Performance modeling of public permissionless blockchains: A survey
Molud Esmaili, Ken Christensen
TL;DR
The paper surveys performance modeling of public permissionless blockchains, highlighting queueing-theory as the dominant analytical tool and complementing it with workload and traffic modeling. It reviews Bitcoin (PoW), Ethereum 2.0 (PoS), and Algorand (BA/VRF), detailing performance criteria and a spectrum of queueing models (M/G/1, M/M/1, G/M/1, GI/GI/1) and other approaches. It also covers workload characterization, network topology modeling, benchmarking with Blockbench and BCTMark, and traffic analyses to inform predictive performance evaluation. The study identifies gaps, such as the need for simulators for Eth2 and Algorand and more comprehensive analyses of newer blockchains, and it proposes directions for future research to balance performance with security and to develop representative workloads.
Abstract
Public permissionless blockchains facilitate peer-to-peer digital transactions, yet face performance challenges specifically minimizing transaction confirmation time to decrease energy and time consumption per transaction. Performance evaluation and prediction are crucial in achieving this objective, with performance modeling as a key solution despite the complexities involved in assessing these blockchains. This survey examines prior research concerning the performance modeling blockchain systems, specifically focusing on public permissionless blockchains. Initially, it provides foundational knowledge about these blockchains and the crucial performance parameters for their assessment. Additionally, the study delves into research on the performance modeling of public permissionless blockchains, predominantly considering these systems as bulk service queues. It also examines prior studies on workload and traffic modeling, characterization, and analysis within these blockchain networks. By analyzing existing research, our survey aims to provide insights and recommendations for researchers keen on enhancing the performance of public permissionless blockchains or devising novel mechanisms in this domain.