Intelligent Solar Forecasting of Power Generation in a Single-axis Solar Tracking Pv System Using a Modern Machine Learning Method

Solar energy remains one of the most promising and widely adopted renewable resources globally. In the post-fossil fuel era, solar power has gained prominence as a sustainable alternative to dwindling natural resources and as a solution to the urgent demand for carbon-neutral energy. The escalation of global warming and climate change, driven by CO2 emissions from traditional power plants, represents a critical environmental threat. Consequently, global initiatives are shifting toward the 2030 Sustainable Development Goals (SDGs) to foster environmental restoration. This project aligns with SDG 7 (Affordable and Clean Energy) by developing an optimized prototype for solar energy harvesting. Findings: While solar adoption is increasing across residential, commercial, and industrial sectors to reduce operational costs, maximizing efficiency remains a challenge. Current automation techniques, such as solar tracking—modeled after the heliotropic movement of sunflowers—significantly enhance energy capture. However, these systems face limitations due to atmospheric factors like cloud cover, dust accumulation, and seasonal shifts. Although Dual-Axis trackers (moving East-West and North-South) offer maximum efficiency, their high capital cost makes them inaccessible for many users.Methods: To address the balance between cost and performance, this research introduces a single-axis solar tracking prototype integrated with Machine Learning (ML). By utilizing ML algorithms to predict and identify the optimal angle of solar radiation, the system dynamically adjusts the panel's orientation for peak power extraction. This methodology provides a high-efficiency, cost-effective alternative to traditional tracking systems, opening new horizons for accessible solar technology.