# Selective Task offloading for Maximum Inference Accuracy and Energy efficient Real-Time IoT Sensing Systems

arXiv: https://arxiv.org/abs/2402.16904 · HTML: https://mlsanity.com/paper/2402.16904/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Artificial Intelligence for Suicide Assessment using Audiovisual Cues: A Review](https://mlsanity.com/paper/2201.09130/) (2022)
- [Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint](https://mlsanity.com/paper/2112.11413/) (2021)
- [Blockchain Application on the Internet of Vehicles (IoV)](https://mlsanity.com/paper/2205.03832/) (2022)
- [Task Offloading for Smart Glasses in Healthcare: Enhancing Detection of Elevated Body Temperature](https://mlsanity.com/paper/2308.07193/) (2023)
- [Efficient Fog Node Placement using Nature-Inspired Metaheuristic for IoT Applications](https://mlsanity.com/paper/2302.05948/) (2023)
- [A Fast Task Offloading Optimization Framework for IRS-Assisted Multi-Access Edge Computing System](https://mlsanity.com/paper/2307.08474/) (2023)
- [Context-Aware Service Recommendation System for the Social Internet of Things](https://mlsanity.com/paper/2308.08499/) (2023)
- [IP-UNet: Intensity Projection UNet Architecture for 3D Medical Volume Segmentation](https://mlsanity.com/paper/2308.12761/) (2023)

## Built on by (most cited first, 1 of 1)

- [QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference](https://mlsanity.com/paper/2506.23934/) (2025)

## Abstract (arXiv)

The recent advancements in small-size inference models facilitated AI deployment on the edge. However, the limited resource nature of edge devices poses new challenges especially for real-time applications. Deploying multiple inference models (or a single tunable model) varying in size and therefore accuracy and power consumption, in addition to an edge server inference model, can offer a dynamic system in which the allocation of inference models to inference jobs is performed according to the current resource conditions. Therefore, in this work, we tackle the problem of selectively allocating inference models to jobs or offloading them to the edge server to maximize inference accuracy under time and energy constraints. This problem is shown to be an instance of the unbounded multidimensional knapsack problem which is considered a strongly NP-hard problem. We propose a lightweight hybrid genetic algorithm (LGSTO) to solve this problem. We introduce a termination condition and neighborhood exploration techniques for faster evolution of populations. We compare LGSTO with the Naive and Dynamic programming solutions. In addition to classic genetic algorithms using different reproduction methods including NSGA-II, and finally we compare to other evolutionary methods such as Particle swarm optimization (PSO) and Ant colony optimization (ACO). Experiment results show that LGSTO performed 3 times faster than the fastest comparable schemes while producing schedules with higher average accuracy.