An intelligent energy management and traffic predictive model for autonomous vehicle systems

In recent times, the utilization of autonomous vehicles (AVs) has been significantly increased over the globe. It is because of the tremendous rise in familiarity and the usage of artificial intelligence approaches in distinct application areas. Though AVs offer several benefits like congestion control, accident prevention, and so on, energy management and traffic flow prediction (TFP) remain a challenging issue. This paper concentrates on the design of intelligent energy management and TFP (IEMTFP) technique for AVs using multi-objective reinforced whale optimization algorithm (RWOA) and deep learning (DL). The proposed model involves an energy management module using fuzzy logic system to reach the specified engine torque with respect to different measures. For optimal tuning of the variables involved in the fuzzy logic membership functions (MFs), RWOA is employed to further reduce the energy utilization. Besides, the proposed model uses a DL-based bidirectional long short-term memory (Bi-LSTM) technique to perform TFP. For validating the efficacy of the IEMTFP technique, an extensive experimental validation is carried out. The resultant values ensured the goodness of the IEMTFP model in terms of energy management and TFP.