Litcius/Paper detail

A Hybrid Multi-Objective Optimization for 6G-Enabled Internet of Things (IoT)

Shailendra Pratap Singh, Naween Kumar, Gyanendra Kumar, Balamurugan Balusamy, Ali Kashif Bashir, Yasser D. Al‐Otaibi

2024IEEE Transactions on Consumer Electronics20 citationsDOI

Abstract

The advent of 6G-enabled networks marks a transformative era in the Internet of Things (IoT), promising unparalleled connectivity and innovation. These networks are set to revolutionize the IoT landscape by offering remarkable capabilities, including ultra-high data speeds, ultra-low latency, and extensive network coverage and connectivity. However, optimizing such networks’ is a complex challenge, mainly when dealing with numerous conflicting objectives. So far, existing works have employed heuristic or meta-heuristic algorithms to address this issue. This research introduces a novel approach, ‘Hybrid Multi-Objective Optimization,’ which combines Multi-Objective forms of Red fox (RFOX) optimization with Differential Evolution (DE) to address this issue. This hybrid framework is designed to solve the complexity of Multi-Objective optimization within the context of 6G-enabled IoT networks. It leverages the flexibility and search capabilities of RFOX, along with the population-based search techniques of DE. The primary objective of this research paper is to identify the Pareto-optimal front, which encapsulates the complex trade-offs among various conflict objectives in Multi-Objective optimization. Extensive simulation outcomes demonstrate the significant efficacy of the proposed algorithm for its adaptability, diversity, and multi-objective optimization capabilities compared to existing ones in terms of data throughput, delay, energy efficiency, and packet loss ratio in 6G-enabled IoT applications.

Topics & Concepts

Internet of ThingsComputer scienceWeb of ThingsComputer networkComputer securityIoT and Edge/Fog ComputingAdvanced MIMO Systems OptimizationDigital Transformation in Industry