IRS-Enhanced Parallel Offloading or Direct Offloading: An Online Semi-Distributed Optimization for Latency Sensitive MEC

The surge in task-intensive applications underscores the critical need for mobile edge computing (MEC) to deliver low-latency services that cater to the computational demands of user equipment (UE). Computing density is inherently heterogeneous and dynamic, driven by the varying demands of UEs acros...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE internet of things journal s. 1
Hlavní autori: Chen, Guolin, Huang, Xiaoxia
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: IEEE 2025
Predmet:
Array signal processing
Computational efficiency
Computational modeling
Delays
Intelligent reflecting surface (IRS)
mobile edge computing (MEC)
Optimization
Planning
Real-time systems
semi-distributed optimization
Servers
Upper bound
Wireless communication
ISSN:2327-4662, 2327-4662
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The surge in task-intensive applications underscores the critical need for mobile edge computing (MEC) to deliver low-latency services that cater to the computational demands of user equipment (UE). Computing density is inherently heterogeneous and dynamic, driven by the varying demands of UEs across space and time. To address the challenges posed by heterogeneous computing density, we propose a novel hybrid offloading framework that enables resource-constrained devices to dynamically choose between direct offloading and intelligent reflecting surface (IRS)-enhanced parallel offloading, thereby minimizing overall latency, improving resource utilization and adapting to varying conditions. Additionally, for prompt computation distribution, we propose an online semi-distributed optimization based on a two-timescale approach. Combining long-term centralized planning with short-term distributed computation assignment, this framework enables low-complexity distributed task allocation while ensuring performance and stability. Furthermore, we develop an equivalence and relaxation approach to derive an upper bound for completion delay of servers, which greatly simplifies the computation complexity of completion delay of tasks. Our proposed online semi-distributed algorithm converges, with reduced delay 24.03% and 32.68% compared to existing IRS-enhanced parallel offloading scheme and direct offloading scheme.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2025.3631737