EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predictive Cloud Balancing with Application-Layer Traffic Forecasts

Jan Kaiser, Maximilian Schmitz

SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL · 07.10.2026 · 4 (2) · 202-215

DOI: 10.66238/smsrj.v4i2.80 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL, online erschienen am 07.10.2026. Verfasst von Jan Kaiser und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern cloud computing environments face increasingly volatile and complex workloads, rendering traditional reactive load balancing mechanisms insufficient for maintaining optimal performance and resource utilization. This paper presents a comprehensive investigation into predictive cloud balancing leveraging application-layer traffic forecasts. By utilizing Layer 7 telemetry data, which provides deep insights into user intent and specific application requests, the proposed architecture accurately anticipates traffic surges and shifts before they impact infrastructure. We formulate a predictive resource allocation framework that integrates time-series forecasting models with dynamic load distribution algorithms. The study systematically reviews the evolution of cloud load balancing, moving from network-layer heuristics to intelligent, application-aware orchestration. A robust methodology is developed, employing advanced mathematical modeling to capture the temporal dependencies of application requests and optimize server assignment under capacity constraints. Extensive simulated experiments are conducted to evaluate the proposed predictive strategy against baseline reactive approaches, focusing on metrics such as tail latency, server utilization, and energy efficiency. The results demonstrate that application-layer forecasting significantly reduces response degradation during flash-crowd events while minimizing unnecessary resource provisioning. This research contributes a foundational architecture for next-generation cloud gateways, establishing a paradigm where load balancers operate proactively, driven by granular application-level intelligence.

Zitieren

APA

Kaiser, J., & Schmitz, M. (2026). Predictive Cloud Balancing with Application-Layer Traffic Forecasts. SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL, 4(2), 202-215. https://doi.org/10.66238/smsrj.v4i2.80

Vancouver

Kaiser J, Schmitz M. Predictive Cloud Balancing with Application-Layer Traffic Forecasts. SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL. 2026;4(2):202-215. doi:10.66238/smsrj.v4i2.80

BibTeX
@article{Kaiser2026,
  author = {Kaiser, Jan and Schmitz, Maximilian},
  title = {Predictive Cloud Balancing with Application-Layer Traffic Forecasts},
  journal = {SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {202--215},
  doi = {10.66238/smsrj.v4i2.80}
}
Kostenlos starten →