Loading...
10 results
Search Results
Now showing 1 - 10 of 10
- Developing a new simulation and visualization platform for researching aspects of mobile network performancePublication . Amaro, C.; Saraiva, T.; Duarte, D.; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, A.Nowadays, mobile networks represent one of the most innovative and challenging technological and research-oriented fields of work. The growth on user subscriptions and the advances introduced by Artificial Intelligence (AI) and Internet of Things (IoT), greatly enhanced the complexity and potential of communication networks. The increase on variety of devices and exchanged mobile data traffic resulted in demanding requirements for the network providers. As networks tend to scale and data to increase, some problems start to arise. Traffic congestion, packet loss and high latency being some examples. Therefore, it is important to introduce powerful tools and methods to tackle these challenges. On this perspective, several studies have highlighted AI systems, mainly Machine Learning (ML) algorithms, as the most promising methods, in the context of wireless networks, by improving the overall performance and efficiency. This work proposes to integrate several network optimization algorithms, already developed, in a common and unified visualization platform. These algorithms were developed in C# and Python and some of them use supervised and unsupervised ML techniques. The proposed solution includes multi-threading processes to deal with concurrent simulations, a proxy to communicate between platforms and a dynamic visual interface.
- An ubiquitous 2.6 GHz radio propagation model for wireless networks using self-supervised learning from satellite imagesPublication . Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioThe performance of any Mobile Wireless Network (MWN) is dependent on the appropriate level of radio coverage, with Path Loss (PL) models being a valuable resource for its evaluation. Recently, advancements in Machine Learning (ML) and Deep Neural Networks (DNNs) have been applied to radio propagation to produce new data-driven PL models. Notoriously, these advancements have also allowed the inclusion of non-classical inputs, such as satellite images. However, data-driven PL models are often developed under the assumption that training and test data distributions are similar, which is a weak assumption in real-world scenarios. Thus, generalization (i.e., the model’s ability to perform on different data distributions) is a crucial aspect of data-driven PL models in the context of Mobile Network Operators (MNOs). This paper proposes a new data-driven PL model, the Ubiquitous Satellite Aided Radio Propagation (USARP) model, developed to enhance the geographical generalization capabilities of empirical PL models, by using satellite images. The USARP model considers self-supervised learning to extract general data representations of the radio environment from satellite images, improving the PL prediction Root Mean Square Error (RMSE) of the 3rd Generation Partnership Project (3GPP) PL model in the order of 9 dB, and for a data distribution distinct from the training data. Moreover, it was demonstrated the potential of the USARP model in terms of geographical and radio environment generalization. Although the generalization capabilities of ML regression algorithms are limited, the chosen USARP architecture and the use of regularization techniques had a positive impact on its geographical generalization performance.
- Root cause analysis of low throughput situations using boosting algorithms and the TreeShap analysisPublication . Cilinio, M.; Duarte, David; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, A.Detecting and diagnosing the root cause of failures in mobile networks is an increasingly demanding and time consuming task, given its technological growing complexity. This paper focuses on predicting and diagnosing low User Downlink (DL) Average Throughput situations, using supervised learning and the Tree Shapley Additive Explanations (SHAP) method. To fulfill this objective, Boosting classification models are used to predict a failure/non-failure binary label. The influence of each counter on the overall model’s predictive performance is performed based on the TreeSHAP method. From the implemen tation of this technique, it is possible to identify the main causes of low throughput, based on the analysis of the most critical counters in fault detection. Furthermore, from the identification of these counters, it is possible to define a system for diagnosing the most probable throughput degradation cause. The described methodology allowed not only to identify and quantify low throughput situations in a live network due to the occurrence of misadjusted configuration parameters, radio problems and network capacity problems, but also to outline a process for solving them.
- Automated joint access and backhaul planning for 5G millimeter-wave small cell networksPublication . Marques, Beatriz; Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, A.Mobile backhauling, small cells and millimeter waves (mmWaves) are key important technologies to support the next-generation cellular networks. The 5th generation (5G) radio networks introduce several different elements from the previous generations and hence, network planning became even more complex. In this work, the focus is on creating a radio network planning algorithm towards 5G mmWave small cell architectures. The algorithm is divided between the radio access network and the backhaul network. The former aims to find optimal locations for small cells to guarantee coverage requirements, while the latter creates backhaul links between the small cells according to a specific topology, and chooses which of them should be gateways. The results give some insights on base station (BS) and gateway density, and demonstrate that the topology most likely to meet Quality of Service (QoS) requirements, while minimizing the number of gateways, is the mesh network. However, tree and star topologies are also useful in certain scenarios. The work also includes a comparison between the 28 GHz and 60 GHz frequency bands, which are two common candidates for mmWave backhauling.
- Lisbon mobility simulations for performance evaluation of mobile networksPublication . Vieira, Pedro; Vieira, Manuel; Queluz, Maria Paula; Rodrigues, AntónioIn this paper a novel realistic vehicular mobility model is introduced. It captures the moving-in-groups, conscious travelling, and introduces the concept of smart travelling while following drivers’ social behavior extracted from inquiries and experimental traffic measurements. Under the model, a routing algorithm is considered. The routing algorithm minimizes the distance to a target on a step by step form, in every street crossing. This is done under a hierarchic street level structure that optimizes travel speed and quality. The mobility model was simulated for Lisbon case study and directional statistical results were compared with experimental measurements from Lisbon Municipality control center. The output shows a good correlation between simulated and experimental values.
- A machine learning driven methodology for alarm prediction towards self-healing in wireless networksPublication . Mata, Luís; Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioAlthough Artificial Intelligence (AI) is already used by 5th Generation (5G) to support specific network functions, the increased complexity of 6th Generation (6G) will demand the adoption of extended AI capabilities to enhance network efficiency. Moreover, high network performance and availability at a sustainable cost will be crucial to emerging applications, such as autonomous vehicles and smart cities. In this context, operators are expected to implement Self-Healing Operations (SHOs) to transition from reactive handling of network faults to a preventive approach, relying on statistical learning of network data. This paper proposes a Machine Learning (ML)-driven methodology to predict network faults using generic Fault Management (FM) data, enabling the implementation of preventive actions to avoid service degradation or failure. The evaluation of this methodology using live network data revealed statistical associations among certain network faults, considering both time and root-cause factors. Therefore, FM data and two ML models, namely Logistic Regression (LR) and Light Gradient Boosting Model (LGBM), were used to predict network faults, achieving a 93% success rate within a 60-minute anticipation period.
- Analysis and optimization of 5G coverage predictions using a beamforming antenna model and real drive test measurementsPublication . Sousa, Marco; Alves, André; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioThe ability to estimate radio coverage accurately is fundamental for planning and optimizing any wireless network, notably when a new generation, as the 5(th) Generation (5G), is in an early deployment phase. The knowledge acquired from radio planning of previous generations must be revisited, particularly the used path loss and antennas models, as the 5G propagation is intrinsically distinct. This paper analyses a new beamforming antenna model and distinct path loss models - 3(rd) Generation Partnership Project (3GPP) and Millimetre-Wave Based Mobile Radio Access Network for Fifth Generation Integrated Communications (mmMAGIC) - applying them to evaluate 5G coverage in 3-Dimensional (3D) synthetic and real scenarios, for outdoor and indoor environments. Further, real 5G Drive Tests (DTs) were used to evaluate the 3GPP path loss model accuracy in Urban Macro (UMa) scenarios. For the new antenna model, it is shown that the use of beamforming with multiple vertical beams is advantageous when the Base Station (BS) is placed below the surrounding buildings; in regular UMa surroundings, one vertical beam provides adequate indoor coverage and a maximized outdoor coverage after antenna tilt optimization. The 3GPP path loss model exhibited a Mean Absolute Error (MAE) of 21.05 dB for Line-of-Sight (LoS) and 14.48 dB for Non-Line-of-Sight (NLoS), compared with real measurements. After calibration, the MAE for LoS and NLoS decreased to 5.45 dB and 7.51 dB, respectively. Moreover, the non-calibrated 3GPP path loss model led to overestimations of the 5G coverage and user throughput up to 25% and 163%, respectively, when compared to the calibrated model predictions. The use of Machine Learning (ML) algorithms resulted in path loss MAEs within the range of 4.58 dB to 5.38 dB, for LoS, and within the range of 3.70 dB to 5.96 dB, for NLoS, with the Random Forest (RF) algorithm attaining the lowest error.
- On the Use of Spatial Graphs for Performance Degradation Root-Cause Analysis Toward Self-Healing Mobile NetworksPublication . Mata, Luís; Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioOn the road to the sixth generation of cellular networks (6G), the need to ensure a sustainable usage of natural resources, amid increased competition and cost pressures, has driven the adoption of text Self-Healing Mobile Networks to enhance operational efficiency of current and future wireless networks. This paradigm shift relies on Artificial Intelligence (AI) to increase automation of network functions, notably by applying predictive fault detection and automatic root-cause analysis. In this context, this paper proposes a Deep Learning (DL) model for text self-healing operations based on a Spatial Graph Convolutional Neural Network (SGCN), which is applied to evaluate the performance degradation of Base Stations (BSs) and uncover the underlying root-causes. The advantages of the proposed DL model are threefold. Firstly, it is especially suited for wireless network applications, leveraging the SGCN to account for spatial dependencies among BSs and their physical characteristics. Secondly, the proposed model offers the flexibility to process diverse types of predictive features, including Performance Management (PM), Fault Management (FM), or other data types. Thirdly, it incorporates an explainability module that pinpoints the input features, such as PM counters, with the most significant influence on BS performance, thereby shedding light on its root-cause factors. The proposed model was evaluated on a live 4G network dataset and the results confirmed its effectiveness in identifying BS performance degradation. An F1-score of 89.6% was achieved in the classification of performance failures, which includes a 27% reduction in false negatives compared to prior research outcomes. In a live network environment, this reduction translates into substantial improvements in Quality of Experience (QoE) for the end users and cost savings for the Mobile Network Operators (MNOs).
- Evaluating 5G coverage in 3D scenarios under configurable antenna beam patternsPublication . Jesus, Francisco; Sousa, Marco; Freitas, Filipe; Vieira, Pedro; Rodrigues, A.; Queluz, Maria PaulaActive Antenna Systems (AASs) play a key role in the performance of 5 th Generation (5G) networks as they enable the use of Massive Multiple-Input Multiple-Output (mMIMO) and directional beamforming. Besides, AASs can be configured with distinct broadcast beams configurations. In this work, the coverage provided by the broadcast beam configurations of a real AAS is evaluated. A 3-Dimensional (3D) configurable synthetic scenario was proposed to evaluate the resulting 5G coverage from all the possible antenna beam configurations. This analysis revealed that beam configurations with several horizontal beams and one vertical are recommended for urban macro deployments. Moreover, it was demonstrated that the percentage of covered area in a real scenario is approximated by an equivalent synthetic scenario with a Pearson correlation of 0.98. The synthetic scenario has the advantage of not requiring 3D building databases. Finally, an interference analysis in multi-site real scenarios was conducted, where it was verified that some antenna configurations introduce excessive interference for the level of coverage provided.
- Improving a cluster based directional channel model in realistic macro-cell environmentPublication . Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioIn this paper a realistic directional channel model that is an extension of the COST 273 channel model is presented. The model uses a cluster of scatterers and visibility region generation based strategy with increased realism, due to the introduction of terrain and clutter information. New approaches for path-loss prediction and line of sight modeling are considered, affecting the cluster path gain model implementation. The new model was implemented using terrain, clutter, street and user mobility information for the city of Lisbon, Portugal. Some of the model's outputs are presented, mainly path loss and small/large-scale fading statistics.