“Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome.”
Class synopsis for Stanford’s Machine Learning course on Coursera.
In a recent post, we discussed the complexity of managing virtualised networks. When we combine the device multiplication effect of network virtualisation (eg NFV / SDN) and IoT (Internet of Things), we’re on the verge of a touch-point explosion. OSS and related management suites will have device numbers to manage that are multiple times greater than today (even if via NMS/EMS or equivalents).
The human operator is already unable to identify all the important events and correlations that are taking place in even small, simple networks, so the larger, more complex networks of the future will be even more challenging. This is where computer assisted diagnosis and learning will be so important.
Predictive analysis, pattern matching, root-cause, efficiency optimisation and many other artificial learning algorithms will be fundamental building blocks of future OSS. If you don’t already have this capability within your OSS, what’s your roadmap for getting there soon?
Another interesting point to note around this touch-point explosion is how your OSS is licensed. Are you charged licensing fees based on number of devices managed?Read the Passionate About OSS Blog for more or Subscribe to the Passionate About OSS Blog by Email