Zero-touch network management is one of the most ambitious yet strongly required paradigms for beyond 5G and 6G mobile communication systems. Achieving full automation requires a closed loop that combines (i) network status data collection and processing, (ii) predictive capabilities based on such data to anticipate upcoming needs, and (iii) effective decision making that best addresses such future needs through proper network control and orchestration. Recent seminal works have proposed approaches to jointly implement the last two phases above via a single deep learning model trained on past network status to directly optimize future decisions. This is achieved by designing custom loss functions that directly embed the management task objective. Experiments with real-world measurement data have demonstrated that this strategy leads to substantial performance gains across diverse network management tasks. In this paper, we go one step beyond the loss tailoring schemes above, and introduce a loss meta-learning paradigm that (i) reduces the need for human intervention at model design stage, (ii) eases explainability and transferability of trained deep learning models for network management, and (iii) outperforms custom losses across a range of controlled experiments and practical use cases.

A variety of network management and orchestration (MANO) tasks take advantage of predictions to support anticipatory decisions. In many practical scenarios, such predictions entail two largely overlooked challenges: (i) the exact relationship between the predicted values (e.g., reserved resources) and the performance objective (e.g., quality of experience of end users) is often tangled and cannot be known a priori, and (ii) the objective is linked in many cases to multiple predictions that contribute to it in an intertwined way (e.g., resources to reserved are limited and must be shared among competing flows). We present AutoManager, a novel meta-learning model that can support complex MANO tasks by addressing these two challenges. Our solution learns how multiple intertwined predictions affect a common performance goal, and steers them so as to attain the correct operation point under a-priori unknown loss functions. We demonstrate AutoManager in practical, complex use cases based on real-world traffic measurements; our experiments show that the model produces forecasts that are accurate and tailored to the MANO task in a fully automated way.

The ability to forecast mobile traffic patterns is key to resource management for mobile network operators and planning for local authorities. Several Deep Neural Networks (DNN) have been designed to capture the complex spatio-temporal characteristics of mobile traffic patterns at scale. These models are complex black boxes whose decisions are inherently hard to explain. Even worse, they have proven vulnerable to adversarial attacks which undermine their applicability in production networks. In this paper, we conduct a first in-depth study of the vulnerabilities of DNNs for large-scale mobile traffic forecasting. We propose DeExp, a new tool that leverages EXplainable Artificial Intelligence (XAI) to understand which Base Stations (BSs) are more influential for forecasting from a spatio-temporal perspective. This is challenging as existing XAI techniques are usually applied to computer vision or natural language processing and need to be adapted to the mobile network context. Upon identifying the more influential BSs, we run state-of-the art Adversarial Machine Learning (AML) techniques on those BSs and measure the accuracy degradation of the predictors. Extensive evaluations with real-world mobile traffic traces pinpoint that attacking BSs relevant to the predictor significantly degrades its accuracy across all the scenarios.

Intent-Based Networking mandates that high-level human-understandable intents are automatically interpreted and implemented by network management entities. As a key part in this process, it is required that network orchestrators activate the correct automated decision model to meet the intent objective. In anticipatory networking tasks, this requirement maps to identifying and deploying a tailored prediction model that can produce a forecast aligned with the specific –and typically complex– network management goal expressed by the original intent. Current forecasting models for network demands or network management optimize generic, non-flexible, and manually designed objectives, hence do not fulfil the needs of anticipatory Intent-Based Networking. To close this gap, we propose LossLeaP, a novel forecasting model that can autonomously learn the relationship between the prediction and the target management objective, steering the former to minimize the latter. To this end, LossLeaP adopts an original deep learning architecture that advances current efforts in automated machine learning, towards a spontaneous design of loss functions for regression tasks. Extensive experiments in controlled environments and in practical application case studies prove that LossLeaP outperforms a wide range of benchmarks, including state-of-the-art solutions for network capacity forecasting.