| dc.description.abstract | In order to increase the online vehicle velocity prediction (VVP) strategy’s forecast performance, an adaptive VVP strategy considering traffic signals is presented for multiple scenarios. Initially, the algorithm of a general regressive neural network (GRNN) paired with data sets of the ego-vehicle, the vehicle in front, and traffic lights is used in traffic scenarios, which increasingly improves the prediction accuracy. To ameliorate the robustness of the algorithm, then the strategy is optimized by particle swarm optimization (PSO) and k-fold cross-validation to find the optimal parameters of GRNN in real-time, which constructs an adaptive online PSO-GRNN VVP strategy with multi-information fusion to adapt with different operating situations. To verify the proposed strategy, traffic scenarios are established inside the co-simulation environment. The adaptive online PSO-GRNN VVP strategy is then deployed to a variety of simulated scenarios to test its efficacy under various operating situations. Finally, the simulation results reveal that in urban and highway scenarios, the prediction accuracy is separately increased by 31.3% and 48.3% when compared to the traditional GRNN VVP strategy with fixed parameters utilizing only the historical ego-vehicle velocity data set. Energy problems in today’s world are becoming more and more prominent: fossil energy is in short supply, and excessive carbon emissions aggravate the greenhouse effect. In this context, the new energy vehicle industry has developed rapidly. Hybrid cars are a very popular vehicle, because it is affordable, free from range anxiety, energy efficient and environmentally friendly. In a hybrid car, there is a small module that always calculates how much energy the engine and the battery need to output each time the accelerator is stepped on. This paper uses the traffic information to help improve the accuracy of online vehicle velocity prediction in the short-term future, and the adaptability of this prediction algorithm to dynamic working conditions. Thus, this algorithm provides accurate information for the energy distribution module to achieve the lowest energy consumption in a journey. Combined with our research results, hybrid cars can predict the short-term future velocity in real time during operation, and automatically adjust the energy distribution ratio, so that when we drive a hybrid car from home to work, no matter whether the road conditions are congested or smooth today, we can all achieve more fuel savings, thereby reducing the cost of use and carbon emissions. | |
