# Hierarchical Online-Scheduling for Energy-Efficient Split Inference with Progressive Transmission

arXiv: https://arxiv.org/abs/2601.08135 · HTML: https://mlsanity.com/paper/2601.08135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022)
- [Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization](https://mlsanity.com/paper/2305.13553/) (2023)
- [Multi-user Co-inference with Batch Processing Capable Edge Server](https://mlsanity.com/paper/2206.06304/) (2022)
- [DVFS-Aware DNN Inference on GPUs: Latency Modeling and Performance Analysis](https://mlsanity.com/paper/2502.06295/) (2025)
- [Integrated Sensing and Edge AI: Realizing Intelligent Perception in 6G](https://mlsanity.com/paper/2501.06726/) (2025)
- [EMM: Energy-Aware Mobility Management for Mobile Edge Computing in Ultra Dense Networks](https://mlsanity.com/paper/1709.02582/) (2017)
- [Joint Optimization of Video-based AI Inference Tasks in MEC-assisted Augmented Reality Systems](https://mlsanity.com/paper/2301.01010/) (2023)
- [Robust DNN Partitioning and Resource Allocation Under Uncertain Inference Time](https://mlsanity.com/paper/2503.21476/) (2025)

## Abstract (arXiv)

Device-edge collaborative inference with Deep Neural Networks (DNNs) faces fundamental trade-offs among accuracy, latency and energy consumption. Current scheduling exhibits two drawbacks: a granularity mismatch between coarse, task-level decisions and fine-grained, packet-level channel dynamics, and insufficient awareness of per-task complexity. Consequently, scheduling solely at the task level leads to inefficient resource utilization. This paper proposes a novel ENergy-ACcuracy Hierarchical optimization framework for split Inference, named ENACHI, that jointly optimizes task- and packet-level scheduling to maximize accuracy under energy and delay constraints. A two-tier Lyapunov-based framework is developed for ENACHI, with a progressive transmission technique further integrated to enhance adaptivity. At the task level, an outer drift-plus-penalty loop makes online decisions for DNN partitioning and bandwidth allocation, and establishes a reference power budget to manage the long-term energy-accuracy trade-off. At the packet level, an uncertainty-aware progressive transmission mechanism is employed to adaptively manage per-sample task complexity. This is integrated with a nested inner control loop implementing a novel reference-tracking policy, which dynamically adjusts per-slot transmit power to adapt to fluctuating channel conditions. Experiments on ImageNet dataset demonstrate that ENACHI outperforms state-of-the-art benchmarks under varying deadlines and bandwidths, achieving a 43.12% gain in inference accuracy with a 62.13% reduction in energy consumption under stringent deadlines, and exhibits high scalability by maintaining stable energy consumption in congested multi-user scenarios.