AI-Driven Serverless Framework for Automated Software Development LLM-Generated Hybrid Fuzzy Integration of WPM, TOPSIS, and Particle Swarm Optimization in DevOps Pipelines
DOI:
https://doi.org/10.15662/IJEETR.2021.0305003Keywords:
AI-Driven Software Development, Serverless Computing, Large Language Models (LLMs), Weighted Product Method (WPM), TOPSIS, Particle Swarm Optimization (PSO), Hybrid Fuzzy Framework, DevOps Automation, Cloud-Native Architecture, Intelligent CI/CD Pipelines, Software OptimizationAbstract
The rapid evolution of software engineering toward automation and intelligence has accelerated the need for serverless, AI-driven frameworks that streamline development workflows and optimize system performance. This research introduces an AI-Driven Serverless Framework that leverages Large Language Models (LLMs) for code generation and decision support within DevOps pipelines. The framework integrates the Weighted Product Method (WPM) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) within a hybrid fuzzy environment, enhanced through Particle Swarm Optimization (PSO) to enable adaptive learning and continuous improvement in software delivery processes.
The proposed architecture enables real-time automation of software development stages—from requirements prioritization to deployment—by combining fuzzy logic reasoning and swarm intelligence to manage uncertainty and optimize multi-criteria decision-making. LLM-generated components support intelligent automation, while PSO algorithms optimize parameter selection for performance, scalability, and cost-efficiency in serverless cloud environments.
Experimental evaluation in simulated DevOps pipelines demonstrates substantial improvements in code generation accuracy, build automation, and deployment latency reduction compared to traditional CI/CD approaches. The study contributes a scalable and intelligent model for next-generation cloud-native DevOps, uniting AI, optimization algorithms, and serverless architectures for self-adaptive, automated software development.
References
1. Buyya, R., Yeo, C. S., Venugopal, S., Broberg, J., & Brandic, I. (2009). Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utility. Future Generation Computer Systems, 25(6), 599–616. https://doi.org/10.1016/j.future.2008.12.001
2. Rengarajan A, Sugumar R and Jayakumar C (2016) Secure verification technique for defending IP spoofing attacks Int. Arab J. Inf. Technol., 13 302-309
3. Anand, L., & Neelanarayanan, V. (2019). Liver disease classification using deep learning algorithm. BEIESP, 8(12), 5105–5111.
4. Sudhan, S. K. H. H., & Kumar, S. S. (2016). Gallant Use of Cloud by a Novel Framework of Encrypted Biometric Authentication and Multi Level Data Protection. Indian Journal of Science and Technology, 9, 44.
5. Anugula Sethupathy, Utham Kumar. (2018). Self-Healing Systems and Telemetry-Driven Automation in DevOps Pipelines. International Journal of Novel Research and Development. 3. 148-155. 10.56975/ijnrd.v3i7.309065.
6. Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2020). Artificial intelligence using TOPSIS method. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 3(6), 4305-4311.
7. Chen, S. M., & Cheng, S. H. (2010). Fuzzy multiple attributes group decision-making based on ranking interval type-2 fuzzy sets of linguistic variables. Information Sciences, 180(4), 724–745. https://doi.org/10.1016/j.ins.2009.10.012
8. Dean, J., & Ghemawat, S. (2008). MapReduce: Simplified data processing on large clusters. Communications of the ACM, 51(1), 107–113. https://doi.org/10.1145/1327452.1327492
9. Eberhart, R. C., & Kennedy, J. (1995). A new optimizer using particle swarm theory. In Proceedings of the Sixth International Symposium on Micro Machine and Human Science (pp. 39–43). IEEE.
10. Fox, A., & Patterson, D. A. (2009). Engineering long-lasting software: An agile approach using cloud computing. University of California, Berkeley.
11. Hwang, C. L., & Yoon, K. (1981). Multiple attribute decision making: Methods and applications. Springer.
12. Lin, C. T., & Lee, C. S. G. (1996). Neural fuzzy systems: A neuro-fuzzy synergism to intelligent systems. Prentice Hall.
13. Mishra, A., & Tripathy, A. R. (2016). A comparative study of multi-criteria decision-making methods for software requirement prioritization. International Journal of Computer Applications, 144(9), 1–6.
14. Rajaraman, A., & Ullman, J. D. (2011). Mining of massive datasets. Cambridge University Press.
15. Chiranjeevi, K. G., Latha, R., & Kumar, S. S. (2016). Enlarge Storing Concept in an Efficient Handoff Allocation during Travel by Time Based Algorithm. Indian Journal of Science and Technology, 9, 40.
16. Amuda, K. K., Kumbum, P. K., Adari, V. K., Chunduru, V. K., & Gonepally, S. (2020). Applying design methodology to software development using WPM method. Journal ofComputer Science Applications and Information Technology, 5(1), 1-8.
17. Anand, L., & Neelanarayanan, V. (2019). Feature Selection for Liver Disease using Particle Swarm Optimization Algorithm. International Journal of Recent Technology and Engineering (IJRTE), 8(3), 6434-6439.
18. Cherukuri, B. R. (2019). Serverless revolution: Redefining application scalability and cost efficiency. https://d1wqtxts1xzle7.cloudfront.net/121196636/WJARR_2019_0093-libre.pdf?1738736725=&response-content-disposition=inline%3B+filename%3DServerless_revolution_Redefining_applica.pdf&Expires=1762272213&Signature=XCCyVfo54ImYDZxM5lPQQ2nkTOzAKecpW86qlfne0lLpMlvC6WaoSiOBsyS3SyoPj8nAPWdSqFOeiZqIwKsTriCNb6de-mfqXndHQwXRcrA7aVAoQ2txD12Ph36pxjJRJehcVlRK0o878Lh-1nc2mmtJEssNhLC8sVziFBjWuaUiW2Gr0YEZ8ZgIOfHv7gPNREi4JzDmIxpr8eTxb08LoN8KlFSLgouF4SpPoejQYmYOW7JRNijqsMnyhfjSsDv8fdrjSbkb2w-GD7tWhZHVT-1Vu03XPRsjVN-fbMtINmy9tAbgjElqevLlU36g54NdZ8VG4H2pouSeuv55VROnlA__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA
19. Muthirevula, G. R., Kotapati, V. B. R., & Ponnoju, S. C. (2020). Contract Insightor: LLM-Generated Legal Briefs with Clause-Level Risk Scoring. European Journal of Quantum Computing and Intelligent Agents, 4, 1-31.
20. M.Sabin Begum, R.Sugumar, "Conditional Entropy with Swarm Optimization Approach for Privacy Preservation of Datasets in Cloud", Indian Journal of Science and Technology, Vol.9, Issue 28, July 2016
