Multi-range vehicle speed prediction using vehicle connectivity for enhanced energy efficiency of vehicles
An integrated speed prediction framework based on historical traffic data mining and real-time V2I communications for CAVs. The present framework provides multi-horizon speed predictions with different fidelity over short and long horizons. The present multi-horizon speed prediction is integrated with an economic model predictive control (MPC) strategy for the battery thermal management (BTM) of connected and automated electric vehicles (EVs) as a case study. The simulation results over real-world urban driving cycles confirm the enhanced prediction performance of the present data mining strategy over long prediction horizons. Despite the uncertainty in long-range CAV speed predictions, the vehicle level simulation results show that 14% and 19% energy savings can be accumulated sequentially through eco-driving and BTM optimization (eco-cooling), respectively, when compared with normal-driving and conventional BTM strategy.
1. A system for multi-range vehicle speed prediction along a travel corridor having a plurality of intersections for enhanced energy management of a vehicle, the system comprising:
a data-driven prediction module configured to receive historic traffic data from at least one of GPS, a connected vehicle database, and traffic signal timing data along the travel corridor for long-term vehicle speed prediction, organize the historic traffic data into a plurality of bins, and determine and output long-range speed predictions;
a model-based speed prediction and planning module configured to receive real-time traffic data including connected vehicle data and traffic signal timing and phasing data, estimate queuing dynamics at signalized intersections along the travel corridor using a shockwave profile model to estimate a queue length at each of the plurality of intersections for eco-trajectory planning, and output a short-range speed prediction;
an integration module configured to integrate the short-range and long-range speed predictions to output a multi-range speed forecast; and
a control module configured to solve a real-time optimization to minimize energy consumption of the vehicle while simultaneously enforcing power and thermal system constraints and output a model predictive control (MPC) signal to the vehicle and associated control actions in response to the multi-range speed forecast for predictive controlling of an operation of the vehicle power and thermal systems.
2. The system according to claim 1 , further comprising an integrated energy management module configured to optimize the energy management of the vehicle through at least one of eco-driving and eco-cooling or eco-heating.
3. The system according to claim 2 wherein eco-driving comprises optimizing the vehicle speed with respect to real-time traffic data in short-range.
4. The system according to claim 2 wherein eco-cooling or eco-heating comprises optimizing the power and thermal systems of the vehicle over multiple short- and long-ranges.
5. A method of simultaneous management of power and thermal systems of connected and automated vehicles for enhanced energy management of a vehicle, the method comprising:
receiving historic traffic data for long-term prediction;
receiving real-time vehicle to infrastructure (V2I) information using a communication system for queuing dynamics estimation and prediction for eco-trajectory planning and eco-driving; and
predicting a speed trajectory of a connected and automated vehicle based on the historical traffic data and real-time V2I information and outputting a model predictive control (MPC) signal responsive thereto to the vehicle power and thermal systems.