Predictive Intelligent Routing for Multi-Cloud Enterprise Workloads
DOI:
https://doi.org/0.63397/ISCSITR-IJCSE_2026_07_01_003Keywords:
Multi-cloud, intelligent routing, enterprise architecture, predictive modeling, traffic steering, FinOps, service reliabilityAbstract
Enterprises increasingly deploy business-critical workloads across multiple cloud providers to improve resilience, reduce vendor lock-in, and optimize cost-performance outcomes. Yet, most multi-cloud traffic steering remains static or reactive, relying on fixed weights and health-check failover that respond after customers experience degradation. This manuscript presents a predictive intelligent routing framework that combines telemetry-driven forecasting, constraint-first governance enforcement, multi-objective decisioning, and operational safety controls to steer traffic proactively. A controlled 30-day simulation compares baseline round-robin routing to predictive routing across p95 latency, error rate, and cost per 10,000 requests. Results show consistent improvements in tail-latency stability, reduced error exposure, and lower unit cost, supported by 95% confidence intervals. The framework targets general enterprise workloads and can be implemented using common observability, gateway, and FinOps tooling [6] [8].
References
J. Dean and L. A. Barroso, “The Tail at Scale,” Communications of the ACM, vol. 56, no. 2, pp. 74–80, 2013. doi: 10.1145/2408776.2408794. Available: https://www.barroso.org/publications/TheTailAtScale.pdf
P. Mell and T. Grance, “The NIST Definition of Cloud Computing,” NIST Special Publication 800-145, 2011. Available: https://nvlpubs.nist.gov/nistpubs/legacy/sp/nistspecialpublication800-145.pdf
B. Beyer, C. Jones, J. Petoff, and N. R. Murphy, Site Reliability Engineering: How Google Runs Production Systems. O’Reilly, 2016. Available: https://sre.google/sre-book/table-of-contents/
C. Labovitz, A. Ahuja, A. Bose, and F. Jahanian, “Delayed Internet Routing Convergence,” IEEE/ACM Transactions on Networking, vol. 9, no. 3, pp. 293–306, 2001. doi: 10.1109/90.929852. Available: https://pages.cs.wisc.edu/~suman/courses/740/papers/labovitz01ton.pdf
Z. Li et al., “Machine Learning for Networking: Workflow, Advances and Opportunities,” IEEE Communications Surveys & Tutorials, 2020. doi: 10.1109/COMST.2019.2958792. Available: https://ieeexplore.ieee.org/document/8965215
FinOps Foundation, “FinOps Framework,” 2023. Available: https://www.finops.org/framework/
J. Gama, I. Žliobaitė, A. Bifet, M. Pechenizkiy, and A. Bouchachia, “A Survey on Concept Drift Adaptation,” ACM Computing Surveys, vol. 46, no. 4, 2014. doi: 10.1145/2523813. Available: https://doi.org/10.1145/2523813
R. L. Keeney and H. Raiffa, Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Cambridge University Press, 1993 (orig. 1976). Available: https://scispace.com/pdf/decisions-with-multiple-objectives-preferences-and-value-18632c08oi.pdf
P. Mockapetris, “Domain Names—Implementation and Specification,” IETF RFC 1035, 1987. Available: https://datatracker.ietf.org/doc/html/rfc1035
J. H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001. doi: 10.1214/aos/1013203451. Available: https://projecteuclid.org/journals/annals-of-statistics/volume-29/issue-5/Greedy-function-approximation-A-gradient-boosting-machine/10.1214/aos/1013203451.full
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Sankalp Shrivastava (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
