Interval forecasting of photovoltaic power generation on green ship under Multi-factors coupling. (March 2023)

• Record Type: Journal Article
• Authors: Lan, Hai; Gao, Jingjie; Hong, Ying-Yi; Yin, He
• Is Part Of: Sustainable energy technologies and assessments. Volume 56(2023)
• Publication Date: 2023-03
• Subjects: Extreme learning machine -- Interval prediction framework -- Machine learning -- Shipboard photovoltaic system -- Ship rolling; Renewable energy sources -- Periodicals; Energy development -- Technological innovations -- Periodicals; Electric power production -- Periodicals; Energy storage -- Periodicals; 333.79
• DOI: 10.1016/j.seta.2023.103088
• Languages: English
• ISSNs: 2213-1388

Abstract

Highlights: A shipboard PV prediction model is established based on its output char- acteristics. An interval forecast framework based on ML error and PV unpredictability is proposed. The proposed prediction framework is appropriate for various forecasting engines. The interval prediction method using an improved ELM combined with K-Means reduced the PIAW by 26.38% at a confidence level of 98%. Experimental verification of the applicability of the method in practical scenarios. Abstract: Shipboard photovoltaic power generation is affected by various factors, such as meteorological factors, navigation, and ship rolling. Traditional power prediction methods of the land-based grid do not apply to solar ships. Considering the unavoidable Machine Learning algorithm errors and solar energy fluctuations, an interval prediction framework based on a combination of neural network and kernel density estimation methods is proposed. Its generality is demonstrated by comparing different prediction engines. An improved Extreme Learning Machine approach is used to enhance model robustness, considering the computational speed constraints of online prediction. The improved ELM prediction method is at least 5.26% more accurate than the other forecast engines. Considering the sensitivity of the prediction results to the input data, the K-Means clustering is deployed to cluster the historical data to improve the forecast accuracy. The enhanced prediction framework performs well at different confidence levels (85%-98%). Through experimental verification and comparison with diverse state-of-art benchmarks, the effectiveness and stability of the method are proved. At a confidence level of 98%, the prediction interval average width of the proposed method is at least 26.38% smaller relative to other advanced interval prediction methods. It provides the potential to be applied in a ship's power system.