Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204054,
        author = {Vishnu Prabhakar and Mr. Bhupesh},
        title = {Intelligent Autonomous Systems for Climate Forecasting and Cloud-Native Performance Optimization: A Review of Generative Agentic AI and Kubernetes Autoscaling Frameworks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {621-628},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204054},
        abstract = {Latest advances in Artificial Intelligence, cloud-local computing, and self-sustaining machine layout have significantly converted present day computational infrastructures. two predominant technological domains have mainly won interest in current years: intelligent disaster forecasting the use of Generative Agentic artificial Intelligence (AI), and adaptive cloud-native autoscaling the use of Kubernetes event-pushed Autoscaling (KEDA). each domain names address tremendously dynamic environments in which speedy choice-making, actual-time adaptability, and operational resilience are crucial.
This evaluates paper significantly analyzes and synthesizes the findings of modern-day studies guidelines. the primary makes a speciality of self-reliant climate forecasting and disaster early caution structures powered by Generative Agentic AI, where wise retailers combine environmental sensing, predictive analytics, reasoning, and adaptive reaction coordination. the second investigates the performance behavior of Kubernetes-primarily based autoscaling architectures the usage of KEDA and Prometheus-pushed custom metrics for microservice scalability optimization.
The assessment highlights how self-sufficient selection intelligence improves prediction accuracy, warning lead time, scalability, and emergency responsiveness in climate structures, at the same time as wise autoscaling mechanisms improve carrier reliability, latency control, and workload balancing in cloud-native infrastructures. Comparative evaluation demonstrates that both systems depend heavily on adaptive comments loops, actual-time facts processing, and intelligent orchestration to gain resilient operation below uncertain and hastily changing situations.
Furthermore, the paper identifies shared research demanding situations which includes parameter sensitivity, computational overhead, explainability, interoperability, safety risks, and scalability limitations. eventually, future studies opportunities regarding predictive orchestration, self-mastering intelligent agents, virtual twin integration, facet intelligence, and independent optimization frameworks are discussed.},
        keywords = {Generative Agentic AI, weather Forecasting, catastrophe Early caution, Kubernetes, KEDA, Prometheus, Autoscaling, Cloud-local structures, self-reliant choice Intelligence, overall performance Optimization.},
        month = {June},
        }