Hybrid Local-Cloud Storage Optimization for Blockchain-Based IoT Systems

Abstract

The ubiquitous deployment of Internet of Things (IoT) in smart building ecosystems generates massive volumes of multi-dimensional data, rendering secure storage and efficient retrieval paramount challenges. Although blockchain technology ensures data integrity and traceability, applying it to resource-constrained IoT networks exposes a fundamental “storage trilemma” among cost, latency, and scalability. Conventional approaches, relying on either static local retention or full cloud offloading, fail to reconcile these conflicting objectives. In this paper, we propose a Heat-Driven Hybrid Storage (HDHS) architecture that addresses limitations of existing hybrid storage systems-which rely on static parameters and reactive policiesthrough three key innovations: predictive heat modeling, dynamic redundancy adaptation, and multi-objective optimization. Specifically, HDHS incorporates a time-decay model with cost-aware uncertainty estimation to forecast block access “heat” under noisy conditions. Based on these predictions, the system dynamically tunes redundancy rates and utilizes rateless fountain codes to optimize the trade-off between storage footprint and data durability. Furthermore, we design a cloud-window optimizer that addresses a multi-objective trade-off to determine an effective boundary for local-cloud data migration. Extensive experiments on real-world datasets demonstrate that our scheme achieves a 40.7% reduction in storage costs, maintains sub-3ms query latency for 74.7% of queries, and ensures 99% + data reliability in permissioned blockchain environments.