Global forward-predicting dynamic routing for traffic concurrency space stereo multi-layer scale-free network

This paper proposed a novel routing strategy with two tunable parameters, [Formula: see text], [Formula: see text], based on the dynamic local information in a finite buffer network. The system behaves differently from that with a local routing strategy based on the degree with an adjustable parameter [Formula: see text]. Simulations show that, under dynamic local strategy, the maximal capacity of the network system increases with [Formula: see text] whereas it increases with the decrement of [Formula: see text] in the case of all the nodes having identical delivering ability. The dynamic local routing performs much better than the local routing, which is demonstrated by a larger value of the critical packet generation rate. We found that buffer coefficient has a limited impact on the performance of network system. We also demonstrate that a smaller [Formula: see text] would be better if we want to have an excellent traffic capacity considering the travel time, average path length and waiting time. Our study will be helpful to improve traffic performance in finite buffer networks.

show abstract

An Intelligent Network Traffic Prediction Scheme Based on Ensemble Learning of Multi-Layer Perceptron in Complex Networks

Wang

Cao

Wen

et al. 2023

Electronics

View full text Add to dashboard Cite

At present, the amount of network equipment, servers, and network traffic is increasing exponentially, and the way in which operators allocate and efficiently utilize network resources has attracted considerable attention from traffic forecasting researchers. However, with the advent of the 5G era, network traffic has also shown explosive growth, and network complexity has increased dramatically. Accurately predicting network traffic has become a pressing issue that must be addressed. In this paper, a multilayer perceptron ensemble learning method based on convolutional neural networks (CNN) and gated recurrent units (GRU) spatiotemporal feature extraction (MECG) is proposed for network traffic prediction. First, we extract spatial and temporal features of the data by convolutional neural networks (CNN) and recurrent neural networks (RNN). Then, the extracted temporal features and spatial features are fused into new spatiotemporal features through integrated learning of a multilayer perceptron, and a spatiotemporal prediction model is built in the sequence-to-sequence framework. At the same time, the teacher forcing mechanism and attention mechanism are added to improve the accuracy and convergence speed of the model. Finally, the proposed method is compared with other deep learning models for experiments. The experimental results show that the proposed method not only has apparent advantages in accuracy but also shows some superiority in time training cost.

show abstract

Global forward-predicting dynamic routing for traffic concurrency space stereo multi-layer scale-free network

Cited by 3 publications

References 33 publications

Global Dynamic One-Step-Prediction Resource Allocation Strategy for Space Stereo Multi-layer Data Asymmetric Scale-Free Network

Global Dynamic One-Step-Prediction Resource Allocation Strategy for Space Stereo Multi-layer Data Asymmetric Scale-Free Network

Traffic dynamics based on dynamic local routing protocol in a finite buffer network

An Intelligent Network Traffic Prediction Scheme Based on Ensemble Learning of Multi-Layer Perceptron in Complex Networks

Contact Info

Product

Resources

About