Tag: ml

Recently, energy efficiency has been pointed out as one of the key requirements within mobile networks. The development of intelligent algorithms providing RAN with EE features is possible when having access to the KPIs, and proper control actions, e.g., cell on/off switching, or RF channel reconfiguration. These features together with a ML framework are available in the O-RAN architecture. This post provides an overview of the EE framework according to the use cases specified by the O-RAN ALLIANCE. It is followed by the implementation of the ES-rApp as per Rimedo Labs' implementation.

Recently, security has been pointed out as one of the critical aspects moving forward within the O-RAN domain. Expanded threat surface, as well as specific security challenges and opportunities, have been identified. This whitepaper provides an overview of security topics in O-RAN, specifically in 5G/6G mobile radio networks. We also consider artificial intelligence embedded in the network edge as a great tool to support security. We present some xApps applied to detect and mitigate example attacks. Conclusions and a discussion on the directions of future developments follow this.

One of the key aspects of the Open RAN is embedding native intelligence within the O-RAN framework. To this end, AI/ML plays a crucial role. Some of the goals for AI/ML within RAN are: decreasing the manual effort of going through large data amounts to diagnose issues and make decisions, or predicting the future to take proactive actions. This is being addressed from the beginning within O-RAN ALLIANCE. In this post, we discuss the overall framework for machine learning within O-RAN, including architectural aspects and use cases.

When talking about future RAN security, one has to consider threats related to the radio segment of a network, and the expanded attack surface, due to the open architecture and interfaces in O-RAN. Those should be expanded by a discussion on AI algorithms security, as AI is to be embedded in multiple network tiers starting from UE, gNB at the edge of the network in the MEC module and in a cloud. In this post, present considerations on threats and opportunities that O-RAN specifications create for network security to deliberations on how AI at the network edge can, on one hand, be a target of attacks, and on the other, increase the network security.

The baseline 5G system was specified within 3GPP Releases 15 and 16, also known as 5G Phase-1 and 5G Phase 2. There are interesting developments within 3GPP, which evolved the system towards Rel-17. More recently, the standardization took the step towards a significant update with the so-called, “5G-Advanced” using Rel-18 for that purpose. This whitepaper provides an overview of the latest development steps along with outlining the main Work- and Study-Items of both 3GPP Rel-17 and Rel-18 within RAN and SA2 work groups.

5G standard is still evolving with new 3GPP releases issued periodically, leading to 5G-Advanced and possibly 5G-Advanced Pro in coming years. However, all major players (researchers, vendors, mobile network operators, regulators) have already started their 6G activities in line with the tradition of having G+ every 10 years. This blog post provides an overview of the current state of 5G and outlines requirements and potential technologies for 6G.