Elaheh Nabavi Nia | Searcharxiv

arXiv2026

Performance Cost Tradeoffs in Intelligent Load Balancing for Multi Data Center Cloud Systems: From Static Policies to Adaptive Resource Distribution

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.

cs.DC↗

arXiv2025

Enhancing Live Broadcast Engagement: A Multi-modal Approach to Short Video Recommendations Using MMGCN and User Preferences

The purpose of this paper is to explore a multi-modal approach to enhancing live broadcast engagement by developing a short video recommendation system that incorporates Multi-modal Graph Convolutional Networks (MMGCN) with user preferences. To provide personalized recommendations tailored to individual interests, the proposed system considers user interaction data, video content features, and contextual information. With the aid of a hybrid approach combining collaborative filtering and content-based filtering techniques, the system can capture nuanced relationships between users, video attributes, and engagement patterns. Three datasets are used to evaluate the effectiveness of the system: Kwai, TikTok, and MovieLens. Compared to baseline models, such as DeepFM, Wide & Deep, LightGBM, and XGBoost, the proposed MMGCN-based model shows superior performance. A notable feature of the proposed model is that it outperforms all baseline methods in capturing diverse user preferences and making accurate, personalized recommendations, resulting in a Kwai F1 score of 0.574, a Tiktok F1 score of 0.506, and a MovieLens F1 score of 0.197. We emphasize the importance of multi-modal integration and user-centric approaches in advancing recommender systems, emphasizing the role they play in enhancing content discovery and audience interaction on live broadcast platforms.

cs.IR↗