Skip to content
Open access

Towards High-Throughput and Low-Latency Heterogeneous Blockchains via RL-Driven Network Sharding

Dec 2026 · IEEE transactions on computers · Vol 75, pp. 4363-4374 · 0 citations · 18 references

TL;DR

PabShard is proposed, an intelligent sharding framework for heterogeneous blockchain systems that leverages reinforcement learning to adaptively regulate shard operations according to network states and workload conditions and develops an adaptive block generation rate control mechanism that dynamically regulates the processing capability of individual shards.

Abstract

Sharded blockchains enable scalable distributed ledgers by partitioning transaction workloads into multiple parallel processing shards. However, existing sharding protocols for heterogeneous blockchain environments mainly focus on mitigating performance degradation caused by uneven node bandwidth, while overlooking dynamic network variations, such as bandwidth fluctuations, unstable packet delivery, and transaction queue accumulation. These factors result in inefficient shard utilization and significant performance disparities among shards. To address these issues, we propose PabShard, an intelligent sharding framework for heterogeneous blockchain systems. PabShard leverages reinforcement learning to adaptively regulate shard operations according to network states and workload conditions. Specifically, we address two key challenges. First, to achieve effective shard organization under heterogeneous network conditions, we design a PPO-driven shard control mechanism that dynamically adjusts shard configurations based on observed system states. Meanwhile, an asymmetric bandwidth-adaptive asynchronous Merkle tree (BA-AMT) is introduced to improve transaction verification efficiency by exploiting available bandwidth resources. Second, to alleviate transaction congestion caused by heterogeneous shard processing capacities, we develop an adaptive block generation rate control mechanism that dynamically regulates the processing capability of individual shards. We implement PabShard on a Huawei Cloud cluster with heterogeneous bandwidth configurations ranging from 20 to 60 Mbit/s, where each physical host supports numerous virtualized blockchain nodes. Extensive experiments against representative sharding protocols, including Monoxide, GearBox, and Manifoldchain, demonstrate the effectiveness of PabShard. Under a transaction arrival rate of 3000 TPS with eight shards, PabShard achieves a 12.3% throughput improvement and reduces confirmation latency by 14.8% compared with the best-performing baseline.

Read PDF

Similar papers

#graph neural networks Open access Dec 2026

GPBchain: A GNN-Assisted Framework for Optimizing Sharding Blockchain Reconfiguration

An unsupervised sharding blockchain framework based on Graph Neural Network (GNN) called GPBchain is proposed, which achieves explicit joint optimization of CST reduction and inter-shard workload balancing, thereby enhancing the overall throughput of sharding blockchain systems.

Kai-Min Zhang, Xing-Wei Wang, Bo Yi et al. · 0 citations
Open access Sep 2026

Benchmarking Consensus Protocols for High-Performance Permissioned Blockchain Systems

This study presents a comparative evaluation of four Hyperledger Besu consensus algorithms, namely Ethash, Clique, QBFT, and IBFT 2.0, executed under identical hardware, network topology, and genesis configurations to quantify latency, throughput, and system overhead.

Muhammet Furkan Ozara, A. Akbulut, Mustafa Kara et al. · 0 citations
Book Open access Nov 2026

Poros: Secure and Highly Parallel Sharding Blockchain with Optimized Cross-Shard Transaction Processing

Sharding blockchain is a promising approach to improving blockchain scalability by partitioning the network into multiple parallel shards. However, most existing sharding blockchains adopt Byzantine fault tolerance (BFT) as the black-box intra-shard building block, incurring redundant steps. Moreover, a single leader i...

Zhuo-Cheng Pan, Jian-Wei Liu, An-Di Liu et al. · 0 citations
Book Open access Nov 2026

Areopagus: Asynchronous Sharding Blockchain Tolerating Corrupted Shards with Optimized Overhead

Sharding technology alleviates the scalability bottleneck of traditional blockchains by partitioning the network into multiple shards, thereby improving throughput through parallel consensus execution. However, limited fault tolerance within individual shards degrades overall system fault tolerance and necessitates lar...

Yi-Zhong Liu, An-Di Liu, Yuxuan Hu et al. · 0 citations
Open access Sep 2026

Anatomy of NEAR Sharded Blockchain: A Longitudinal Workload Characterization

Blockchain sharding promises higher throughput, but production evidence on how real workloads interact with shard topology remains limited. We present a longitudinal characterization of the NEAR Protocol from 2020 to 2025 using historical on-chain data, analyzing both ecosystem structure and shard-level behavior across...

Md. Ahsan Habib, Lu Peng · 0 citations
Preprint Oct 2026

QuarkShard: Decomposing Cross-Shard Requests into Single-Input Transactions

Sharding blockchains enhance scalability by distributing the workload across multiple shards. Within sharding blockchains, securely and efficiently processing cross-shard user requests remains a pivotal challenge. Traditional sharding blockchain protocols execute cross-shard requests under a processing paradigm that tr...

Chang-Yu Duan, Zhi-Xuan Fang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.