Ericsson Cell Anomaly Detector rApp
Ericsson | Network Optimization
Cell Anomaly Detector is a deep learning rApp that automatically observes and groups possible performance anomalies a network can suffer. Main use cases:
- Automatic identification of different cell issue patterns.
- Apply deep learning techniques to the cell performance, configuration and alarms.
Cell Anomaly Detector automatically detects a wide range of issues that cannot be seen with traditional methodologies. As a result, the network performance is significantly improved, and user-perceived performance degradations are minimized.
Better-than-human capability
When more than one issue co-exists in a cell, it is usually hard for an engineer to identify all the contributing factors simultaneously. However, with this non-supervised learning algorithm, both hidden and new issues can be detected by the anomaly detector, evolving both the classification and the insights delivered.
High prediction accuracy
The field verifications have shown an issue detection and prediction accuracy of between 92–98 percent. This means the solution accurately replicates the technical analysis that a senior engineer can perform
Embedded with expert Ericsson domain expertise
A number of Ericsson’s technical experts in the network optimization domain have been working on the most advanced and complex networks. The knowledge gained from those real project experiences is embedded into Cell Anomaly Detector machine learning training.
| Ericsson enables communications service providers to capture the full value of connectivity. The company’s portfolio spans the following business areas: Networks, Cloud Software and Services, Enterprise Wireless Solutions, Global Communications Platform, and Technologies and New Businesses. It is designed to help our customers go digital, increase efficiency and find new revenue streams. Ericsson’s innovation investments have delivered the benefits of mobility and mobile broadband to billions of people globally. Ericsson stock is listed on Nasdaq Stockholm and on Nasdaq New York |  |