This study presents a new energy management system (EMS) for the optimised operation of power sources of a hybrid charging station for electric vehicles and fuel cell vehicles. It is composed of a photovoltaic (PV) system, a battery and a hydrogen system as energy storage systems (ESSs), a grid connection, six fast charging units and a hydrogen supplier. The proposed EMS is designed to reduce the utilisation costs of the ESS and make them work, as much as possible, around their maximum efficiency points. The optimisation function depends on a cost prediction system that calculates the net present cost of the components from their previous performance and a fuzzy logic system designed for improving their efficiency. Finally, a particle swarm optimisation algorithm is used to solve the optimisation function and obtain the required power for each ESS. The proposed EMS is checked under Simulink environment for long-term simulations (25 years). By comparing the EMS with a simpler one that optimises only the costs, it is proved that the proposed EMS achieves better efficiency of the charging station (+7.35%) and a notable reduction in the loss of power supply probability (−57.32%) without compromising excessively its average utilisation cost (+1.81%). Nomenclature Modelling of the hybrid charging station A ELZ constant B ELZ constant CAP nominal capacity of the hydrogen tank Cycle H2 cycle between 0 and the current power Cycle H2 nom

No abstract

Solar energy is one of the main renewable energy sources capable of contributing to supply global energy demand. However, the solar resource is intermittent, making its integration into the electrical system a difficult task. Hence, we present and compare two machine learning techniques, Deep Learning (DL) and Support Vector Regression (SVR), to verify their behavior for solar forecasting. After testing with data from Spain, the results showed that the Mean Absolute Percentage Error (MAPE) for predictions using DL and SVR is 7.9% and 8.52%, respectively and the better MAPE is in the range of −10% to 10% of errors. The DL achieved the best results for solar energy forecast, but it is worth mentioning that the SVR also obtained satisfactory results.

Renewable energy (RE) resources such as solar are increasingly being used worldwide. Solar resource shows high availability, but presents an intermittent characteristic, causing oscillations in the electricity production. Intermittence is one of the main barriers for the use of solar plants in a system that needs to balance demand and electricity production. Aiming to contribute to a larger use of the solar resource in the world energy matrix, we propose a solar irradiance prediction methodology, developed from data collected in Fortaleza-CE (latitude: −03° 43′, longitude: −38° 32′). Predictions were developed using Multilayer Perceptron (MLP) Back propagation Artificial Neural Network (ANN) with the advance of 1 hour. In the best ANN performance, 41.9% of the predictions obtained up to 5% of error, 58.7% obtained errors lower than 10% and 68.6% obtained errors lower than 15%. MAPE (mean absolute percentage error) of 6.11% was found, which can be considered good, since errors found in previous works reached 20%.

No abstract