Computer Science

In a world where Artificial Intelligence revolutionizes inference, prediction and decision-making tasks, Digital Twins emerge as game-changing tools. A case in point is the development and optimization of Cooperative Intelligent Transportation Systems (C-ITSs): a confluence of cyber-physical digital infrastructure and (semi)automated mobility. Herein we introduce Digital Twin for self-dRiving Intelligent VEhicles (DRIVE). The developed framework tackles shortcomings of traditional vehicular and network simulators. It provides a flexible, modular, and scalable implementation to ensure large-scale, city-wide experimentation with a moderate computational cost. The defining feature of our Digital Twin is a unique architecture allowing for submission of sequential queries, to which the Digital Twin provides instantaneous responses with the "state of the world", and hence is an Oracle. With such bidirectional interaction with external intelligent agents and realistic mobility traces, DRIVE provides the environment for development, training and optimization of Machine Learning based C-ITS solutions.

Densification and multi-band operation in 5G and beyond pose an unprecedented challenge for mobility management, particularly for inter-frequency handovers. The challenge is aggravated by the fact that the impact of key inter-frequency mobility parameters, namely A5 time to trigger (TTT), A5 threshold1 and A5 threshold2 on the system's performance is not fully understood. These parameters are fixed to a gold standard value or adjusted through hit and trial. This paper presents a first study to analyze and optimize A5 parameters for jointly maximizing two key performance indicators (KPIs): Reference signal received power (RSRP) and handover success rate (HOSR). As analytical modeling cannot capture the system-level complexity, a data driven approach is used. By developing XGBoost based model, that outperforms other models in terms of accuracy, we first analyze the concurrent impact of the three parameters on the two KPIs. The results reveal three key insights: 1) there exist optimal parameter values for each KPI; 2) these optimal values do not necessarily belong to the current gold standard; 3) the optimal parameter values for the two KPIs do not overlap. We then leverage the Sobol variance-based sensitivity analysis to draw some insights which can be used to avoid the parametric conflict while jointly maximizing both KPIs. We formulate the joint RSRP and HOSR optimization problem, show that it is non-convex and solve it using the genetic algorithm (GA). Comparison with the brute force-based results show that the proposed data driven GA-aided solution is 48x faster with negligible loss in optimality.

Non-orthogonal multiple access (NOMA) is a key technology to enable massive machine type communications (mMTC) in 5G networks and beyond. In this paper, NOMA is applied to improve the random access efficiency in high-density spatially-distributed multi-cell wireless IoT networks, where IoT devices contend for accessing the shared wireless channel using an adaptive p-persistent slotted Aloha protocol. To enable a capacity-optimal network, a novel formulation of random channel access management is proposed, in which the transmission probability of each IoT device is tuned to maximize the geometric mean of users' expected capacity. It is shown that the network optimization objective is high dimensional and mathematically intractable, yet it admits favourable mathematical properties that enable the design of efficient data-driven algorithmic solutions which do not require a priori knowledge of the channel model or network topology. A centralized model-based algorithm and a scalable distributed model-free algorithm, are proposed to optimally tune the transmission probabilities of IoT devices and attain the maximum capacity. The convergence of the proposed algorithms to the optimal solution is further established based on convex optimization and game-theoretic analysis. Extensive simulations demonstrate the merits of the novel formulation and the efficacy of the proposed algorithms.

A deadlock in a packet switching network is a state in which one or more messages have not yet reached their target, yet cannot progress any further. We formalize three different notions of deadlock in the context of packet switching networks, to which we refer as global, local and weak deadlock. We establish the precise relations between these notions, and prove they characterize different sets of deadlocks. Moreover, we implement checking of deadlock freedom of packet switching networks using the symbolic model checker nuXmv. We show experimentally that the implementation is effective at finding subtle deadlock situations in packet switching networks.

In this article we revisit Wireless Sensor Networks from a contemporary perspective, after the surge of the Internet of Things. First, we analyze the evolution of distributed monitoring applications, which we consider inherited from the early idea of collaborative sensor networks. Second, we evaluate, within the current context of networked objects, the level of adoption of low-power multi-hop wireless, a technology pivotal to the Wireless Sensor Network paradigm. This article assesses the transformation of this technology in its integration into the Internet of Things, identifying outdated requirements and providing a critical view on future research directions.

The vast majority of applications at this moment rely on centralized servers to relay messages between clients, where these servers are considered trusted third-parties. With the rise of blockchain technologies over the last few years, there has been a move away from both centralized servers and traditional federated models to more decentralized peer-to-peer alternatives. However, there appears to be a trilemma between security, scalability, and decentralization in blockchain-based systems. Deconstructing this trilemma using well-known threat models, we define a typology of centralized, federated, and decentralized architectures. Each of the different architectures has this trilemma play out differently. Facing a possible decentralized future, we outline seven hard problems facing decentralization and theorize that the differences between centralized, federated, and decentralized architectures depend on differing social interpretations of trust.

The number of connected Internet of Things (IoT) devices within cyber-physical infrastructure systems grows at an increasing rate. This poses significant device management and security challenges to current IoT networks. Among several approaches to cope with these challenges, data-based methods rooted in deep learning (DL) are receiving an increased interest. In this paper, motivated by the upcoming surge of 5G IoT connectivity in industrial environments, we propose to integrate a DL-based anomaly detection (AD) as a service into the 3GPP mobile cellular IoT architecture. The proposed architecture embeds autoencoder based anomaly detection modules both at the IoT devices (ADM-EDGE) and in the mobile core network (ADM-FOG), thereby balancing between the system responsiveness and accuracy. We design, integrate, demonstrate and evaluate a testbed that implements the above service in a real-world deployment integrated within the 3GPP Narrow-Band IoT (NB-IoT) mobile operator network.

We present DeepIA, a deep neural network (DNN) framework for enabling fast and reliable initial access for AI-driven beyond 5G and 6G millimeter (mmWave) networks. DeepIA reduces the beam sweep time compared to a conventional exhaustive search-based IA process by utilizing only a subset of the available beams. DeepIA maps received signal strengths (RSSs) obtained from a subset of beams to the beam that is best oriented to the receiver. In both line of sight (LoS) and non-line of sight (NLoS) conditions, DeepIA reduces the IA time and outperforms the conventional IA's beam prediction accuracy. We show that the beam prediction accuracy of DeepIA saturates with the number of beams used for IA and depends on the particular selection of the beams. In LoS conditions, the selection of the beams is consequential and improves the accuracy by up to 70%. In NLoS situations, it improves accuracy by up to 35%. We find that, averaging multiple RSS snapshots further reduces the number of beams needed and achieves more than 95% accuracy in both LoS and NLoS conditions. Finally, we evaluate the beam prediction time of DeepIA through embedded hardware implementation and show the improvement over the conventional beam sweeping.

Methods for accurate prediction of radio signal quality parameters are crucial for optimization of mobile networks, and a necessity for future autonomous driving solutions. The power-distance relation of current empirical models struggles with describing the specific local geo-statistics that influence signal quality parameters. The use of empirical models commonly results in an over- or under-estimation of the signal quality parameters and require additional calibration studies. In this paper, we present a novel model-aided deep learning approach for path loss prediction, which implicitly extracts radio propagation characteristics from top-view geographical images of the receiver location. In a comprehensive evaluation campaign, we apply the proposed method on an extensive real-world data set consisting of five different scenarios and more than 125.000 individual measurements. It is found that 1) the novel approach reduces the average prediction error by up to 53% in comparison to ray-tracing techniques, 2) A distance of 250-300 meters spanned by the images offer the necessary level of detail, 3) Predictions with a root-mean-squared error of approximately 6 dB is achieved across inherently different data sources.

In this paper, a proactive dynamic spectrum sharing scheme between 4G and 5G systems is proposed. In particular, a controller decides on the resource split between NR and LTE every subframe while accounting for future network states such as high interference subframes and multimedia broadcast single frequency network (MBSFN) subframes. To solve this problem, a deep reinforcement learning (RL) algorithm based on Monte Carlo Tree Search (MCTS) is proposed. The introduced deep RL architecture is trained offline whereby the controller predicts a sequence of future states of the wireless access network by simulating hypothetical bandwidth splits over time starting from the current network state. The action sequence resulting in the best reward is then assigned. This is realized by predicting the quantities most directly relevant to planning, i.e., the reward, the action probabilities, and the value for each network state. Simulation results show that the proposed scheme is able to take actions while accounting for future states instead of being greedy in each subframe. The results also show that the proposed framework improves system-level performance.