Predictive analytics for networks are helping businesses optimize their network performance, anticipate network capacity related requirements, and eventually forecast future much more efficiently than ever. Gartner has estimated the value of network monitoring software market at roughly $2.1 Billion, this figure is presently increasing at a growth rate of 15.9% annually. The demand for predictive analytics in network monitoring software has grown beyond enterprises and datacentres.

Most of existing IPHost monitor types are passive, meaning they are being polled by IPHost – directly, or via remote network agent. There are two “active” monitors, that perform “Event” type alert, when receiving data from remote host: Syslog monitor and SNMP Generic Trap monitor. Although it’s not possible to transform all possible passive monitors to active, there are several approaches to make monitoring nearly real-time in certain situations.

The issue of network baseline arose quite some time ago. Everything started from the understanding that networks are not static entities, but are a set of elements that change over time. It was also understood that networks are not only made up of physical and tangible elements, such as a router or a switch, but we must also have more abstract elements, such as the traffic pattern over a WAN link, for example.