An urban short-term traffic flow prediction model based on wavelet neural network with improved whale optimization algorithm

To solve the problem of urban traffic congestion is a major challenge to modern society. Short-term urban traffic flow prediction is the key to realizing traffic control and vehicle guidance on the relief of traffic congestion to make a better city experience. Short-term urban traffic flow is characterized by a high level of time-variation, nonlinearity and randomness. To tackle this problem and to improve the performance of short-term traffic flow prediction, the author of this paper comes up with an improved whale optimization algorithm (IWOA) and tries to introduce it into the wavelet neural network (WNN) so as to optimize its initial weights and wavelet factors via iteration and to establish a short-term traffic flow prediction model based on Wavelet Neural Network with Improved Whale Optimization Algorithm (IWOA-WNN). This model appears to predict traffic flow in a more effective manner and it can remedy the defects of wavelet neural network which usually leads to low prediction accuracy and slow response. The experimental results show that compared with the pure WNN model and WOAWNN model, the IWOA-WNN model has turned out to be a great improvement in terms of absolute error and percentage of absolute error.

Automated summary

The paper presents a short-term traffic flow prediction model based on the Improved Whale Optimization Algorithm in Wavelet Neural Network, which shows better performance in predicting traffic flow and improving prediction accuracy compared to existing models.