Abstract
The automotive industry is witnessing a surge in the production of electric vehicles (EVs) driven by stringent emission regulations. Despite this growth, heavy-duty truck fleets, particularly in waste collection, remain predominantly combustion-based ones. Waste collection is critical in urban environments, presenting unique challenges due to confined operational regions. One alternative to increase EVs in waste collection is to substitute the smaller truck fleets used for waste collection in constrained environments, such as narrow streets, by EVs. In this paper, we present a new formulation for the waste collection problem that considers a truck fleet comprised of smaller EVs and regular combustion trucks. The smaller trucks are proposed for the waste collection of specific sites (i.e. dumpsters in narrow streets). Our formulation considers battery limitations of electric trucks and flexible time windows for the waste collection task. The solution was validated by comparing the emission of CO2 and collection costs of a fleet comprised solely of combustion trucks and the hybrid fleet proposed here. The results showed that using a hybrid fleet significantly reduced waste collection costs and environmental impacts.

Abstract
The Integrated Access and Backhaul (IAB) 5G network architecture, introduced in 3GPP Release 16, leverages a shared 5G spectrum for both access and backhaul networks. Due to the novelty of IAB, there is a lack of suitable implementations and performance evaluations. This paper addresses this gap by proposing EMU-IAB, a mobility emulator for private standalone 5G IAB networks. The proposed emulation environment comprises a 5G Core Network, an IAB-enabled Radio Access Network (RAN), leveraging the Open-RAN (O-RAN) architecture. The RAN includes a fixed IAB Donor, a mobile IAB Node, and multiple User Equipments (UEs). The mobility of the IAB Node is managed through EMU-IAB, which allows defining the path loss of emulated wireless channels. The validation of EMU-IAB was conducted under a realistic IAB node mobility scenario, addressing different traffic demand from the UEs.

Abstract
Grid-forming (GF) converters based on renewable energy sources are a fundamental piece of future power systems. In particular, the design specifications of GF converters in photovoltaic (PV) applications are difficult to meet because PV inverters lack energy storage. The operation of GF-PV inverters under normal conditions has already been addressed in the existing literature. However, the operation in case of large disturbances, such as faults, has rarely been explored. In this paper, a GF controller for a two-stage PV inverter that is robust against faults is presented. This control system includes several improvements compared to the traditional GF controller. Power feedforwards and saturations are applied to improve the transient performance. Also, a method to keep the virtual swing equation synchronised when the current saturates is presented. Remarkably, there is no need to change the controller structure during faults. Simulations of a PV inverter connected to a simple power system based on a diesel generator and loads are conducted. The results show that the proposed countermeasures improve the performance of GF-PV inverters in case of faults. In addition, it is shown that keeping the phase of the virtual swing equation and the grid voltage space vector synchronised is important to avoid the collapse of the dc-link voltage. Suggestions for further research are presented in the last part of the work.

Abstract
Multi-Access Edge Computing (MEC) represents the central concept that enables the creation of new applications and services that bring the benefits of edge computing to networks and users. By implementing applications and services at the edge, close to users and their devices, it becomes possible to take advantage of extremely low latency, substantial bandwidth, and optimized resource usage. However, enabling this approach requires careful integration between the MEC framework and the open 5G core. This work is dedicated to designing a new service that extends the functionality of the Multi-Access Traffic Steering (MTS) API, acting as a strategic bridge between the realms of MEC and the 5G core. To accomplish this objective, we utilize free5GC (open-source project for 5G core) as our 5G core, deployed on the Kubernetes cluster. The proposed service is validated using this framework, involving scenarios of high user density. To conclude whether the discussed solution is valid, KPIs of 5G MEC applications described in the scientific community were sought to use as a comparison parameter. The results indicate that the service effectively addresses the described issues while demonstrating its feasibility in various use cases such as e-Health, Paramedic Support, Smart Home, and Smart Farms.

Abstract
In various machine learning applications, classification plays an important role in categorizing and predicting data. To improve the classification performance, it is crucial to identify and remove the anomalies. Also, class imbalance in many machine learning applications is a very common problem since most classifiers tend to be biased toward the majority class by ignoring the minority class instances. Thus, in this research, we propose a new under-sampling technique based on anomaly detection and removal to enhance the performance of imbalanced classification problems. To demonstrate the effectiveness of the proposed method, comprehensive experiments are conducted on forty imbalanced data sets and two non-parametric hypothesis tests are employed to show the statistical difference in classification performances between the proposed method and other traditional resampling methods. From the experiment, it is shown that the proposed method improves the classification performance by effectively detecting and eliminating the anomalies among true-majority or pseudo-majority class instances.

Abstract
Several approaches have been developed over time aiming to improve the localization aspects, especially in mobile robotics. Besides the more traditional techniques, mainly based on analytical models, artificial intelligence has emerged as an interesting alternative. The current study proposes to explore the machine learning model structure optimization for pose estimation, using the RobotAtFactory 4.0 competition as the main context. Using a Bayesian Optimization-based framework, the parameters of a Multi-Layer Perceptron (MLP) model, trained to estimate the components of the 2D pose (x, y, and theta) of the robot were optimized in four different scenarios of the same context. The results obtained showed a quality improvement of up to 60% on the estimation when compared with the modes without any optimization. Another aspect observed was the different optimizations found for each model, even in the same scenario. An additional interesting result was the possibility of the reuse of optimization between scenarios, presenting an interesting approach to reduce time and computational resources.