A fine tune hyper parameter Gradient Boosting model for CPU utilization prediction in cloud DOI Creative Commons
Savita Khurana, Gaurav Sharma,

Bhawna Sharma

и другие.

Research Square (Research Square), Год журнала: 2023, Номер unknown

Опубликована: Окт. 9, 2023

Abstract CPU utilization prediction is key factor for efficient resource management and capacity planning in cloud computing environments. By accurately predicting patterns, managers can dynamically distribute workloads to ensure optimal of resources. The load be equally distributed among virtual machines, leading a reduction VM migration overhead time. This optimization significantly improves the overall performance cloud. proactive approach enables usage, minimizing risk bottlenecks maximizing system performance. In this paper Gradient Boosting model with hyper parameter tuning based upon grid search (GBHT) proposed enhance prediction. Multiple weak learners are combined produce powerful model. hyperparameters used its as well predictive accuracy. Different machine learning deep models examined side by side. results clearly demonstrate that GBHT contribute superior then traditional (SVM, KNN, Random Forest, Boost), (LSTM, RNN, CNN), time series (Facebook Prophet) hybrid models, combining LSTM Boost SVM. demonstrates compared other achieving lowest MAPE 0.01% high accuracy an R2 score 1.00.

Язык: Английский

Mobility-aware computational offloading in mobile edge networks: a survey DOI

Sardar Khaliq uz Zaman,

Ali Imran Jehangiri, Tahir Maqsood

и другие.

Cluster Computing, Год журнала: 2021, Номер 24(4), С. 2735 - 2756

Опубликована: Апрель 9, 2021

Язык: Английский

Процитировано

91
Performance Analysis of Machine Learning Centered Workload Prediction Models for Cloud DOI
Deepika Saxena, Jitendra Kumar, Ashutosh Kumar Singh

и другие.

IEEE Transactions on Parallel and Distributed Systems, Год журнала: 2023, Номер 34(4), С. 1313 - 1330

Опубликована: Янв. 30, 2023

The precise estimation of resource usage is a complex and challenging issue due to the high variability dimensionality heterogeneous service types dynamic workloads. Over last few years, prediction traffic has received ample attention from research community. Many machine learning-based workload forecasting models have been developed by exploiting their computational power learning capabilities. This paper presents first systematic survey cum performance analysis-based comparative study diversified learning-driven cloud models. discussion initiates with significance predictive management followed schematic description, operational design, motivation, challenges concerning these Classification taxonomy different approaches into five distinct categories are presented focusing on theoretical concepts mathematical functioning existing state-of-the-art methods. most prominent belonging class thoroughly surveyed compared. All classified implemented common platform for investigation comparison using three benchmark traces via experimental analysis. essential key indicators evaluated concluded discussing trade-offs notable remarks.

Язык: Английский

Процитировано

42
MAG-D: A multivariate attention network based approach for cloud workload forecasting DOI Open Access
Yashwant Singh Patel, Jatin Bedi

Future Generation Computer Systems, Год журнала: 2023, Номер 142, С. 376 - 392

Опубликована: Янв. 10, 2023

Язык: Английский

Процитировано

35
Predictive intelligence using ANFIS‐induced OWAWA for complex stock market prediction DOI Open Access
Walayat Hussain, José M. Merigó, Muhammad Raheel Raza

и другие.

International Journal of Intelligent Systems, Год журнала: 2021, Номер 37(8), С. 4586 - 4611

Опубликована: Ноя. 8, 2021

Traditional time series prediction methods are unable to handle the complex nonlinear relationship of a large data set. Most existing techniques manage multiple dimensions set, due which computational complexity escalates with increasing size Many machine learning (ML) known unknown predictions. This paper presents new forecasting method in neural network structure based on induced ordered weighted average (IOWA) (WA) and fuzzy series. The proposed model is more efficient than handling other traditional methods. can accommodate IOWA operator, average, relevance degree each concept particular problem for prediction. contribution this twofold. First, it contributes theory by proposing IOWAWA layer second application approach predict stock market data. robustness tested using Australian Securities Exchange (ASX) considering case study housing property sector. We further compare accuracy sixteen experimental results demonstrate that outperforms

Язык: Английский

Процитировано

42
Multivariate workload and resource prediction in cloud computing using CNN and GRU by attention mechanism DOI
Javad Dogani, Farshad Khunjush,

Mohammad Reza Mahmoudi

и другие.

The Journal of Supercomputing, Год журнала: 2022, Номер 79(3), С. 3437 - 3470

Опубликована: Сен. 4, 2022

Язык: Английский

Процитировано

36
A hybrid deep neural network approach to estimate reference evapotranspiration using limited climate data DOI
Gitika Sharma, Ashima Singh, Sushma Jain

и другие.

Neural Computing and Applications, Год журнала: 2021, Номер 34(5), С. 4013 - 4032

Опубликована: Ноя. 12, 2021

Язык: Английский

Процитировано

35
Accurate Prediction of Workloads and Resources With Multi-Head Attention and Hybrid LSTM for Cloud Data Centers DOI
Jing Bi, Haisen Ma, Haitao Yuan

и другие.

IEEE Transactions on Sustainable Computing, Год журнала: 2023, Номер 8(3), С. 375 - 384

Опубликована: Март 20, 2023

Currently, cloud computing service providers face big challenges in predicting large-scale workload and resource usage time series. Due to the difficulty capturing nonlinear features, traditional forecasting methods usually fail achieve high prediction performance for sequences. Besides, there is much noise original series of resources workloads. If these are not de-noised by smoothing algorithms, results can meet providers' requirements. To do so, this work proposes a hybrid model named VAMBiG that integrates V ariational mode decomposition, an xmlns:xlink="http://www.w3.org/1999/xlink">A daptive Savitzky-Golay (SG) filter, xmlns:xlink="http://www.w3.org/1999/xlink">M ulti-head attention mechanism, xmlns:xlink="http://www.w3.org/1999/xlink">Bi directional xmlns:xlink="http://www.w3.org/1999/xlink">G rid versions Long Short Term Memory (LSTM) networks. adopts signal decomposition method variational decompose complex non-linear into low-frequency intrinsic functions. Then, it adaptive SG filter as data pre-processing tool eliminate extreme points such Afterwards, bidirectional grid LSTM networks capture features dimension ones, respectively. Finally, multi-head mechanism explore importance different dimensions. aims predict workloads highly variable traces clouds. Extensive experimental demonstrate achieves higher-accuracy than several advanced approaches with datasets from Google Alibaba cluster traces.

Язык: Английский

Процитировано

13
Application-Oriented Cloud Workload Prediction: A Survey and New Perspectives DOI Open Access
Binbin Feng, Zhijun Ding

Tsinghua Science & Technology, Год журнала: 2024, Номер 30(1), С. 34 - 54

Опубликована: Сен. 11, 2024

Язык: Английский

Процитировано

4
COSCO2 : AI ‐augmented evolutionary algorithm based workload prediction framework for sustainable cloud data centers DOI

R. Karthikeyan,

V. Balamurugan,

Robin Cyriac

и другие.

Transactions on Emerging Telecommunications Technologies, Год журнала: 2022, Номер 34(1)

Опубликована: Окт. 3, 2022

Abstract Workload prediction is the necessary factor in cloud data center for maintaining elasticity and scalability of resources. However, accuracy workload very low, because redundancy, noise, low center. Therefore, this article, a tree hierarchical deep convolutional neural network (T‐CNN) optimized with sheep flock optimization algorithm based work load proposed sustainable centers. Initially, historical from preprocessed using kernel correlation method. The T‐CNN approach used dynamic environment. weight parameters model are by algorithm. COSCO2 method has accurately predicts upcoming reduces extravagant power consumption at evaluated utilizing two benchmark datasets: (i) NASA, (ii) Saskatchewan HTTP traces. simulation implemented java tool calculated. From simulation, attains 20.64%, 32.95%, 12.05%, 32.65%, 26.54% high accuracy, 27.4%, 26%, 23.7%, 34.7%, 36.5% lower energy validating NASA dataset, similarly 20.75%, 19.06%, 29.09%, 23.8%, 20.5% 20.84%, 18.03%, 28.64%, 30.72%, 33.74% traces dataset than existing approaches, like auto adaptive differential evolution BiPhase learning‐based network, error preventive score time series forecasting models, methods prediction, self‐directed

Язык: Английский

Процитировано

15
An intelligent model for efficient load forecasting and sustainable energy management in sustainable microgrids DOI Creative Commons

Rupesh Rayalu Onteru,

Sandeep Vuddanti

Discover Sustainability, Год журнала: 2024, Номер 5(1)

Опубликована: Июль 30, 2024

Abstract Microgrids have emerged as a promising solution for enhancing energy sustainability and resilience in localized distribution systems. Efficient management accurate load forecasting are one of the critical aspects improving operation microgrids. Various approaches prediction using statistical models discussed literature. In this work, novel framework that incorporates machine learning (ML) techniques is presented an solar wind generation. The anticipated approach also emphasizes time series-based microgrids with precise estimation State Charge (SoC) battery. A unique feature proposed utilizes historical data employs series analysis coupled different ML to forecast demand commercial scenario. Long Short-Term Memory (LSTM) Linear Regression (LR) employed experimental study under three cases, such (i) generation, (ii) and, (iii) SoC results show Random Forest (RF) LSTM performs well respectively. On other hand, Artificial Neural Network (ANN) model exhibited superior accuracy terms estimation. Further, Graphical User Interface (GUI) developed evaluating efficacy framework.

Язык: Английский

Процитировано

3