Eduardo Pires

Abstract
Wind power is becoming an important source of electrical energy production. In an onshore wind farm (WF), the electrical energy is collected at a substation from different wind turbines through electrical cables deployed over ground ditches. This work considers the WF layout design assuming that the substation location and all wind turbine locations are given, and a set of electrical cable types is available. The WF layout problem, taking into account its lifetime and technical constraints, involves selecting the cables to interconnect all wind turbines to the substation and the supporting ditches to minimize the initial investment cost plus the cost of the electrical energy that is lost on the cables over the lifetime of the WF. It is assumed that each ditch can deploy multiple cables, turning this problem into a more complex variant of previously addressed WF layout problems. This variant turns the problem best fitting to the real case and leads to substantial gains in the total cost of the solutions. The problem is defined as an integer linear programming model, which is then strengthened with different sets of valid inequalities. The models are tested with four WFs with up to 115 wind turbines. The computational experiments show that the optimal solutions can be computed with the proposed models for almost all cases. The largest WF was not solved to optimality, but the final relative gaps are small.

Abstract
A new algorithm based on the ant colony optimization (ACO) method for the multiple traveling salesman problem (mTSP) is presented and defined as ACO-BmTSP. This paper addresses the problem of solving the mTSP while considering several salesmen and keeping both the total travel cost at the minimum and the tours balanced. Eleven different problems with several variants were analyzed to validate the method. The 20 variants considered three to twenty salesmen regarding 11 to 783 cities. The results were compared with best-known solutions (BKSs) in the literature. Computational experiments showed that a total of eight final results were better than those of the BKSs, and the others were quite promising, showing that with few adaptations, it will be possible to obtain better results than those of the BKSs. Although the ACO metaheuristic does not guarantee that the best solution will be found, it is essential in problems with non-deterministic polynomial time complexity resolution or when used as an initial bound solution in an integer programming formulation. Computational experiments on a wide range of benchmark problems within an acceptable time limit showed that compared with four existing algorithms, the proposed algorithm presented better results for several problems than the other algorithms did.

Abstract
The massive industrialization of products in a factory environment requires testing the product at a stage before its exportation to the sales market. For example, the end-of-line tests at Continental Advanced Antenna contribute to the validation of an antenna's functionality, a product manufactured by this organization. In addition, the storage of information from the testing process allows the data manipulation through automated machine learning algorithms in search of a beneficial contribution. Studies in this area (automatic learning/machine learning) lead to the search and development of tools designed with objectives such as preventing anomalies in the production line, predictive maintenance, product quality assurance, forecast demand, forecasting safety problems, increasing resources, proactive maintenance, resource scalability, reduced production time, and anomaly detection, isolation, and correction. Once applied to the manufacturing environment, these advantages make the EOL system more productive, reliable, and less time-consuming. This way, a tool is proposed that allows the visualization and previous detection of trends associated with faults in the antenna testing system. Furthermore, it focuses on predicting failures at Continental's EOL.

Abstract
The last two decades have witnessed a new paradigm in terms of electrical energy production. The production of electricity from renewable sources has come to play a leading role, thus allowing us not only to face the global increase in energy consumption, but also to achieve the objectives of decarbonising the economies of several countries. In this scenario, where onshore wind energy is practically exhausted, several countries are betting on constructing offshore wind farms. Since all the costs involved are higher when compared to onshore, optimising the efficiency of this type of infrastructure as much as possible is essential. The main aim of this paper was to develop an optimisation model to find the best wind turbine locations for offshore wind farms and to obtain the wind farm layout to maximise the profit, avoiding cable crossings, taking into account the wake effect and power losses. The ideal positioning of wind turbines is important for maximising the production of electrical energy. Furthermore, a techno-economic analysis was performed to calculate the main economic indicators, namely the net present value, the internal rate of return, and the payback period, to support the decision-making. The results showed that the developed model found the best solution that maximised the profits of the wind farm during its lifetime. It also showed that the location of the offshore substation played a key role in achieving these goals.

Abstract
Currently, distributed software systems have evolved at an unprecedented pace. Modern software-quality requirements are high and require significant staff support and effort. This study investigates the use of a supervised machine learning model, a Multi-Layer Perceptron (MLP), for anomaly detection in microservices. The study covers the creation of a microservices infrastructure, the development of a fault injection module that simulates application-level and service-level anomalies, the creation of a system monitoring dataset, and the creation and validation of the MLP model to detect anomalies. The results indicate that the MLP model effectively detects anomalies in both domains with higher accuracy, precision, recovery, and F1 score on the service-level anomaly dataset. The potential for more effective distributed system monitoring and management automation is highlighted in this study by focusing on service-level metrics such as service response times. This study provides valuable information about the effectiveness of supervised machine learning models in detecting anomalies across distributed software systems.