[ICACE2022] Prediction of container throughout of Qingdao port using optimized echo state network and improved particle swarm optimization
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The container throughput in a container logistics system is an important technical index, irrespective of the method used to manage and forecast the port throughput. The Qingdao port, one of the most important ports in North China, has the advantage of being located in the "One belt One Road" position. At present, the forecasting method for the container transportation throughput of Qingdao port still needs to be optimized, and a model that can predict its development trend needs to be constructed. Echo state networks (ESN) have been widely used in time-series prediction owing to their simple structure and fast convergence speed. To solve the problem of the applicability of the random weight matrix generated in the ESN to a specific time series, this study proposes an improved particle swarm optimization (PSO) algorithm to optimize partial random weights in the ESN. Compared to the standard particle swarm optimization algorithm, the inertia weight and learning factor were adjusted to improve the optimization performance of the algorithm. Furthermore, by comparing the historical data with the predicted values, the prediction accuracy of the model was found to be over 98%. The container throughput of Qingdao port from 2022 to 2024 was predicted, which showed that the container throughput of Qingdao Port will maintain a rapid and stable growth trend.
Abstract
The container throughput in a container logistics system is an important technical index, irrespective of the method used to manage and forecast the port throughput. The Qingdao port, one of the most important ports in North China, has the advantage of being located in the "One belt One Road" position. At present, the forecasting method for the container transportation throughput of Qingdao port still needs to be optimized, and a model that can predict its development trend needs to be constructed. Echo state networks (ESN) have been widely used in time-series prediction owing to their simple structure and fast convergence speed. To solve the problem of the applicability of the random weight matrix generated in the ESN to a specific time series, this study proposes an improved particle swarm optimization (PSO) algorithm to optimize partial random weights in the ESN. Compared to the standard particle swarm optimization algorithm, the inertia weight and learning factor were adjusted to improve the optimization performance of the algorithm. Furthermore, by comparing the historical data with the predicted values, the prediction accuracy of the model was found to be over 98%. The container throughput of Qingdao port from 2022 to 2024 was predicted, which showed that the container throughput of Qingdao Port will maintain a rapid and stable growth trend.
참고문헌 (19)
- 박순철, "인공신경망을 이용한 머플러의 피로 수명 예측", 한국마린엔지니어링학회지, 37(8), pp.869~876 (2013), 한국마린엔지니어링학회[DOI]
- Y. Zhang, "Time series forecasting based on echo state network optimized by improved particle swarm algorithm", Computer Science & Application, 11(8), pp.2070~2079 (2021)
- 이준혁, "기계학습 알고리즘을 활용한 베어링의 고장 예측 알고리즘 개발에 관한 연구", 한국마린엔지니어링학회지, 43(6), pp.455~462 (2019), 한국마린엔지니어링학회[DOI]
- M. Laner, "Parsimonious fitting of long-range dependent network traffic using ARMA models", IEEE Communications Letters, 17(12), pp.2368~2371 (2013)
- C. Narendra Badu, "A moving-average filter based hybrid ARIMA-ANN model for forecasting time series data", Applied Soft Computing, 23, pp.27~38 (2014)
- 정영준, "Forecasting earning of VLCC tankers using artificial neural networks", 한국마린엔지니어링학회지, 42(10), pp.851~858 (2018), 한국마린엔지니어링학회[DOI]
- K. Li, "Chaotic time series prediction based on IBH-LSSVM and its application to short-term prediction of dynamic fluid level of the oil wells", Information and Control, 45(2), pp.241~247
- K. Xue, "P2P traffic prediction model based on wavelet transform and ESN", Computer Engineering and Design, 34(4), pp.1147~1152 (2013)
- N. Chouikhi, "PSO-based analysis of echo state network parameters for time series for ecasting", Applied Soft Computing, 55, pp.211~225 (2017)
- A. Jamal, "A wavelet-neural networks model for time series", 2021IEEE 11th IEEE Symposium on Computer Applications &Industrial Electronics (ISCAIE), pp.325~330 (2021)
- M. T. I. S. Al Wadia, "Selecting wavelet transforms model in forecasting financial time series data based on ARIMA model", Applied Mathematical Sciences, 5(7), pp.315~326 (2011)
- P. Areekul, "Neuralwavelet approach for short term price forecasting in deregulated power market", Journal of International Council on Electrical Engineering, 1(3) (2011)
- H. Wei, "Internet traffic prediction based on wavelet neural network", Computer Science, 38(10A) (2011)
- H. Jaeger, "Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication", Science, 304(5667), pp.78~80 (2004)
- H. Wang, "Optimizing the echo state network with a binary particle swarm optimization algorithm", Knowledge-Based Systems, 86, pp.182~193 (2015)
- P. Yu, "Time series prediction based on echo state network", Acta Electronica Sinica, 38 (2010)
- R. Tiaojuan, "Prediction of nonlinear time series based on elastic small-world echo state network", Computer Applications and Software, 33(4) (2012)
- D. Li, "Structure optimization for echo state network based on contribution", Tsinghua Science and Technology, 24(1), pp.97~105 (2019)
- S. Bodi, "Roughness prediction model based on improved particle swarm optimization neural network", Modular Machine Tool and Automatic Machining Technology, 33(4) (2011)