Search

• The snake optimization algorithm (SOA) and the Improved snake optimization algorithm (ISOA) are proposed to extract the parameters for photovoltaic cells. • The performance of SOA and ISOA is compared with the ones of the best algorithms from specialized literature. • ISOA proved their performance in comparison with the algorithms considered for the three photovoltaic cells analyzed. The accurate extraction of photovoltaic cells and panels parameters is very important in order to precisely forecast their generated energy, to rapidly identify the maximum power point, both for the manufacturer in order to verify the quality control during the production process, and for the researchers to improve their quality, efficiency and also study the photovoltaic cells degradation. This paper is the first to propose the usage of the Snake optimization metaheuristic algorithms to extract the parameters of three photovoltaic cells: monocrystalline commercial silicon, amorphous silicon, and RTC France. The Snake algorithms are used for the one diode and two diode models to extract five and seven parameters respectively. The root mean square error statistical test has been performed in order to prove the algorithm performance. The comparison with the algorithms published in specialized literature reveals that the Snake algorithm outperforms several others, but is not the best. An improved version is developed and the results show that it gives better results than, or at least the same as the best ones. The improvement in root mean square error, when the improved snake algorithm is used, is 16% in the case of the monocrystalline silicon photovoltaic cell for the two diode model, 5.3% in the case of the amorphous silicon photovoltaic cell for the two diode model, and it is slightly better for the RTC France photovoltaic cell, from 0.002 to 0.11% when the best algorithms are considered. The Snake algorithms give very good results, especially the improved one, even for a small population size and a limited number of iterations. Thus, for the improved snake algorithm, the iterations number and the population size are 100 and 80, in the case of the monocrystalline photovoltaic cells, for one diode model, and 200 and 40 respectively for two diode model, 100 and 120 in the case of the amorphous silicon photovoltaic cell for one diode model and 120 and 120 respectively for two diode model, 150 and 100 in the case of RTC photovoltaic cell for one diode model and 150 and 80 respectively for two diode model. This reduces the computational time for the extraction of the photovoltaic cell parameters. The computational time for the improved snake algorithm is half of the necessary one for one of the best algorithms, the hybrid successive discretization algorithm. Therefore, the snake optimization algorithm, especially the improved one is one of the best algorithms that can be used for the parameters extraction of the photovoltaic cells. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) algorithms have shown their capability to complement human analysis in the understanding of complex phenomena. Their advantages essentially rely on the flexibility of their construction that allows capturing complex relationships between inputs and outputs of a problem and also on their ability to adapt themselves via a learning phase to the available information. As a result, AI is widely used in many scientific fields and especially those related to the nuclear industry. This work deals an application of AI based on several classical machine learning approaches for the study of Reactivity Initiated Accidents (RIA) in the CABRI experimental pulse reactor located at the Cadarache research center, southern France. We focus on the interpretation of the fuel rod behaviour during the power pulse using the online fuel motion monitoring system called the hodoscope. The objective of this paper is to investigate how AI algorithms can be used for the automatic detection of a generic fuel delocalization from the signals recorded by the hodoscope. [ABSTRACT FROM AUTHOR]