PerfTune360: Self-Optimizing AI Framework for Cloud-Native Microservices
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V5I3P123Keywords:
AI-Based Optimization, Microservices Performance Tuning, Autonomous Profiling, Neural Optimization, Cloud-Native Systems, Adaptive Caching, Workload Prediction, Continuous FeedbackAbstract
PerfTune360 is a self-optimizing platform powered by these AI that uses continuous learning, adaptive profiling as well as autonomous tuning to make these cloud-native microservices work better. In modern distributed systems, microservices have many problems including configuration drift, different workloads, unpredictable traffic patterns & latency limits that make the system very less stable & the user experience worse. PerfTune360 tackles these problems by adding an artificial neural optimization engine that constantly checks runtime metrics, finds these performance problems, and changes system settings in actual time. The design uses positive reinforcement learning along with predictive modeling to forecast how the workload will behave, making it less difficult to scale up & down while controlling expenditures effectively. PerfTune360 adds lightweight agents to service these meshes, which means there is little extra work to do while still giving you a lot of information about dependencies along with their communication paths. The system has a closed to the outside world feedback mechanism that lets it fix itself. This makes sure that the speed of response is always at its best and the reaction times are continuously consistent, regardless of how the amount of work changes. Tests indicate that PerfTune360 substantially decreases the average reaction time, boosts worker efficiency by making more effective use of resources, and ensures excellent performance in a variety of setting up circumstances. Its modular as well as platform-agnostic structure also lets it interact with popular cloud orchestration applications like Kubernetes, which makes it easy to add existing pipelines rather than halting them from functioning. PerfTune360 marks a shift to self-managing cloud performance, turning traditional manual tuning into an intelligent, self-adapting process that ensures continued efficiency, resilience & scalability for microservice ecosystems of the future generation.
References
[1] Alonso, Juncal, et al. "Optimization and prediction techniques for self-healing and self-learning applications in a trustworthy cloud continuum." Information 12.8 (2021): 308.
[2] Zeb, Shah, et al. "Toward AI-enabled NextG networks with edge intelligence-assisted microservice orchestration." IEEE Wireless Communications 30.3 (2023): 148-156.
[3] Lawal, Sani. "Cloud-Native Machine Learning Models for Intelligent Workload Orchestration in ERP Systems." Available at SSRN 5510058 (2023).
[4] Parakala, Adityamallikarjunkumar. "RPA+ AI→ Intelligent Process Automation (IPA)." International Journal of AI, BigData, Computational and Management Studies 4.3 (2023): 112-123.
[5] Ranjan, Rahul, Navya Vemuri, and Kamala Venigandla. "Autonomous DevOps: integrating RPA, AI, and ML for self-optimizing development pipelines." Asian Journal of Multidisciplinary Research & Review 3.2 (2022): 214-231.
[6] Thota, Ravi Chandra. "Optimizing Kubernetes workloads with AI-driven performance tuning in AWS EKS." International Journal of Science and Research Archive 9.2 (2023): 1-11.
[7] Kulkarni, Vinita Harish. "Evolving Web Frameworks and Intelligent Query Processing: Integrating Deep Learning and WPM-Based Decision Support in Cloud-Native Software Development." International Journal of Computer Technology and Electronics Communication 4.4 (2021): 3813-3816.
[8] Perumallaplli, Ravikumar. "AI-Driven Resource Allocation in Containerized Microservices Architecture." Available at SSRN 5228709 (2013).
[9] Chileshe, Lombe. "Intelligent Resource Orchestration Using AI-Driven Predictive Algorithms for Scalable Cloud Systems." American International Journal of Computer Science and Technology 5.6 (2023): 13-24.
[10] Guntupalli, Bhavitha. "Clean Code in the Real World: Principles I Actually Use." International Journal of Emerging Trends in Computer Science and Information Technology 1.1 (2020): 66-74.
[11] Pimentel, Eliaquim, et al. "Self-adaptive microservice-based systems-landscape and research opportunities." 2021 International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). IEEE, 2021.
[12] Vaidhyanathan, Karthik. "Data-driven self-adaptive architecting using machine learning." (2021).
[13] Al-Hinai, Aisha. "Real-Time Resource Orchestration for AI-Enhanced Java Applications in Kubernetes." (2022).
[14] Parakala, Adityamallikarjunkumar, and Srinivas Achanta. "Transforming Government Workflows with AI-Driven RPA." International Journal of AI, BigData, Computational and Management Studies 3.4 (2022): 82-92.
[15] Manso Fernández Argüelles, Carlos Agustín. "Cloud-native orchestration and automation for disaggregated networks." (2023).
[16] Hall, Thomas, Christopher Harris, and Zafar Iqbal. "Unified Intelligence: Integrating AI Infrastructure and MLOps for Scalable Real-Time Analytics in Cloud-Based Systems." (2021).
[17] Guntupalli, Bhavitha. "The Evolution of ETL: From Informatica to Modern Cloud Tools." International Journal of AI, BigData, Computational and Management Studies 2.2 (2021): 66-75.
[18] Lawal, Garba Sani. "Generative AI Models for Automating Enterprise Resource Planning in Cloud Ecosystems." (2023).
[19] Kelvin, Jerry. "Frameworks for Seamless Data Flow between On-Premises Systems and Cloud Platforms." (2022).
[20] Krishna Chaitanaya Chittoor, “Building AI-Powered Financial Risk Analytics Platforms Using Distributed Big Data Infrastructure”, JOURNAL OF EMERGING TRENDS AND NOVEL RESEARCH, 1(6), PP-a26-a33, 2023, https://rjpn.org/jetnr/papers/JETNR2306003.pdf.
