1. ACPS
  2. All Volumes and Issues
  3. Volume 9, Number 2, 2024
  4. Serverless Ai Agents in the Cloud

Serverless Ai Agents in the Cloud

ACPS.
2024;
Volume 9, Number 2
: pp. 115 - 120
Authors:
  1. Oleh Chaplia
  2. Halyna Klym
  3. Edgars Elsts
1
Lviv Polytechnic National University
2
Lviv Politechnic National University
3
Institute of Solid State Physics, University of Latvia

Integrating AI agents within serverless architectures offers a modern approach to deploying and executing intelligent applications. Leveraging the advantages of serverless computing, AI agents can dynamically respond to varying workloads without the overhead of managing the underlying infrastructure. This article explores the concept of scalable serverless AI agents in the cloud, detailing their architecture, benefits and drawbacks, challenges, and real-world applications. The paper provides advantages and drawbacks of the serverless approach. Then a proof-of-concept has been developed, deployed and tested. The AI agent code was deployed to Azure Functions, Google Cloud Functions, and AWS Lambda and tested. As a result, improvements to availability, resilience, reliability, and scalability qualities have been proposed to mitigate the previously defined drawbacks.

cloud computing
cyber-physical systems
AI agents
microservices
serverless
  1. Serôdio, C., Mestre, P., Cabral, J., Gomes, M., & Branco, F. (2024).  Software and Architecture Orchestration for Process Control in Industry 4.0 Enabled by Cyber- Physical Systems Technologies. Applied Sciences, 14(5),Article 5. DOI: 10.3390/app14052160
  2. Guldner,  A.,  et  al.  (2023).  A framework  for  AI-based self-adaptive   cyber-physical    process   systems.    it    - Information Technology, 65(3), 113–128. DOI: 10.1515/itit-2023-0001
  3. Goel, S. (2024). Towards building Autonomous   AI Agents and Robots for Open World Environments. New Zealand.
  4. Chaplia, O., Klym, H., & Popov, A. I. (2024). An Approach to Improving Availability of Microservices for Cyber-Physical Systems. ACPS, 9(1), 16–23. DOI: 10.23939/acps2024.01.016
  5. Raith, P., Nastic, S.,  & Dustdar,  S.  (2023).  Serverless Edge Computing—Where We Are and What Lies Ahead. IEEE Internet Computing, 27(3), 50–64. DOI: 10.1109/MIC.2023.3260939
  6. Park,  J.  S.,  O’Brien,  J.  C.,  Cai,  C.  J.,  Morris,  M.  R., Liang, P., & Bernstein, M. S. (2023). Generative Agents: Interactive Simulacra of Human Behavior. arXiv. DOI: 10.48550/arXiv.2304.03442
  7. Wu, Q., et al. (2023). AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv. DOI: 10.48550/arXiv.2308.08155
  8. Kaur, N., & Mittal, A. (2021). Fog Computing Serverless Architecture for Real-Time Unpredictable Traffic. IOP Conference Series: Materials Science and Engineering, 1022(1), 012026. DOI: 10.1088/1757-899X/1022/1/012026
  9. Aslanpour, M. S., Toosi, A. N., Cheema, M. A., Chhetri, M. B., & Salehi, M. A. (2024). Load balancing for heterogeneous serverless edge computing: A performance-driven and empirical approach. Future Generation Computer Systems, 154, 266–280. DOI: 10.1016/j.future.2024.01.020
  10. Liu, Z., Zhang, Y., Li, P., Liu, Y., & Yang, D. (2023). Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization. arXiv. DOI: 10.48550/arXiv.2310.02170
  11. Al-Doghman, F., Moustafa, N., Khalil, I., Sohrabi, N., Tari, Z., & Zomaya, A. Y. (2023). AI-Enabled Secure Microservices in Edge Computing: Opportunities and Challenges. IEEE Transactions on Services Computing, 16(2), 1485–1504. DOI: 10.1109/TSC.2022.3155447
  12. Kallas, K., Zhang, H., Alur, R., Angel, S., & Liu, V. (2023). Executing Microservice Applications  on Serverless, Correctly. Proceedings of the ACM on Programming Languages, 7. DOI: 10.1145/3571206
  13. Merlino, G., Tricomi, G., D’Agati, L., Benomar, Z., Longo, F., & Puliafito, A. (2024). FaaS for IoT: Evolving Serverless towards Deviceless in I/Oclouds. Future Generation Computer Systems, 154, 189–205. DOI: 10.1016/j.future.2023.12.029
  14. Jagutis, M., Russell, S., & Collier, R. (2023). Flexible simulation of traffic with microservices, agents & REST. International Journal of Parallel, Emergent and Distributed                       Systems,               38(6).      DOI: 10.1080/17445760.2023.2242183
  15. Crawford, N., et al.  (2024).  BMW  Agents—A Framework for Task Automation Through Multi-Agent Collaboration. DOI: 10.48550/ARXIV.2406.20041
  16. Liu, Z., Yu, H., Fan, G., & Chen, L. (2022). Reliability modelling and optimization for microservice-based cloud application using multi-agent system. IET Communications, 16(10). DOI: 10.1049/cmu2.12371