# Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers

arXiv: https://arxiv.org/abs/2503.04148 · HTML: https://mlsanity.com/paper/2503.04148/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 55 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](https://mlsanity.com/paper/2007.00708/) (2020)
- [Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours](https://mlsanity.com/paper/1904.02877/) (2019)
- [Chasing Carbon: The Elusive Environmental Footprint of Computing](https://mlsanity.com/paper/2011.02839/) (2020)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors](https://mlsanity.com/paper/1903.05898/) (2019)
- [Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service](https://mlsanity.com/paper/2304.09781/) (2023)
- [AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing](https://mlsanity.com/paper/2407.05633/) (2024)
- [Let's Wait Awhile: How Temporal Workload Shifting Can Reduce Carbon Emissions in the Cloud](https://mlsanity.com/paper/2110.13234/) (2021)
- [OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload](https://mlsanity.com/paper/2307.03290/) (2023)
- [GreenScale: Carbon-Aware Systems for Edge Computing](https://mlsanity.com/paper/2304.00404/) (2023)
- [CarbonCP: Carbon-Aware DNN Partitioning with Conformal Prediction for Sustainable Edge Intelligence](https://mlsanity.com/paper/2404.16970/) (2024)
- [Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks](https://mlsanity.com/paper/2407.01054/) (2024)
- [Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chips](https://mlsanity.com/paper/2308.05869/) (2023)
- [A Guide to Reducing Carbon Emissions through Data Center Geographical Load Shifting](https://mlsanity.com/paper/2105.09120/) (2021)
- [RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices](https://mlsanity.com/paper/2411.17867/) (2024)

## Built on by (most cited first, 2 of 2)

- [Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems](https://mlsanity.com/paper/2609.13559/) (2026)
- [MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks](https://mlsanity.com/paper/2609.14660/) (2026)

## Abstract (arXiv)

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.