Claim Missing Document
Check
Articles

Found 1 Documents
Search

Evaluation and Comparison of Load Balancing Algorithm Performance in the Implementation of Weighted Least Connections and Round Robin in Cloud Computing Environment Fawwazi, Mohammad Mika; Putra, Eka; Putri, Nadya Andhika
Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 6, No 1 (2025)
Publisher : Universitas Muhammadiyah Sumatera Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/jcositte.v6i1.21731

Abstract

Weighted Least Connections (WLC) and Round Robin algorithms are two commonly used load balancing methods in cloud computing environments. Both have different approaches in distributing requests to servers, which impacts system performance. WLC takes into account the number of active connections and the capacity of each server, so that servers with larger capacities receive more requests, while Round Robin distributes requests sequentially regardless of server conditions. This study compares the performance of the two algorithms based on several parameters, including response time, throughput, and CPU utilization. The results show that WLC is superior in systems with heterogeneous servers, where WLC is able to adjust the load distribution based on the capacity and number of active connections, thereby improving system efficiency and performance. Faster response time and balanced CPU utilization are achieved by WLC, while Round Robin is more suitable for environments with servers with similar specifications. Although Round Robin works well in simple conditions, this algorithm often causes load imbalance on low-capacity servers in complex environments. Based on the results of the study, WLC is recommended for environments with server heterogeneity and dynamic loads, because this algorithm significantly improves resource efficiency and reduces server bottlenecks. Thus, WLC provides more optimal performance than Round Robin in scenarios that require more intelligent load distribution.