Machine learning (ML) models, data and software need to be regularly updated whenever essential version updates are released and feasible for integration. This is a basic but most challenging requirement to satisfy in the edge, due to the various system constraints and the major impact that an update can have on robustness and stability. In this paper, we formulate for the first time the ML model versioning optimization problem, and propose effective solutions, including the update automation with reinforcement learning (RL) based algorithm. We study the edge network environment due to the known constraints in performance, response time, security, and reliability, which make updates especially challenging. The performance study shows that model version updates can be fully and effectively automated with reinforcement learning method. We show that for every range of server load values, the proper versioning can be found that improves security, reliability and/or ML model accuracy, while assuring a comparably lower response time.

Efficient topology management in future 6G networks is a fundamental challenge for dynamic network creation based on location services, where each autonomous sub-network can be tailored to specific application scenarios. This paper studies the performance of a novel topology change management system in a 6G network dynamically organized into autonomous sub-networks. We propose and analyze an algorithm for intelligent prediction of topology changes and compare it with a monitoring-based approach. A case study on edge video distribution, aligned with 3GPP and ETSI MEC (Multi-access Edge Computing) standards, demonstrates the system's practical relevance. The proposed topology change prediction algorithm optimizes and selects the best machine learning models based on the scenario under study. For link change scenario, the results show that ANN demonstrates the best performance in identifying cases with no changes, slightly outperforming random forest and XGBoost. For user mobility scenario, XGBoost is more efficient in learning patterns for topology change prediction. In terms of cost efficiency, our ML-based approach represents a significantly cost-effective alternative to traditional monitoring approaches.

We consider the problem of signaling rate and performance for control and management of reconfigurable intelligent surfaces (RISs) in next-generation mobile networks. To this end, we first analytically determine the rates of RIS reconfigurations and handover using a stochastic geometry network model. We derive closed-form expressions of these rates, while taking into account static obstacles (both known and unknown), self-blockage, RIS location density, and variations in the angle and direction of user mobility. Based on the derived rates, we analyze the signaling rates of a sample novel signaling protocol, which we propose as an extension of the current handover signaling protocol. We evaluate the signaling overhead due to RIS reconfigurations and the related energy consumption. We also provide a capacity planning analysis of the related RIS control plane server for its dimensioning in the network management system. The results quantify the impact of known and unknown obstacles on the RIS reconfiguration rate and the handover rate as a function of device density and mobility. We evaluate the scalability of the model, the related signaling overhead, energy efficiency, and server capacity in the control plane. To the best of our knowledge, this is the first analytical model to derive the closed form expressions of RIS reconfiguration rates, along with handover rates, and relate its statistical properties to the signaling rate and performance in next-generation mobile networks.

Campus networks are expected to include various new features compared to 4G and 5G networks, such as the exploitation of THz frequency bands and real-time network optimization. Furthermore, to enable future-proof network control, the Digital Twin Network (DTN) reference architecture can be exploited to create an autonomic network system that provides intent-based interfaces and offers a complete adaptive network control tailored for campus network applications. This paper discusses such architecture and presents a case study focused on a THz system that can adapt its coding and modulation parameters in response to channel degradation due to environmental changes. Finally, simulation results evince the advantages of the proposed architecture.

With rapid advances in containerization techniques, the serverless computing model is becoming a valid candidate execution model in edge networking, similar to the widely used cloud model for applications that are stateless, single purpose and event-driven, and in particular for delay-sensitive applications. One of the cloud serverless processes, i.e., the auto-scaling mechanism, cannot be however directly applied at the edge, due to the distributed nature of edge nodes, the difficulty of optimal resource allocation, and the delay sensitivity of workloads. We propose a solution to the auto-scaling problem by applying reinforcement learning (RL) approach to solving problem of efficient scaling and resource allocation of serverless functions in edge networks. We compare RL and Deep RL algorithms with empirical, monitoring-based heuristics, considering delay-sensitive applications. The simulation results shows that RL al-gorithm outperforms the standard, monitoring-based algorithms in terms of total delay of function requests, while achieving an improvement in delay performance by up to 50%.

Serverless computing has emerged as a new execution model which gained a lot of attention in cloud computing thanks to the latest advances in containerization technologies. Recently, serverless has been adopted at the edge, where it can help overcome heterogeneity issues, constrained nature and dynamicity of edge devices. Due to the distributed nature of edge devices, however, the scaling of serverless functions presents a major challenge. We address this challenge by studying the optimality of serverless function scaling. To this end, we propose Semi-Markov Decision Process-based (SMDP) theoretical model, which yields optimal solutions by solving the serverless function scaling problem as a decision making problem. We compare the SMDP solution with practical, monitoring-based heuristics. We show that SMDP can be effectively used in edge computing networks, and in combination with monitoring-based approaches also in real-world implementations.

The evolution towards Industry 4.0 is driving the need for innovative solutions in the area of network management, considering the complex, dynamic and heterogeneous nature of ICT supply chains. To this end, Intent-Based networking (IBN) which is already proven to evolve how network management is driven today, can be implemented as a solution to facilitate the management of large ICT supply chains. In this paper, we first present a comparison of the main architectural components of typical IBN systems and, then, we study the key engineering requirements when integrating IBN with ICT supply chain network systems while considering AI methods. We also propose a general architecture design that enables intent translation of ICT supply chain specifications into lower level policies, to finally show an example of how the access control is performed in a modeled ICT supply chain system.

Optical networks are prone to power jamming attacks intending service disruption. This paper presents a Machine Learning (ML) framework for detection and prevention of jamming attacks in optical networks. We evaluate various ML classifiers for detecting out-of-band jamming attacks with varying intensities. Numerical results show that artificial neural network is the fastest (106 detection per second) for inference and most accurate (≈ 100%) in detecting power jamming attacks as well as identifying the optical channels attacked. We also discuss and study a novel prevention mechanism when the system is under active jamming attacks. For this scenario, we propose a novel resource reallocation scheme that utilizes the statistical information of attack detection accuracy to lower the probability of successful jamming of lightpaths while minimizing lightpaths' reallocations. Simulation results show that the likelihood of jamming a lightpath reduces with increasing detection accuracy, and localization reduces the number of reallocations required.