Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.11899 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917265439457280 |
|---|---|
| author | Najafabadi, Saeid Aghasoleymani Nia, Elaheh Nabavi |
| author_facet | Najafabadi, Saeid Aghasoleymani Nia, Elaheh Nabavi |
| contents | Cloud computing infrastructures increasingly rely on geographically distributed data centers to meet the growing demand for low latency, high availability, and cost-efficient service delivery. In this context, load balancing plays a critical role in optimizing resource utilization while maintaining acceptable quality of service (QoS) under dynamic and heterogeneous workloads. This study presents a comprehensive performance and cost evaluation of three widely used load balancing strategies, namely Round Robin, Equally Spread Current Execution Load, and Throttled, within a multi data center cloud environment using the Cloud Analyst simulation framework. Multiple deployment scenarios are examined by varying data center locations, user base distribution, network latency, and workload intensity. Key performance metrics, including overall response time, data center processing time, request handling behavior, and operational cost such as virtual machine and data transfer costs, are analyzed across two strategy steps. The results indicate that while the Round Robin strategy achieves lower internal processing times, the Equally Spread and Throttled strategies provide improved workload stability and reduced peak response times under high demand conditions. Furthermore, distributing resources across multiple data centers significantly reduces user perceived latency and enhances system scalability, albeit with associated cost tradeoffs. The findings demonstrate that no single load balancing strategy is universally optimal; instead, performance and cost efficiency depend on workload characteristics, geographic distribution, and system objectives. This work offers practical insights for cloud service providers and system designers, emphasizing the importance of intelligent resource distribution and adaptive load balancing policies for sustainable and high-performance cloud infrastructures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11899 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Performance Cost Tradeoffs in Intelligent Load Balancing for Multi Data Center Cloud Systems: From Static Policies to Adaptive Resource Distribution Najafabadi, Saeid Aghasoleymani Nia, Elaheh Nabavi Distributed, Parallel, and Cluster Computing Cloud computing infrastructures increasingly rely on geographically distributed data centers to meet the growing demand for low latency, high availability, and cost-efficient service delivery. In this context, load balancing plays a critical role in optimizing resource utilization while maintaining acceptable quality of service (QoS) under dynamic and heterogeneous workloads. This study presents a comprehensive performance and cost evaluation of three widely used load balancing strategies, namely Round Robin, Equally Spread Current Execution Load, and Throttled, within a multi data center cloud environment using the Cloud Analyst simulation framework. Multiple deployment scenarios are examined by varying data center locations, user base distribution, network latency, and workload intensity. Key performance metrics, including overall response time, data center processing time, request handling behavior, and operational cost such as virtual machine and data transfer costs, are analyzed across two strategy steps. The results indicate that while the Round Robin strategy achieves lower internal processing times, the Equally Spread and Throttled strategies provide improved workload stability and reduced peak response times under high demand conditions. Furthermore, distributing resources across multiple data centers significantly reduces user perceived latency and enhances system scalability, albeit with associated cost tradeoffs. The findings demonstrate that no single load balancing strategy is universally optimal; instead, performance and cost efficiency depend on workload characteristics, geographic distribution, and system objectives. This work offers practical insights for cloud service providers and system designers, emphasizing the importance of intelligent resource distribution and adaptive load balancing policies for sustainable and high-performance cloud infrastructures. |
| title | Performance Cost Tradeoffs in Intelligent Load Balancing for Multi Data Center Cloud Systems: From Static Policies to Adaptive Resource Distribution |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2507.11899 |