Given the necessity of transitioning to renewable energy and the importance of sustainability management in power grids, this research aims to analyze the quantitative indicators affecting this domain. The primary innovation of this paper lies in presenting a data-driven analytical platform that bridges the gap between theoretical literature and real-world data analysis by integrating intelligent models. Unlike conventional methods, this study employs classification and clustering algorithms—specifically Random Forest (RF), Support Vector Machine (SVM), and K-Means clustering. Furthermore, to enhance validation metrics, two novel hybrid models were developed: the first combining Random Forest and SVM, and the second integrating clustering with SVM. These models were applied to quantitative data, including industrial electricity consumption, renewable energy production, electricity pricing, and total national electricity consumption, to conduct a robust numerical analysis. Conducted within a positivist paradigm using a quantitative methodology, this research identifies a growing trend in renewable energy production and demonstrates that rising electricity prices encourage industrial units to invest in on-site power generation. A key policy innovation of this study is the proposal of a comprehensive model for balancing energy production and consumption in the industrial sector, offering strategic solutions such as time-of-use pricing, smart energy management systems, and carbon taxation within the framework of a circular energy economy. The results not only improve the accuracy of large-scale energy data analysis through the proposed hybrid models but also provide an operational roadmap for policymakers to achieve electrical sustainability by fostering direct industrial participation in renewable energy power plants.