Electricity is an essential part of modern life, and imagining even a single day without it is difficult. Most daily products that surround human life, either directly or indirectly, depend on electricity. However, generating this valuable electricity is not an easy task. Traditionally, fossil fuels have been used for electricity generation, which is environmentally unfriendly and causes significant damage to the Earth, including the creation of the greenhouse effect leading to global warming and the release of harmful greenhouse gases into the atmosphere. This traditional method relies on non-renewable energy sources. As the global population continues to grow, the demand for electrical power increases, exacerbating environmental concerns. Renewable energy sources, such as tidal, hydro, wind, and solar energy, offer environmentally friendly alternatives. Researchers are increasingly integrating machine learning (ML) and deep learning (DL) techniques into the renewable energy conversion process to enhance efficiency. Despite the advancements, existing research has both advantages and disadvantages. This survey examines the pros and cons of recent research on renewable energy combined with ML and DL techniques. Additionally, it evaluates the limitations of current methodologies and proposes effective solutions to address these challenges. This research paper focuses on various methods based on renewable energy conversion techniques, including power prediction, energy conversion, and energy forecasting, using DL and ML approaches for renewable energy sources such as tidal, hydropower, wind, and solar.