Wind energy and wave energy are considered to have enormous potential as renewable energy sources in the energy system to make great contributions in transitioning from fossil fuel to renewable energy. However, the uncertain, erratic, and complicated scenarios, as well as the tremendous amount of information and corresponding parameters, associated with wind and wave energy harvesting are difficult to handle. In the field of big data handing and mining, artificial intelligence plays a critical and efficient role in energy system transition, harvesting and related applications. The derivative method of deep learning and its surrounding prolongation structures are expanding more maturely in many fields of applications in the last decade. Even though both wind and wave energy have the characteristics of instability, more and more applications have implemented using these two renewable energy sources with the support of deep learning methods. This paper systematically reviews and summarizes the different models, methods and applications where the deep learning method has been applied in wind and wave energy. The accuracy and effectiveness of different methods on a similar application were compared. This paper concludes that applications supported by deep learning have enormous potential in terms of energy optimization, harvesting, management, forecasting, behavior exploration and identification.
Wave energy has been studied and explored because of its enormous potential to supply electricity for human activities. However, the uncertainty of its spatial and temporal variations increases the difficulty of harvesting wave energy commercially. There are no large-scale wave converters in commercial operation yet. A thorough understanding of wave energy dynamic behaviors will definitely contribute to the acceleration of wave energy harvesting. In this paper, about 40 years of meteorological data from the Gulf of Mexico were obtained, visualized, and analyzed to reveal the wave power density hotspot distribution pattern, and its correlation with ocean surface water temperatures and salinities. The collected geospatial data were first visualized in MATLAB. The visualized data were analyzed using the deep learning method to identify the wave power density hotspots in the Gulf of Mexico. By adjusting the temporal and spatial resolutions of the different datasets, the correlations between the number of hotspots and their strength levels and the surface temperatures and salinities are revealed. The R value of the correlation between the wave power density hotspots and the salinity changes from −0.371 to −0.885 in a negative direction, and from 0.219 to 0.771 in a positive direction. For the sea surface temperatures, the R values range from −0.474 to 0.393. Certain areas within the Gulf of Mexico show relatively strong correlations, which may be useful for predicting the wave energy behavior and change patterns.
Offshore oil and gas platforms use gas turbine with natural gas or fuel diesel for their high demand of power. Due to the declining amount of gas available, high carbon footprint, increasing cost of fuel and inefficient operating, alternative energy options are necessary and imminent. Most offshore oil and gas platforms locate in deep water surrounded by huge amount of energetic wave resources, hence, the feasibility of supplying offshore oil facilities electricity by hybrid wave and wind energy farms based on daily energy power production instead of annual average was conducted in this project. The hybrid energy farm was modeled and validated by applying meteorological data in Gulf of Mexico area from WaveWatch III system. With the hindcast wave and wind condition data from 1979 to 2019, daily energy generation of the hybrid energy farm was estimated. Meantime, the feasibility of suppling offshore oil and gas facilities by the proposed combined hybrid farm was assessed. The project optimized the configuration of the hybrid wave and wind energy farm to satisfy offshore oil and gas platform demands and reduce the variation of power generation, so that it may be feasibility to gradually substitute the gas turbines. Through matching the local wave and wind conditions, the project was able to maximize the power output while minimize the variation within limited ocean surface area. The project addressed the advantages of hybrid wave and wind devices, as well as theoretical prospection of wave harvesting device and wind turbine combination. To validate the proposed optimization model, a case study was explored by using Vesta V90 3MW wind turbines and Pelamis 750kW wave energy converters to supply five offshore platforms in more than 45 m deep water areas. The results indicated the possibility of bringing wave energy into large commercial operation and utilization with minor investment and environmental impact.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.