Communications networks are perhaps the most complex machines on the planet. They use vast amounts of hardware, rely on complex software, and are physically distributed over land, underwater, and in orbit. They increasingly provide essential services that underpin almost every aspect of life. Managing networks and optimising their performance is a vast challenge, and will become many times harder with the advent of 5G. The 4th Annual CW Technology Conference will explore this challenge and how Machine Learning and AI may be applied to build more reliable, secure and better performing networks.
Is the AI community aware of the challenges facing network providers? Are the network operators and providers aware of how the very latest developments in AI may provide solutions? The conference will aim to bridge the gap between AI/ML and communications network communities, making each more aware of the nature and scale of the problems and the potential solutions.
This one day conference, held at the University of Cambridge Computer Lab on September 27th 2018, is aimed at data scientists and network engineers in universities, infrastructure suppliers, and software providers.
What is it that makes communications networks so hard to manage?
- They use a wide range of technologies ranging from physical transmission through switching and networking to high-level applications and distributed computing.
- Wireless access is becoming preferred both by human users and for machines, using local and wide-area networks including cellular and satellite and bandwidth from a few kilobits to gigabits per second.
- Multiple systems have to interwork - multinational IP and cloud; national fixed and mobile networks; local networks at home; shared neutral host networks; fixed and wireless in-building networks; cellular networks with roaming.
But users naturally expect to all these to frictionlessly work together, all the time, and give a great experience. End to end services are expected to work irrespective of the networks that deliver them and require widely varying performance characteristics, from low-latency real-time control to high capacity data transmission. And all of it requires high levels of security. The move to virtualisation and integration of local and self-built networks is making the picture even more complex. Somehow network operators have to manage, control, configure, and maintain all of this.
Automation is therefore no longer a nice-to-have but essential for operating the network.
The move to distributed computing, and technologies around data collection, mining and management bring opportunities to solve these problems. How can machine learning and AI tools build more reliable, secure and better performing networks?
About the CW Technology & Engineering Conference
The annual CW TEC provides a vibrant and dynamic form for harnessing knowledge, driving lively debate and networking at a senior level. It offers a more low-level, technical and focused agenda than the International Conference, exploring an emerging problem space that the CW community has highlighted as being particularly worthy of debate. Past event topics have included quantum computing and the impact on spectral value of mobile, satellite, TV, IoT and wearable technologies. The conference format and agenda is driven by the CW membership and this year the organising committee includes Steve Unger, John Haine, Sylvia Lu, Paul Ceely, Phil Claridge and Zahid Ghadialy.