In this article is evaluates the different tracking and search methods of the maximum power point (MPPT) in photovoltaic solar systems (PV), these methods are very extensive and use different algorithms, some of them based on artificial intelligence between others with the objective of finding the MPPT in a PV system consisting of a solar panel accompanied by a direct current to direct current (DC-DC) converter. There are five wellknown algorithms that find the MPPT with their respective characteristics, and are assigned rating values using the Entropy method by weight (EW) based on the Shannon Entropy; in the end of this work, is it gets a table of scores of these methods.
This paper analyzes a Dual Active Bridge seriesresonant DC–DC converter for solar photovoltaic DC microgrid. These converters are particularly attracted for renewable energy applications due to high switching frequency with low switching losses. The analysis is composed of the equivalent circuit using Fourier series. Besides, the steady-state response is shown where the current flow depends only on the phase shift modulation. MPPT algorithm is designed and discussed. Finally, the simulations results using the PSIM software for a 500 W prototype are shown.
This article aims to estimate irradiance using measured parameters from a real photovoltaic system. For this study, output current and voltage values were used from a set of solar panels with a capacity of 10 kW and a 10 kVA power inverter, which provide the necessary data for irradiance estimation. The data was collected at a sampling frequency of 15 seconds. To achieve this goal, an Artificial Neural Network (ANN) was applied to the reference data, which includes time series of solar irradiance, current, and voltage produced by the photovoltaic panels on different days of the year under varying weather conditions. Once the ANN is trained, its performance will be validated by comparing the estimation generated by the network with data from a reference cell on the days selected for the study. Additionally, the model will be evaluated using data from other days, not used in the training, to verify its ability to generalize under different meteorological conditions.
En el presente trabajo se hace un análisis de la situación de paridad de red entre las fuentes de energía eléctrica convencionales para el caso del Perú, que vendría hacer la energía hidroeléctrica y termoeléctrica, con las recursos de energía renovables o simplemente energías renovables en este caso se analiza las energía solar fotovoltaica instalado entre Moquegua, Tacna y Arequipa. Se ve como se calculan las tarifas que pagan el usuario final de tipo residencial, así como las tarifas actuales proporcionadas por los organismos correspondientes. Posteriormente se ve la evolución de la energía solar fotovoltaica y las cuatro subastas que se dieron en el Perú, y como estos costos han ido descendiendo de manera significativa. Finalmente se ve que al final se logra el objetivo de conseguir la paridad de red.
This paper presents the design and implementation of a low-cost autonomous vehicle prototype that employs machine learning (ML) and computer vision techniques. The prototype integrates a ResNet-18 convolutional neural network (CNN), trained using PyTorch and deployed on an NVIDIA Jetson Nano-a compact, GPU-accelerated computing platform based on the JetBot architecture. The objective is to demonstrate the feasibility of implementing ML algorithms on affordable embedded hardware for real-time navigation tasks such as lane detection and path following. The development workflow includes image data acquisition, model training, and validation through physical testing on a $2.44 ~\mathrm{m} \times 1.24 ~\mathrm{m}$ modular track. More than 2,600 labeled images were used to train the model across five $t$ rack $s$ cenarios, $w$ ith $t$ he $b$ est $c$ onfiguration ob tained after 60 epochs. Experimental results show that the trained ResNet-18 model achieved up to 70 % trajectory-tracking accuracy and a continuous navigation distance of 208 cm before deviation. These results confirm t hat the J etson N ano p latform c an effectively execute CNN-based control tasks in real time. This study contributes to scalable and cost-effective autonomous vehicle research by bridging the gap between theoretical ML applications and practical embedded implementations in resource-constrained environments.