The Internet of Things (IoT) is a vision of a future society where an ever-increasing number of heterogeneous physical devices ("things") obtain Internet connectivity, thus enabling a large number of applications for a broad range of industries and society at large. Mobile network operators, expected to provide the network infrastructure for many of these applications, face an unprecedented level of complexity. This complexity not only relates to the number of applications that share the network infrastructure, but also to the different network Quality of Service (QoS) requirements these applications have. To achieve economies of scale, automation in management of those applications throughout their lifecycle is essential. In this paper, we propose an architecture that automates allocation, monitoring and deallocation of both cloud and cellular network resources to ensure QoS for applications that involve connected devices communicating with cloud-hosted software. We describe an implementation of this architecture using a combination of open source, commercial, and custom components and evaluate it through a series of measurements. Results show that our implementation can simultaneously support mobile broadband and low latency, high availability mission-critical applications.

Federated Learning ( FL ) has emerged as a prominent distributed learning paradigm that allows multiple users to collaboratively train a model without sharing their data thus preserving privacy. Within the scope of privacy preservation, information privacy regulations such as GDPR entitle users to request the removal (or unlearning) of their contribution from a service that is hosting the model. For this purpose, a server hosting an ML model must be able to unlearn certain information in cases such as copyright infringement or security issues that can make the model vulnerable or impact the performance of a service based on that model. While most unlearning approaches in FL focus on Horizontal Federated Learning (HFL), where clients share the feature space and the global model, Vertical Federated Learning (VFL) has received less attention from the research community. VFL involves clients (passive parties) sharing the sample space among them while not having access to the labels. In this paper, we explore unlearning in VFL from three perspectives: unlearning passive parties, unlearning features, and unlearning samples. To unlearn passive parties and features we introduce VFU-KD which is based on knowledge distillation (KD) while to unlearn samples, VFU-GA is introduced which is based on gradient ascent (GA). To provide evidence of approximate unlearning, we utilize Membership Inference Attack (MIA) to audit the effectiveness of our unlearning approach. Our experiments across six tabular datasets and two image datasets demonstrate that VFU-KD and VFU-GA achieve performance comparable to or better than both retraining from scratch and the benchmark R2S method in many cases, with improvements of (0 − 2%). In the remaining cases, utility scores remain comparable, with a modest utility loss ranging from 1 − 5%. Unlike existing methods, VFU-KD and VFU-GA require no communication between active and passive parties during unlearning. However, they do require the active party to store the previously communicated embeddings.

The development of Quality of Experience (QoE) models using Machine Learning (ML) is challenging, since it can be difficult to share datasets between research entities to protect the intellectual property of the ML model and the confidentiality of user studies in compliance with data protection regulations such as General Data Protection Regulation (GDPR). This makes distributed machine learning techniques that do not necessitate sharing of data or attribute names appealing. One suitable use case in the scope of QoE can be the task of mapping QoE indicators for the perception of quality such as Mean Opinion Scores (MOS), in a distributed manner. In this article, we present Distributed Ensemble Learning (DEL), and Vertical Federated Learning (vFL) to address this context. Both approaches can be applied to datasets that have different feature sets, i.e., split features. The DEL approach is ML model-agnostic and achieves up to $12\%$ accuracy improvement of ensembling various generic and specific models. The vFL approach is based on neural networks and achieves on-par accuracy with a conventional Fully Centralized machine learning model, while exhibiting statistically significant performance that is superior to that of the Isolated local models with an average accuracy improvement of $26\%$. Moreover, energy-efficient vFL with reduced network footprint and training time is obtained by further tuning the model hyper-parameters.

With emerging ML techniques showing great potential in prediction performance, there is an inclination towards ML for network management. Although modern mobile network deployments have access to essential data storage and computational resources, they would benefit remarkably from more sustainable and cost-effective approaches for ML applications. Data-efficient AI allows network vendors to train ML models on less data, which relieves memory and computational requirements. To explore a solution to these problems, this paper dives deeper into SNN, a promising data-efficient ML technique. Furthermore, to improve data efficiency, an extension of the SNN framework is proposed by applying a memory-based continual learning algorithm, Experience Replay. Empirical evaluations are conducted using several datasets, including a dataset from real live mobile networks, to illustrate the potential of SNNs and to highlight the contribution to sustainable AI for mobile networks. The findings show that in this context, SNNs can outperform standard classification neural networks, under both the standard multi-class classification case and the continual learning case, while trained on significantly less data.

Transfer learning (TL) and domain adaptation (DA) are well-known approaches in the AI literature that can be used to address the fundamental challenge of data scarcity. TL and DA propose ways to reuse previously trained models to compensate for missing data or the absence of labeled information, which often comes at the cost of manual work. The potential of TL and DA has only recently started to demonstrate its worth in the telecommunication area as mobile networks are undergoing significant changes to become AI-native. As such, an AI-native network is one that allows for swapping a classical implementation of a network function with one that is data-driven and powered by an AI algorithm. In this book chapter, we present our experiences and findings while working with TL and DA to build AI-native networks. More specifically, we share our findings when applying TL and DA in network management use cases for service performance, end-to-end latency, and block call rate prediction. Via these use cases, and to overcome limitations with TL and DA, we introduce enhancements such as source selection, unsupervised domain adaptation, and transfer learning in distributed intelligence. These enhancements can benefit the general AI community and other industries.

Distributed intelligence (DI) is becoming increasingly important in mobile networks due to privacy and regulatory restrictions on data movement. This trend is fueled by a surge in data volume required for training machine learning models, and increasing computational and storage capabilities of devices, and network nodes near data collection points. Techniques such as Federated and Split Learning, applied in horizontal and vertical feature spaces, enable efficient training of machine learning models while maintaining data privacy. Despite the adoption of DI techniques in mobile networks, there are still gaps and areas in mobile network architecture where DI is either not applied or not taking advantage of its full potential. To that end, this paper provides a state-of-the-art overview of the adoption of DI in mobile networks from the perspective of standardization. We identify the importance of machine learning model lifecycle management (ML LCM) and position DI as an extension of that. From this overview, gaps and limitations are identified and presented. To overcome these limitations, we perform a thought experiment which lowers ML LCM with DI capability from Core Network (CN) to Radio Access Networks (RAN) which are distributed by nature. In that setting a set of Key Performance Indicators (KPIs) to quantify the performance of different DI techniques is introduced. These KPIs aim at quantifying computational overhead, memory/storage requirements, communication footprint, model efficiency and robustness, flexibility and privacy. We evaluate these KPIs on a RAN use case, that of secondary carrier prediction and show the interplay between model efficiency and computational footprint which are important metrics to consider when migrating from a centralized to a distributed setting. Finally, we provide additional enhancements to improve these KPIs and thus further promote the adoption of DI techniques.