Autonomous Task Offloading Decision-Making in IIoT Using Digital Twin-Driven Swarm Intelligence Optimization
Dr. Arasuraja GanesanAssociate Professor, Department of Management Studies, St. Joseph’s Institute of Technology, OMR, Chennai, Tamil Nadu, India. arasuraja.mba@gmail.com0000-0001-6137-1911
Dr.P.Y. Muhammed AnshadAssociate Professor, Department of Data Science, UKF College of Engineering and Technology, Parippally, Kollam, Kerala, India. anshadpy@gmail.com0000-0002-1143-0976
Dr.R. MuzhumathiAssistant Professor, Department of Management Sciences, Velammal Engineering College, Chennai, India. muzhumathi22@gmail.com0009-0008-3513-9527
Abdulaziz SobirovBukhara State Pedagogical Institute, Bukhara, Uzbekistan. aziz.sobirov.86@bk.ru0000-0003-0359-2884
Kazim EshkuvatovAssociate Professor, Candidate of Physical and Mathematical Sciences, Department of Physics and Mathematics, Gulistan State University, Uzbekistan. k_eshkuvatov@mail.ru0009-0003-8388-6993
Dr.M. RameshkumarProfessor and Head, Department of Computer Science and Engineering (IoT), Paavai Engineering College, Namakkal, India. . mrkkumarsin@gmail.com0000-0002-9391-341X
Keywords: Industrial Internet of Things (IIoT), Task Offloading, Digital Twins, Swarm Intelligence based Lion-Bat Fusion Algorithm (SI-LBFA).
Abstract
The Industrial Internet of Things (IIoT) has revolutionized industries by enabling seamless communication between interconnected devices and systems. However, implementing and operating IIoT systems presents several challenges, particularly in the area of task offloading, where computationally demanding tasks are offloaded to and run on remote cloud servers. To make optimal task offloading decisions, this research suggests combining Digital Twins computer simulations of physical objects with advanced optimization methods. By leveraging the real-time monitoring capabilities of Digital Twins (DT) and the efficiency of the Swarm Intelligence-based Lion-Bat Fusion Algorithm (SI-LBFA), the proposed model seeks to reduce mission execution time while accounting for server capacity, bandwidth constraints, and device power consumption. The SI-LBFA, a hybrid optimization method that combines the Lion-Bat Fusion approaches, is employed to refine offloading performance. The efficiency of the proposed model is demonstrated through simulations conducted using MATLAB, with a comprehensive performance analysis highlighting its effectiveness in improving task offloading decisions within IIoT environments.