Citation

Khatoon, Amna and Ullah, Asad and Bello, Aliyu. Uthman and Khan, Adil and Roslee, Mardeni and Amin, Hamda (2025) Fuzzy Logic-Based Task Scheduling for AI-Enabled IoT Edge Devices in Smart Communication Networks. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 92.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

Edge-based Artificial Intelligence (AI) systems in Internet of Things (IoT) communication networks face critical challenges in real-time task allocation due to resource constraints, high event density, and latency sensitivity. Traditional scheduling approaches such as round-robin or static prioritization lack adaptability under dynamic edge workloads. In this study, we propose a fuzzy logic-based task scheduling framework tailored for AI-enabled IoT edge devices, where sensor fusion, image processing, and alert generation occur concurrently. Our method integrates a fuzzy inference engine to dynamically assign task priorities based on multidimensional inputs including task urgency, execution load, and remaining power budget. This scheduler is embedded into an optimized round-robin loop that minimizes context-switching overhead while retaining responsiveness to mission-critical events such as anomaly detection or traffic violations. Mathematical modeling of fuzzy rule design is presented along with evaluation over a simulated STM32-based edge node, where AI-based frame analysis, temperature sensing, and communication payloads are scheduled adaptively. Experimental results show a 17.5% reduction in average latency and a 22.3% improvement in task success rate under fluctuating workloads, compared to baseline approaches. The proposed fuzzy scheduler significantly enhances decision intelligence and responsiveness in communication-intensive edge environments. This work contributes to the development of intelligent scheduling layers for next-generation IoT, vehicular, and AI-driven embedded systems.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Fuzzy logic scheduling, edge computing
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:09
Last Modified:	19 Mar 2026 01:33
URII:	http://shdl.mmu.edu.my/id/eprint/15578

Downloads

Edit (login required)