Cloud Computing Load Forecasting by Using Bidirectional Long Short-Term Memory Neural Network

Lecture notes in networks and systems, Год журнала: 2023, Номер unknown, С. 667 - 682

Опубликована: Ноя. 27, 2023

Язык: Английский

---

Efficient Auto‐scaling for Host Load Prediction through VM migration in Cloud

Concurrency 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

---

A Review on Machine Learning Methods for Workload Prediction in Cloud Computing

Опубликована: 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

---

Multivariate Workload Aware Correlation Model for Container Workload Prediction

Опубликована: Дек. 17, 2023

Язык: Английский

---

Enhanced multivariate singular spectrum analysis‐based network traffic forecasting for real time industrial IoT applications

IET Networks, Год журнала: 2024, Номер 13(4), С. 301 - 312

Опубликована: Март 12, 2024

Abstract Industrial IoT (IIoT) applications are widely used in multiple use cases to automate the industrial environment. Industry 4.0 presents challenges numerous areas, including heterogeneous data, efficient data sensing and collection, real‐time processing, higher request arrival rates, due massive amount of data. Building a time‐sensitive network that supports voluminous dynamic traffic from is complex. Therefore, authors provide insights into networks propose strategy for enhanced management. An multivariate forecasting model adapts Multivariate Singular Spectrum Analysis employed an SDN‐based IIoT network. The proposed method considers flow parameters, such as packet sent received, bytes source rate, round trip time, jitter, rate duration predict future flows. experimental results show can effectively by contemplating every possible variation observed samples average load, delay, inter‐packet sending with improved accuracy. forecast shows reduced error estimation when compared existing methods Mean Absolute Percentage Error 1.64%, Squared 11.99, Root 3.46 2.63.

Язык: Английский

---