6G EdgeAI: Performance Evaluation and Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917996095602688 |
|---|---|
| author | Yang, Chien-Sheng Ku, Yu-Jen Lou, Yuan-Yao Tenny, Nathan Hsu, Alex C. -C. |
| author_facet | Yang, Chien-Sheng Ku, Yu-Jen Lou, Yuan-Yao Tenny, Nathan Hsu, Alex C. -C. |
| contents | Generative AI (GenAI) services powered by large language models (LLMs) increasingly deliver real-time interactions, yet existing 5G multi-access edge computing (MEC) architectures often treat communication and computing as separate domains, limiting their ability to meet stringent latency requirements. To address this challenge, we introduce an Integrated Communication and Computing (ICC) framework where computing capabilities are enabled to reside directly in radio access network (RAN) nodes and jointly manage bandwidth and computing resources. Our queueing-theoretic analysis shows that ICC outperforms 5G MEC, achieving higher service capacity (defined as the maximum arrival rate that maintains a specified fraction of jobs completed within a given delay budget) by 98%. We corroborate these gains through system-level simulations that account for transformer-based LLM workloads, realistic GPU specifications, and a priority-based scheduling scheme. The simulations show that ICC improves service capacity by 60%, demonstrating its potential to enable efficient, cost-effective real-time GenAI services in 6G. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16529 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 6G EdgeAI: Performance Evaluation and Analysis Yang, Chien-Sheng Ku, Yu-Jen Lou, Yuan-Yao Tenny, Nathan Hsu, Alex C. -C. Distributed, Parallel, and Cluster Computing Generative AI (GenAI) services powered by large language models (LLMs) increasingly deliver real-time interactions, yet existing 5G multi-access edge computing (MEC) architectures often treat communication and computing as separate domains, limiting their ability to meet stringent latency requirements. To address this challenge, we introduce an Integrated Communication and Computing (ICC) framework where computing capabilities are enabled to reside directly in radio access network (RAN) nodes and jointly manage bandwidth and computing resources. Our queueing-theoretic analysis shows that ICC outperforms 5G MEC, achieving higher service capacity (defined as the maximum arrival rate that maintains a specified fraction of jobs completed within a given delay budget) by 98%. We corroborate these gains through system-level simulations that account for transformer-based LLM workloads, realistic GPU specifications, and a priority-based scheduling scheme. The simulations show that ICC improves service capacity by 60%, demonstrating its potential to enable efficient, cost-effective real-time GenAI services in 6G. |
| title | 6G EdgeAI: Performance Evaluation and Analysis |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2504.16529 |