Skip to content
Open access

Reinforcement Learning for Adaptive Cloud Resource BI Optimization

2026 · American International Journal of Computer Science and Technology · Vol 8, pp. 80-88 · 0 citations

TL;DR

A framework for dynamically optimizing cloud resource BI based on Reinforcement Learning (RL) model who will continually interact with the cloud environment and learn a set of optimal policies for cloud resource allocation can enhance the analytical responsiveness, minimise resources wastage and enable cost-aware business decision systems.

Abstract

Dynamic cloud environments: These environments have a varying volume of data, query workload, number of users and/or business continuity objectives (SLOs) for Business Intelligence (BI) workloads. Due to these uncertainties, it will be impossible to balance the three important factors of performance, energy efficiency and cost with fixed rule and threshold based autoscaling approaches. In this research article we want to propose a framework for dynamically optimizing cloud resource BI based on Reinforcement Learning (RL) model who will continually interact with the cloud environment and learn a set of optimal policies for cloud resource allocation. This framework consists of five layers such as BI workload monitoring, state space construction, RL decision engine, resource orchestration and evaluation of performance feedback. Every system metric (such as CPU usage, memory usage, query response time, queue length, storage I/O, workload priority and cost constraints) is important. Those can be the scaling of virtual machines, moving containers around and changing memory sizes, prioritizing BI queries, moving workloads from node to node, etc., and are decided by the RL agent. The rewards can be specified as a multi-objective function, which include reduction of response time, reduction of cloud cost, resource utilization gain and SLA and energy consumption satisfaction. The proposed model is adaptive – it adapts itself based on the trends of the historical data or real-time data of BI workload. Algorithms like Q-learning, Deep Q-Networks and Proximal Policy Optimization could be potentially applied for an intelligent decision making in cloud based BI platforms, the study mentions. This framework can enhance the analytical responsiveness, minimise resources wastage and enable cost-aware business decision systems. It also helps businesses in planning for capacity with a pro-active assessment and hand over their real-time dashboards and predictive analytics services. Lastly, reinforcement learning can be leveraged for scaling and adapting for optimal BI workloads in a complex, dynamic and data rich cloud environment.

Read PDF

Similar papers

#reinforcement learning Open access Dec 2026

Optimizing Resource Allocation in Cloud Computing Environments using Reinforcement Learning

A deep reinforcement learning framework for intelligent cloud resource allocation that jointly optimizes resource utilization, Service Level Agreement compliance, infrastructure cost, and energy efficiency, and adapts to workload distribution shifts within 200 episodes without manual retuning is presented.

Msr Prasad · 0 citations
#reinforcement learning Open access Oct 2026

Reinforcement Learning Approach for Optimizing Cloud Resource Utilization with Load Balancing

Cloud computing provides flexible access to processing, storage, and networking resources, but efficient use of these resources remains a difficult management problem. Workloads vary in size, arrival rate, execution time, and resource demand, while virtual machines and containers may differ in capacity and current util...

P. V. K. Sonawane Rutuja Sitaram, J. Mahajan · 0 citations
Review Open access 2026

Dynamic Cloud Resource Optimization Using Reinforcement Learning

Cloud computing offers flexible and scalable access to computational resources, but selecting a suitable resource configuration for a given workload remains a difficult task. High-Performance Computing (HPC) and Artificial Intelligence (AI) workloads have varying computational requirements, and their performance depend...

S. Bachwani, D. Chaudhari, Shreya R. Gothe et al. · 0 citations
Conference Sep 2026

Reinforcement Learning Based SLA-Aware Resource Allocation for Cost-Efficient Cloud Computing

Inefficient resource allocation has been posing a significant problem, leading to increased operational costs and violations of SLAs. Effective scheduling of users' jobs while balancing availability, response time delay and throughput is difficult. This paper proposes an automated resource allocation framework using DQ...

K. Sherin, S. A, Vijayalakshimi V · 0 citations
Open access Oct 2026

ACDO-RL: Safe Reinforcement Learning for Joint Cloud Database Resource and Index Optimization

Operating a cloud database requires continual decisions about compute capacity, memory and physical design under changing workloads, with the goals of meeting a latency service-level objective (SLO) at minimal cost. This paper presents ACDO-RL, a reinforcement learning (RL) framework that controls vCPU scaling, buffer-...

Vishnuvardhan Dr. B · 0 citations
Open access Oct 2026

METHOD OF ADAPTIVE SCALING OF CLOUD RESOURCES BASED ON REINFORCEMENT LEARNING

The article considers the problem of adaptive scaling of cloud infrastructure resources under conditions of dynamic workload changes, uneven utilization of computational resources, and the necessity to ensure stable operation of information services. It has been determined that traditional approaches to horizontal and...

Andrii Pazynin · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.