In the future railway services, wireless communication is the fundamental part and millimeter wave (mmWave) is foreseen to be a key enabler towards the smart railway. An accurate understanding of the propagation environment can assist designing both systems and railway infrastructures for better communication services. In this paper, the influence of typical objects to the mmWave propagation channel are analyzed for “Train-to-infrastructure” and “Intra-wagon” railway scenarios with various configurations. Propagation measurements are conducted in the mmWave band for the 12 most common railway materials. The corresponding electromagnetic parameters are obtained and a 3D ray tracing (RT) simulator is calibrated. The mean absolute error of the simulated S21 parameter is -53.5 dB, indicating that the calibrated RT can be used to generate the close-to-real mmWave channel for railway scenarios. Statistically consistent scenarios and deployments are generated, which enables drawing unbiased numerical results based on intensive RT simulations. The influence of typical objects and corresponding material compositions are then compared and significant objects are determined for each scenario. The results of this work not only imply how the propagation environment impacts on the propagation channel, but also makes suggestions to efficiently reconstruct railway environment models for an accurate RT based channel model. Moreover, the understanding of the influence of the environment at object and material levels will in turn guide the construction of railway infrastructure for better railway services.

In the automotive and rail domains, vehicles are entering the era of full automation thanks to wireless sensors and communication systems, shifting control functions from a human driver to computers. High data rate, robustness, high reliability and ultra-low latency wireless communications are required in the context of autonomous train and safety critical applications. Today, the Future Railway Mobile Communication System (FRMCS) is under development at European level within the International Union of Railways (UIC). This system will answer all the current and future needs of rail. It will be IP based, multi-bearer and resilient to technology evolution. In the context of the development of different FRMCS prototypes by industry, it is crucial to be able to test them in representative Railway radio environments thanks to laboratory tools. Characterization of radio channels in railway environments, by measurements or simulations, is a very active field. In this article, based on broad literature survey, we show that not all the published models are suitable for performance evaluation. Then, we propose a selection of typical Tapped-Delay-Line channel models to be implemented in an original hardware and software testing platform capable to reproduce the effect of representative Railway environments in laboratory, with real time emulation at RF (Radio Frequency) level. Preliminary results in Hilly 3 taps and Cutting 5 taps channel models are presented as a proof of concept of a “zero on site testing” approach, allowing for time and cost savings in the validation of railway communication systems.

Radio access technologies (RATs) are a key topic in railways, enabling them a better service rendering in terms of shorter headways between trains, higher safety levels and higher customer satisfaction. Very often, these railway RATs need a lot of time to be developed, tested and put into service, which implies a lack of efficiency and bottlenecks in the evolution of railway systems. To solve this situation, an emulation platform that considers both the physical layer and the network (this is, able to emulate the end-to-end chain) is envisaged in the EmulRadio4Rail project. Therefore, the physical layer of many railway scenarios must be emulated, which is a remarkable challenge because railways are very diverse. We see Tapped-Delay Lines (TDL) models as the most efficient way for emulation with the available hardware. In the literature, there are many TDL-based channel models for all the scenarios we considered but one: tunnels. Therefore, in order to fill this gap, we develop a novel TDL model for railway tunnels, considering the impact of the rolling stock (both high-speed railway (HSR) and subway trains). The proposed model allows the full characterization of this scenario in terms of power-delay-profile (PDP), Doppler spectrum and fading characteristics.

This article explains the main results obtained from the research carried out in work package two (WP2) of the Roll2Rail (R2R) project. The goal of this project is to develop key technologies and remove already-identified blocking points for radical innovation in the field of railway vehicles to increase their operational reliability and reduce life-cycle costs (LCCs). The project, started in May 2015, has been funded by the Horizon 2020 program of the European Commission. The goal for WP2 is to research both technologies and architectures to develop a new wireless train communication network (TCN) within the IEC 61375 standard series. This TCN is entirely wired today and used for train control and monitoring system (TCMS) functions (some of them safety related), operator-oriented services, and customer-oriented services. The paradigm shift from wired to wireless means a removal of wiring and implies, among other benefits, a significant reduction of LCCs due to the removal of cables and the simplification of the train coupling procedure.

Wireless Big Data has aroused extensive attention, as mass mobile devices have been developed and deployed for the upcoming 5G era. The context information of these devices is of importance for personalized services in a smart environment. Nevertheless, the constant change of scenes challenges to the network operator. In this paper, we propose an ensemble learning scheme for indoor-outdoor classification for a typical urban area, based on the cellular data captured in a commercial LTE network. The variables are extracted by network key performance indicators (KPIs) and radio propagation knowledge. Based on these main variables, the decision trees grow and split by the Gini index of sampled features. Then, all decision trees are assembled as weak learners to built the ensemble scheme, thus improving the discrimination ability. The self-validation results show the ensemble model achieves extreme accurate (with an out-of-bag error lower than 1%) classification for indoor and outdoor environments. Moreover, the prominent variables are selected based on the variable importance of in the initial training. The reconfigured model based on fewer variables and less weak learners also gains the highest accuracy and relative short compute time, compared with other classical machine learning methods.