Short-Term Traffic Flow Prediction Based On IWOA-WNN

Aiming at the nonlinear and random characteristics of short-term traffic flow, an improved whale optimization algorithm (IWOA) is proposed to replace the gradient descent method to optimize the wavelet neural network (WNN) for short-term traffic flow prediction. Firstly, in view of the slow convergence speed and low convergence accuracy of the traditional whale optimization algorithm (WOA), a nonlinear convergence factor a is introduced to balance the global search and local search ability of the algorithm. At the same time, Kent chaotic mapping is used to increase population diversity and enhance the ability of jumping out to fall into local optimum. Secondly, aiming at the problem that the gradient descent method in the wavelet neural network is sensitive to the initial values of the weights and wavelet factors, and is easy to fall into local minimum values, the network weights of the wavelet neural network are optimized by improving the whale optimization algorithm. Finally, the wavelet threshold denoising algorithm is used to process the noise in the raw traffic flow sequence data, and the IWOA-WNN is used to test the short-term traffic flow data set after processing. The results show that the mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the model are 18.03, 2.82 and 13.13%, respectively. Experimental results show that the improved algorithm has higher accuracy than the raw algorithm, and the model can effectively improve the prediction accuracy of short-term traffic flow.