基于灰色马尔科夫模型的温州港货物吞吐量预测

doi:10.3969/j.issn.1674-0696.2024.11.08

摘要/Abstract

摘要： 温州港地处东南沿海黄金海岸线中部，在过去的40 a里，温州港从单一小港，跃升为全国沿海主要港口和国家综合运输体系的重要枢纽，逐步融入全球贸易。为了更好地帮助温州港有关部门和港口企业进行港口生产运营与建设规划指导，首先, 建立了基于灰色马尔科夫的港口货物吞吐量预测模型，对温州港货物吞吐量的趋势和变化进行研究；然后，利用温州港2002—2022年货物吞吐量数据对建立的模型进行验算，结果表明，优化后的灰色马尔科夫预测模型较单一的灰色预测模型精度更高，优化后模型的平均相对误差约为2.1%；最后，对温州港2023—2027年的港口货物吞吐量进行预测，预测结果表明：温州港货物吞吐量呈现逐年波动上升的趋势，这一态势将对温州港的战略定位与长远发展规划产生深远影响，并将进一步推动温州港集疏运体系构建、深水泊位建设和港口辐射网络水平的提升。

关键词: 交通运输工程；货物吞吐量；预测；灰色马尔科夫模型；温州港

Abstract: Wenzhou Port is located in the middle of the golden coastline of the southeast coast. And in the past 40 years, Wenzhou Port has jumped from a single small port to be a major port along the coast of the country and an important hub of the national comprehensive transportation system, which has gradually integrated into global trade. In order to better help the relevant departments of Wenzhou Port and port enterprises to guide the port production operation and construction planning, a grey Markov-based port cargo throughput prediction model was firstly established to study the trend and change of cargo throughput in Wenzhou Port. Then, the established model was verified by the cargo throughput data of Wenzhou Port from 2002 to 2022. The results show that the optimized grey Markov prediction model is more accurate than the single grey prediction model, and the average relative error of the optimized model is about 2.1%. Finally, the port cargo throughput of Wenzhou Port from 2023 to 2027 is predicted. The forecast results show that the cargo throughput of Wenzhou Port shows a fluctuating upward trend year by year, which will greatly affect the strategic positioning and long-term development planning of Wenzhou Port and further promote the construction of the collection and distribution system, the construction of deep-water berths and the level of port radiation network of Wenzhou Port.

Key words: traffic and transportation engineering; cargo throughput; forecast; grey Markov model; Wenzhou Port

中图分类号:

U691.71

常祎妹1，林忆婷1，丁天明2. 基于灰色马尔科夫模型的温州港货物吞吐量预测[J]. 重庆交通大学学报（自然科学版）, 2024, 43(11): 60-67.

CHANG Yimei1, LIN Yiting1, DING Tianming2. Forecast of Cargo Throughput of Wenzhou Port Based on Grey Markov Model[J]. Journal of Chongqing Jiaotong University(Natural Science), 2024, 43(11): 60-67.

参考文献

［1］韦汉超, 谢如鹤. 广东省港口货物吞吐量预测及分析［J］. 物流工程与管理, 2012, 34(3): 41-44.
WEI Hanchao, XIE Ruhe. Forecast and analysis of the port cargo throughput in Guangdong Province ［J］. Logistics Engineering and Management, 2012, 34(3): 41-44.
［2］ GOSASANG V, CHANDRAPRAKAIKUL W, KIATTISIN S. A comparison of traditional and neural networks forecasting techniques for container throughput at Bangkok port ［J］. The Asian Journal of Shipping and Logistics, 2011, 27(3): 463-482.
［3］ RUIZ-AGUILAR J J, TURIAS I J, JIMNEZ-COME M J. Hybrid approaches based on SARIMA and artificial neural networks for inspection time series forecasting ［J］. Transportation Research Part E: Logistics and Transportation Review, 2014, 67: 1-13.
［4］李广儒, 朱庆辉. 基于Elman神经网络的港口货物吞吐量预测［J］. 重庆交通大学学报(自然科学版), 2020, 39(6): 8-12.
LI Guangru, ZHU Qinghui. Forecasting of port cargo throughput based on Elman neural network ［J］. Journal of Chongqing Jiaotong University (Natural Science), 2020, 39(6): 8-12.
［5］梁绍东. 基于数据生成的三次指数平滑预测模型研究［J］. 管理观察, 2018, 38(10): 26-27.
LIANG Shaodong. Research on cubic exponential smoothing prediction model based on data generation ［J］. Management Observer, 2018, 38(10): 26-27.
［6］潘婷. 宁波舟山港货物吞吐量预测分析与思考［D］. 舟山: 浙江海洋大学, 2019.
PAN Ting. Analysis and Thinking on the Forecast of Freight Throughput of Ningbo Zhoushan Port ［D］. Zhoushan: Zhejiang Ocean University, 2019.
［7］ LIU Min, TAYLOR J W, CHOO W C. Further empirical evidence on the forecasting of volatility with smooth transition exponential smoothing ［J］. Economic Modelling, 2020, 93: 651-659.
［8］韩以伦, 徐新新. 基于ARIMA和GM模型的青岛港货物吞吐量预测研究［J］. 水道港口, 2019, 40(2): 241-248.
HAN Yilun, XU Xinxin. Research on cargo throughput forecast of Qingdao Port based on ARIMA and GM ［J］. Journal of Waterway and Harbor, 2019, 40(2): 241-248.
［9］ DRAGAN D, KESHAVARZSALEH A, INTIHAR M, et al. Throughput forecasting of different types of cargo in the Adriatic seaport Koper ［J］. Maritime Policy & Management, 2021, 48(1): 19-45.
［10］黄跃华, 陈小龙. 基于优化GM(1, 1)模型的港口吞吐量预测［J］. 中国航海, 2019, 42(4): 136-140.
HUANG Yuehua, CHEN Xiaolong. Optimized GM (1, 1) model for predicting port throughput ［J］. Navigation of China, 2019, 42(4): 136-140.
［11］陆云峰. 基于组合预测模型的大连港集装箱海铁联运量预测［J］. 中国市场, 2018(27): 21-24.
LU Yunfeng. Prediction of container sea-rail intermodal transportation volume in Dalian port based on combined prediction model ［J］. China Market, 2018(27): 21-24.
［12］朱经君, 兰培真, 徐圣豪. 基于新陈代谢灰色马尔科夫模型的芜湖港集装箱吞吐量预测［J］. 集美大学学报(自然科学版), 2022, 27(4): 333-338.
ZHU Jingjun, LAN Peizhen, XU Shenghao. Prediction of container throughput of Wuhu Port based on metabolic grey Markov model ［J］. Journal of Jimei University (Natural Science), 2022, 27(4): 333-338.
［13］曾勇, 沈最意. 基于改进的灰色马尔科夫模型的集装箱吞吐量预测［J］. 浙江海洋大学学报(自然科学版), 2022, 41(6): 574-582.
ZENG Yong, SHEN Zuiyi. Container throughput prediction based on improved grey-Markov model ［J］. Journal of Zhejiang Ocean University (Natural Science), 2022, 41(6): 574-582.
［14］汤天辰, 李林. 基于灰色马尔科夫模型的上海港集装箱吞吐量预测［J］. 物流科技, 2020, 43(3): 105-108.
TANG Tianchen, LI Lin. Prediction of container throughput of Shanghaiport based on grey Markov model ［J］. Logistics Sci-Tech, 2020, 43(3): 105-108.
［15］田雪, 王丹丹, 王锐月, 等. 基于灰色模型的港口吞吐量预测研究——以曹妃甸港口为例［J］. 数学的实践与认识, 2018, 48(4): 280-284.
TIAN Xue, WANG Dandan, WANG Ruiyue, et al. Research for port throughput prediction based on gray model—Taking Caofeidian Port as an example［J］. Mathematics in Practice and Theory, 2018, 48(4): 280-284.
［16］黄跃华, 陈小龙, 王亚辉. 基于正弦和的GM(1, 1)幂模型在港口吞吐量预测中的应用［J］. 上海海事大学学报, 2019, 40(3): 69-73.
HUANG Yuehua, CHEN Xiaolong, WANG Yahui. Application of GM (1, 1) power model based on sum of sine in port throughput prediction ［J］. Journal of Shanghai Maritime University, 2019, 40(3): 69-73.
［17］斯彩英. 基于灰色加权马尔科夫模型的港口货物吞吐量预测——以宁波舟山港为例［J］. 数学的实践与认识, 2023, 53(2): 46-57.
SI Caiying. Prediction of port cargo throughput based on grey weighted Markov chain mode—Take Ningbo Zhoushan Port as an example ［J］. Mathematics in Practice and Theory, 2023, 53(2): 46-57.
［18］李文瀚. 基于灰色理论的D港区需求预测与港口规划研究［D］. 青岛: 青岛大学, 2020.
LI Wenhan. Demand Prediction and Port Planning of D Port Area Based on Grey Theory ［D］. Qingdao: Qingdao University, 2020.
［19］姜汝翰. 基于灰色模型的青岛港集装箱吞吐量预测研究［D］. 大连: 大连海事大学, 2019.
JIANG Ruhan. Research on the Prediction of Container Throughput of Qingdao Port Based on Grey Model ［D］. Dalian: Dalian Maritime University, 2019.
［20］王振振, 苌道方, 朱宗良, 等. 基于ES-Markov模型的港口集装箱季度吞吐量分析与预测［J］. 中国航海, 2019, 42(4): 125-130.
WANG Zhenzhen, CHANG Daofang, ZHU Zongliang, et al. Analysis and prediction of port quarterly container throughput with ES-Markov model ［J］. Navigation of China, 2019, 42(4): 125-130.
［21］罗亚琼. 基于灰色马尔科夫模型的基坑开挖变形预测［D］. 昆明: 昆明理工大学, 2021.
LUO Yaqiong. Deformation Analysis of Foundation Pit Excavation Based on Grey Markov Model Prediction ［D］. Kunming: Kunming University of Science and Technology, 2021.
［22］林小明, 华晨, 胡尊乐, 等. 马尔科夫链在溧阳市降水量预测中的应用［J］. 江苏水利, 2022(7): 41-45.
LIN Xiaoming, HUA Chen, HU Zunle, et al. Application of Markov chain in precipitation prediction and analysis of Liyang City ［J］. Jiangsu Water Resources, 2022(7): 41-45.
［23］杜柏松, 艾万政, 胡林燕, 等. 基于优化灰色马尔科夫动态模型的上海港集装箱吞吐量预测［J］. 上海海事大学学报, 2021, 42(1): 76-81.
DU Baisong, AI Wanzheng, HU Linyan, et al. Container throughput prediction of Shanghai Port based on optimized grey Markov dynamic model ［J］. Journal of Shanghai Maritime University, 2021, 42(1): 76-81.
［24］孙鑫. 改进灰色—马尔科夫理论在斜拉桥施工控制中的应用研究［D］. 重庆: 重庆交通大学, 2020.
SUN Xin. Application Research of Improved Gray-Markov Theory in Construction Control of Cable-Stayed Bridge ［D］. Chongqing: Chongqing Jiaotong University, 2020.
［25］周敏. 地震灾害下应急物资需求预测与供应策略仿真研究［D］. 北京: 北京交通大学, 2019.
ZHOU Min. Emergency Material Demand Forecasting and Supply Strategy Simulation under Earthquake Disaster［D］. Beijing: Beijing Jiaotong University, 2019.

[1]	李广儒，张新，朱庆辉. 基于Adaboost的改进Elman神经网络港口吞吐量预测方法[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 1-5.
[2]	李广儒，朱庆辉. 基于Elman神经网络的港口货物吞吐量预测[J]. 重庆交通大学学报（自然科学版）, 2020, 39(06): 8-12.
[3]	王凤武，张晓博，吉哲，王乐. 基于多变量LSTM模型的青岛港集装箱吞吐量预测[J]. 重庆交通大学学报（自然科学版）, 2022, 41(10): 54-61.
[4]	邓萍1，刘淑龙2. 基于FGM-SVR组合模型的港口吞吐量预测[J]. 重庆交通大学学报（自然科学版）, 2023, 42(8): 132-138.
[5]	丁天明，潘宁，杜柏松，艾万政. 基于改进灰色马尔可夫的港口货物吞吐量预测研究[J]. 重庆交通大学学报（自然科学版）, 2023, 42(9): 130-136.