This paper presents a proactive forecasting model for auto-scaling serverless functions. The framework predicts incoming load spikes using historical access patterns, ensuring elasticity and cost optimization across hybrid cloud environments.

Noah Elliott Chambers, Tan Mei Qing, Ishan Dev Patel, Scarlett June Holloway, Pedro Emilio Vargas

This research proposes a semantic model for automated workflow generation in scientific clouds. Ontologies guide task decomposition and service selection, enabling researchers to compose complex experiments with minimal configuration and enhanced reproducibility.

Caleb Maxwell Hart, Zhang Rui Wei, Nila Karthika Shenoy, Grace Arabella Foster, Diego Manuel Ortega

We introduce an intelligent tiering system for data lake storage in multi-zone cloud infrastructures. The algorithm dynamically classifies data based on access frequency, reducing storage costs while maintaining performance and availability standards.

Elijah Oscar Dean, Liu Xiu Hong, Rajeev Govind Shenbagaraman, Alice Flora Newton, Andres Jorge Castillo

This paper presents a quantum entropy-based profiling model for inspecting encrypted traffic. Deployed at the edge, it uses distributed analytics to identify malicious patterns in real-time without decrypting sensitive data streams.

Mason Julian Barrett, Wu Lei Xian, Bhavna Satyadev Murugan, Zoe Margaret Chadwick, Enrico Rafael Dominguez

This paper proposes a resilient microservices framework integrating graph-based fault tolerance and distributed tracing. The architecture reduces recovery time and enhances service continuity under fault conditions in complex cloud-native systems.

Giovanni Marco Ruiz, Zhang Yi Chen, Abhay Vignesh Anand, Penelope Grace Stafford, Joaquin Matias Herrera

This study presents a container orchestration model integrating edge-aware federated policies. It enhances deployment efficiency using cross-layer resource metrics and minimizes latency in edge-cloud collaboration environments.

Mitchell Ezra Langston, Lin Hao Cheng, Kavitha Sunder Narayan, Madeleine Elise Porter, Tomasz Wojciech Brzezinski

This paper explores federated learning frameworks for industrial IoT applications using cloud-supported pipelines. It introduces workflow-aware updates to optimize convergence, privacy, and communication cost in multi-cloud IoT networks.

Bryson Andrew Fielding, Zhu Ling Wei, Nishka Manoj Kumar, Adelaide Faith Jennings, Leonardo Bruno Costa

We propose a runtime optimization model for Function-as-a-Service platforms using genetic algorithms. It reduces energy consumption by shaping resource usage dynamically across varying workloads in green cloud architectures.

Calvin Owen Blackwell, Xu Mei Jing, Haritha Muralidhar Naidu, Fiona Emily Rutherford, Sergio Daniel Guzman