@article{ART003364203},
author={Pil-Seong Jeong},
title={Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={7},
pages={1-11}
TY - JOUR
AU - Pil-Seong Jeong
TI - Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 7
PB - The Korean Society Of Computer And Information
SP - 1
EP - 11
SN - 1598-849X
AB - This study compares modality-specific specialized models distributed across a heterogeneous edge cluster with single-device omnimodal deployment under identical tasks. A cluster of Jetson AGX Orin, Raspberry Pi 5+Hailo-8, and Orange Pi 5 Plus runs MobileViT-S, Whisper-tiny, and DistilBERT via gRPC, benchmarked against LLaVA-1.5-7B FP16, its INT4 quantization, and Qwen2-VL-2B FP16. The distributed configuration is 80–288× faster on Vision, 3.7–25× faster on Text, and up to 806× more energy-efficient, with Text F1 within 2.8 percentage points across all four configurations. Effect decomposition attributes 3.93× to quantization and 1.75× to model size reduction, with an additional 63.5× from distribution itself, confirming independence from model size and quantization. The 17–195× cost-normalized advantage is retained across five wired-to-wireless network scenarios; distributed clusters thus suit concurrent multi-modal serving, while omnimodal deployment suits cross-modal reasoning.
KW - Edge AI;Distributed Inference;Heterogeneous Edge Cluster;Specialized Model;Omnimodal Model;Performance Characterization
DO -
UR -
ER -
Pil-Seong Jeong. (2026). Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference. Journal of The Korea Society of Computer and Information, 31(7), 1-11.
Pil-Seong Jeong. 2026, "Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference", Journal of The Korea Society of Computer and Information, vol.31, no.7 pp.1-11.
Pil-Seong Jeong "Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference" Journal of The Korea Society of Computer and Information 31.7 pp.1-11 (2026) : 1.
Pil-Seong Jeong. Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference. 2026; 31(7), 1-11.
Pil-Seong Jeong. "Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference" Journal of The Korea Society of Computer and Information 31, no.7 (2026) : 1-11.
Pil-Seong Jeong. Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference. Journal of The Korea Society of Computer and Information, 31(7), 1-11.
Pil-Seong Jeong. Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference. Journal of The Korea Society of Computer and Information. 2026; 31(7) 1-11.
Pil-Seong Jeong. Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference. 2026; 31(7), 1-11.
Pil-Seong Jeong. "Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference" Journal of The Korea Society of Computer and Information 31, no.7 (2026) : 1-11.
