Elastic neural network method for load prediction  in cloud computing grid

Qaddoum, Kefaya; El-Emam, Nameer N.; Abualhaj, Mosleh A.

doi:10.11591/ijece.v9i2.pp1201-1208

Cited by 9 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many challenges such as VM migration, server allocation, scalability, availability and fault tolerance yet to be address for the efficiency of cloud computing. Kefaya S. Qaddoum et al [2] are concerned with the concept of servers' load balancing; a method of distributing the load among various nodes of all distributed systems in order to utilize resources and work response time to improve scalability and user satisfaction. Readjustment of load through dynamic resource allocation is presented to adapt to changing needs.…”

Section: Hajer Toumi Et Almentioning

confidence: 99%

Clustering Based Prediction for VM Workload in Green Computation

Saxena

2024

AJCT

View full text Add to dashboard Cite

In order to support the different new generation equipment and technologies, cloud computing is depends to deal with the bulky data. Because a rich amount of data is generated using these devices and processing such big data need the cloud servers which can scale the computational ability according to demand. On the other hands to perform computation we need huge power supply and cooling system that increases the power consumption and emission of harmful gases. Thus, need to achieve green computing by reducing power consumption of computational cloud. In this context, we found VM(virtual machine) workload scheduling can be a good strategy to efficiently utilize the computational resources and reducing power consumption of cloud server.Basically, the physical machines contain a number of virtual machines (VMs). These VMs are used to deal with the workload appeared for processing. If we better utilize the resources then we can process large number of jobs in less amount of VMs. Additionally, we can also turn off the ideal machines to reduce the power consumption. In this context the proposed work is motivated to work with VM scheduling techniques to achieve green computing. In recent literature we also identified that there are two kinds of VM scheduling approaches active and proactive. The proactive technique is more effective as compared to active approaches, due to prior knowledge of the workload on VM. So, in this paper we proposed green cloud predictive model for VMs workload using unsupervised learning (i.e clustering) like K-Mean, K-Medoid, Fuzzy C-Mean (FCM),Self-Organizing Map(SOM) to predict the future workload for VM's scheduling and find the efficient clustering among them for workload prediction in view of green computing. The efficiency of clustering-based prediction is measured on parameters like accuracy, error rate.

show abstract

Section: Hajer Toumi Et Almentioning

confidence: 99%

Clustering Based Prediction for VM Workload in Green Computation

Saxena

2024

AJCT

View full text Add to dashboard Cite

show abstract

“…It shows that GRU performs better among the compared techniques. To construct an emerging framework to anticipate the VM workload, [34] introduces a modified Elastic Adaptive Neural Network (EANN), equipped with modified adaptive smoothing errors. Recurrent neural network with Back Propagation Through Time (BPTT) algorithm has better capability to precisely estimate host CPU usage in [35].…”

Section: Related Workmentioning

confidence: 99%

BHyPreC: A Novel Bi-LSTM Based Hybrid Recurrent Neural Network Model to Predict the CPU Workload of Cloud Virtual Machine

Karim

Maswood²,

Das

et al. 2021

IEEE Access

View full text Add to dashboard Cite

With the advancement of cloud computing technologies, there is an ever-increasing demand for the maximum utilization of cloud resources. It increases the computing power consumption of the cloud's systems. Consolidation of cloud's Virtual Machines (VMs) provides a pragmatic approach to reduce the energy consumption of cloud Data Centers (DC). Effective VM consolidation and VM migration without breaching Service Level Agreement (SLA) can be attained by taking proactive decisions based on cloud's future workload prediction. Effective task scheduling, another major issue of cloud computing also relies on accurate forecasting of resource usage. Cloud workload traces exhibit both periodic and non-periodic patterns with the sudden peak of load. As a result, it is very challenging for the prediction models to precisely forecast future workload. This prompted us to propose a hybrid Recurrent Neural Network (RNN) based prediction model named BHyPreC. BHyPreC architecture includes Bidirectional Long Short-Term Memory (Bi-LSTM) on top of the stacked Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). Here, BHyPreC is used to predict future CPU usage workload of cloud's VM. Our proposed model enhances the non-linear data analysis capability of Bi-LSTM, LSTM, and GRU models separately and demonstrates better accuracy compared to other statistical models. The effect of variation of historical window size and training-testing data size on these models is observed. The experimental result shows that our model gives higher accuracy and performs better in comparison to Autoregressive Integrated Moving Average (ARIMA), LSTM, GRU, and Bi-LSTM model for both short-term ahead and long-term ahead prediction.INDEX TERMS Cloud Computing, deep learning, recurrent neural network, time series analysis, virtual machine, workload prediction.

show abstract

“…The various factors influencing load balancing in DCN include the energy of nodes, residual bandwidth, scalability of the network, types of flows. With the increasing number of devices in the network, managing the network traffic is becoming very difficult [2]. Avoiding buffer overflows is another major concern.…”

Section: Introductionmentioning

confidence: 99%

Traffic-aware adaptive server load balancing for software defined networks

Fancy

Pushpalatha

2021

IJECE

View full text Add to dashboard Cite

Servers in data center networks handle heterogenous bulk loads. Load balancing, therefore, plays an important role in optimizing network bandwidth and minimizing response time. A complete knowledge of the current network status is needed to provide a stable load in the network. The process of network status catalog in a traditional network needs additional processing which increases complexity, whereas, in software defined networking, the control plane monitors the overall working of the network continuously. Hence it is decided to propose an efficient load balancing algorithm that adapts SDN. This paper proposes an efficient algorithm TA-ASLB-traffic-aware adaptive server load balancing to balance the flows to the servers in a data center network. It works based on two parameters, residual bandwidth, and server capacity. It detects the elephant flows and forwards them towards the optimal server where it can be processed quickly. It has been tested with the Mininet simulator and gave considerably better results compared to the existing server load balancing algorithms in the floodlight controller. After experimentation and analysis, it is understood that the method provides comparatively better results than the existing load balancing algorithms.

show abstract

Elastic neural network method for load prediction in cloud computing grid

Cited by 9 publications

References 16 publications

Clustering Based Prediction for VM Workload in Green Computation

Clustering Based Prediction for VM Workload in Green Computation

BHyPreC: A Novel Bi-LSTM Based Hybrid Recurrent Neural Network Model to Predict the CPU Workload of Cloud Virtual Machine

Traffic-aware adaptive server load balancing for software defined networks

Contact Info

Product

Resources

About