Interactive Temporal Recurrent Convolution Network for Traffic Prediction in Data Centers

Cao, Xiaofeng; Zhong, Yuhua; Zhou, Yun; Jiang, Wang; Zhu, Cheng; Zhang, Weimin

doi:10.1109/access.2017.2787696

Cited by 91 publications

(51 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Explaining research chronological, including research design, research procedure (in the form of algorithms, Pseudocode or other), how to test and data acquisition [18], [19]. The description of the course of research should be supported references so that the explanation can be accepted scientifically [20], [21].…”

Section: Methodsmentioning

confidence: 99%

Elastic neural network method for load prediction in cloud computing grid

Qaddoum

El-Emam²,

Abualhaj

2019

IJECE

View full text Add to dashboard Cite

Cloud computing still has no standard definition, yet it is concerned with Internet or network on-demand delivery of resources and services. It has gained much popularity in last few years due to rapid growth in technology and the Internet. Many issues yet to be tackled within cloud computing technical challenges, such as Virtual Machine migration, server association, fault tolerance, scalability, and availability. The most we are concerned with in this research is balancing servers load; the way of spreading the load between various nodes exists in any distributed systems that help to utilize resource and job response time, enhance scalability, and user satisfaction. Load rebalancing algorithm with dynamic resource allocation is presented to adapt with changing needs of a cloud environment. This research presents a modified elastic adaptive neural network (EANN) with modified adaptive smoothing errors, to build an evolving system to predict Virtual Machine load. To evaluate the proposed balancing method, we conducted a series of simulation studies using cloud simulator and made comparisons with previously suggested approaches in the previous work. The experimental results show that suggested method betters present approaches significantly and all these approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

Elastic neural network method for load prediction in cloud computing grid

Qaddoum

El-Emam²,

Abualhaj

2019

IJECE

View full text Add to dashboard Cite

show abstract

“…The main novelty of [7] is to include autocorrelation of the time series in the input of the ML algorithm, which leads to superior performance with respect to existing methods. The combination of a special type of LSTM unit, i.e., the Gated Recurrent Units (GRU) and the Convolutional Neural Network (CNN) in the 2D domain (CNN-2D) has been proposed for the task of network traffic prediction in datacenters in [8]. The underlying idea of the work in [8] is to treat network matrices as images and use the CNN2D to find the correlations among traffic exchanged between different pairs of nodes.…”

Section: Related Workmentioning

confidence: 99%

“…The combination of a special type of LSTM unit, i.e., the Gated Recurrent Units (GRU) and the Convolutional Neural Network (CNN) in the 2D domain (CNN-2D) has been proposed for the task of network traffic prediction in datacenters in [8]. The underlying idea of the work in [8] is to treat network matrices as images and use the CNN2D to find the correlations among traffic exchanged between different pairs of nodes. Note that, in literature, the prediction of traffic exchanged among network nodes is more common than the prediction of the load on network links.…”

Section: Related Workmentioning

confidence: 99%

Network Traffic Prediction based on Diffusion Convolutional Recurrent Neural Networks

Andreoletti

Troia

Musumeci

et al. 2019

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

View full text Add to dashboard Cite

By predicting the traffic load on network links, a network operator can effectively pre-dispose resource-allocation strategies to early address, e.g., an incoming congestion event. Traffic loads on different links of a telecom is know to be subject to strong correlation, and this correlation, if properly represented, can be exploited to refine the prediction of future congestion events. Machine Learning (ML) represents nowadays the state-of-the-art methodology for discovering complex relations among data. However, ML has been traditionally applied to data represented in the Euclidean space (e.g., to images) and it may not be straightforward to effectively employ it to model graph-stuctured data (e.g., as the events that take place in telecom networks). Recently, several ML algorithms specifically designed to learn models of graph-structured data have appeared in the literature. The main novelty of these techniques relies on their ability to learn a representation of each node of the graph considering both its properties (e.g., features) and the structure of the network (e.g., the topology). In this paper, we employ a recently-proposed graph-based ML algorithm, the Diffusion Convolutional Recurrent Neural Network (DCRNN), to forecast traffic load on the links of a real backbone network. We evaluate DRCNN's ability to forecast the volume of expected traffic and to predict events of congestion, and we compare this approach to other existing approaches (as LSTM, and Fully-Connected Neural Networks). Results show that DCRN outperforms the other methods both in terms of its forecasting ability (e.g., MAPE is reduced from 210% to 43%) and in terms of the prediction of congestion events, and represent promising starting point for the application of DRCNN to other network management problems.

show abstract

“…They use ANN to effectively predict traffic behavior, improve routing decisions and lower power consumption by up to 31% compared to existing standards. In [21], X. Cao et al propose a mixed prediction model using Convolution Neural Networks (CNN) to study the spatial characteristics of traffic and the Gated Recurrent Unit (GRU), for the temporal factor. The authors manage to improve the error rate, up to 14.3% compared to these methods taken independently.…”

Section: Related Workmentioning

confidence: 99%

Kalman Filtering-based Traffic Prediction for Software Defined Intra-data Center Networks

2019

KSII TIIS

View full text Add to dashboard Cite

Global data center IP traffic is expected to reach 20.6 zettabytes (ZB) by the end of 2021. Intra-data center networks (Intra-DCN) will account for 71.5% of the data center traffic flow and will be the largest portion of the traffic. The understanding of traffic distribution in Intra-DCN is still sketchy. It causes significant amount of bandwidth to go unutilized, and creates avoidable choke points. Conventional transport protocols such as Optical Packet Switching (OPS) and Optical Burst Switching (OBS) allow a one-sided view of the traffic flow in the network. This therefore causes disjointed and uncoordinated decision-making at each node. For effective resource planning, there is the need to consider joining the distributed with centralized management which anticipates the system's needs and regulates the entire network. Methods derived from Kalman filters have proved effective in planning road networks. Considering the network available bandwidth as data transport highways, we propose an intelligent enhanced SDN concept applied to OBS architecture. A management plane (MP) is added to conventional control (CP) and data planes (DP). The MP assembles the traffic spatio-temporal parameters from ingress nodes, uses Kalman filtering predictionbased algorithm to estimate traffic demand. Prior to packets arrival at edges nodes, it regularly forwards updates of resources allocation to CPs. Simulations were done on a hybrid scheme (1+1) and on the centralized OBS. The results demonstrated that the proposition decreases the packet loss ratio. It also improves network latency and throughput-up to 84 and 51%, respectively, versus the traditional scheme. . His research interests include fiberoptic transmission and microwave photonics.Deming Liu received his Ph.D. degree in the department

show abstract

Interactive Temporal Recurrent Convolution Network for Traffic Prediction in Data Centers

Cited by 91 publications

References 24 publications

Elastic neural network method for load prediction in cloud computing grid

Elastic neural network method for load prediction in cloud computing grid

Network Traffic Prediction based on Diffusion Convolutional Recurrent Neural Networks

Kalman Filtering-based Traffic Prediction for Software Defined Intra-data Center Networks

Contact Info

Product

Resources

About