AI-driven reinforced optimal cloud resource allocation (ROCRA) for high-speed satellite imagery data processing

• Published in: Earth science informatics Vol. 17; no. 2; pp. 1609 - 1624
• Main Authors: Inkollu, Uma Maheswara Rao, Sastry, J. K. R.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2024; Springer Nature B.V
• Subjects: Artificial intelligence; Cloud computing; Data processing; Earth and Environmental Science; Earth Sciences; Earth System Sciences; Information Systems Applications (incl.Internet); Machine learning; Ontology; Resource allocation; Satellite data; Satellite imagery; Satellites; Simulation and Modeling; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Cloud Computing; Deep Neural Networks; Quality of Service; Testing as a Service; Reinforced Optimal Resource Allocation
• ISSN: 1865-0473; 1865-0481
• DOI: 10.1007/s12145-024-01242-5

The emergence of cloud computing has brought attention to the broad issue of resource allocation across domains. A thorough and adaptable solution to this complex issue is AI-driven Reinforced Optimal Cloud Resource Allocation, or ROCRA. By expertly fusing artificial intelligence with reinforcement learning, ROCRA develops an adaptive cloud resource allocation plan that works for a wide range of applications. One of the most difficult and remarkable uses of ROCRA is processing Sentinel-2 satellite imagery for earth science applications. The timely, dependable, and effective allocation of resources is required for the processing and analysis of high-resolution satellite data for scientific investigations. By learning from and refining its strategies through its integrated adaptive feedback mechanism, ROCRA maintains its responsiveness to intricate tasks. ROCRA is perfect for dynamic research problems because of its evolutionary nature, which aids in anticipating and preparing for future challenges. We underscore the significance of ROCRA in cloud computing and its transformative potential by framing it as a universal solution, exemplified by tasks such as Sentinel-2 imagery processing. In the expanding field of cloud-based applications and research, ROCRA is an essential tool.