TimesNet-BFT: Mitigating Network State Uncertainty in Byzantine Consensus via Deep Temporal Modeling

TL;DR

This paper introduces TimesNet-BFT, a new framework that improves blockchain consensus by using deep learning to handle unpredictable network conditions.

Contribution

The novel contribution is an entropy-aware framework using deep temporal modeling to optimize BFT protocols under network uncertainty.

Findings

TimesNet-BFT achieves a prediction MAPE below 5% in latency estimation.

It increases throughput by up to 191.9% and reduces latency variance by 73.3% in high-entropy networks.

The framework enables robust zero-shot generalization and maintains consensus safety despite AI prediction errors.

Abstract

Byzantine fault tolerance (BFT) protocols serve as the cornerstone of data consistency in permissioned blockchains; however, their scalability is inherently constrained by stochastic leader-centric bottlenecks and rigid, non-adaptive timeout mechanisms. Existing rule-based heuristics often fail to capture high-entropy and time-varying network latency, leading to frequent view changes and severe performance degradation under network volatility. To mitigate this epistemic uncertainty, this paper proposes TimesNet-BFT, a novel entropy-aware optimization framework. By leveraging TimesNet’s transformation of one-dimensional time series into two-dimensional tensors for multi-periodicity analysis, the framework accurately characterizes stochastic nodal latency patterns to facilitate entropy-minimized dynamic leader election and adaptive timeout strategies. Extensive evaluations conducted on simulated and real-world trace-driven Internet of Vehicles (IoV) scenarios validate the proposed approach, achieving a prediction MAPE below 5% alongside robust zero-shot generalization. Notably, under high-entropy network conditions, the framework demonstrates up to a 191.9% increase in throughput and mitigates latency variance by 73.3%, effectively neutralizing the structural bottlenecks inherent to traditional information-agnostic protocols. Crucially, by mathematically decoupling consensus safety from AI prediction errors, the system introduces an aggressive liveness paradigm that maintains minimal control plane overhead while significantly enhancing the entropic stability of the consensus process.

Figures