# BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms

arXiv: https://arxiv.org/abs/2305.01519 · HTML: https://mlsanity.com/paper/2305.01519/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 1 May 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [Soft Actor-Critic for Discrete Action Settings](https://mlsanity.com/paper/1910.07207/) (2019)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [TensorFlow-Serving: Flexible, High-Performance ML Serving](https://mlsanity.com/paper/1712.06139/) (2017)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning](https://mlsanity.com/paper/2008.12260/) (2020)
- [PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Units](https://mlsanity.com/paper/1909.04548/) (2019)
- [Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments using A3C learning and Residual Recurrent Neural Networks](https://mlsanity.com/paper/2009.02186/) (2020)
- [VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling](https://mlsanity.com/paper/2201.06212/) (2022)
- [DeepRT: A Soft Real Time Scheduler for Computer Vision Applications on the Edge](https://mlsanity.com/paper/2105.01803/) (2021)
- [MCDS: AI Augmented Workflow Scheduling in Mobile Edge Cloud Computing Systems](https://mlsanity.com/paper/2112.07269/) (2021)
- [Tailored Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud System](https://mlsanity.com/paper/2101.06582/) (2021)

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

- [CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads](https://mlsanity.com/paper/2409.01089/) (2024)
- [A Study of Skews, Imbalances, and Pathological Conditions in LLM Inference Deployment on GPU Clusters detectable from DPU](https://mlsanity.com/paper/2509.18114/) (2025)

## Abstract (arXiv)

As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time. Such edge platforms with multiple DNN models pose new challenges for scheduler designs. First, each request may have different service level objectives (SLOs) to improve quality of service (QoS). Second, the edge platforms should be able to efficiently schedule multiple heterogeneous DNN models so that system utilization can be improved. To meet these two goals, this paper proposes BCEdge, a novel learning-based scheduling framework that takes adaptive batching and concurrent execution of DNN inference services on edge platforms. We define a utility function to evaluate the trade-off between throughput and latency. The scheduler in BCEdge leverages maximum entropy-based deep reinforcement learning (DRL) to maximize utility by 1) co-optimizing batch size and 2) the number of concurrent models automatically. Our prototype implemented on different edge platforms shows that the proposed BCEdge enhances utility by up to 37.6% on average, compared to state-of-the-art solutions, while satisfying SLOs.