DLUSEdge: Dynamic Load–Unload Scheduling for Localized LLMs on Resource-Constrained Edge

20-08-2025
Systems Description

Authors: Partha Pratim Ray; Mohan Pratap Pradhan
Published in: KI - Künstliche Intelligenz

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Deploying large language models (LLMs) on resource-constrained edge device presents significant challenges due to their high computational and memory demands. This paper introduces DLUSEdge, an efficient algorithmic framework designed to dynamically manage the loading and unloading of quantized LLMs on edge devices. The framework employs time-bound scheduling to optimize task execution while minimizing resource overhead. Four quantized LLMs, including qwen2.5:0.5b-instruct and granite3-moe:1b-instruct-q4_K_M, were evaluated in real-world scenarios, demonstrating task latency as low as \(1.97 \times 10^9\) ns and switching latency as low as \(2.25 \times 10^9\) ns. Correlation analysis revealed that prompt evaluation metrics strongly influence task latency (\(r > 0.8\)), highlighting key optimization areas. Statistical analysis confirmed significant differences in task performance across models (\(p < 0.001\)). The results validate the effectiveness of DLUSEdge in optimizing resource utilization and task performance, providing a robust solution for localized LLM inferencing. The code is hosted on https://github.com/ParthaPRay/llm_dynamic_load_unload.

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

more than 102.000 books
more than 537 journals

from the following subject areas:

Automotive
Construction + Real Estate
Business IT + Informatics
Electrical Engineering + Electronics
Energy + Sustainability
Finance + Banking
Management + Leadership
Marketing + Sales
Mechanical Engineering + Materials
Insurance + Risk

Secure your knowledge advantage now!

inform now

KI - Künstliche Intelligenz

The Scientific journal "KI – Künstliche Intelligenz" is the official journal of the division for artificial intelligence within the "Gesellschaft für Informatik e.V." (GI) – the German Informatics Society - with constributions from troughout the field of artificial intelligence.

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

more than 67.000 books
more than 340 journals

from the following specialised fileds:

Construction + Real Estate
Business IT + Informatics
Finance + Banking
Management + Leadership
Marketing + Sales
Insurance + Risk

Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

more than 67.000 books
more than 390 journals

from the following specialised fileds:

Automotive
Business IT + Informatics
Construction + Real Estate
Electrical Engineering + Electronics
Energy + Sustainability
Mechanical Engineering + Materials

Secure your knowledge advantage now!

inform now

Metadata
Footnotes
Literature

Title: DLUSEdge: Dynamic Load–Unload Scheduling for Localized LLMs on Resource-Constrained Edge
Authors: Partha Pratim Ray
Mohan Pratap Pradhan
Publication date: 20-08-2025
Publisher: Springer Berlin Heidelberg
Published in: KI - Künstliche Intelligenz
Print ISSN: 0933-1875
Electronic ISSN: 1610-1987
DOI: https://doi.org/10.1007/s13218-025-00895-8

This content is only visible if you are logged in and have the appropriate permissions.