Heterogeneous vehicular communications aim to improve the reliability, security and delay performance of vehicle-to-vehicle (V2V) communications, by utilizing multiple commu-nication technologies. Predicting the path loss through conventional fitting based models and radio frequency (RF) jamming detection through rule based models of different communication schemes fail to address comprehensive mobility and jamming scenarios. In this paper, we propose a machine learning based adaptive link quality estimation and jamming detection scheme for the optimum selection and aggregation of IEEE 802.11p and Vehicular Visible Light Communications (V-VLC) technologies targeting reliable V2V communications. We propose to use Random Forest regression and classifier based algorithms, where multiple individual learners with diversity are trained by using measurement data and the final result is obtained by averaging outputs of all learners. We test our framework on real-world road measurement data, demonstrating up to 2.34 dB and 0.56 dB Mean Absolute Error (MAE) improvement for V-VLC and IEEE 802.11p path loss prediction compared to fitting based models, respectively. The proposed jamming presence detection scheme yields 88.3% accuracy to detect noise interference injection for IEEE 802.11p links, yielding 3% better prediction performance than previously proposed deep convolutional neural network (DCNN) based scheme.

Reconfigurable intelligent surface (RIS)-empowered communication is one of the promising 6G technologies that allows the conversion of the wireless channel into an intelligent transmit entity by manipulating the impinging waves using man-made surfaces. In this paper, the potential benefits of using RISs are investigated for indoor/outdoor setups and various frequency bands (from sub 6 GHz to millimeter-waves). First, a general system model with a single RIS is considered and the effect of the total number of reflecting elements on the probabilistic distribution of the received signal-to-noise ratio and error performance is investigated under Rician fading. Also for this case, the path loss exponent is analyzed by considering empirical path loss models. Furthermore, transmission models with multiple RISs are developed and analyzed for indoor and outdoor non line-of-sight (NLOS) scenarios. The conventional RIS selection strategies are also integrated for systems equipped with multiple RISs for the first time. Through extensive simulations, it is demonstrated that the RIS-assisted systems provide promising solutions for indoor/outdoor scenarios at various operating frequencies and exhibit significant results in error performance and achievable data rates even in the presence of system imperfections such as limited range phase adjustment and imperfect channel phase estimation at RISs.