Energy Consumption Estimation of the Electric Bus Based on Grey Wolf Optimization Algorithm and Support Vector Machine Regression

Electric buses have many significant advantages, such as zero emissions and low noise energy consumption, making them play an important role in saving the operation cost of bus companies reducing urban traffic pollution emissions. Therefore, recent years, cities world dedicate to promoting electrification public transport vehicles. Whereas due limitation on-board battery capacity, driving range electric is relatively short. The accurate estimation consumption on routes premise conducting scheduling optimizing layout charging facilities. This study collected actual data three Meihekou City, China, established support vector machine regression (SVR) model by taking state charge (SOC), trip travel time, mean environment temperature air-conditioning time independent variables; while consumptions route operations served dependent variables. Furthermore, grey wolf optimization (GWO) algorithm was adopted select optimal parameters proposed model. Finally, a based (GWO-SVR) proposed. Three real lines were taken examples validate results show that average percentage error 14.47% 0.7776. In addition, accuracy training are superior genetic algorithm-back propagation neural network grid-search