
























News |
By Asma Adhimi
Ericsson and KDDI have completed a large-scale field trial of AI-driven uplink optimization on a live commercial network in Japan, showing measurable performance gains across both 4G and 5G networks. The trial combined Ericsson’s Uplink Interference Optimizer (UIO) rApp with a third-party rApp from Japanese developer FYRA, running on the Ericsson Intelligent Automation Platform (EIAP).
The work is significant for telecom operators moving toward autonomous networks, particularly as AI-based network optimization becomes increasingly important for handling growing traffic loads and latency-sensitive applications. For eeNews Europe readers, the trial also highlights how open RAN ecosystems and third-party rApps are starting to move from theory into commercial deployment.
The field trial was carried out during the first quarter of 2026 across around 1,500 5G cells and 1,300 4G cells on KDDI’s commercial network. According to Ericsson, the AI-driven optimization platform selectively targeted the busiest cells to improve uplink performance without affecting network stability.
The companies said the tests delivered a 9.6% average throughput improvement in 4G and a 3.1% improvement in 5G, despite uplink traffic increasing by roughly 10% during the evaluation period. Ericsson also reported a 27% improvement in 5G signal-to-interference-plus-noise ratio (SINR), alongside gains in modulation and spectral efficiency.
The deployment marked the first global live-network implementation of Ericsson’s UIO rApp and also the first use of EIAP in a live commercial environment in Japan.
Ericsson said the UIO rApp achieved an autonomy assessment level of 3.86 using an adapted version of the TM Forum’s ANLET methodology, bringing operators closer to Autonomous Networks Level 4.
Jean-Christophe Laneri, Head of Cognitive Network Solutions at Ericsson, said: “The successful field trial with KDDI confirmed the readiness of the UIO rApp, running on the EIAP, for a key role in achieving Autonomous Networks Level 4 (AN L4) live operation. This solution introduces advanced, robust automated optimization within mobile networks, greatly improving subscriber experience. The UIO rApp is now generally available for the global market, with additional AI-driven rApps to follow as part of Ericsson’s expanding rApp portfolio.”
Another key aspect of the trial was the integration of a non-Ericsson application. KDDI tested the FYRA Suite rApp alongside Ericsson’s software to validate EIAP support for third-party applications and compliance with the O-RAN R1 standard.
The companies said this demonstrates how open rApp platforms could support broader telecom innovation ecosystems, allowing local developers to build applications that can scale internationally.
Hiroaki Ando, President and Representative Director of Ericsson Japan, said: “Highly reliable, low-latency uplink performance is a critical foundation for Physical AI use cases, which Japan has identified as a priority area in its semiconductor and digital industry strategy. Ericsson remains committed to continuing our close collaboration with KDDI and to contributing to the advancement of Japanese society and industry.”
Ericsson said the Uplink Interference Optimizer rApp reached general availability during the project, opening the door for wider operator deployments globally.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。