Sonal Shah
In today's rapidly evolving
computing landscape, cloud computing has emerged as a pivotal paradigm that
offers scalable and flexible resource provisioning to meet the demands of
diverse applications. A critical aspect in this environment is load balancing,
a technique that optimally distributes workloads across available resources to
ensure efficient resource utilization, enhanced system performance, and
seamless user experiences. This systematic literature review (SLR) delves into
the realm of optimized load balancing techniques within cloud computing
environments, encompassing various approaches, optimization methods,
challenges, and future trends. The SLR reviews 50 research articles to track
the evolution of load balancing techniques from traditional to modern dynamic
strategies in cloud infrastructures. The review categorizes load balancing
techniques into centralized, decentralized, and hybrid methods, noting their
features and limitations. It highlights the importance of optimization methods,
like meta-heuristics, machine learning, and swarm intelligence, in enhancing
resource allocation and response times, and addresses challenges such as
heterogeneity, scalability, and real-time adaptability.This review also
identifies imminent challenges faced by load balancing in cloud computing
environments. These challenges encompass the intricate interplay between
resource allocation, fluctuating workloads, and dynamic system conditions.
Additionally, the review offers insights into future trends that include harnessing
the power of artificial intelligence and machine learning techniques, exploring
fog and edge computing for load distribution, and exploring hybrid load
balancing strategies to further enhance system efficiency. This review offers a
comprehensive understanding of optimized load balancing in cloud computing,
covering the evolution of techniques, optimization methods, and challenges. It
also identifies emerging trends to guide future research and practice.In the
subsequent sections, we delve deeper into the current state of research,
outlining the proposed approach in alignment with the research objectives.
Subsequently, we expound upon the experimental outcomes attained through the
proposed framework, encapsulating both its methodology and results.
Dynamic load balancing, reactive
fault tolerance, cloud, systematic literature review, resource allocation, task
scheduling, virtual machine, workload management, optimization
VOL.16, ISSUE No.3, September 2024