Dynamics of Ethereum’s EIP-1559 Transaction Fee Mechanism

Abstract

Transaction fee mechanisms are pivotal elements of blockchain economies, as they resolve the inherent scarcity in the number of transactions that can be added to each block. First-price auction mechanisms implemented by early blockchain protocols, however, contributed to pronounced intra-block disparities, unpredictable waiting times, high congestion, and other inefficiencies. To mitigate these effects, alternative fee market mechanism has been proposed, e.g., Ethereum’s EIP-1559. In this article, we investigate the ramifications of EIP-1559 on system performance and user experience. Although we prove that EIP-1559 exhibits chaotic behavior even under optimal conditions, we demonstrate that the influence of this chaotic behavior on the primary design objective of the fee mechanism—blocks whose long-term average size equals the target—is limited. Our theoretical bound shows that block sizes in the EIP-1559 mechanism are lower bounded by target utilization—half-full blocks—and the upper bound is capped at 6% beyond the target. These findings are confirmed by an empirical evaluation that shows that the average discrepancy has been 2.9% under Proof-of-Work and decreases to around 1% or less following Ethereum’s transition to Proof-of-Stake. However, the chaotic oscillations in block sizes and the slow adjustments during periods of demand bursts (e.g., NFT drops) result in undesirable inter-block variations in mining rewards and compromise the overall user experience. To address these issues, we propose an alternative base fee adjustment rule, characterized by a learning rate that adapts according to an additive increase, multiplicative decrease (AIMD) update scheme. Our data-driven simulations show that the latter robustly outperforms the EIP-1559 protocol across various demand scenarios.