Comparing energy consumption for rail transit routes through Symmetric Vertical Sinusoid Alignments (SVSA), and applying artificial neural networks. A case study of Metro Valencia (Spain)

Abstract

This paper presents the training of an artificial neural network using consumption data measured in the metropolitan network of Valencia, Spain, to estimate the energy consumption of a metro system. After calibration and validation of the neural network, the results obtained show that it can be used to predict energy consumption with high accuracy. Once fully trained, the neural network is used for testing hypothetical operational scenarios aimed to reduce the energy consumption of a metro system. These operational scenarios include different vertical alignments that prove that Symmetric Vertical Sinusoid Alignments (SVSA) can reduce energy consumption by 18.41% in contrast to a flat (0% gradient) alignment.Keywords: Symmetric Vertical Sinusoid Alignments (SVSA); gradient; energy consumption; artificial neural networks; metro system.Comparando el consumo energético para rutas de tránsito ferroviario mediante Alineamientos Verticales Sinusoidales Simétricos (SVSA), y aplicando redes neuronales artificiales. Un estudio de caso de MetroValencia (España) ResumenEste artículo presenta el entrenamiento de una red neuronal artificial usando el consumo energético medido en la red metropolitana de Valencia, España, para estimar el consumo energético de un sistema metro. Después de la calibración y validación de la red neuronal, los resultados obtenidos muestran que esta puede ser utilizada para predecir el consumo energético con una gran precisión. Una vez entrenada, la red neuronal es utilizada para probar diferentes escenarios de operación hipotéticos con el objetivo de reducir el consumo energético de un sistema metro. Estos escenarios de operación incluyen diferentes trazados verticales que prueban que los Alineamientos Verticales Sinusoidales Simétricos (SVSA, por sus siglas en inglés) pueden reducir el consumo energético en un 18.41 % en contraste con un alineamiento plano (pendiente del 0%).

Impact of Symmetric Vertical Sinusoid Alignments on Infrastructure Construction Costs: Optimizing Energy Consumption in Metropolitan Railway Lines Using Artificial Neural Networks

“…Their popularity lie in their ability to extract complex patterns within the data and to perceive trends that are very complex to be observed by humans or even by other computer techniques. This is possible because ANNs have an outstanding ability to derive meaning from complex or inaccurate data [21,41,43,44]. McCulloch and Pitts introduced the term ANN in 1943, as they were inspired by the architecture of the nervous systems or brain connections in living beings [45].…”

“…ANNs are used for predicting or classifying values and then optimizing them. ANNs have been applied in several topics, including transportation engineering [46][47][48][49][50] and railways engineering [21,23,24,41,42,51].…”

“…The ANN used for predicting energy consumption in this paper was trained using speed, acceleration, and gradient as input variables, while measured empirical energy consumption was the target variable. In previous works, we showed that these input variables provide good accuracy, thus making it unnecessary to consider another input data to calibrate energy consumption [21,41].…”

“…Knowing the energy consumption in every hypothetical alignment [21], the differences in infrastructure construction costs were then analyzed to find the best hypothetical alignment as a balance between energy consumption and infrastructure construction costs. This analysis may help stakeholders in their decision-making process to find whether it is worth to potentially increase construction costs to reduce later operational costs.…”

“…For instance, various studies have focused on the implementation of regenerative brake [17,18], on-board storage systems [19], and consideration of train load variations and delays as well [12]. Finally, some authors have focused on optimizing track geometry to reduce energy consumption [20][21][22][23][24].…”