Asosiy kontentga oʻtish
proceeding

Autonomous Cloud-Based Framework for Real-Time Global Business Operations and Seamless Scalability in Dynamic Markets

Murodjon A. YuldoshevTuran International UniversityMohammed Rijwan P.St. Joseph's Institute of TechnologyV. MathankumarKarpagam Academy of Higher EducationPrashant Bhavarlal ChordiyaJamal K. AbbasAl-Nisour UniversityJainish RoyKalinga University
2026en
Ochiq kirishOltin

Litsenziya: cc-by

ABI

Annotatsiya

Real-time global business operations in cloud environments require autonomous decision-making across auto-scaling, cost optimization, fault tolerance, and multi-region load balancing at millisecond response speeds that human operators cannot match. This paper proposes an Autonomous Cloud-Based Framework (ACF) combining a reinforcement-learning (RL) auto-scaling engine, a constraint-optimization cost controller, a self-healing fault-detection module, and a global load-balancing AI, deployed across 24 enterprises (manufacturing$\mathrm{n}=9$, retail$\mathrm{n}=8$, services$\mathrm{n}=7$) evaluating 3,600 cloud-operations decisions (2,700 training/900 test, 75/25 chronological split) backed by 28,800,000 cloud transaction records over a 12-month evaluation period. The ACF achieves operations accuracy of 0.884 against expert-validated cloud engineering benchmarks, outperforming ML-only automation (0.764; +15.7%[(0.884-0.764)/0.764]), rule-based automation (0.684; +29.2%), and manual cloud operations (0.524; +68.7% [(0.884-0.524)/0.524]). Deployment outcomes: +384.4% peak throughput handling capacity, −48.4% operational cost, −78.4% unplanned downtime, −42.4% global request latency. Sub-dimension performance: Auto-Scaling$(\mathrm{r}=0.924)$, Cost Optimization (0.884), Fault Tolerance (0.844), and Global Load Balancing (0.784). Network partition events degrade accuracy to 0.784 (−11.3%) and cold-region latency spikes to 0.724 (−18.1%), each with a deployed autonomous mitigation.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar