Laying the groundwork for Beyond 5G success
Will Beyond 5G (B5G) systems succeed in the future? According to scientists, this will mostly depend on the quality of the network intelligence (NI) that will fully automate network management. Although AI models are often thought of as the cornerstone of NI design, AI is not the best tool for all NI tasks. Adopting a pragmatic approach to NI design, the EU-funded DAEMON project analysed which NI tasks can be solved with AI models to develop guidelines on the use of machine learning in network functions. Based on this insight, it has designed NI algorithms to enable a core set of B5G network functionalities. Speaking about progress made to date, Dr Marco Fiore of DAEMON project coordinator IMDEA Networks, Spain, remarks in a news item posted on the institute’s website: “We have designed a number of original NI algorithms that have significantly advanced the state of the art in many practical network functionalities, including virtualized Radio Access Network (vRAN) scheduling, control and orchestration; Virtual Network Function (VNF) placement and control; anomaly detection, prediction and response; Edge resource and slice orchestration; anticipatory resource allocation in the network core; and Reconfigurable Intelligent Surface (RIS) control”.
Better performance, smaller footprint
The advances the project achieves in NI will help to deliver extremely high performance coupled with efficient use of the underlying radio and computational resources. “The project has the potential to introduce changes in mobile networks operations that will highly benefit operators but also customers, who will enjoy better service with lower delays, higher throughput, and more resilient infrastructure,” notes Dr Fiore. “In addition, part of the efforts is dedicated to limiting the energy consumption of network infrastructures, hence reducing the footprint of mobile communications, which has a benefit for the society in these difficult times of global warming.” Project achievements include more than 49 papers published to date, one of which discusses the design and validation of an open-source cloud-native mobile network. As described in the study published in ‘IEEE Communications Magazine’, the network “supports channel emulation and provides an affordable and scalable way of testing orchestration algorithms with standardized VIM interfaces.” Another recent study supported by DAEMON focuses on migration-aware network services with edge computing. Published in the journal ‘IEEE Transactions on Network and Service Management’, the study introduces a priority-induced service migration minimisation algorithm that reduces the mean service downtime of low priority services and the mean admission time of high priority services. The DAEMON consortium has so far filed three patents for solutions developed during the project and has made more than 25 contributions to various standardisation bodies. Furthermore, the development of an intelligent anomaly detection approach for an Internet of things managed connectivity platform by DAEMON project partner Telefónica, Spain, has earned it a spot on the EU’s Innovation Radar. Dr Fiore comments: “The research carried out to date is definitely groundbreaking. It addresses many open problems in the automation of mobile network infrastructure operation and proposes innovative solutions based on either novel design of AI models that are tailored to network environments, or practical updates to the network architecture that improve its capability to accommodate self-management functionalities.” The DAEMON (Network intelligence for aDAptive and sElf-Learning MObile Networks) project ends in December 2023. For more information, please see: DAEMON project website
Keywords
DAEMON, network, mobile network, AI, network intelligence, Beyond 5G, B5G
