Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915184095789056 |
|---|---|
| author | Paramanayakam, Varatheepan Karatzas, Andreas Stamoulis, Dimitrios Anagnostopoulos, Iraklis |
| author_facet | Paramanayakam, Varatheepan Karatzas, Andreas Stamoulis, Dimitrios Anagnostopoulos, Iraklis |
| contents | Edge computing systems struggle to efficiently manage multiple concurrent deep neural network (DNN) workloads while meeting strict latency requirements, minimizing power consumption, and maintaining environmental sustainability. This paper introduces Ecomap, a sustainability-driven framework that dynamically adjusts the maximum power threshold of edge devices based on real-time carbon intensity. Ecomap incorporates the innovative use of mixed-quality models, allowing it to dynamically replace computationally heavy DNNs with lighter alternatives when latency constraints are violated, ensuring service responsiveness with minimal accuracy loss. Additionally, it employs a transformer-based estimator to guide efficient workload mappings. Experimental results using NVIDIA Jetson AGX Xavier demonstrate that Ecomap reduces carbon emissions by an average of 30% and achieves a 25% lower carbon delay product (CDP) compared to state-of-the-art methods, while maintaining comparable or better latency and power efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04148 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers Paramanayakam, Varatheepan Karatzas, Andreas Stamoulis, Dimitrios Anagnostopoulos, Iraklis Machine Learning Distributed, Parallel, and Cluster Computing Performance Edge computing systems struggle to efficiently manage multiple concurrent deep neural network (DNN) workloads while meeting strict latency requirements, minimizing power consumption, and maintaining environmental sustainability. This paper introduces Ecomap, a sustainability-driven framework that dynamically adjusts the maximum power threshold of edge devices based on real-time carbon intensity. Ecomap incorporates the innovative use of mixed-quality models, allowing it to dynamically replace computationally heavy DNNs with lighter alternatives when latency constraints are violated, ensuring service responsiveness with minimal accuracy loss. Additionally, it employs a transformer-based estimator to guide efficient workload mappings. Experimental results using NVIDIA Jetson AGX Xavier demonstrate that Ecomap reduces carbon emissions by an average of 30% and achieves a 25% lower carbon delay product (CDP) compared to state-of-the-art methods, while maintaining comparable or better latency and power efficiency. |
| title | Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Performance |
| url | https://arxiv.org/abs/2503.04148 |