The 5G vision is predicated on two key objectives: delivering on low latency and guaranteeing high reliability. The buildout of 5G infrastructures and the move to a far more dynamic service delivery environment necessitates that operators make a shift in traditional thinking when it comes to the role of artificial intelligence in network operations.
Fundamentally, 5G is all together a different beast – From cloudified networking to edge computing to network slicing, rapidly changing service concepts and new business models require a far more autonomous data processing framework to be put in place. As operators have long toiled with the migration between Gs, the demands of 5G delivery present an invaluable opportunity to overhaul thinking and redesign architectures to embed efficiencies into the very fabric of the network going forward.
The sheer volume and velocity of data traversing the network in a 5G environment demands that automation be woven into the fibre of network operations. Without the ability for the network to predict sudden changes in traffic demands, security risks and user behaviour – to name but a few – 5G service delivery will simply not be achievable. Networks must be at their very core anticipatory and proactive in order to deliver on ultra-reliability when it comes to service continuity.
As noted by Mehdi Bennis of the CWC, “5G and machine learning go hand in hand. Without machine learning, networks simply cannot predict. Without the ability to predict, applications like remote surgery and wireless virtual reality cannot happen.” At present, 4G networks are reactive in their functioning. Whereas, 5G networks are required to be predictive, proactive and anticipatory to enable low latency and high reliability applications. Machine learning allows for networks to self-optimise by enabling systems to autonomously manage performance and QoS, while driving analytics-based decisioning.
Ultimately, it’s all about going back to the fundamentals. 5G heralds a new approach to how networks deliver and it is by leveraging machine learning techniques that operators will realise the true innovation potential of 5G.