전기추진 선박의 발전 방향과 실데이터를 활용한 전력 부하 예측

진성훈¹ ; 홍창우²^{, *}

1해군 소령/잠수함사령부
2해군 소령/해군사관학교 기계시스템공학과 교수

Electric Power Load Forecasting Using Real Data and the Recent Advancements of Electric Propulsion Ships

Sung Hoon Jin¹ ; Chang Woo Hong²^{, *}

1LCDR, ROK Navy/Submarine Force Command
2LCDR, ROK Navy/Professor, Dept. of Mechanical System Engineering, ROK Naval Academy

Correspondence to: ^*Chang Woo Hong Republic of Korea Naval Academy PO box number 88-4-1, 1 Jungwon-ro, Jinhae-gu, Changwon-si, Gyungnam, 51704, Republic of Korea Tel: +82-55-907-5304 E-mail: spearw@navy.ac.kr

초록

본 논문에서는 가스 운반선의 실데이터를 활용한 전력 부하 예측 실험결과를 도출하였다. 먼저 전기추진 함정의 도입으로 인한 전기에너지 중요성과 패러다임의 변화를 소개하고, 전력 부하 예측기법과 예측 사례를 살펴보았다. 전력 부하 예측 실험은 가스 운반선의 실데이터를 활용하여 딥러닝으로 수행하였으며 높은 정확도를 도출하였다. 이후 대한민국 해군에서의 적용과 향후 발전 방향에 대해 논의하였다.

Abstract

In this paper, the results of the electric power load forecasting experiment using the actual data of the gas carrier were derived. First, the importance of electric energy and paradigm changes due to the introduction of electric propulsion vessels were introduced, and electric power load forecasting techniques and prediction cases were examined. The electric power load forecasting experiment was performed through deep learning using the actual data of the gas carrier, and high accuracy was derived. After that, the application of the Korean Navy and the direction of future development were discussed.

Keywords:

DTC(Decision Tree Classification), All Electric Ship, Electric Power Load Forecasting, Gas Carrier, Deep Learning

키워드:

전기추진 함정, 전력 부하 예측, 가스 운반선, 딥 러닝

Acknowledgments

이 논문은 2021년도 해군 군수사령부 함정기술지에 발표된 내용을 편집한 논문임.

References

Maxim A. Dulebenets, “Advantages and disadvantages from enforcing emission restrictions within emission control areas”, Maritime Business Review ISSN: 2397-3757, 2016. [https://doi.org/10.1108/MABR-05-2016-0011]
G. S. Babu, P. Zhao, and X.-L. Li. “Deep convolutional neural network based regression approach for estimation of remaining useful life,” In International conference on database systems for advanced applications, Springer, 2016, pp. 214-228. [https://doi.org/10.1007/978-3-319-32025-0_14]
S. Zheng, K. Ristovski, A. Farahat, and C. Gupta. “Long short-term memory network for remaining useful life estimation,” 2017 IEEE international conference on prognostics and health management(ICPHM), 2017, pp. 88-95. [https://doi.org/10.1109/ICPHM.2017.7998311]
Makridakis S, Spiliotis E, AssimakopoulosV, “Statistical and Machine Learning forecasting methods: Concerns and ways forward,” PLoS ONE, 13(3), 2018. [https://doi.org/10.1371/journal.pone.0194889]
Tae-Young Kim, Sung-Bae Cho, Predicting residential energy consumption using CNN-LSTM neural networks, Energy, Volume 182, 2019, pp. 72-81. [https://doi.org/10.1016/j.energy.2019.05.230]
Gkerekos, C., Lazakis, I. and Theotokatos, G., 2019. Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study. Ocean Engineering, 188, p.106282. [https://doi.org/10.1016/j.oceaneng.2019.106282]
MojtabaMerzadi, YacineTerriche et al., “A Deep Learning Method for Short-Term Dynamic Positioning Load Forecasting in Maritime Microgrids,” Applied Science, 2020. [https://doi.org/10.3390/app10144889]
Zhicheng Cui, Wenlin Chen, and Yixin Chen, “Multi-Scale Convolutional Neural Networks for Time Series Classification,” Computer Vision and Pattern Recognition, May 2016.
Jayasinghe, S. G., Meegahapola, L., Fernando, N., Jin, Z., & Guerrero, J. M., 2017, Review of ship microgrids: System architectures, storage technologies and power quality aspects. inventions, 2(1), 4. [https://doi.org/10.3390/inventions2010004]