Minimizing the computation latency of FDMA‐based wireless powered edge computing network

The 0–1 mixed integer programming problem of binary offloading on wireless powered mobile edge computing (WP‐MEC) networks requires joint optimization of binary and continuous variables, which is computationally expensive for traditional techniques and difficult to solve within the channel coherence...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IET communications Jg. 17; H. 17; S. 2030 - 2039
Hauptverfasser: Chen, Xi, Jiang, Guodong, Chi, Kaikai, Zhang, Shubin, Wei, Xinchen, Chen, Gang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Stevenage John Wiley & Sons, Inc 01.10.2023
Wiley
Schlagworte:
Algorithms
Bandwidths
Complexity
Continuity (mathematics)
Convex analysis
convex programming
Deep learning
delay estimation
Edge computing
Energy consumption
frequency division multiple access
Integer programming
Internet of Things
Linear programming
Machine learning
Mixed integer
Mobile computing
Network latency
Optimization
Power
Radio frequency
Scheduling
Unmanned aerial vehicles
Wireless networks
Workloads
ISSN:1751-8628, 1751-8636
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The 0–1 mixed integer programming problem of binary offloading on wireless powered mobile edge computing (WP‐MEC) networks requires joint optimization of binary and continuous variables, which is computationally expensive for traditional techniques and difficult to solve within the channel coherence time under time‐varying condition. Using machine learning models to output variable values is also challenging. Hence, designing efficient and low‐complexity algorithms is crucial for optimal network performance. This paper focuses on the computation latency of the FDMA‐based WP‐MEC network and proposes a task‐offloading algorithm to minimize the total completion delay (TCD). The TCD minimization is modelled as a 0–1 MIP problem and is decomposed into a master problem of optimizing the offloading decision and the sub‐problem of optimizing other parameters under a given offloading decision. The sub‐problem is solved using optimization method, while the master problem is solved using a deep reinforcement learning algorithm. Simulation results show that the proposed algorithm can achieve almost minimal TCD with low complexity.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1751-8628
1751-8636
DOI:10.1049/cmu2.12676