.png){kind=icon}
.png){kind=icon}
Return
GA-MO: Pareto-Optimal Split Computing for Deep Edge Intelligence
.png){kind=icon}
PRE
AI
DOI：10.1142/S219688882650003X.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deploying deep neural networks (DNNs) on resource-constrained devices requires hybrid device-cloud inference in which end-to-end latency and data transmission must be optimized jointly. Existing Dynamic Split Computing (DSC) methods primarily target latency and overlook the computation-communication trade-off; as a result, varying bandwidth and batch size can lead to suboptimal operating points (e.g. excessive transmission for marginal latency gains). We propose Genetic Algorithm Multi-Objective (GA-MO), a genetic-algorithm framework that constructs Pareto fronts across diverse bandwidth scenarios and supports adaptive runtime selection. GA-MO jointly reduces inference latency and transmission load to satisfy application-specific performance requirements, including common real-time constraints. Beyond single-objective baselines, GA-MO is further shown to outperform a weighted-sum multi-objective approach, highlighting the effectiveness of evolutionary search in exploring the split-computing design space. Experiments on EfficientNet-B0 and VGG16 show that GA-MO outperforms DSC, achieving 55-60% lower latency and 52-62% bandwidth savings, with a 100% win rate across all tested conditions. These results indicate that GA-MO is an effective and scalable approach to multi-objective optimization for hybrid edge-cloud inference.
Keywords:
Genetic algorithm
multi-objective optimization
split computing
hybrid edge-cloud inference
latency
communication efficiency
Journal
V
IF:
1.1
Papers:
18
Citations:
0