A novel dynamic resource allocation framework for metaverse using quantum-inspired neural network

The complex and multi-dimensional nature of the metaverse demands that resources be allocated optimally to ensure smooth operations. Traditional approaches are inherently limited in scalability and in ensuring Quality of Service (QoS) in such volatile situations. This study introduces a Quantum-inspired Neural Network (QINN) framework to enhance resource allocation prediction in the Metaverse. The framework is hierarchically designed, with resources distributed across the cloud, edge, and user layers, and includes admission control. Spatial consistency modeling (SCM) and latency transformation (LT) were used to simulate Metaverse workloads from the Google ClusterData2019 dataset, which was then normalized and encoded into quantum-inspired representations. A quantum-inspired neural network is trained in a hybrid manner to forecast resource demands, aiding dynamic resource allocation. Admission control can rank admission requests by resource availability and priority and distribute resources fairly and efficiently using the QINN predictions. Performance was evaluated using the Fidelity Score, Quantum State Distance (QSD), acceptance probability and utilization metrics. The framework achieves 90.1% CPU, 87.4% memory and 79.6% bandwidth utilization at the declared operating point and has a 0.026 SLA violation rate and 0.988 task completion rate. Admission control admits 0.902 of offered sessions at an average reward of 0.664 (0.855 normalized by the priority mix), against reactive and heuristic baselines evaluated on the same traces and seeds. Encoding fidelity between the predicted and true demand states reaches 0.985 with a quantum state distance of 0.015; these are reported as encoding diagnostics rather than as measures of allocation quality. Training the quantum-inspired model requires 195.7 s relative to a closed-form classical reference, an overhead of approximately 12,443 times, with training and inference overheads reported separately because they differ by orders of magnitude. The proposed framework demonstrates promising scalability of dynamic resource allocation in simulated Metaverse environments; however, in practice, it would need to be integrated with a thorough cost-benefit analysis.

Authors

Institutions

Publication Details

Journal
Cluster Computing
Published
2026-11-16
DOI
https://doi.org/10.1007/s10586-026-06774-7
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

A novel dynamic resource allocation framework for metaverse using quantum-inspired neural network

Farhan Amin, Abdu Salam, Fahd Mohammed Aldosari, Isabel de la Torre Díez et al.
1 links
Cluster Computing
Cloud Computing and Resource Management
article

A novel dynamic resource allocation framework for metaverse using quantum-inspired neural network

Farhan Amin, Abdu Salam, Fahd Mohammed Aldosari, Isabel de la Torre Díez, Sultan Saaed Almalki, Muhammad Asif, Alina Eugenia Pascual Barrera, Carlos Osorio García
article en

Abstract

The complex and multi-dimensional nature of the metaverse demands that resources be allocated optimally to ensure smooth operations. Traditional approaches are inherently limited in scalability and in ensuring Quality of Service (QoS) in such volatile situations. This study introduces a Quantum-inspired Neural Network (QINN) framework to enhance resource allocation prediction in the Metaverse. The framework is hierarchically designed, with resources distributed across the cloud, edge, and user layers, and includes admission control. Spatial consistency modeling (SCM) and latency transformation (LT) were used to simulate Metaverse workloads from the Google ClusterData2019 dataset, which was then normalized and encoded into quantum-inspired representations. A quantum-inspired neural network is trained in a hybrid manner to forecast resource demands, aiding dynamic resource allocation. Admission control can rank admission requests by resource availability and priority and distribute resources fairly and efficiently using the QINN predictions. Performance was evaluated using the Fidelity Score, Quantum State Distance (QSD), acceptance probability and utilization metrics. The framework achieves 90.1% CPU, 87.4% memory and 79.6% bandwidth utilization at the declared operating point and has a 0.026 SLA violation rate and 0.988 task completion rate. Admission control admits 0.902 of offered sessions at an average reward of 0.664 (0.855 normalized by the priority mix), against reactive and heuristic baselines evaluated on the same traces and seeds. Encoding fidelity between the predicted and true demand states reaches 0.985 with a quantum state distance of 0.015; these are reported as encoding diagnostics rather than as measures of allocation quality. Training the quantum-inspired model requires 195.7 s relative to a closed-form classical reference, an overhead of approximately 12,443 times, with training and inference overheads reported separately because they differ by orders of magnitude. The proposed framework demonstrates promising scalability of dynamic resource allocation in simulated Metaverse environments; however, in practice, it would need to be integrated with a thorough cost-benefit analysis.

Cluster ComputingVol. 30(1)
Universidad de Valladolid (ES), Abdul Wali Khan University Mardan (PK), Umm al-Qura University (SA), Universidad Europea del Atlántico (ES), University of Business and Technology (SA), Universidad Internacional Iberoamericana (MX), Institute of Public Administration (SA), Frankfurt University of Applied Sciences (DE), Yeungnam University (KR)
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