This paper presents an evaluation of the use of deep learning architectures for forecasting electrical energy consumption in residential environments. The main contribution of this study lies in the development and assessment of a hybrid forecasting framework that integrates multiscale temporal analysis and weather data, enabling evaluation of predictive performance across different temporal granularities, forecast horizons, and aggregation levels. Single and hybrid models were compared, trained with high-resolution data from a single residence, both considering only endogenous variables and including exogenous variables (weather data). The results showed that, among all models tested in this study, the hybrid LSTM + GRU model achieved the highest predictive performance, with R² values of 94.62% using energy data and 95.25% when weather variables were included. Intermediary granularities, particularly the 6 steps, offered the best balance between temporal detail and predictive robustness for the tests performed. Furthermore, short-time windows aggregation (1 to 5 min) showed better accuracy, while the inclusion of weather data in scenarios with larger aggregation windows and longer horizons provided additional gains. The results reinforce the potential of hybrid deep learning models as effective tools for forecasting residential electricity consumption, with possible practical applications in energy management, automation, and integration of distributed energy resources.

In environments with numerous converters, there is a need for highly efficient. The LLC resonant converter is a good candidate for microgrid applications, as it features low switching losses and a wide voltage regulation range. However, designing magnetic components with lower losses remains a challenge for designers. This paper presents a methodology for reducing losses in the LLC resonant converter by integrating the tank design with the construction design of the transformer and resonant inductor. An algorithm generates a list of feasible components, filtered by constraints on flux density, core temperature, inductance, and winding resistance. The filters select resonant tank element designs that operate at the ideal core temperature, with fewer turns, and that limit current circulation. The tank elements were constructed for validation through experimental results on a 1 kW prototype. Experimental results demonstrated a peak efficiency of 97.48% under ideal thermal conditions. Losses in the resonant tank were reduced by 6.6% compared to ambient operation. Further efficiency (up to 97.52%) was achieved by increasing the magnetizing inductance. The results confirm that the integration of the magnetic design with the design of the resonant tank allows the reduction of losses in LLC converters.

Although Brazil is in the last mile of achieving universal electricity access, the Amazon region represents the country’s most critical electrification frontier, where remote energy expansion has largely failed to integrate clean alternatives. This study presents the design and techno-economic assessment of a hybrid off-grid microgrid tailored for the Amazon, incorporating a multi-source architecture that combines micro-hydro (MH), wind power (WT), solar photovoltaics (PV), diesel generation (DG), and battery energy storage systems (BESS). Three locations in Amazonas, Roraima, and Tocantins were evaluated under three scenarios: a hybrid system with DG, a fully renewable system without DG, and a green scenario that accounts for demand-side flexibility and selected technical and economic conditions. Optimization was performed using the HOMER tool for a typical isolated community. The hybrid configuration achieved a DG generation share of 0.7 (RSS, DG–WT–PV–MH–BESS), 0.9% (Jalapão, DG–WT–PV–MH–BESS), and 6.8% (Labrea, DG–PV–BESS). The fully renewable scenario resulted in Levelized Cost of Energy (COE) values ranging from 0.146 USD/kWh (RSS) to 0.388 USD/kWh (Lábrea), while the green scenario yielded COEs between 0.089 USD/kWh (RSS) and 0.190 USD/kWh (Lábrea). This study reveals the role of MH in reducing storage requirements, installed capacity, and system cost. The results are promising for presenting a competitive cost of energy.

Este capítulo apresenta uma análise técnica e comparativa do desempenho de quatro sensores industriais de corrente, dois baseados no efeito Hall (LA 100-P e ACS712) e dois transformadores de corrente (SCT-013 e DCT104), aplicados a conversores CC-CA (inversores) voltados para microrredes e eletromobilidade. O estudo investiga o comportamento dos transdutores operando em condições de subutilização da faixa dinâmica, limitando a medição a apenas 5% do valor nominal máximo de cada componente. A avaliação é fundamentada em duas métricas principais: a Relação Sinal-Ruído (SNR), quantificada a partir do sinal de saída utilizando a Transformada Rápida de Fourier (FFT), e a banda passante, aferida experimentalmente por meio de um analisador de redes vetorial adotando o critério de atenuação de -3 dB. Os resultados experimentais indicam que as maiores larguras de banda e os melhores níveis de SNR correspondem aos sensores LA 100-P (malha fechada) e SCT-013, ambos atingindo o patamar de 4 MHz. Em contrapartida, os modelos DCT104 e ACS712 apresentaram limitações em altas frequências, com bandas passantes mais estreitas e relações sinal-ruído severamente degradadas. Conclui-se que, para a implementação de inversores de baixa potência operando sob regime de carga oscilante, os sensores LA 100-P e SCT-013 configuram as alternativas mais seguras e assertivas para garantir a precisão da aquisição de dados e a estabilidade das malhas de controle.

Supercapacitor modules for energy storage systems often require complex active balancing circuits to manage voltage imbalances between series-connected cells. This paper proposes a modified forward converter topology that passively charges and balances supercapacitor modules simultaneously. The proposed solution is modular, provides galvanic isolation, and is self-regulating, eliminating the need for dedicated sensors or complex control logic. Voltage equalization is achieved autonomously through coupled inductors, naturally directing current to the cells with the lowest voltage during the period when the converter is off. This work details the operating principle of the converter and analyzes two architectures: a non-crossover configuration and a crossover configuration. This study validated the system performance through PSIM simulations and a hardware prototype. The experimental results demonstrate that both configurations successfully charge and balance the supercapacitors. However, the crossover and non-crossover configurations achieve faster equalization under certain imbalance conditions. In contrast, the crossed configuration exhibits a smaller final voltage discrepancy between cells compared to the non-crossover architecture. The proposed converter proves to be a simple, robust, and effective solution for managing supercapacitor modules.

Este capítulo apresenta a implementação de uma ferramenta de Inteligência Artificial, fundamentada em Algoritmos Genéticos (AG), para a otimização de rotas logísticas de manutenção preventiva na indústria. O estudo de caso aborda o Problema do Caixeiro Viajante (PCV) aplicado a uma indústria de bebidas, com o objetivo de determinar a rota diária mais curta para um técnico inspecionar oito equipamentos (clientes), respeitando as restrições operacionais de iniciar e terminar a jornada na base e de visitar cada local apenas uma vez. A modelagem matemática e a simulação computacional foram desenvolvidas na ferramenta de otimização do software Matlab, transpondo o problema geográfico para matrizes de distância e utilizando cromossomos de 24 bits para a decodificação dos trajetos. Os resultados computacionais demonstraram que o algoritmo convergiu com sucesso para rotas altamente satisfatórias e otimizadas. Na análise comparativa com a elaboração convencional, a distância física da rota planejada pelo algoritmo apresentou uma grande proximidade à rota empírica manual. Contudo, o grande diferencial heurístico revelou-se na otimização drástica do tempo de planejamento de backoffice, que reduziu a análise humana de cerca de quinze minutos para apenas três minutos por trajeto simulado. A substituição do planejamento manual pela rotina automatizada representa, assim, um avanço expressivo na produtividade e na eficiência da gestão de manutenção da equipe.