• Jeewesh kumar Jha
• Dr. Gurjeet Singh
• Dr. Sudhir Pathak
• Abhidha Verma

This paper proposes a new framework for scheduling cloud resources that explicitly integrates the Age of Information (AOI) metric into the scheduling decision process, enabling direct quantification and optimization of information freshness. The framework uses an improved deep reinforcement learning (DRL) method to learn how to adapt scheduling policies in changing cloud environments. A multidimensional reward function is designed to jointly optimize AOI, resource utilization, and task completion performance, allowing system-level freshness optimization without compromising efficiency. Prioritized experience replay and n-step learning are added to the training process to make learning more stable and faster. Extensive simulation results demonstrate that the proposed framework consistently achieves lower average AOI under diverse workload conditions while satisfying resource capacity and energy consumption constraints. These findings provide both theoretical insights and practical guidance for improving real-time cloud service quality and supporting timely decision-making in cloud and edge computing environments

Age of Information (AOI) Cloud resource scheduling Deep reinforcement learning Real-time optimization Edge computing

"DECENTRALIZED CLOUD RESOURCE SCHEDULING USING BLOCKCHAIN-ASSISTED AGE OF INFORMATION–AWARE DEEP REINFORCEMENT LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.a123-a136, January-2026, Available :http://www.jetir.org/papers/JETIR2601015.pdf

"DECENTRALIZED CLOUD RESOURCE SCHEDULING USING BLOCKCHAIN-ASSISTED AGE OF INFORMATION–AWARE DEEP REINFORCEMENT LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppa123-a136, January-2026, Available at : http://www.jetir.org/papers/JETIR2601015.pdf