A Probabilistic Approach to Load Balancing in Multi-Cloud Environments via Machine Learning and Optimization Algorithms

Seyed Salar Sefati, Ahmed M. Nor, Bahman Arasteh, Răzvan Crăciunescu, Ciprian-Romeo Comşa

Journal of Grid Computing 2025 article cited by 26

Source Open-access PDF More in Software & Coding

importance 4/10 ai assisted Cloud Computing and Resource Management cloud computing stage: research

Problem

Efficiently assigning tasks to compatible clouds in dynamic multi-cloud environments is a crucial challenge, especially for ultra-reliable, low-latency applications.

Why it matters

Poor load balancing degrades latency and reliability for demanding applications.

What the AI did

Combined probabilistic modeling of task-to-cloud compatibility (DFND using multivariate normal distributions over CPU, memory, bandwidth, latency) with Tasmanian Devil Optimization for task assignment.

Results

CloudSim simulations demonstrated significant improvements over state-of-the-art methods; specific numbers not stated in abstract.

Impact

Simulation-only evidence of improved task assignment; real-world deployment not shown.

Record

Venue	Journal of Grid Computing
Published	2025
Work type	article
Authors	Seyed Salar Sefati, Ahmed M. Nor, Bahman Arasteh, Răzvan Crăciunescu, Ciprian-Romeo Comşa
Citations	26 (OpenAlex, at import time)
References	47
Model or method	Decision Functions with Normal Distributions (DFND); Tasmanian Devil Optimization (TDO)
Organization	not stated in source
Primary source	https://doi.org/10.1007/s10723-025-09805-6
Open access	hybrid
Keywords	load balancing, multi-cloud, probabilistic modeling, metaheuristic optimization, CloudSim, URLLC

Importance rating

4 / 10

real but narrower advance

Load balancing framed as crucial for URLLC multi-cloud apps, but evidence is CloudSim simulation only; no real-world scale or deployment shown.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Software & Coding

#	Paper	Year	Citations	Importance
1	ImageNet classification with deep convolutional neural networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton	2017	106,345	8
2	Deep Residual Learning for Image Recognition Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun	2016	221,134	8
3	Faster sorting algorithms discovered using deep reinforcement learning Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco S...	2023	175	8
4	A deep learning‐based approach for software vulnerability detection using code metrics Fazli Subhan, Xiaoxue Wu, Lili Bo, Xiaobing Sun, Muhammad Rahman	2022	42	7
5	Deep Learning-Based Attack Detection and Classification in Android Devices Alfonso Gómez, Antonio Muñoz	2023	41	7