A novel load prediction method for hybrid electric ship based on working condition classification

Abstract

In order to effectively optimize the load distribution between power sources during the navigation of hybrid ships, a method for predicting ship load demand based on real-time classification according to different working conditions is proposed. The k-means clustering algorithm is used to quantify the voyage history data to classify the ship’s navigation conditions into fast-changing conditions and slow-changing conditions. Some characteristic parameters related to working conditions are selected as input. Then, input and the category of working conditions are put into least squares support vector machine to learn and train to get an online working condition classifier. The genetic algorithm is used to optimize the radial-based neural network to predict the load demand under fast-changing conditions, use the Markov chain model to predict the load demand under slow-changing conditions, so as to obtain the most accurate future load demand of the ship. The simulation results show that the proposed prediction models under different conditions have higher precision, which is an effective means of predicting the load demand for hybrid power ships.

Keywords

Hybrid power ship condition classification prediction load demand

Get full access to this article

View all access options for this article.

References

Abbiati

Salandra

Bursi

, et al. (2018) A composite experimental dynamic substructuring method based on partitioned algorithms and localized Lagrange multipliers. Mechanical Systems and Signal Processing 100: 85–112.

Amber

Ahmad

Aslam

, et al. (2018) Intelligent techniques for forecasting electricity consumption of buildings. Energy 157 (8): 886–893.

Barman

Choudhury

(2019) Season specific approach for short-term load forecasting based on hybrid FA-SVM and similarity concept. Energy 174 (5): 886–896.

Demidova

Klyueva

Pylkin

(2019) Hybrid approach to improving the results of the SVM classification using the random forest algorithm. Procedia Computer Science 150: 455–461.

Dimopoulou

Oppermann

Boggasch

, et al. (2018) A Markov decision process for managing a hybrid energy storage system. Journal of Energy Storage 19 (10): 160–169.

Hou

Song

Hofmann

, et al. (2019) Adaptive model predictive control for hybrid energy storage energy management in all-electric ship microgrids. Energy Conversion and Management 198: 111929.

Hou

Jing

Hofmann

(2018) Adaptive model predictive control with propulsion load estimation and prediction for all-electric ship energy management. Energy 150: 887–889.

Hunter

(2018) Kemeny’s function for Markov chains and Markov renewal processes. Linear Algebra and its Applications 559: 54–72.

Jia

Zhao

Ding

(2016) An optimized RBF neural network algorithm based on partial least squares and genetic algorithm for classification of small sample. Applied Soft Computing 48: 373–384.

10.

Jiang

Wang

(2017) Short-term wind speed forecasting using a hybrid model. Energy 119 (1): 561–577.

11.

Kolmanovsky

Sivergina

Sun

(2006) Simultaneous input and parameter estimation with input observers and set-membership parameter bounding. International Journal of Adaptive Control and Signal Processing 20(5): 225–246.

12.

Lin

Zhao

Pan

, et al. (2019) Energy management for a dual-motor coupling propulsion electric bus based on model predictive control. Energy Procedia 158: 2744–2749.

13.

Liu

Wang

, et al. (2018) Markov velocity predictor and radial basis function neural network-based real-time energy management strategy for plug-in hybrid electric vehicles. Energy 152: 427–444.

14.

Liu

Wang

Yang

(2018) Online Markov Chain-based energy management for a hybrid tracked vehicle with speedy Q-learning. Energy 160: 544–555.

15.

Nielson

Bhaganagar

Meka

, et al. (2019) Using atmospheric inputs for Artificial Neural Networks to improve wind turbine power prediction. Energy 190: 116273.

16.

Rahman

(2018) isGPT: An optimized model to identify sub-Golgi protein types using SVM and Random Forest based feature selection. Artificial Intelligence in Medicine 84: 90–100.

17.

Tian

(2020) Chaotic characteristic analysis of network traffic time series at different time scales. Chaos, Solitons & Fractals 130: 109412.

18.

Vaidyanathan

(2007) The theory of linear prediction. Synth Lect Signal Process: 2(1): 1–184.

19.

Wang

Zhao

Fan

(2010) Chaotic time series analysis method for ship electric load forecasting. Journal of Dalian University of Technology 50(1): 141–144.

20.

Fan

(2014) Maximum matrix element method for determining the number of hidden layer nodes in RBF neural network. Computer Engineering and Applications 20: 77–79.

21.

Xiang

Ding

Wang

, et al. (2017) Energy management of a dual-mode power-split hybrid electric vehicle based on velocity prediction and nonlinear model predictive control. Applied Energy 189: 640–653.

22.

Yin

Perakis

Wang

(2018) A real-time ship roll motion prediction using wavelet transform and variable RBF network. Ocean Engineering 160: 10–19.

23.

Yuan

Chen

Jiang

, et al. (2019) Prediction interval of wind power using parameter optimized Beta distribution based LSTM model. Applied Soft Computing Journal 82: 105550.