Erma Perenda

About

Erma Perenda is a rising researcher at the forefront of integrating distributed machine learning with industrial robotic systems, focusing on the critical intersection of edge computing, federated learning, and cooperative task management. Her most-cited work, “Cooperative Partial Task-Offloading for Heterogeneous Industrial Robotic MEC System Using Spectral and Energy-Efficient Federated Learning” (2023), tackles the complex challenge of enabling collaborative decision-making among networked intelligent machines. Perenda’s key contribution lies in developing a novel framework that harmonizes sensing, communication, and computation—specifically, she proposes a spectral and energy-efficient federated learning approach to optimize partial task-offloading in heterogeneous multi-access edge computing (MEC) environments. This work directly addresses the cross-fertilization of components essential for scalable, real-time industrial automation. While her citation count is still growing, the foundational nature of her research positions her as an emerging voice in the field. Her achievements include pioneering a method that balances spectral efficiency with energy constraints, a critical step toward practical, cooperative robotic systems. For students and researchers, Perenda’s work offers a compelling blueprint for integrating machine learning tools with physical systems to achieve intelligent, collaborative task management in Industry 4.0.

Research Focus

Key Achievements

Top Papers

1. 1
   Cooperative Partial Task-Offloading for Heterogeneous Industrial Robotic MEC System Using Spectral and Energy-Efficient Federated Learning

   3 citations · 2023

Key Collaborators

Contact & Links