Wind power generation has presented an important development around the world. However, its integration into electrical systems presents numerous challenges due to the variable nature of the wind. Therefore, to maintain an economical and reliable electricity supply, it is necessary to accurately predict wind generation. The Wind Power Prediction Tool (WPPT) has been proposed to solve this task using the power curve associated with a wind farm. Recurrent Neural Networks (RNNs) model complex non-linear relationships without requiring explicit mathematical expressions that relate the variables involved. In particular, two types of RNN, Long Short-Term Memory (LSTM) and Echo State Network (ESN), have shown good results in time series forecasting. In this work, we present an LSTM+ESN architecture that combines the characteristics of both networks. An architecture similar to an ESN is proposed, but using LSTM blocks as units in the hidden layer. The training process of this network has two key stages: (i) the hidden layer is trained with a descending gradient method online using one epoch; (ii) the output layer is adjusted with a regularized regression. In particular, the case is proposed where Step (i) is used as a target for the input signal, in order to extract characteristics automatically as the autoencoder approach; and in the second stage (ii), a quantile regression is used in order to obtain a robust estimate of the expected target. The experimental results show that LSTM+ESN using the autoencoder and quantile regression outperforms the WPPT model in all global metrics used.

In recent years, Convolutional Neural Networks (CNN) have been widely used for real-world applications in the field of computer vision. Their class-leading performance, however, depends heavily on the architecture used for a given problem. In most cases, the architectures are manually optimized by the researchers, a time-consuming process hard to achieve without prior knowledge of CNN. In this paper, we propose a new genetic algorithm for the optimization of the CNN architecture for a given image classification problem. This algorithm extends and refines existing research in the field, by allowing depth exploration, introducing a novel sequential crossover operator, using an incremental selective pressure schedule over evolution (favoring higher diversity in early generations) and by evaluating individual performances over the validation set with early stopping. The technique is validated in three image classification dataset, namely, CIFAR10, MNIST and Caltech256 datasets, which are widely used benchmarks for image classification algorithms. We evaluate the performance and total execution time over these datasets, and compare our results with those achieved by the best genetic methods published so far. In all cases, we achieve better results in terms of test accuracy, consistently over different datasets, while remaining in the same orders of magnitude of execution time of the fastest approaches.

In the field of engineering, complex problems often arise that require solutions. The implementation of specific algorithms to tackle these problems becomes an essential part of this area, and optimizing these algorithms plays a crucial role in achieving good results with the available resources. The Vehicle Routing Problem (VRP) has been a central topic in distribution and logistics for decades. New VRP models and tools are continuously developed to address the challenges of modern logistics. The Energy Minimizing Vehicle Routing Problem (EMVRP) is a VRP model where the objective is to minimize the total amount of energy consumed by a fleet of vehicles. The VRP literature has focused on solving the problem using a variety of approaches and techniques, including exact methods, heuristics, metaheuristics, and hybrid algorithms. Hybrid algorithms combine different techniques, such as heuristics and metaheuristics, to obtain more effective solutions. This work presents the implementation of four hybrid algorithms to tackle the EMVRP. These algorithms combine machine learning clustering techniques, such as K-Means and K-Medoids, with metaheuristic approaches inspired by ant colony systems. The proposed algorithms are: Free Ant + K-Means, Free Ant + K-Medoids, Restricted Ant + K-Means, and Restricted Ant + K-Medoids. The Free Ant and Restricted Ant algorithms were subjected to testing using different instances from CVRPLIB, and the obtained results are promising compared to other metaheuristic techniques described in the literature. However, these results also indicate a wide scope for experimentation and algorithm tuning.