Objective <p>Advanced information exchange and monitoring platforms have been created due to the incorporation of IoT technology and artificial intelligence into educational systems. These platforms make it possible to collect, analyze, and make decisions about data in real time, which improves the efficiency, dependability, and long-term viability of the education network.</p> Methods <p>Investigating an IoT-based platform created for information exchange and tracking within the solar systems implemented in schools, and analyzing the tracking platform of the educational management system is the goal of this project. The Pelican optimized support vector machine (PO-SVM) was proposed in this study to achieve the sharing and tracking platform of educational management. We collect solar system sensed data and use min–max normalization to preprocess the raw data in order to remove noisy or redundant data before analyzing the performance of the suggested method. Following that, kernel-based linear discriminant analysis (K-LDA) was used to extract features.</p> Results <p>The performance of the proposed strategy was evaluated in terms of accuracy, precision, recall, sensitivity, specificity, and f-measure metrics, and it was also contrasted with other approaches. The results of this study use statistical will give important insights into the possible advantages of incorporating data mining methods into a solar system IoT platform. The outcomes can support the creation of effective allocation of resources in educational management that is smarter and more effective, promote sustainability, and encourage the broad use of energy from renewable sources.</p>