基于LSTM的中国香港港口燃油价格预测  

Forecast of Hong Kong Port in china Fuel Price Based on LSTM

作　　者：朱俊杰 ZHU Junjie(School of Navigation and Shipping,Shandong Jiaotong University,Weihai 264200,China)

机构地区：[1]山东交通学院航运学院,山东威海264200

出　　处：《现代信息科技》2023年第8期103-106,共4页Modern Information Technology

摘　　要：船加油港作为海上的重要交通枢纽在航运业中地位显著,而吸引船舶靠港加油次数已经成为评价一个港口地位的重要指标。由于港口之间燃油价格的差异,所以科学准确的预测港口燃油价格对航运企业在计划船队航线和航速时有着至关重要的现实意义。文章采用长短期记忆模型(LSTM)对中国香港港口燃油价格进行预测和实证分析,通过将LSTM模型与ARIMA模型的预测结果进行比较分析,结果表明LSTM模型的预测精度更好。As an important transportation hub at sea,the refueling port has a prominent position in the shipping industry,and the number of times to attract ships to refuel has become an important indicator to evaluate the status of a port.Due to the differences in fuel prices between ports,scientifically and accurately predicting port fuel prices is of vital practical significance to shipping companies when planning fleet routes and speeds.In this paper,the Long-Short-Term Memory model(LSTM)is used to forecast and empirically analyze fuel prices in Hong Kong ports in china.By comparing and analyzing the forecast results of the LSTM model with the ARIMA model,the results show that the forecast accuracy of the LSTM model is better.

关 键 词：中国香港港 港口燃油价格 预测 LSTM模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]