The Prediction And Fuzzy Evaluation Of Container Throughput Based On WOA

With the rapid development of the global economy,the economic prosperity of a country is closely related to the transport capabilities of ports.However,the planning,construction,production capacity and capital investment of a port are all have a vital relationship with the prediction of it's container throughput.The existing port container throughput forecasting methods are mostly based on traditional regression and time series methods.Combination model can greatly improve the accuracy of prediction,therefore,this paper proposes a hybrid forecasting and evaluating model,which including the Variational Mode Decomposition(VMD),Phase Space Reconstruction(PSR),Whale Optimization Algorithm(WOA)and fuzzy evaluation.First,the original data series are decomposed to many sub-sequences by VMD.Secondly,the input form of each sub-sequence is determined by C-C based PSR.Afterwards,SVR models which parameters c and g are optimized by WOA are used for prediction.Further more,in order to evaluate the prediction accuracy of the proposed hybrid model,the fuzzy comprehensive evaluation is employed to compare the real value and the prediction results.The proposed hybrid model is applied to the monthly container throughput data from 2001.01 to 2017.01 of Shanghai port,the results show that the hybrid model proposed in this paper can significantly reduce the prediction error.