Mukhit Zhanuzakov
Al-Farabi Kazakh National University

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Checkpointing for scalable crash-tolerance in the context of enterprise digitalization systems Gulnar Tultayevna Balakayeva; Paul Ezhilchelvan; Mukhit Zhanuzakov
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.12040

Abstract

This paper presents a scalable fault-tolerant framework for enterprise digitalization systems using optimized checkpointing and rollback-recovery mechanisms. The study introduces a novel mathematical model to determine optimal checkpointing intervals, minimizing performance overhead while ensuring rapid recovery from failures. A dual-redundant storage strategy (local disks and remote databases) enhances resilience against both application crashes and server failures. Experimental evaluations demonstrate the system's effectiveness: in crash scenarios, recovery times (RT) improved by 47% compared to non-checkpointed systems, while adding only 2.5% overhead during normal operations. The framework maintains linear scalability through backup server integration, supporting enterprise growth without compromising reliability. Performance metrics reveal that at an optimal checkpointing interval of 0.5 seconds, the system achieves 92% process continuity during frequent failures, with a breakdown rate of xi at 0.1. These results provide empirical validation of the design's ability to balance fault tolerance with operational efficiency. The research contributes practical insights for implementing resilient digital infrastructures, addressing critical challenges in enterprise system reliability and continuous service availability. The novelty of this work lies in combining an analytically derived checkpointing model with a practical and scalable system design. This approach provides a clear and efficient balance between fault tolerance and performance, offering a practical solution for improving reliability and continuous service availability in enterprise systems.