In this paper, we focus on a cache-enabled networks, where a content requested by user equipments (UEs) can be delivered by means of multi-hop relaying via unmanned aerial vehicles (UAVs) and/or via other UEs exploiting device-to-device (D2D) communication. For such scenario, we optimize transmission power allocation, bandwidth allocation, and route selection to minimize the content delivery duration. The formulated problem is a mixed-integer nonlinear programming (MINLP) problem and, thus, it is hard to solve. Hence, we first solve the power and bandwidth allocation by a cooperative game among all transmitting nodes involved in the content delivery process and we prove that this game is a potential game. Then, we introduce a fast-converging iterative algorithm employing an approximate better-response mechanism for the resource allocation (i.e., power and bandwidth). After that, we design a low-complexity greedy algorithm jointly handling route selection and power and bandwidth allocation. The algorithm selects transmission routes to deliver the requested contents to the UEs and, after each selection, the resource allocation at the transmitting nodes involved in the content delivery process (i.e., GBS, UAVs, and relaying UEs) is updated. The simulation results demonstrate that the proposed scheme reduces the average content delivery duration by up to 23.2% compared to the best-performing benchmark algorithm.

In this paper, we focus on a cache-enabled multi-hop network, where the unmanned aerial vehicles (UAVs), the user equipment (UEs), or both can serve as relays to deliver contents to individual users from a ground base station (GBS). We formulate a power optimization problem with the objective to minimize the sum content delivery delay. We show the optimization problem is non-convex, thus, we propose a novel heuristic algorithm to allocate the power to individual contents at individual hops in multi-hop scenario. The proposed heuristic algorithm iteratively re-allocates the transmission power among the contents at the same transmitting node. To reduce the number of iteration, the proposed algorithm enables parallel power re-allocation for multiple content pairs and dynamic adaptation of power re-allocation steps, thereby enabling faster convergence of the algorithm. We demonstrate that our proposal reduces the average content delivery duration by up to 31.8 % compared to state-of-the-art works. At the same time, proposal is suitable for real systems due to a very fast convergence.

The caching paradigm has been introduced to alleviate backhaul traffic load and to reduce latencies due to massive never ending increase in data traffic. To fully exploit the benefits offered by caching, unmanned aerial vehicles (UAVs) and device-to-device (D2D) communication can be further utilized. In contrast to prior works, that strictly limits the content delivery routes up to two hops, we explore a multi-hop communications scenario, where the UAVs, the UEs, or both can relay the content to individual users. In this context, we formulate the problem for joint route selection and power allocation to minimize the overall system content delivery duration. First, motivated by the limitations of existing works, we consider the case where the nodes may transmit content simultaneously rather than sequentially and propose simple yet effective approach to allocate the transmission power. Second, we design a low-complexity greedy algorithm jointly handling route selection and power allocation. The simulation results demonstrate that the proposed greedy algorithm outperforms the benchmark algorithm by up to 56.98% in terms of content delivery duration while it achieves close-to-optimal performance.

Wireless communication systems heavily rely on accurate path loss prediction for effective radio frequency (RF) planning. In this paper, we propose a novel approach to path loss prediction by leveraging explainable machine learning techniques. Leveraging a public data set containing crucial environmental factors such as distance, longitude, latitude, elevation, altitude, and clutter height, we employ Extreme Gradient Boosting (XGBoost). Through rigorous cross-validation, we determine the optimal parameters for the XGBoost model. Subsequently, we apply explainable machine learning techniques, including SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), to unlock the black box of machine learning method and gain deeper insights into the model's predictions. Some visualizations to enrich our understanding of the relationships between input features and path loss are presented. This study offers transparency and interpretability in path loss prediction by its findings, thereby enhancing the applicability of machine learning in RF planning.

The design and deployment of fifth-generation (5G) wireless networks pose significant challenges due to the increasing number of wireless devices. Path loss has a landmark importance in network performance optimization, and accurate prediction of the path loss, which characterizes the attenuation of signal power during transmission, is critical for effective network planning, coverage estimation, and optimization. In this sense, we utilize machine learning (ML) methods, which overcome conventional path loss prediction models drawbacks, for path loss prediction in a 5G network system to facilitate more accurate network planning, resource optimization, and performance improvement in wireless communication systems. To this end, we utilize a novel approach, nested cross validation scheme, with ML to prevent overfitting, thereby getting better generalization error and stable results for ML deployment. First, we acquire a publicly available dataset obtained through a comprehensive measurement campaign conducted in an urban macro-cell scenario located in Beijing, China. The dataset includes crucial information such as longitude, latitude, elevation, altitude, clutter height, and distance, which are utilized as essential features to predict the path loss in the 5G network system. We deploy Support Vector Regression (SVR), CatBoost Regression (CBR), eXtreme Gradient Boosting Regression (XGBR), Artificial Neural Network (ANN), and Random Forest (RF) methods to predict the path loss, and compare the prediction results in terms of Mean Absolute Error (MAE) and Mean Square Error (MSE). As per obtained results, XGBR outperforms the rest of the methods. It outperforms CBR with a slight performance differences by 0.4% and 10% in terms of MAE and MSE metrics, respectively. On the other hand, it outperforms the rest of the methods with clear performance differences. Ultimately, the paper presents ML deployment with the novel approach from which network planning, resource optimization, and performance improvement in wireless communication systems will benefit as well according to the obtained results.

Fifth-generation (5G) mobile communication networks have recently emerged in various fields, including high-speed trains. However, the dense deployment of 5G millimeter wave (mmWave) base stations (BSs) and the high speed of moving trains lead to frequent handovers (HOs), which can adversely affect the Quality-of-Service (QoS) of mobile users. As a result, HO optimization and resource allocation are essential considerations for managing mobility in high-speed train systems. In this paper, we model system performance of a high-speed train system with a novel machine learning (ML) approach that is nested cross validation scheme that prevents information leakage from model evaluation into the model parameter tuning, thereby avoiding overfitting and resulting in better generalization error. To this end, we employ ML methods for the high-speed train system scenario. Handover Margin (HOM) and Time-to-Trigger (TTT) values are used as features, and several KPIs are used as outputs, and several ML methods including Gradient Boosting Regression (GBR), Adaptive Boosting (AdaBoost), CatBoost Regression (CBR), Artificial Neural Network (ANN), Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and k-Nearest Neighbor Regression (KNNR) are employed for the problem. Finally, performance comparisons of the cross validation schemes with the methods are made in terms of mean absolute error (MAE) and mean square error (MSE) metrics are made. As per obtained results, boosting methods, ABR, CBR, GBR, with nested cross validation scheme superiorly outperforms conventional cross validation scheme results with the same methods. On the other hand, SVR, KNRR, KRR, ANN with the nested scheme produce promising results for prediction of some KPIs with respect to their conventional scheme employment.