{ Markettagged:True , MatchedLanguageCode:True }

Network performance

The complexity of today’s networks is extensive, and it will only increase in the coming years. We are evolving from a cell centric network to a user centric network. Explore how we are using Artificial Intelligence to enhance the performance Ericsson Radio System portfolio in the Network to address the increasing complexities.

Artificial Intelligence - enabled handover

As networks continue to evolve, more and more layers are added, managing customer demands for a non-interrupted performance both in terms of data and voice becomes a challenge. Using Artificial Intelligence techniques, we have developed machine learning algorithms integrated at the edge of network within the baseband that leads to up to 2X Faster inter-frequency handover.

Transport Intelligent Function (TIF)

The complexity of transport configuration is growing in many operators’ networks, especially with the introduction of the RAN features like Elastic RAN and 5G. TIF enables end-to-end transport auto-integration, autoconfiguration and auto-optimization based on RAN policies.

Antennas on rooftop

Energy efficiency

The increasing growth in data traffic will always drive the need for additional capacity. New sites will have to be installed, capacity will need to be added and henceforth the operator will see the energy cost at a rise. Through our AI enabled solutions in this area, we aim to break this direct correlation that exists between additional network equipment and related energy costs.

Network Intelligence autonomic incident management

Autonomic incident management

With the addition of millions of new monitored devices that will come on the existing networks. With the data traffic, there will be an exponential growth of the number of alarms from the network. The work to determine which of these alarms are affecting the network services and to resolve these will become overwhelming. Autonomic Incident Management, as a part of Ericsson Network Manager, provides automatic detection, enrichment and prioritization of network incidents by means of different cases of machine-learning.