No abstract

No abstract

For grid stability, operation, and planning, solar irradiance forecasting is crucial. In this paper, we provide a method for predicting the Global Horizontal Irradiance (GHI) mean values one hour in advance. Sky images are utilized for training the various forecasting models along with measured meteorological data in order to account for the short-term variability of solar irradiance, which is mostly caused by the presence of clouds in the sky. Additionally, deep learning models like the multilayer perceptron (MLP), convolutional neural networks (CNN), long short-term memory (LSTM), or their hybridized forms are widely used for deterministic solar irradiance forecasting. The implementation of probabilistic solar irradiance forecasting, which is gaining prominence in grid management since it offers information on the likelihood of different outcomes, is another task we carry out using quantile regression. The novelty of this paper lies in the combination of a hybrid deep learning model (CNN-LSTM) with quantile regression for the computation of prediction intervals at different confidence levels. The training of the different machine learning algorithms is performed over a year’s worth of sky images and meteorological data from the years 2019 to 2020. The data were measured at the University of French Polynesia (17.5770° S, 149.6092° W), on the island of Tahiti, which has a tropical climate. Overall, the hybrid model (CNN-LSTM) is the best performing and most accurate in terms of deterministic and probabilistic metrics. In addition, it was found that the CNN, LSTM, and ANN show good results against persistence.

In order to decarbonize electricity production in insular tropical regions, hydrogen as an energy vector appears to be a promising solution. But some issues have to be dealt with, like the overall yield of the hydrogen chain. Moreover, thermochemical systems can produce cooling by thermal recovery. In this paper, we study a system composed by an electrolyzer, a hydrogen fuel cell, a Li-ion battery pack and a thermochemical reactor coupled with a conventional ammonia heat pump. In this system, the waste-heat from the electrolyzer and the fuel cell are used to desorb a thermochemical reactor for a differed production of cooling. A Mixed Integer Linear Program is used to optimize the energy management, taking into account the electrical and thermal load demand and the aging of the electrolyzer, the fuel cell and the battery. Results show that the system is able to provide the electrical and thermal needs of the load and the use of the thermochemical cooling system improves the fuel cell and the electrolyzer efficiency by 21% and 15% respectively compared to a system without thermochemical storage.