Multi-batch Scheduling for Improving Performance of Hyperledger Fabric based IoT Applications

Blockchain technology has been regarded as a paradigm that enables enterprises to deploy decentralized Internet of things (IoT) applications, which require security, mutual truthfulness, privacy, and data reliability. However, the adoption of blockchain technology on IoT applications has been limited due to the lack of blockchain's capability to process a huge amount of transaction requests from IoT devices. In this paper, we propose a new transaction processing mechanism, called Accelerator, which improves the performance of blockchain-based IoT applications in terms of transaction throughput and latency. Two key design ideas of Accelerator lie in: (i) independent modular structure that can be implemented without changing the incumbent blockchain network and (ii) adaptive multi-batch scheduling engine for robust performance. We first provide a mathematical analysis that is used to choose the parameters of Accelerator to maximize the performance. Moreover, we implement Accelerator on a decentralized blockchain network using Hyperledger Fabric and perform the extensive test using Hyperledger Caliper. We show that Accelerator achieves 8x transaction throughput improvement without sacrificing latency.