@Article{cmes.2025.074378,
AUTHOR = {Yingying Zhou, Wenlong Shen, Tianzhe Jiao, Chaopeng Guo, Jie Song},
TITLE = {AI-Enabled Perspective for Scaling Consortium Blockchain},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {145},
YEAR = {2025},
NUMBER = {3},
PAGES = {3087--3131},
URL = {http://www.techscience.com/CMES/v145n3/65010},
ISSN = {1526-1506},
ABSTRACT = {As consortium blockchains scale and complexity grow, scalability presents a critical bottleneck hindering broader adoption. This paper meticulously extracted 150 primary references from IEEE Xplore, Web of Science, Google Scholar, and other reputable databases and websites, providing a comprehensive and structured overview of consortium blockchain scalability research. We propose a scalability framework that combines a four-layer architectural model with a four-dimensional cost model to analyze scalability trade-offs. Applying this framework, we conduct a comprehensive review of scaling approaches and reveal the inherent costs they introduce. Furthermore, we map the artificial intelligence (AI)-enabled methods to the scaling approaches and analyze their effectiveness in enhancing scalability and mitigating these inherent costs. Based on this analysis, we identify the root causes of the remaining costs unresolved by AI and the new trade-offs introduced by AI integration, and propose promising research opportunities for AI-enabled consortium blockchain scalability, guiding future work toward more adaptive, intelligent, and cost-efficient consortium blockchain systems.},
DOI = {10.32604/cmes.2025.074378}
}