Affiliation:
1. Department of Mechanical and Industrial Engineering, Sustainable Energy Systems Engineering, MSC 191 Texas A&M University-Kingsville, Kingsville, Texas
2. Department of Mechanical and Industrial Engineering, MSC 191 Texas A&M University-Kingsville, Kingsville, Texas
Abstract
Abstract
The activities in the Gulf of Mexico are thriving with a considerable number of oil and gas platforms operating in this area. Wave power can provide a substantial portion of clean power to substitute for the inefficient gas turbines used on the platforms. Wave power density (wave energy flux) is one of the ways for directly assessing the potential and available wave power. The task of a wave energy capture device is to effectively capture the wave energy flux. The average wave power density is generally between 20 kW/m and 65 kW/m in the Gulf of Mexico. During tropical storms or hurricanes, the theoretical wave power density could reach 1,600 kW/m. However, higher wave height and period could damage the energy capture devices. This project explores the correlation pattern between available wave power density hotspots and hurricane-induced wave distribution within 10 years (2010-2019) using a deep convolutional neural network.
The correlation pattern was explored and validated by applying meteorological data in the Gulf of Mexico area from the NOAA WAVEWATCH III system. A wave power hotspot was defined as an event when wave power density over a certain threshold during a period of time in a predefined location. The distribution of wave power hotspots has the segmentation threshold on wave power depending on the wave energy converter, location, wave height and wave period. The meteorological data from WAVEWATCH III was visualized as images of wave power density in 3-hour time steps, which were used for wave power density hotspot identification, classification and localization through a deep convolutional neural network.
With the distribution of wave power density hotspots along with the coordinates attached through matching the local wave and hurricane-induced wave conditions and the GIS mapping support, the project was able to reveal the impacts of hurricanes based on pattern recognition between the wave power hotspots distribution and hurricane-induced wave track distribution. Meanwhile, the comparison of the wave power density hotspot distribution with extreme weather conditions and under the regular circumstances was analyzed. The results could also provide feedback to and support wave energy harvesting or hurricane forecasting and harvesting.
Reference23 articles.
1. Monthly Energy Review and Short-Term Energy Outlook (STEO);U.S. Energy Information Administration
2. Wave energy utilization: A review of the technologies;Antonio;Renewable and sustainable energy reviews,2010
3. Renewable Energy Market Update 2021;IEA,2021
4. Renewable energy market update;IEA,2020
5. Decomposing scale and technique effects of financial development and foreign direct investment on renewable energy consumption;Shahbaz;Energy,2022