Skip to main navigation Skip to search Skip to main content

RL-Based Energy-Efficient Computation Offloading under Deadline Constraints in Multi-User Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper addresses the challenge of energy-efficient computation offloading in multi-user, single-cloudlet systems under deadline constraints. While offloading AI workloads to a shared cloudlet can augment edge device capabilities, it faces cloudlet contention and wireless channel variability, complicating energy-latency trade-offs. We propose a fine-grained, level-wise reinforcement learning (RL) framework that makes per-level offloading decisions in real-time. Our RL approach, based on an actor-critic (A2C) agent, dynamically adapts to bandwidth fluctuations and cloudlet queue states while adhering to fractionally allocated deadlines. Our method reduces energy consumption by 33% compared to local-only execution, by 42% compared to a coarse-grained approach, and by 56% compared to all-cloudlet offloading, while consistently meeting deadlines and maintaining low runtime overhead.

Original languageEnglish (US)
Title of host publicationProceedings of the ICCSPA 2026 - 7th International Conference on Communications, Signal Processing, and their Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331561284
DOIs
StatePublished - 2026
Event7th International Conference on Communications, Signal Processing, and their Applications, ICCSPA 2026 - Alcala, Spain
Duration: Jun 15 2026 → Jun 18 2026

Publication series

NameProceedings of the ICCSPA 2026 - 7th International Conference on Communications, Signal Processing, and their Applications

Conference

Conference7th International Conference on Communications, Signal Processing, and their Applications, ICCSPA 2026
Country/TerritorySpain
CityAlcala
Period6/15/26 → 6/18/26

Keywords

  • Computation offloading
  • Edge computing
  • reinforcement learning (RL)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Instrumentation
  • Signal Processing
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'RL-Based Energy-Efficient Computation Offloading under Deadline Constraints in Multi-User Systems'. Together they form a unique fingerprint.

Cite this