rApps

Traffic prediction and steering

Congestion is a common problem for 4G and 5G networks. It occurs when traffic demand exceeds a cell's capacity due to many users or high data usage in an area.

This results in delays, reduced download speeds, and network accessibility issues, that impact users' experience and service quality.

An intelligent solution capable of predicting and steering the traffic is necessary to avoid such issues.

rApps effect example:

Traffic Steering Manager rApp checks if cells have Physical Resource Block (PRB) or Physical Downlink Control Channel (PDCCH) congestion in 4G and 5G networks and suggests modifications to facilitate correct balancing through traffic absorption by other carriers or available neighbors.

Accelerated network deployments and configuration management

One of the main impediments in network deployment is the inconsistency created by having several engineers and automations configuring new equipment and making changes to optimize the parameters and achieve the performance targets.

In these cases, rApps will detect and fix any inconsistency or misconfiguration in minutes, making deployment much faster and improving the user experience.

rApps effect examples:

Ericsson Automated Configuration Consistency (EACC) rApp enables users to uncover baseline configuration consistency errors. It corrects inconsistencies found in either open-loop or closed-loop mode and can roll back configuration changes if a KPI degradation is detected.

Ericsson RAN Lifecycle Orchestrator rApp enables automation of the full lifecycle of RAN operations by simplifying integration in an Open RAN architecture and future-proofing operations for Cloud RAN and purpose-built RAN solutions. 

Learn more

Reduced energy consumption 

Optimizing networks to reduce energy consumption while maintaining high performance is challenging and requires innovative strategies. As networks’ complexity grows, this challenge demands intelligent solutions that will help balance environmental sustainability and operational efficiency while paving the way for future network advancements.

rApps effect example:

The Energy Cockpit rApp, one of the Ericsson rApps that help optimize and reduce energy consumption, analyzes the whole network every 15 minutes, down to the cell level, and decides which power-saving features should be activated, considering traffic impact.

This is an example of how rApps excel at speed, scalability, and agility, compared to standard automation tools.

Learn more

Faster anomaly detection and fault management

Network performance is often optimized by combining manual and automated rule-based instructions with predetermined thresholds for each performance metric. As the network complexity grows, the number of rules increases, making maintaining these algorithms manually a highly complex task. 

Intelligent automation using rApps can augment or replace existing manual processes to improve network performance and reduce costs.

rApps effect example:

Ericsson Cell Anomaly Detector rApp is a deep learning app that automatically monitors and categorizes potential performance anomalies within a network. Its primary use cases include automatically identifying various cell issue patterns and applying deep learning techniques to assess cell performance, configuration, and alarms.

The Cell Anomaly Detector leverages advanced algorithms to identify a broad spectrum of issues that traditional methodologies might overlook.

Learn more

Coverage optimization

The growing demand for high-speed data and seamless connectivity, along with the surge in connected devices, is putting significant strain on mobile networks. One major challenge is managing the limited radio spectrum, which is crucial for running services smoothly. Efficient spectrum use helps ensure reliable connections, minimizes delays, and meets the increasing need for data transmission.

rApps effect examples:

Coverage Optimiser rApp uses network data and advanced geospatial analytics to gain precise insights into traffic distribution and accurately identify offending cells. Once overshooting and undershooting cells are identified, the solution follows predefined policies and applies iterative configuration changes, such as adjusting the antenna coverage.

Ericsson AAS Cell Shaper rApp is designed for the optimization of Advanced Antenna Systems (AAS) using AI reinforcement learning techniques. It optimizes cell-level digital tilt in the vertical plane and beamwidth in the horizontal plane. It automatically adjusts to the unique characteristics of each cell and its surrounding network, resulting in an optimized radio environment and improved traffic distribution.

Automatic anomaly detection 

CSPs must continually optimize network performance, minimize downtime, and enhance operational efficiency. To ensure service continuity and effectively resolve both simple and complex issues, precise and actionable insights are essential. These insights help deliver high availability while keeping operational costs low. rApps empower CSPs by facilitating automatic anomaly detection and predicting performance trends.

rApps effect example:

Naavik AI-based Anomaly Detection rApp utilizes a data-driven causality graph to analyze and interpret multidimensional data sources in real time. It enables rapid identification of correlations and causations within critical RAN KPIs, essential for effective root cause analysis.