SARO-MB3-BiGRU: A novel model for short-term traffic flow forecasting in the context of big data

In order to further improve the accuracy of short-term traffic flow prediction on designated sections of highways, a combined prediction model is designed in this paper to predict the traffic flow on designated sections of highways. Firstly, for the shortcomings of artificial rabbits optimization (ARO) algorithm, sine cosine ARO (SARO) is proposed by incorporating sine cosine algorithm (SCA) idea into ARO, and introducing the non-linear sinusoidal learning factor. Secondly, three mobile inverted bottleneck convolution (MBConv) modules are utilized to form the MB3 module, and with BiGRU are utilized to form the MB3-BiGRU combined prediction model. Finally, the MB3-BiGRU model is optimized by SARO to achieve short-term prediction of traffic flow. The analysis results show that using the United Kingdom highway dataset as the data source, the SARO-MB3-BiGRU presented in this paper reduces the root mean squared error (RMSE) by 32.58%, the mean absolute error (MAE) by 30.25%, and the decision coefficient (R²) reaches 0.96729, as compared to BiGRU. Compared with other common models and algorithms, the SARO has good solving capabilities and versatility, and the SARO-MB3-BiGRU model has been greatly improved in terms of prediction accuracy and generalization ability, which has better prediction ability and engineering reference value.