Applied Machine Learning in Load Balancing

Junaidi, Junaidi; Wibowo, Prasetyo Adi; Yuniasri, Dini; Damayanti, Putri; Shiddiqi, Ary Mazharuddin; Pratomo, Baskoro Adi

doi:10.12962/j24068535.v18i2.a940

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Junaidi et al 17 have proposed an ML‐based load balancer to predict the state of the servers within clusters. Based on this prediction, the server that helps avoid potential delays is selected to forward users' queries.…”

Section: Literature Reviewmentioning

confidence: 99%

Machine learning‐based load distribution and balancing in heterogeneous database management systems

Abdennebi

Elakaş

Taşyaran

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary For dynamic and continuous data analysis, conventional OLTP systems are slow in performance. Today's cutting‐edge high‐performance computing hardware, such as GPUs, has been used as accelerators for data analysis tasks, which traditionally leverage CPUs on classical database management systems (DBMS). When CPUs and GPUs are used together, the architectural heterogeneity, that is, leveraging hardware with different performance characteristics jointly, creates complex problems that need careful treatment for performance optimization. Load distribution and balancing are crucial problems for DBMSs working on heterogeneous architectures. In this work, focusing on a hybrid, CPU‐GPU database management system to process users' queries, we propose heuristical and machine‐learning‐based (ML‐based) load distribution and balancing models. In more detail, we employ multiple linear regression (MLR), random forest (RF), and Adaboost (Ada) models to dynamically decide the processing unit for each incoming query based on the response time predictions on both CPU and GPU. The ML‐based models outperformed the other algorithms, as well as the CPU and GPU‐only running modes with up to 27%, 29%, and 40%, respectively, in overall performance (response time) while answering intense real‐life working scenarios. Finally, we propose to use a hybrid load‐balancing model that would be more efficient than the models we tested in this work.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Machine learning‐based load distribution and balancing in heterogeneous database management systems

Abdennebi

Elakaş

Taşyaran

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

An Efficient Load Balancing Using Genetic Algorithm in Cloud Computing

Saputra

Wibowo

Pratomo

et al. 2022

2022 11th Electrical Power, Electronics, Communications, Controls and Informatics Seminar (EECCIS)

View full text Add to dashboard Cite

Intelligent process migration in heterogeneous distributed systems

Marecos Brizuela,

La Red Martínez,

Agostini

et al. 2024

Comput. Artif. Intell.

View full text Add to dashboard Cite

In distributed processing environments, multiple groups of processes are found sharing resources and competing for access. These processes may or may not require synchronization and it is essential to reach a consensus to manage access to resources in a way that establishes a strict order, thus ensuring mutual exclusion. The proposal presented is an innovative and effective solution for the management of shared resources in distributed systems, which allows solving problems related to overload and workload balancing. The evaluation of the state of computational loads and the final comparison using standard deviation are useful tools to detect and correct imbalances in the system. In addition, the possibility of establishing initial configurations of the algorithm for each particular situation allows adapting the solution to the specific needs of each system.

show abstract

Applied Machine Learning in Load Balancing

Cited by 3 publications

References 0 publications

Machine learning‐based load distribution and balancing in heterogeneous database management systems

Machine learning‐based load distribution and balancing in heterogeneous database management systems

An Efficient Load Balancing Using Genetic Algorithm in Cloud Computing

Intelligent process migration in heterogeneous distributed systems

Contact Info

Product

Resources

About