SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control

Deep reinforcement learning (DRL) promises adaptive control for future mobile networks but conventional agents remain reactive: they act on past and current measurements and cannot leverage short-term forecasts of exogenous KPIs such as bandwidth. Augmenting agents with predictions can overcome this temporal myopia, yet uptake in networking is scarce because forecast-aware agents act as closed-boxes; operators cannot tell whether predictions guide decisions or justify the added complexity. We propose SIA, the first interpreter that exposes in real time how forecast-augmented DRL agents operate. SIA fuses Symbolic AI abstractions with per-KPI Knowledge Graphs to produce explanations, and includes a new Influence Score metric. SIA achieves sub-millisecond speed, over 200x faster than existing XAI methods. We evaluate SIA on three diverse networking use cases, uncovering hidden issues, including temporal misalignment in forecast integration and reward-design biases that trigger counter-productive policies. These insights enable targeted fixes: a redesigned agent achieves a 9% higher average bitrate in video streaming, and SIA's online Action-Refinement module improves RAN-slicing reward by 25% without retraining. By making anticipatory DRL transparent and tunable, SIA lowers the barrier to proactive control in next-generation mobile networks.

SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks

The operation of future 6th-generation (6G) mobile networks will increasingly rely on the ability of deep reinforcement learning (DRL) to optimize network decisions in real-time. DRL yields demonstrated efficacy in various resource allocation problems, such as joint decisions on user scheduling and antenna allocation or simultaneous control of computing resources and modulation. However, trained DRL agents are closed-boxes and inherently difficult to explain, which hinders their adoption in production settings. In this paper, we make a step towards removing this critical barrier by presenting SymbXRL, a novel technique for explainable reinforcement learning (XRL) that synthesizes human-interpretable explanations for DRL agents. SymbXRL leverages symbolic AI to produce explanations where key concepts and their relationships are described via intuitive symbols and rules; coupling such a representation with logical reasoning exposes the decision process of DRL agents and offers more comprehensible descriptions of their behaviors compared to existing approaches. We validate SymbXRL in practical network management use cases supported by DRL, proving that it not only improves the semantics of the explanations but also paves the way for explicit agent control: for instance, it enables intent-based programmatic action steering that improves by 12% the median cumulative reward over a pure DRL solution.

Empowering Wireless Network Applications with Deep Learning-based Radio Propagation Models

The efficient deployment and operation of any wireless communication ecosystem rely on knowledge of the received signal quality over the target coverage area. This knowledge is typically acquired through radio propagation solvers, which however suffer from intrinsic and well-known performance limitations. This article provides a primer on how integrating deep learning and conventional propagation modeling techniques can enhance multiple vital facets of wireless network operation, and yield benefits in terms of efficiency and reliability. By highlighting the pivotal role that the deep learning-based radio propagation models will assume in next-generation wireless networks, we aspire to propel further research in this direction and foster their adoption in additional applications.

CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting

This paper introduces CloudLSTM, a new branch of recurrent neural network models tailored to forecasting over data streams generated by geospatial point-cloud sources. We design a Dynamic Convolution (D-Conv) operator as the core component of CloudLSTMs, which allows performing convolution operations directly over point-clouds and extracts local spatial features from sets of neighboring points that surround different elements of the input. This maintains the permutation invariance of sequence-to-sequence learning frameworks, while enabling learnable neighboring correlations at each time step -- an important aspect in spatiotemporal predictive learning. The D-Conv operator resolves the grid-structural data requirements of existing spatiotemporal forecasting models (e.g. ConvLSTM) and can be easily plugged into traditional LSTM architectures with sequence-to-sequence learning and attention mechanisms. As a case study, we perform antenna-level forecasting of the data traffic generated by mobile services, demonstrating that the proposed CloudLSTM achieves state-of-the-art performance with measurement datasets collected in operational metropolitan-scale mobile network deployments.

Multi-Service Mobile Traffic Forecasting via Convolutional Long Short-Term Memories

Network slicing is increasingly used to partition network infrastructure between different mobile services. Precise service-wise mobile traffic forecasting becomes essential in this context, as mobile operators seek to pre-allocate resources to each slice in advance, to meet the distinct requirements of individual services. This paper attacks the problem of multi-service mobile traffic forecasting using a sequence-to-sequence (S2S) learning paradigm and convolutional long short-term memories (ConvLSTMs). The proposed architecture is designed so as to effectively extract complex spatiotemporal features of mobile network traffic and predict with high accuracy the future demands for individual services at city scale. We conduct experiments on a mobile traffic dataset collected in a large European metropolis, demonstrating that the proposed S2S-ConvLSTM can forecast the mobile traffic volume produced by tens of different services in advance of up to one hour, by just using measurements taken during the past hour. In particular, our solution achieves mean absolute errors (MAE) at antenna level that are below 13KBps, outperforming other deep learning approaches by up to 31.2%.