Prediction of Permissioned Blockchain Performance for Resource Scaling Configurations
This addresses the challenge of resource provisioning for cloud service providers and users of BaaS, offering a practical solution to replace trial-and-error methods, though it is incremental as it builds on prior work.
The paper tackles the problem of configuring blockchain-as-a-service (BaaS) for optimal performance by developing machine learning models to predict network reliability and throughput based on scaling configurations, achieving prediction errors of ~1.9%.
Blockchain is increasingly offered as blockchain-as-a-service (BaaS) by cloud service providers. However, configuring BaaS appropriately for optimal performance and reliability resorts to try-and-error. A key challenge is that BaaS is often perceived as a ``black-box,'' leading to uncertainties in performance and resource provisioning. Previous studies attempted to address this challenge; however, the impacts of both vertical and horizontal scaling remain elusive. To this end, we present machine learning-based models to predict network reliability and throughput based on scaling configurations. In our evaluation, the models exhibit prediction errors of ~1.9%, which is highly accurate and can be applied in the real-world.