.png){kind=icon}
Return
Multidimensional resource load-aware task migration in mobile edge computing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.future.2025.108091.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• This paper presents a model to minimize load imbalance and ensure timely workflow completion in multi-user MEC with complex dependencies. • This paper designs a GRU-2LSTM hybrid model for real-time user movement prediction, combining LSTM’s long-term and GRU’s short-term efficiency. • This paper develops FMADDPG, a federated deep reinforcement learning algorithm for optimized workflow migration and resource allocation in MEC. • Simulations show our strategy reduces load imbalance by 10%–20% and timeout rate by 7%–27%, outperforming existing methods.
Keywords:
MEC
load imbalance
workflow completion
GRU-2LSTM
federated deep reinforcement learning
Journal
F
IF:
0
Papers:
642
Citations:
0
Organization
No organization information available
Cited Papers
ShareSaveShareSaveLatency and Energy-Aware Load Balancing in Cloud Data Centers: A Bargaining Game Based Approach
PREAI
ShareSaveDDPG-based optimal task placement strategy for computation offloading in green mobile edge networks
PREAI
ShareSaveShareSaveShareSaveApplying Hybrid Lstm-Gru Model Based on Heterogeneous Data Sources for Traffic Speed Prediction in Urban Areas.png)
SENSORS
OAAI
SENSORSIF3.5
OAAIShareSave
View more