| Title: |
Energy-Aware Task Offloading in Fog-Cloud-IoT Ecosystem Using Reinforcement Learning |
| Authors: |
Revathi, N.; Suryaprabha, Dr. D.; Chithrakumar, Dr. T.; Shanmugapriya, A.; Sundar, Dr. R.; Ramachandran, Reshma |
| Source: |
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES; Vol. 12 No. 1 (2026); 145-160 ; 2457-0370 |
| Publisher Information: |
XLESCIENCE |
| Publication Year: |
2026 |
| Collection: |
International Journal of Advances in Signal and Image Sciences (IJASIS) |
| Subject Terms: |
Fog computing; cloud computing; Internet of Things (IoT); reinforcement learning; energy efficiency; Q-learning; task offloading; latency reduction; resource allocation; sustainable computing |
| Description: |
With the proliferation of Internet of Things (IoT) applications, the fog–cloud computing paradigm has emerged as a crucial architecture for achieving low latency, energy efficiency, and scalability in distributed systems. However, optimal task offloading across heterogeneous fog and cloud layers remains a significant challenge due to dynamic workloads, limited fog resources, and varying network conditions. This paper proposes an energy-aware task offloading framework using reinforcement learning (RL) to intelligently distribute computation between fog and cloud nodes. The RL agent learns optimal offloading strategies by interacting with the environment, dynamically balancing energy consumption, execution latency, and network load. A Q-learning-based optimization model is employed to determine the most efficient offloading decisions, while the energy model accounts for computation, transmission, and idle power consumption at both fog and cloud layers. Simulation results demonstrate that the proposed RL-based approach achieves a 31% reduction in average energy consumption and a 27% improvement in task response time compared to baseline heuristic and static scheduling techniques. The model adapts efficiently under fluctuating workloads and variable network bandwidth, maintaining service quality while minimizing energy footprint. This intelligent task offloading strategy is particularly effective for real-time IoT applications such as smart healthcare, connected vehicles, and industrial automation, ensuring sustainable and resource-efficient operation across the Fog–Cloud–IoT ecosystem. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
English |
| Relation: |
https://xlescience.org/index.php/IJASIS/article/view/435/161; https://xlescience.org/index.php/IJASIS/article/view/435 |
| DOI: |
10.29284/ijasis.12.1.2026.145-160 |
| Availability: |
https://xlescience.org/index.php/IJASIS/article/view/435; https://doi.org/10.29284/ijasis.12.1.2026.145-160 |
| Rights: |
https://creativecommons.org/licenses/by/4.0 |
| Accession Number: |
edsbas.C6193A75 |
| Database: |
BASE |