Performance Modeling and Analysis of the Bitcoin Inventory Protocol

Abstract

Blockchains are currently gaining attention as a newly emerging technology in both academia and industry, capable of impacting a variety of domains beyond cryptocurrencies. Performance modeling can be used to provide us with a deeper understanding of the behavior and dynamics within blockchain peer-to-peer networks. Blockchain system architects can leverage network models to properly tune their system and to reduce design costs significantly. In this paper, we focus on the original and well-established Bitcoin blockchain network. In particular, we propose a random graph model for performance modeling and analysis of the inventory-based protocol for block dissemination. This model addresses the impact of key blockchain parameters on the overall performance of Bitcoin. We derive some explicit and closed-form equations for block propagation delay and traffic overhead. We implement our model using the popular network simulator OMNet++. We validate the accuracy of our theoretical model and its implementation with our dataset mined from the Bitcoin network. Our results show the trade-off between the default number of connections per node, network bandwidth, and block size in order to compute the optimal block propagation delay over the network.