Application of artificial neural networks for electric load forecasting on railway transport

Proposed algorithm for smart grid DDoS detection based on deep learning

“…A typical neural network comprises numerous small, interconnected processes called neurons, each generating a string of activations with real values. Environmental sensors activate input neurons, and weighted connections from previously active neurons excite more neurons (Komyakov, Erbes, & Ivanchenko, 2015;Liang et al, 2021;Schmidhuber, 2015) (see Fig. 3).…”

A review of modelling and optimisation methods applied to railways energy consumption

“…(Açikbas and Soylemez, 2008) used a NN to generate multiple driving scenarios, although it only provided simplified results (namely, the point along the line where coasting starts) and not a full simulation of the train movement. Other authors have used NN to model the energy consumption of a complete railway network (Komyakov et al, 2015) or the position of multiple trains (Chen et al, 2016). Sometimes NN are combined with a deterministic model to incorporate a particular feature to the simulation, such as braking curves (Y. or the behaviour of train operators (Dündar and Şahin, 2013), or to identify coasting points (Chuang et al, 2009).…”

Application of Genetic Algorithms for Driverless Subway Train Energy Optimization

“…To estimate the energy consumed by the train and the travel time [33][34][35], a simulator using Matlab-Simulink has been implemented. The equivalent mass of the train is modeled by the following:…”