Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Guided-Mutation Genetic Algorithm for Mobile IoT Network Relay

Gyupil Kam, Kiseop Chung

TL;DR

This work tackles the NP-hard problem of jointly optimizing relaying topology and TDMA time-slot allocation in energy-harvesting IoT networks with mobility. It introduces a guided-mutation genetic algorithm (GMGA) that modulates mutation probability by link-cost metrics, establishes the validity of an Iterative Balancing (IB) time-slot allocation through $R_k(\mathbf{t})$ equality and KKT duality, and proposes a mobility-aware iterative relaying topology that reuses prior-frame results for rapid adaptation. The approach yields three main contributions: (i) a theoretical proof that equalizing node rates maximizes the minimum rate under fixed topology, (ii) a GMGA capable of finding sub-optimal yet computation-efficient topologies with mutation-rate guidance, and (iii) a mobility-aware topology algorithm enabling frame-to-frame updates in dynamic environments. Across stationary and mobility scenarios, GMGA delivers higher $R_{\min}$ than baseline schemes and closely matches optimal performance while substantially reducing computation time relative to VAE-based methods, demonstrating practical feasibility for real-time network management in mobile EH-IoT. This framework advances energy-efficient, mobility-tolerant IoT relay design with TDMA and EH, offering a scalable solution for next-generation wireless systems.

Abstract

The Internet of Things (IoT) is a communication scheme which allows various objects to exchange several types of information, enabling functions such as home automation, production management, healthcare, etc. In addition, energy-harvesting (EH) technology is considered for IoT environment in order to reduce the need for management and enhance maintainability. Moreover, since environments considering outdoor elements such as pedestrians, vehicles and drones have been on the rise recently, it is important to consider mobility when designing an IoT network management scheme. However, calculating the optimal relaying topology is considered as an NP-hard problem, and finishing computation for mobility environment before the channel status changes is important to prevent delayed calculation results. In this article, our objective is to calculate a sub-optimal relaying topology for stationary and mobile system within reasonable computation time. To achieve our objective, we validate an iterative balancing time slot allocation algorithm introduced in the previous study, and propose a guided-mutation genetic algorithm (GMGA) that modulates the mutation rate based on the channel status for rational exploration. Additionally, we propose a mobility-aware iterative relaying topology algorithm, which calculates relaying topology in a mobility environment using an inheritance of the sub-optimal relaying topology calculations. Simulation results verify that our proposed scheme effectively solves formulated IoT network problems compared to other conventional schemes, and also effectively handles IoT environments including mobility in terms of minimum rate budget and computation time.

Guided-Mutation Genetic Algorithm for Mobile IoT Network Relay

TL;DR

This work tackles the NP-hard problem of jointly optimizing relaying topology and TDMA time-slot allocation in energy-harvesting IoT networks with mobility. It introduces a guided-mutation genetic algorithm (GMGA) that modulates mutation probability by link-cost metrics, establishes the validity of an Iterative Balancing (IB) time-slot allocation through equality and KKT duality, and proposes a mobility-aware iterative relaying topology that reuses prior-frame results for rapid adaptation. The approach yields three main contributions: (i) a theoretical proof that equalizing node rates maximizes the minimum rate under fixed topology, (ii) a GMGA capable of finding sub-optimal yet computation-efficient topologies with mutation-rate guidance, and (iii) a mobility-aware topology algorithm enabling frame-to-frame updates in dynamic environments. Across stationary and mobility scenarios, GMGA delivers higher than baseline schemes and closely matches optimal performance while substantially reducing computation time relative to VAE-based methods, demonstrating practical feasibility for real-time network management in mobile EH-IoT. This framework advances energy-efficient, mobility-tolerant IoT relay design with TDMA and EH, offering a scalable solution for next-generation wireless systems.

Abstract

The Internet of Things (IoT) is a communication scheme which allows various objects to exchange several types of information, enabling functions such as home automation, production management, healthcare, etc. In addition, energy-harvesting (EH) technology is considered for IoT environment in order to reduce the need for management and enhance maintainability. Moreover, since environments considering outdoor elements such as pedestrians, vehicles and drones have been on the rise recently, it is important to consider mobility when designing an IoT network management scheme. However, calculating the optimal relaying topology is considered as an NP-hard problem, and finishing computation for mobility environment before the channel status changes is important to prevent delayed calculation results. In this article, our objective is to calculate a sub-optimal relaying topology for stationary and mobile system within reasonable computation time. To achieve our objective, we validate an iterative balancing time slot allocation algorithm introduced in the previous study, and propose a guided-mutation genetic algorithm (GMGA) that modulates the mutation rate based on the channel status for rational exploration. Additionally, we propose a mobility-aware iterative relaying topology algorithm, which calculates relaying topology in a mobility environment using an inheritance of the sub-optimal relaying topology calculations. Simulation results verify that our proposed scheme effectively solves formulated IoT network problems compared to other conventional schemes, and also effectively handles IoT environments including mobility in terms of minimum rate budget and computation time.
Paper Structure (14 sections, 1 theorem, 16 equations, 8 figures, 2 tables, 1 algorithm)

This paper contains 14 sections, 1 theorem, 16 equations, 8 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Contributions and Organization
  3. Related Works
  4. System Model and Problem Formulation
  5. System Model
  6. Problem Formulation
  7. Proposed Methodology
  8. Proof of Validity for Iterative Balancing Time Slot Allocation Algorithm
  9. Guided-Mutation Genetic Algorithm Based Topology Algorithm
  10. Mobility-aware Iterative Relaying Topology Algorithm
  11. Performance Analysis and Discussions
  12. Test Environment and Parameter Configuration
  13. Experiment Analysis and Discussion
  14. Conclusions

Key Result

Proposition 1

Let us define the amount of bits/Hz the $k$th node itself can transmit as $R_k(\mathbf{t})$ with given $\mathbf{c}$ and $k^*=\mathop{\mathrm{argmin}}\limits\limits_{k}{R_k(\mathbf{t})}$. Then, a condition to maximize $R_{k^*}(\mathbf{t})$ where $t_1+t_2+...+t_{N_d}=T$ is $R_1(\mathbf{t})=R_2(\mathb

Figures (8)

  • Figure 1: System model example when $N_d=6$, $N_b=1$.
  • Figure 2: Structure flow chart of the mobility-aware iterative relaying topology algorithm to find $\mathbf{c^*}$ and $\mathbf{t^*}$ throughout the simulation.
  • Figure 3: Change in relaying topology of mobility simulation over time for $N_{d}=10$, $N_{b}=1$ example.
  • Figure 4: Computation time of 6 different schemes with respect to the number of nodes, $N_d$.
  • Figure 5: Stationary performance comparison with respect to the number of PBs, $N_b$ in $N_d\in\{5,6,7\}$
  • ...and 3 more figures

Theorems & Definitions (2)

  • Proposition 1
  • proof