Abstract
The use of metaheuristics to solve real-life problems has increased in recent years since they are easy to implement, and the problems become easy to model when applying metaheuristic approaches. However, arguably the most important aspect is the simulation time since results can be obtained from metaheuristic methods in a much smaller time, and with a good approximation to the results obtained with exact methods. In this work, the Genetic Algorithm (GA) metaheuristic is adapted and applied to solve the optimization of electricity markets participation portfolios. This work considers a multiobjective model that incorporates the calculation of the profit and the risk incurred in the electricity negotiations. Results of the proposed approach are compared to those achieved with an exact method, and it can be concluded that the proposed GA model can achieve very close results to those of the deterministic approach, in much quicker simulation time.

Abstract
This paper proposes a novel case-based reasoning (CBR) approach to support the intelligent management of energy resources in a residential context. The proposed approach analyzes previous cases of consumption reduction in houses, and determines the amount that should be reduced in each moment and in each context, in order to meet the users' needs in terms of comfort while minimizing the energy bill. The actual energy resources management is executed using the SCADA House Intelligent Management (SHIM) system, which schedules the use of the different resources, taking into account the suggested reduction amount. A case study is presented, using data from Brazilian consumers. Several scenarios are considered, representing different combinations concerning the type of house/inhabitants, the season, the type of used energy tariff, the use of Photovoltaic system (PV) generation, and the maximum amount of allowed reduction. Results show that the proposed CBR approach is able to suggest appropriate amounts of energy reduction, which result in significant reductions of the energy bill, while, with the use of SHIM, minimizing the reduction of users' comfort.

Abstract
This paper presents a Support Vector Machine (SVM) based approach for energy consumption forecasting. The proposed approach includes the combination of both the historic log of past consumption data and the history of contextual information. By combining variables that influence the electrical energy consumption, such as the temperature, luminosity, seasonality, with the log of consumption data, it is possible for the proposed method by find patterns and correlations between the different sources of data and therefore improves the forecasting performance. A case study based on real data from a pilot microgrid located at the GECAD campus in the Polytechnic of Porto is presented. Data from the pilot buildings are used, and the results are compared to those achieved by several states of the art forecasting approaches. Results show that the proposed method can reach lower forecasting errors than the other considered methods.

Abstract
The increasing penetration of renewable generation brings a significant escalation of intermittency to the power and energy system. This variability requires a new degree of flexibility from the whole system. The active participation of small and medium players becomes essential in this context. This is only possible by using adequate forecasting techniques applied both to the consumption and to generation. However, the large number of incontrollable factors, such as the presence of consumers in the building, the luminosity, or external temperature, makes the forecasting of energy consumption an arduous task. This paper addresses the electrical energy consumption forecasting problem, by studying the correlation between the solar radiation and the electrical consumption of lights. This study is performed by means of three forecasting methods, namely a multi-layer perceptron artificial neural network, a support vector regression method, and a linear regression method. The performed studies are analyzed using data gathered from a real installation - campus of the Polytechnic of Porto, in real time.

Abstract
In the field of gaming artificial intelligence, selecting the appropriate machine learning approach is essential for improving decision-making and automation. This paper examines the effectiveness of deep reinforcement learning (DRL) within interactive gaming environments, focusing on complex decision-making tasks. Utilizing the Unity engine, we conducted experiments to evaluate DRL methodologies in simulating realistic and adaptive agent behavior. A vehicle driving game is implemented, in which the goal is to reach a certain target within a small number of steps, while respecting the boundaries of the roads. Our study compares Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) in terms of learning efficiency, decision-making accuracy, and adaptability. The results demonstrate that PPO successfully learns to reach the target, achieving higher and more stable cumulative rewards. Conversely, SAC struggles to reach the target, displaying significant variability and lower performance. These findings highlight the effectiveness of PPO in this context and indicate the need for further development, adaptation, and tuning of SAC. This research contributes to developing innovative approaches in how ML can improve how player agents adapt and react to their environments, thereby enhancing realism and dynamics in gaming experiences. Additionally, this work emphasizes the utility of using games to evolve such models, preparing them for real-world applications, namely in the field of vehicles' autonomous driving and optimal route calculation.

Abstract
The Industry 4.0 paradigm (I4.0) supports the improvement of industrial processes through Information and Communication Technologies (ICT), with information systems providing real-time information to humans and machines, in order to make the production process more flexible and efficient. In this context, Virtual Assistants (VA) collect and process production data and provide contextualized and real-time information to the workers in the production environment. This paper presents a prototype of a VA developed to collect production data from heterogeneous sources in the factory, process them based on contextual information, and provide workers with useful information to assist them in taking informed decisions. In that context, VA can represent a valuable aid to improve overall productivity and efficiency in the I4.0 factories. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.