Empirical Analysis of GNN Architectures for VM Power Consumption Prediction

Show simple item record

dc.contributor.author Kaburu, Morris
dc.contributor.author Gikunda, Patrick
dc.contributor.author Moso, Juliet Chebet
dc.date.accessioned 2026-08-31T09:45:35Z
dc.date.available 2026-08-31T09:45:35Z
dc.date.issued 2026-05
dc.identifier.citation M. Kaburu, P. Gikunda and J. Moso (2026) "Empirical Analysis of GNN Architectures for VM Power Consumption Prediction", IST-Africa 2026 Conference Proceedings, Miriam Cunningham and Paul Cunningham (Eds), IST-Africa Institute and IIMC, 2026, ISSN: 2576-8581, ISBN: 978-1-905824-76-2, https://doi.org/10.67725/IST-Africa.2026.OFPX9691 en_US
dc.identifier.uri https://doi.org/10.67725/IST-Africa.2026.OFPX9691
dc.identifier.uri https://repository.dkut.ac.ke:8080/xmlui/handle/123456789/21669
dc.description.abstract Power consumption prediction for virtual machines (VMs) is key in improving energy efficiency, capacity planning and sustainability in cloud computing. In this work, we present a comprehensive empirical study that compares several Graph Neural Network (GNN) architectures such as Graph Convolutional Network (GCN), GraphSAGE, Graph Attention Network (GAT), a Temporal GAT / dynamic graph design, GIN, R-GCN, Graph Transformer and Graph NODE for predicting VM power consumption using a real VM monitoring dataset. We assess the impact of different graph construction strategies including k-nearest neighbour, feature similarity threshold and temporal adjacency on predictive performance. Using standard regression metrics (MAE, MSE, RMSE, R²), we reveal that while all GNN models struggle to consistently surpass a naïve mean baseline, feature similarity threshold provides better performance and T-GAT architecture perform better than other. We analyze failure modes and offer recommendations for future work, including richer feature engineering, learned graph structures, and hybrid temporal-spatial modelling. en_US
dc.language.iso en en_US
dc.publisher IST-Africa Institute and IIMC International Information Management Corporation Ltd en_US
dc.subject Graph Neural Networks en_US
dc.subject VM Power Prediction en_US
dc.subject GCN en_US
dc.subject GraphSAGE en_US
dc.subject GAT en_US
dc.subject Temporal GNN en_US
dc.subject GIN en_US
dc.subject T-GATs en_US
dc.subject R-GCN en_US
dc.subject Graph Node en_US
dc.subject Cloud Energy en_US
dc.subject Spatio-Temporal Forecasting en_US
dc.title Empirical Analysis of GNN Architectures for VM Power Consumption Prediction en_US
dc.type Presentation en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account