Bwtech, a provider of end-to-end performance monitoring and optimisation solutions for the mobile communication industry, announced the launch of an innovative tool, NetWarden.
The new tool takes advantage of state-of-the-art AI/ML algorithms to correlate all the data sources collected from across the network in order to automatically provide actionable insights for network monitoring, optimisation and troubleshooting.
The first automation step begins by identifying network anomalies across the thousands of network elements. Utilising propriety Machine Learning Anomaly Detection algorithms, real network issues are identified, based on historical behavior of each Network Element and each Performance Indicator.
NetWarden then automatically correlates multiple data sources such as the alarm, configuration and performance data along with the logically related network elements to discover and identify the probable root causes of the anomalies, root causes that are extremely difficult to identify using traditional engineering techniques.
Finally, the tool proposes a course of action for fast and effective resolution of issues. On the whole, NetWarden reduces the average time taken for the network monitoring, troubleshooting and optimisation process by around 90%.
The new Bwtech’s tool allows network engineers to monitor, optimise and troubleshoot thousands of network elements in a much smarter way with an innovative and intuitive User Interface that is designed to significantly improve engineers productivity.
NetWarden is fully integrated into NetChart, a complete Performance Assurance platform, that includes Performance Monitoring, Configuration Management, Fault Management and Geo-location. This integration makes it extremely easy to switch from the innovative optimisation approach to a more traditional one and to correlate the automated troubleshooting with the customer experience provided by the geolocation data.
With the migration to 5G and NFV-based networks, NetWarden’s Machine Learning and real automation approach to network monitoring and optimisation becomes crucial when effectively managing extremely complex networks, networks that can no longer be monitored and optimised only by engineers or with rule-based algorithms.