Short-Term Traffic Flow Prediction Based on SVR and LSTM

To alleviate traffic congestion and support the development of real-time traffic and public transport, this paper conducts research on adopting support vector regression (SVR) and long short term memory (LSTM) to predict traffic flow of the lane, and then compares the results with that using the quadratic exponential smoothing. The consequence shows that SVR and LSTM have better prediction accuracy, about 1%–3% in terms of MAPE, than quadratic exponential smoothing, and SVR is slightly better than LSTM. Furthermore, in order to improve the predictive accuracy of model, we compare the performance of grid search, whale optimization algorithm (WOA) and genetic algorithm (GA) respectively in the respect of optimizing models’ parameters. The optimization effect of WOA-SVR and WOA-LSTM is better than the other two models respectively, about 0.9% and 2.52% better than GA-SVR and GA-LSTM while 0.29% and 2.32% better than GridSearch-SVR and GridSearch-LSTM considering MAPE.