Emerging serious games mark the beginning of a new era in video games. Emerging serious games introduce advances in distributed artificial intelligence into their design in order to guide the player’s manipulation of a specific subject in an adaptive way. In this article, we present a city simulator game, called Metropolis, which generates emergent properties. Metropolis can be used by a smart city for city planning, to make collective decisions, and for other purposes. This paper describes why Metropolis can be classified as a serious game. It also analyzes how its emergent properties can be used for managing a smart city, and especially how it promotes e-participation as an e-decision-making tool within the context of urban planning. In addition, this paper explores how Metropolis can be used to analyze a smart city’s emergent citizen and urban patterns (urban spatial distribution) based on strong e-participation.

Un motor de juegos serios emergentes (MJSE) debe hacer explícito la posibilidad de emergencia en un juego serio, a partir delmanejo coordinado de tramas de juegos, adaptadas al contexto educativo especifico donde se esté desarrollando el juego. En particular, en anteriores trabajos se ha propuesto una arquitectura jerárquica para el MJSE, constitutiva de submotores. El objetivo principal de este trabajo es especificar los submotores encargados del proceso de emergencia del juego serio, los cuales se basan en el algoritmo de optimización basado en colonias de hormigas (ACO). Dichos submotores realizan la gestión del conjunto de tramas de juego según el contexto-dominio educativo de interés, de tal manera de fusionarlas en una única trama, para hacer de esta forma emerger la dinámica del juego serio. Adicionalmente, en este trabajo se analiza el comportamiento de dichos submotores en un caso de estudio, mostrando resultados muy alentadores como MJSE.

This work defines a new component of the emerging serious game engine, called the plot adaptive system, which allows the updating of a serious game according to the theme that is being given in a smart classroom. This component is based on an Ant Colony Optimization Algorithm that changes the plots/frames in the game to follow the desired theme in the smart classroom. Thus, this new component manages a set of game plots that may be of interest in an educational-context to dynamically modify a serious game initially conceived for a subject taught in the smart classroom, in order to adequate it to the current pedagogical context. The novelty of the approach is that it adapts the serious game to the educational context where it takes place. Additionally, this paper analyzes the behavior of the plot adaptive system in a case study, and presents three experiments with very encouraging results

A video game adaptation system (SAV) for serious emergent games (JSE), allows emergent behaviors in the game, such as the appearance of environments, events, narratives and characters, among others, in order to adapt to the context in the one that is developing. In previous articles the architecture of a JSE engine has been proposed. Furthermore, a first subsystem has been proposed that allows the emergence of a JSE according to the objectives of the environment, based on the ant colony optimization algorithm (ACO). In the present work, the second component of said architecture is specified, the SAV, which allows its dynamic adaptation (during the JSE). The SAV is made up of the sub-layers of strategies, sequences and properties, which manage each of these types of possible emergencies in a JSE, with the intention of dynamically adapting it to the context-domain where the game is being played. Furthermore, in this work the behavior of these sublayers is analyzed in a specific case study, showing very encouraging results of SAV in the educational context of an intelligent classroom (SaCI).

The integration of photovoltaic (PV) energy into the power grid requires precise forecasting due to its dependence on the variability of weather conditions. This study explores the effectiveness of neural network models for predicting PV energy generation using historical meteorological and temporal data from Austria over a two-year period. We implement and compare multiple neural machine learning approaches, including Multilayer Perceptrons (MLPs), Recurrent Neural Networks (RNNs), and Convolutional Neural Networks (CNNs), against traditional statistical models such as Decision Trees (DTs), Linear Regression (LR), and Random Forest (RF). Our methodology introduces novel data preprocessing techniques, including cyclical encoding of time features, to improve prediction accuracy. Results demonstrate that RNN models outperform other architectures in single-step forecasting, achieving a Mean Squared Error (MSE) of 0.045 and a Mean Absolute Error (MAE) of 0.0427, while CNNs prove superior for multi-step predictions. These findings highlight the potential benefits of applying predictive deep learning techniques for optimal PV energy management, contributing to grid stability and sustainability. This study systematically compares the effectiveness of traditional and deep learning models for photovoltaic energy prediction under the same data preprocessing conditions, including the cyclical encoding of temporal features that provides a continuous representation of the time frame allowing its use as an input feature. This study identifies the specific strengths of each model (RNN for single-step prediction, CNN for multi-step prediction) for Central European climates, validated on Austria’s unique meteorological dataset.