Prediction of IoT Traffic Using the Gated Recurrent Unit Neural Network- (GRU-NN-) Based Predictive Model

Patil, Sonali Appasaheb; Raj, L. Arun; Singh, Bhupesh Kumar

doi:10.1155/2021/1425732

Cited by 17 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Introduced by Cho et al [58], GRUs can be seen as a simple version of LSTMs, in the sense they have 2 gates, update and reset, and according to the authors are much simpler to compute and implement. In Patil et al [59], IoT traffic prediction is developed with the use of GRUs, where the results are shown to be more accurate than the ones obtained via ARIMA modeling. In Fu et al [60], GRU and LSTM NN are used to forecast traffic flow in the state of California; similarly to the previous paper, both approaches presented more accurate results than autoregressive moving average models.…”

Section: ) Grumentioning

confidence: 99%

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

et al. 2023

View full text Add to dashboard Cite

This paper presents a review of the literature on network traffic prediction, while also serving as a tutorial to the topic. We examine works based on autoregressive moving average models, like ARMA, ARIMA and SARIMA, as well as works based on Artifical Neural Networks approaches, such as RNN, LSTM, GRU, and CNN. In all cases, we provide a complete and self-contained presentation of the mathematical foundations of each technique, which allows the reader to get a full understanding of the operation of the different proposed methods. Further, we perform numerical experiments based on real data sets, which allows comparing the various approaches directly in terms of fitting quality and computational costs. We make our code publicly available, so that readers can readily access a wide range of forecasting tools, and possibly use them as benchmarks for more advanced solutions.

show abstract

Section: ) Grumentioning

confidence: 99%

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Therefore, this method has a limited effect in optimizing the forwarding strategy of the switches. The authors in [10] use a gated recurrent unit neural network (GRU-NN) to achieve better accuracy in predicting network traffic. The authors in [11,12] propose a routing strategy that employs the convolutional neural networks (CNN) to select routing paths according to the online network traffic.…”

Section: Related Researchmentioning

confidence: 99%

“…In this paper, our optimization objective is to maximize the network carrying capacity and minimize the link-loadbalancing factor φ, as shown in Equation (9). Equation (10) represents the limiting condition for obtaining the optimization objective:…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

“…In recent years, because of its robust learning algorithm and excellent performance, deep learning has been gradually applied to computer networks. Many studies have used supervised learning methods in SDN to realize intelligent network management [8][9][10][11][12][13][14]. However, supervised learning requires a great many datasets for training, and slow decision-making in dynamic network scenarios also poses a problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Chen

Wang

Ou³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Due to the rapid development of network communication technology and the significant increase in network terminal equipment, the application of new network architecture software-defined networking (SDN) combined with reinforcement learning in network traffic scheduling has become an important focus of research. Because of network traffic transmission variability and complexity, the traditional reinforcement-learning algorithms in SDN face problems such as slow convergence rates and unbalanced loads. The problems seriously affect network performance, resulting in network link congestion and the low efficiency of inter-stream bandwidth allocation. This paper proposes an automatic load-balancing architecture based on reinforcement learning (ALBRL) in SDN. In this architecture, we design a load-balancing optimization model in high-load traffic scenarios and adapt the improved Deep Deterministic Policy Gradient (DDPG) algorithm to find a near-optimal path between network hosts. The proposed ALBRL uses the sampling method of updating the experience pool with the SumTree structure to improve the random extraction strategy of the empirical-playback mechanism in DDPG. It extracts a more meaningful experience for network updating with greater probability, which can effectively improve the convergence rate. The experiment results show that the proposed ALBRL has a faster training speed than existing reinforcement-learning algorithms and significantly improves network throughput.

show abstract

“…Consequently, the application's behavior toward the user has improved, allowing the user to better comprehend and make decisions under high-stress situations [48] . In [49] prediction of IoT traffic has attracted the researchers for the better use of bandwidth. Internet of things [50] suggested the methods for digital information access for better use of time and space complexity.…”

Section: Related Workmentioning

confidence: 99%

A Novel Blockchain Based Secured and QoS Aware IoT Vehicular Network in Edge Cloud Computing

et al. 2022

View full text Add to dashboard Cite

A software-defined vehicular network is made up of an IoT (Internet of Things) based vehicular ad-hoc network and a software-defined network. For better communication in IoT based vehicle networks, researchers are now working on the VANET (Vehicular Ad-hoc Network) to increase the overall system performance. To maximize the VANET ad-hoc network's information application performance and reliability, edge computing has gained the attention of researchers. In current research, cloud computing is used for message related task execution, which increases the response time. We propose a Software-defined Fault Tolerance and QoS-Aware (Quality of Service) IoT-Based Vehicular Networks Using Edge Computing Secured by Blockchain to reduce overall communication delay, message failure fault tolerance, and secure service provisioning for VANET ad-hoc networks in this article. We proposed heuristic algorithms to solve the above mentioned problems of response delay, message failure, fault tolerance, and security provided by the Blockchain. The proposed model gets vehicle messages through SDN (Software defined network) nodes, which are placed on nearby edge servers, and the edge servers are validated by the blockchain to provide secure services to vehicles. The SDN controller, which exists on an edge server, which is placed on the road side to overcome communication delays, receives different messages from the vehicles and divides these messages in to two different categories. The message division is performed by the edge server by judging the time line, size, and emergency situation. SDN controller organized these messages and forwarded them to their destination. After the message is delivered to its destination, a fault tolerance mechanism checks their acknowledgements. If the message delivery fails, the fault tolerance algorithm will resend the failure message. The proposed model is implemented using a custom simulator and compared with the latest VANET based QoS and fault tolerance models. The result shows the performance of the proposed model, which decreased the overall message communication delay by 55% of the normal and emergency messages by using the edge server SDN controller. Furthermore, the proposed model reduces the execution time, security risk, and message failure ratio by using the edge server, cloud server and blockchain infrastructure.

show abstract

Prediction of IoT Traffic Using the Gated Recurrent Unit Neural Network- (GRU-NN-) Based Predictive Model

Cited by 17 publications

References 21 publications

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

A Novel Blockchain Based Secured and QoS Aware IoT Vehicular Network in Edge Cloud Computing

Contact Info

Product

Resources

About