
Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Май 10, 2024
Язык: Английский
Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Май 10, 2024
Язык: Английский
Cluster Computing, Год журнала: 2023, Номер 27(4), С. 4491 - 4514
Опубликована: Ноя. 28, 2023
Язык: Английский
Процитировано
2Concurrency and Computation Practice and Experience, Год журнала: 2023, Номер 36(4)
Опубликована: Окт. 6, 2023
Summary The expeditious deployment of Cloud applications and services on wide‐ranging Data Centres (CDC) gives rise to the utilization many resources. Moreover, by increase in resource utilization, virtualization also greatly impacts achieving desired performance. major challenges are detecting over‐utilized or under‐utilized hosts at right time proper scaling Virtual Machines (VM) accurate host. Auto‐scaling Computing allows service providers scale up down resources automatically provides on‐demand computing power storage capacities. Effective autonomous eventually reduce load, energy consumption, operating costs. In this paper, an efficient auto‐scaling approach for predicting host load through VM migration has been proposed. ensemble method using different time‐series forecasting models proposed forecast approaching workload Based predicted algorithms have devised detect VMs can be migrated. designed validated experimentation a real‐time Google cluster dataset. technique significantly improves average CPU reduces over‐utilization under‐utilization. It minimizes response time, level agreement violations, slighter number migrations overhead.
Язык: Английский
Процитировано
1Опубликована: Ноя. 1, 2023
Workload prediction is one of the critical parts resource provisioning in cloud computing and its evolved branches such as serverless edge computing. Effective stands a crucial element within realm edge-cloud Accurate workloads essential for effective allocation resources. plays role enhancing efficiency, reducing costs, optimizing performance, maintaining high level quality service, minimizing energy consumption. In this paper, we conduct comprehensive review state-of-the-art Machine Learning (ML) Deep (DL) algorithms employed workload other similar platforms We compared selected papers terms utilized methods techniques, predicted factors, accuracy metrics, dataset. Additionally, to facilitate usability comparison, articles sharing advantages disadvantages are organized into table. Finally, paper concludes by addressing current challenges future research directions.
Язык: Английский
Процитировано
1Опубликована: Дек. 17, 2023
Язык: Английский
Процитировано
1Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Май 10, 2024
Язык: Английский
Процитировано
0