foundation of intelligent IP network architecture, current IP networks have many uncertainties, both in terms of demand and supply. On the demand side, services and networks can't negotiate properly, and the service layer does not define clear expectations — service intents — for the network layer. In terms of supply, the IP network is statistically multiplexed, and as services and traffic change, so too does network resource usage. To eliminate demand-side uncertainties, service intents need to be accurately sensed. The service layer can then notify the network layer about service requirements; or the network layer can deduce expectations for connection services by analyzing service traffic behavior — a service model — to proactively identify terminals, users, and service types. In addition, the network management, analysis, and control platform eliminates supply uncertainties by using AI algorithms — such as neural networks — to build network models, detect and analyze network status in real-time, and understand network resource usage. An intelligent experience also entails matching service intents with network resources to provide ongoing connection services that meet service expectations at minimal cost, achieving the goal of an application-driven experience.

Autonomous driving is key to improving the user experience. Traditional complaint-driven approaches pose significant challenges to network O&M. For instance, network O&M departments are usually the last to know about network problems, and therefore the user experience cannot be guaranteed. Instead, predictive O&M is required in the fast-moving environment of today. Network status needs to be detected in real-time to determine whether network problems or potential risks exist. Paired with fault model matching, root causes can be accurately located, with faults automatically rectified. This ultimately helps resolve network issues before they affect the user experience, preventing services from being impacted.

idn img en 03

For Partners

If you are already a Partner, please click here to get more marketing resources.
Click here to visit the Partner zone to check enquiry status, manage orders, get support, or learn more about Huawei Partners.