OPTIMIZING LOAD BALANCING IN FOG COMPUTING: A SURVEY OF AI-POWERED APPROACHES
Al-Shodhana · 30.01.2026 · 14 (1) · 548-560
DOI: 10.70644/as.v14.i1.45 ↗Kurz gefasst
Fachartikel in der Zeitschrift Al-Shodhana, online erschienen am 30.01.2026. Verfasst von Sowmya Jyothi und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
By bringing networking, storage, and processing capabilities closer to Internet of Things (IoT) devices at the network edge, fog computing has emerged as a promising paradigm to get beyond the limitations of cloud computing. Fog computing offers low latency, real-time processing, and location awareness—all of which are essential for time-sensitive Internet of Things applications—in contrast to traditional cloud architectures. However, load balancing is severely hampered by the dispersed, dynamic, and varied nature of fog environments, which has a direct impact on scalability, energy eficiency, performance, and reliability. To maximize distributed resources while reducing latency and preventing resource overload, fog node balancing must be done effectively. Because fog nodes frequently have limited power budgets, energy optimization is equally crucial. This means that workload management techniques are needed to reduce energy consumption without sacrificing performance. AI methods that have demonstrated great promise for optimizing load balancing in fog computing include machine learning, deep learning, reinforcement learning, and federated learning. These techniques enable systems to respond eficiently to changing workloads and resource fluctuations by offering predictive, adaptive, and self-optimizing capabilities. According to recent studies, AI-driven methods increase system resilience and dependability in heterogeneous environments while improving Quality of Service (QoS) metrics like response time, energy consumption, and throughput. This survey examines AI-powered load balancing techniques for fog computing in detail, evaluating and contrasting current methods along with their advantages, disadvantages, and use cases. For large-scale fog ecosystems, it also highlights issues like scalability, privacy protection, energy-conscious optimization, and hybrid models.
Zitieren
APA
Jyothi, S., & B, S. (2026). OPTIMIZING LOAD BALANCING IN FOG COMPUTING: A SURVEY OF AI-POWERED APPROACHES. Al-Shodhana, 14(1), 548-560. https://doi.org/10.70644/as.v14.i1.45
Vancouver
Jyothi S, B S. OPTIMIZING LOAD BALANCING IN FOG COMPUTING: A SURVEY OF AI-POWERED APPROACHES. Al-Shodhana. 2026;14(1):548-560. doi:10.70644/as.v14.i1.45
BibTeX
@article{Jyothi2026,
author = {Jyothi, Sowmya and B, Santhosh},
title = {OPTIMIZING LOAD BALANCING IN FOG COMPUTING: A SURVEY OF AI-POWERED APPROACHES},
journal = {Al-Shodhana},
year = {2026},
volume = {14},
number = {1},
pages = {548--560},
doi = {10.70644/as.v14.i1.45}
}
EUVIMED