Hybrid Clustering Algorithms for Skill Profiling in Microgrid and Distributed Energy Resources Education
Abstract
Hybrid clustering algorithms have emerged as powerful tools for addressing the complexity of skill profiling in technical education, particularly in fields such as microgrids and distributed energy resources (DERs), where interdisciplinary knowledge and hands-on expertise are critical for workforce readiness. Traditional training approaches often fail to capture the multi-dimensional nature of students' competencies, leading to skill gaps in system operation, control, and integration of renewable technologies. The problem lies in accurately mapping students' heterogeneous learning patterns and technical proficiency to craft adaptive learning trajectories that ensure comprehensive understanding of both theoretical and practical aspects. To overcome the issues, the paper propose a Hybrid Clustering for Skill Profiling (HCSP) framework that integrates <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex>-means for fast partitioning with hierarchical agglomerative clustering (HAC) for structural refinement, leveraging their complementary strengths to achieve both scalability and fine-grained grouping. The HCSP algorithm incorporates domain-specific performance indicators such as control system simulations, energy management case studies, and laboratory-based DER integration tasks. Experimental results on a dataset of microgrid-focused training programs demonstrated that HCSP significantly outperforms singlemodel clustering in terms of cluster cohesion, interpretability, and alignment with expert evaluations, achieving a 15% improvement in normalized mutual information and better mapping of learner trajectories. The findings indicate that adaptive curricula generated through HCSP can more effectively identify high-potential learners, guide intervention for underperformers, and promote collaborative learning in team-based projects. In conclusion, HCSP provides an intelligent and scalable methodology for deriving actionable skill profiles to enhance education in microgrid and DER domains, thereby supporting workforce transformation in the clean energy transition.