International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 11 | Nov 2025
p-ISSN: 2395-0072
www.irjet.net
INTELLIGENT LOAD BALANCING IN CLOUD ENVIRONMENTS Santhosh C 1, Sangeeths A 2 1PG student, Department Of Computer Applications, Jaya College Of Arts and Science, Thiruninravur, Tamilnadu, India 2Assistant Professor, Department Of Computer Applications, Jaya College Of Arts and Science , Thiruninravur,
Tamilnadu, India ------------------------------------------------------------------------***---------------------------------------------------------------------------------Abstract – Beloglazov et al. (2012) proposed an energy- Cloud computing has revolutionized the IT industry by providing scalable and on-demand resources over the internet. However, with the increasing number of users and dynamic workloads, load balancing has become critical challenge in ensuring system performance, resource utilization, and service reliability. Intelligent load balancing techniques use artificial intelligence (AI), machine learning (ML), and optimization algorithms to dynamically allocate resources across servers or virtual machines to handle workloads efficiently. This paper explores the concept of intelligent load balancing in cloud environments, focusing on algorithms, techniques, and strategies used to distribute workloads effectively. It discusses traditional and modern AI-based load balancing approaches, evaluates their performance, and highlights their role in improving scalability, response time, and fault tolerance in cloud infrastructure. The paper concludes by emphasizing the future potential of intelligent systems in achieving fully autonomous and energy-efficient cloud environments. Key Words: Cloud Computing, Load Balancing, Artificial Intelligence, Resource Management, Optimization I.INTRODUCTION (Size 11 cambria font) Cloud computing has revolutionized the way computing resources are delivered and utilized by offering on-demand access to shared pools of configurable resources such as servers, storage, and applications. It enables users to deploy, manage, and scale applications efficiently without worrying about the underlying infrastructure. However, with the continuous growth of data and increasing number of users, effective resource management and task distribution have become critical challenges in cloud environments.
1. LITERATURE-REREVIEW Numerous researchers have proposed intelligent methods for load balancing in cloud environments: Efficient resource allocation method for cloud data centers using adaptive threshold-based techniques to minimize energy consumption while maintaining performance. Gawali and Shined (2018) introduced a load balancing algorithm using artificial bee colony optimization that improved task scheduling efficiency and reduced processing time. Mishra et al. (2019) designed a hybrid approach combining genetic algorithms with particle swarm optimization (PSO) for dynamic workload distribution. Sharma and Kumar (2020) explored deep learning-based load prediction models to improve decision-making accuracy in cloud systems. Patel et al. (2021) proposed a reinforcement learning-based system that autonomously adjusts resource allocation to handle fluctuating user demands.
2.COMMON TECHNIQUES AND ARCHITECTURES Machine learning models such as regression, decision trees, and neural networks predict workload trends and automatically allocate resources based on performance metrics like CPU usage, memory consumption, and network latency. Intelligent load
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 1026