Sustainability-Aware Scheduling of LLM Inference Tasks on Heterogeneous Geo-Distributed Infrastructures Using an Improved Golden Jackal Optimization Approach

Most of the energy consumed and carbon emitted by Large Language Models (LLMs) over their lifetimes is associated with inference as opposed to training. The device that receives each request decides the cost, carbon emitted, and how fast the response returns. We treat inference scheduling of LLMs as an optimization problem. Energy, carbon, and adherence to service-level agreements (SLA) are the objectives. We consider the optimization problem in single-objective and multi-objective form. Two key aspects that distinguish this work from previous attempts are: (1) treatment of each device as a distinct unit for measuring inference latency, and (2) SLA violations that depend on the schedule itself. For the optimization of LLM inference scheduling across heterogeneous, geo-distributed devices, we enforce capacity through a soft penalty that is normalized by total demand. This helps to keep the optimization meaningful when the demand exceeds the capacity of the device pool. The optimization problem is NP-hard. We present Improved Golden Jackal Optimization (IGJO) to solve this optimization problem. IGJO combines quasi-reflected opposition at initialization with a stagnation-driven controller that monitors the population’s coefficient of variation and raises the opposition rate as diversity collapses. We improved twelve metaheuristics by integrating the same mechanisms as IGJO. IGJO, therefore, competes against eleven other algorithms that have the same improvements. We conduct experiments on three synthetically generated workloads and two oversubscribed production workloads (Azure LLM inference and BurstGPT), and each workload has twenty common-seeded runs. We perform Friedman and Wilcoxon tests with Holm correction. The enhancement improves the algorithms broadly, but has some clear limits and those are reported. In single-objective mode, IGJO has the best average fitness and average Friedman rank. Of the 55 pairwise tests, IGJO won 47. Similarly, in the multi-objective case, IGJO also performs best. Here, IGJO won 45 out of the 55 pairwise comparisons. Against simple scheduling rules and the closely related FPC method, IGJO is better on every workload in both modes, with a fitness gap over FPC of 12.5–28.5%. IGJO shows the greatest advantage for the workloads that model the conditions faced in actual practice, namely, the constrained and oversubscribed settings.

Authors

Institutions

Publication Details

Journal
Computers
Published
2026-11-16
DOI
https://doi.org/10.3390/computers15110841
Primary Topic
Cloud Computing and Resource Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Sustainability-Aware Scheduling of LLM Inference Tasks on Heterogeneous Geo-Distributed Infrastructures Using an Improved Golden Jackal Optimization Approach

Ahmad Sawalmeh, Sharif Naser Makhadmeh, Yousef K. Sanjalawe, Mohammed Azmi Al‐Betar
Computers
Cloud Computing and Resource Management
article

Sustainability-Aware Scheduling of LLM Inference Tasks on Heterogeneous Geo-Distributed Infrastructures Using an Improved Golden Jackal Optimization Approach

Ahmad Sawalmeh, Sharif Naser Makhadmeh, Yousef K. Sanjalawe, Mohammed Azmi Al‐Betar
article en

Abstract

Most of the energy consumed and carbon emitted by Large Language Models (LLMs) over their lifetimes is associated with inference as opposed to training. The device that receives each request decides the cost, carbon emitted, and how fast the response returns. We treat inference scheduling of LLMs as an optimization problem. Energy, carbon, and adherence to service-level agreements (SLA) are the objectives. We consider the optimization problem in single-objective and multi-objective form. Two key aspects that distinguish this work from previous attempts are: (1) treatment of each device as a distinct unit for measuring inference latency, and (2) SLA violations that depend on the schedule itself. For the optimization of LLM inference scheduling across heterogeneous, geo-distributed devices, we enforce capacity through a soft penalty that is normalized by total demand. This helps to keep the optimization meaningful when the demand exceeds the capacity of the device pool. The optimization problem is NP-hard. We present Improved Golden Jackal Optimization (IGJO) to solve this optimization problem. IGJO combines quasi-reflected opposition at initialization with a stagnation-driven controller that monitors the population’s coefficient of variation and raises the opposition rate as diversity collapses. We improved twelve metaheuristics by integrating the same mechanisms as IGJO. IGJO, therefore, competes against eleven other algorithms that have the same improvements. We conduct experiments on three synthetically generated workloads and two oversubscribed production workloads (Azure LLM inference and BurstGPT), and each workload has twenty common-seeded runs. We perform Friedman and Wilcoxon tests with Holm correction. The enhancement improves the algorithms broadly, but has some clear limits and those are reported. In single-objective mode, IGJO has the best average fitness and average Friedman rank. Of the 55 pairwise tests, IGJO won 47. Similarly, in the multi-objective case, IGJO also performs best. Here, IGJO won 45 out of the 55 pairwise comparisons. Against simple scheduling rules and the closely related FPC method, IGJO is better on every workload in both modes, with a fitness gap over FPC of 12.5–28.5%. IGJO shows the greatest advantage for the workloads that model the conditions faced in actual practice, namely, the constrained and oversubscribed settings.

ComputersVol. 15(11)
University of Jordan (JO), Chulalongkorn University (TH), Ajman University (AE), Petra University (JO)
Cloud Computing and Resource Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon