Network Applications as an enabler for AI-driven Autonomous networking

ICT-41 5GASP took part in IEEE ICC 2023 Industry Forum & Exhibition (IF&E) in Rome, May 29th 2023, represented by Dr Xenofon Vasilakos (*). Dr Vasilakos attended as an invited speaker to the IF&E workshop “PR-2: SELF-ORGANIZING, SELF-MANAGING (AI-DRIVEN) AUTONOMOUS 6G NETWORKS” to present 5GASP’s approach on “Network Applications as an enabler for AI-driven Autonomous networking” as we are progressing gradually from the fifth (5G) towards the sixth generation (6G) of future telecommunication networks.

The programme details were announced here:

(*) Xenofon Vasilakos is a member of Smart Internet Lab & BDFI, the University of Bristol (UoB profile, Google Scholar).

Network Applications as an enabler for AI-driven Autonomous networking

Toward 6G, 5GASP investigates self-managing & self-organisation automation through an ecosystem of special AI-driven enabler Network Applications. The latter satisfy automation intents by other, hence “enhanced” Network Applications or services. Prototype paradigm cases include network and performance predictions facilitating proactive resource orchestration adapting to 6G network and user dynamics without human intervention. Such AI-based automation offers business-compliant automation and service agility improving network and service quality. AI-driven enabler, self-organised or managed Network Application prototypes are briefed below.

(1) Efficient MEC Handover (EMHO) Network Application (AI-driven Autonomy enabler)

This Network Application relies on cooperative Machine Learning (ML) predictions for preserving and even enhancing the service quality of enhanced Network Applications running over a Multi-access Edge Computing (MEC) platform. The current prototype leverages mobile Radio Resource Control (RRC) monitoring data with a second ML layer of cooperative models predicting MEC handovers.

(2) Virtual On-Board Unit (vOBU) provisioning Network Application (AI self-organisation)

This Network Application deploys a digital twin (DT) of a car on-board unit (OBU) on the nearest MEC node of its location. The TD can be “migrated” to car’s nearest edge as a twin (virtual) vOBU acting as a proxy, and its migration automatically begins upon cars’ movement. To avoid bottlenecks, this Network Application can pose an intent for forecasting future car locations with EMHO’s mobility prediction ML, thus allowing it to proactively deploy vOBU.

(3) PrivacyAnalyser Network Application (self-management)

PrivacyAnalyser is a cross-vertical cloud-native application running either at network Core or MEC. Among other features, it caters for ML network data classification from UE and/or IoT devices, and privacy evaluation and analysis. Also, PrivacyAnalyser is converging toward ML-based network management and orchestration via EMHO’s exposed ML predictions, enabling smart scale-in/out MEC pods proactively, better than the default container autoscaling for improving energy efficiency.

(4) Remote Human Driving Network Application (AI-driven self-management & self-organisation)

This Network Application enables remote autonomous vehicle operation in unusual/dangerous situations. The intent is to ensure reliable, low-latency, high-quality real-time video transmission via AI optimised network latency, but also via EMHO Network Application handover predictions to automatically deploy appropriate applications with optimised slice features matching dynamic needs.

Impact, lessons learnt, and future steps

5GASP targets the creation of an Open Source Software (OSS) repository and of a VNF marketplace targeting SMEs with OSS examples and building blocks, as well as the incubation of a community of Network Application developers, assisted with tools and services that can enable: (i) to capture business and other intents for “improving network quality” via Network Application AI-driven network automation leveraging continuously monitoring, hence offering minimal human intervention; (ii) an early validation and certification of network services allowing monitoring to ensure alignment with business intents; (iii) focusing on inter-domain use-cases supporting day-to-day testing and validation activities, and security/trust of 3rd party IPR running in our testbeds.

The main lessons learnt so far can be summarised as:

  1. AI-driven automation is key to network and service automation to avoid human intervention and improve QoS.
  2. 6G Network automation is possible with AI-driven Network Applications and Network Applications consuming AI-driven artefacts, e.g. predictions or dynamic network orchestration suggestions.

Regarding next steps, the project has already reached a maturity level which Network Applications deployed using the developed tools and procedures. The project is currently looking for Network Applications developers outside of the consortium looking to validate their 5G applications and willing to adopt the 5GASP methodology and tools, as well as innovative 6G automation Network Applications.


  • A. Bonea et. Al, Automated onboarding, testing and validation for Network Applications and Verticals, ISSCS Iasi, 2021.
  • Kostis Trantzas et al., An automated CI/CD process for testing and deployment of Network Applications over 5G infrastructure, IEEE International Mediterranean Conference on Communications and Networking, 7–10 September 2021.
  • X. Vasilakos et al., Towards Low-latent & Load-balanced VNF Placement with Hierarchical Reinforcement Learning, IEEE International Mediterranean Conference on Communications and Networking, 7–10 September 2021.
  • M. Bunyakitanon et al., HELICON: Orchestrating low-latent & load-balanced Virtual Network Functions, IEEE ICC 2022.
  • R. Direito, et al., Towards a Fully Automated System for Testing and Validating Network Applications, NetSoft 2022, 2022.
  • X. Vasilakos et al., Towards an intelligent 6G architecture: the case of jointly Optimised handover and Orchestration, WWRF47, 2022.
  • N. Uniyal et al., On the design of a native Zero-touch 6G architecture, WWRF47, 2022.