Segmented Storage Based on Parallel Execution for IoT Blockchains

Abstract

Internet of Things (IoT) blockchains are characterized by the difference in storage resources, computing power, and high dynamic of node topologies. In view of the demand for short-time and high-concurrency execution of events in IoT blockchain transaction scenarios, we propose a lightweight segmented storage based on parallel execution for IoT blockchains. This method breaks through the technical difficulties of 2-D ledger design for event parallelism, de-blocking lightweight synchronization of cross-domain data, and global consistency maintenance of asynchronous ledger, and achieves parallel execution of events and lightweight segmented storage of resource-constrained nodes. First, the event cumulative verification and differential generation algorithm is proposed to reduce the redundancy propagation in event distribution and voting. Second, the effective concurrent consensus confirmation mechanism of events is proposed to implement the distributed batch confirmation of valid events, which guarantees the low-latency confirmation of events. Furthermore, the data lightweight segmented storage mechanism is proposed to implement the data lightweight segmented storage of the resource-constrained nodes combined with the design of the LBPS Chain ledger structure. Simulation results show that the LBPS Chain outperforms LDV, Layerchain, and GpDB by 85%, 88%, and 52% in terms of storage cost. Compared to the Hashgraph, our method effectively increases the throughput by 89% and has scalability in reducing the storage cost and increasing throughput.