Search

In 2021, the residential sector had an electricity consumption of around 39% in México. Householders influence the quantity of energy they manage in a home due to their preferences, culture, and economy. Hence, profiling the householders' behavior in communities allows designers or engineers to build strategies that promote energy reductions. The household socially connected products ease routine tasks and help profile the householder. Furthermore, gamification strategies model householders' habits by enhancing services through ludic experiences. Therefore, a gamified smart community concept emerged during this research as an understanding that this type of community does not need a physical location but has similar characteristics. Thus, this paper proposes a three-step framework to tailor interfaces. During the first step, the householder type and consumption level were analyzed using available online databases for Mexico. Then, two artificial neural networks were built, trained, and deployed during the second step to tailor an interactive interface. Thus, the third step deploys an interactive and tailored dashboard. Moreover, the research analysis reflected the predominant personality traits. Besides, some locations have more electricity consumption than others associated with the relative humidity, the outdoor temperature, or the poverty level. The interactive dashboard provides insights about the game elements needed depending on the personality traits, location, and electricity bill. Therefore, this proposal considers all householders (typical and non-typical users) to deploy tailored interfaces designed for smart communities. Currently, the game elements proposed during this research are reported by the literature, so their adoption is assured. [ABSTRACT FROM AUTHOR]

Due to the intermittent nature of solar energy, accurate photovoltaic power predictions are very important for energy integration into existing energy systems. The evolution of deep learning has also opened the possibility to apply neural network models to predict time series, achieving excellent results. In this paper, a five layer CNN-LSTM model is proposed for photovoltaic power predictions using real data from a location in Temixco, Morelos in Mexico. In the proposed hybrid model, the convolutional layer acts like a filter, extracting local features of the data; then the temporal features are extracted by the long short-term memory network. Finally, the performance of the hybrid model with five layers is compared with a single model (a single LSTM), a CNN-LSTM hybrid model with two layers and two well known popular benchmarks. The results also shows that the hybrid neural network model has better prediction effect than the two layer hybrid model, the single prediction model, the Lasso regression or the Ridge regression. [ABSTRACT FROM AUTHOR]