Packet Inter-Reception Time Conditional Density Estimation Based on Surrounding Traffic Distribution

Abstract

Cooperation is an enabler for autonomous vehicles. A promising application of cooperative driving is high-density platooning, where trucks drive with low inter-vehicle distances. It aims at increasing the road and fuel efficiency whilst guaranteeing safety. The safe and efficient coordination of the control requires the regular and reliable exchange of V2V messages. The performance of the vehicular application has been shown to be strongly affected by the variation of the performances of the communications system. To be able to adapt their functional settings to these variations, vehicles need the ability to predict it. We present a prediction model for the packet inter-reception time platoon messages in an IEEE 802.11p network. This performance indicator is the subject of extensive research as it captures the irregularity of input for the control loop. The prediction model uses conditional density estimation based on the exponential distribution. We fit this model using a multi-layer perceptron regressor based on features representing the surrounding communication environment. The presented results are based on data collected during a full scale platooning simulations using ns-3 and SUMO. We compare different environment abstraction models and show the potential of on-line learning. INDEX TERMS Vehicular ad hoc networks, intelligent vehicles, prediction algorithms, cooperative systems. GUILLAUME JORNOD received the B.Sc. and M.Sc. degrees in environmental science and engineering (ing. env. dipl. EPF) from the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, in 2012 and 2014, respectively, and the M.Sc. degree in management from University College London, U.K., in 2015. He is currently pursuing the Ph.D. degree in the field of vehicle-to-vehicle communications in conjunction with Technische Universität Braunschweig, under the supervision of Prof. Dr.-Ing. T. Kürner.

Fuel Efficient High-Density Platooning Using Future Conditions Prediction

“…Leveraging the tracing capabilities of ns-3, we gather instantaneous IVD, speed, fuel consumption and graph deviation time series for combinations of the control parameters. The rationale behind using a network simulator in this functional study is to enable running the fuel saving methods in the scope of framework including predictive communications algorithms, such as described in [18], in the future. The parameters for the communications systems are detailed in this paper.…”

“…The PIR is foreseen to suddenly drop (e.g., from 0.5 s to 0.05 s), to remain stable for a duration of T F and then to increase back to its original value. In this example scenario, the future prediction of the PIR can either come from the network [3] or from a decentralized system [18]. The lower PIR value is finally translated into a minimum IVD, d m .…”

“…The prediction algorithm that provides the PQoS could run on a base station, or be running on the nodes. In [18], we presented an algorithm for such decentralized QoS prediction; this algorithm can be used to provide the prediction of future conditions required as input for the method presented in the present paper. Part of the content of this paper is based on the fuel saving study presented in [19].…”

Time-Dependent Performance Modeling for Platooning Communications at Intersection

“…based on which c k,i,m (t) and µ k,i,m (t) can be calculated according to Eqs. ( 26) and (27). Then Ṅk,i,m (t) in Eq.…”

Decentralized Cooperative Resource Allocation with Reliability at Four Nines

“…Even though the perception is collective, each individual robot will be governed by a control loop. This control loop is vulnerable to variations in the arrival timing of the input [3], and these timing variations should be kept at a minimum.…”