Deep Learning-Based Forecasting of Cellular Network Utilization at Millisecond Resolutions

Nagib, Ahmad M.; Abou-zeid, Hatem; Hassanein, Hossam S.; Sediq, Akram Bin; Boudreau, Gary

doi:10.1109/icc42927.2021.9500858

Cited by 10 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the wide coverage of deep neural network, it has been used for deep learning and has achieved great success in a series of prediction problems in the past decade, such as intelligent transportation system [ 26 ] , urban traffic prediction [ 36 ] and cellular network prediction [ 45 ] . In addition, there are Generative Adversarial Network (GAN) [ 28 ] , Deep Neural Network (DNN) [ 36 ] , Attention‐based Periodic‐Temporal neural Network (APTN) [ 37 ] , Multi‐Stage Attention Spatial‐Temporal Graph Networks (MASTGN) [ 39 ] , Neural Architecture Search (NAS) [ 46 ] .…”

Section: User Demand and Traffic Modelingmentioning

confidence: 99%

“…3) Deep learning models The main advantages of deep learning model include high precision prediction performance and high scalability. The deep learning models used in the study include convolutional neural network (CNN) [21][22][23][24] , graph convolutional network (GCN) [25][26][27][28][29][30][31][32] , long short-term memory (LSTM) [33][34][35][36][37][38][39][40][41][42][43][44][45] . The GCN model is expressed as…”

Section: Traffic Modelsmentioning

confidence: 99%

“…The main advantages of deep learning model include high precision prediction performance and high scalability. The deep learning models used in the study include convolutional neural network (CNN) [ 21–24 ] , graph convolutional network (GCN) [ 25–32 ] , long short‐term memory (LSTM) [ 33–45 ] . The GCN model is expressed as

\begin{matrix} right left right left right left right left right left right left3pt0.2777777777777778em 2em 0.2777777777777778em 2em 0.2777777777777778em 2em 0.2777777777777778em 2em 0.2777777777777778em 2em 0.2777777777777778em \\ f (H^{(l)}, A) = σ ({\hat{D}}^{- \frac{1}{2}} \overset{falseˆ}{A} {\hat{D}}^{- \frac{1}{2}} H^{(l)} W^{(l)}) \end{matrix}

where input layer is

H (0) = X

, output layer is

H (L) = Z

, and

L

is the number of layers.…”

Section: User Demand and Traffic Modelingmentioning

confidence: 99%

See 2 more Smart Citations

Real‐World Wireless Network Modeling and Optimization: From Model/Data‐Driven Perspective

Yang

Zhang

Ren

et al. 2022

Chinese J of Electronics

View full text Add to dashboard Cite

With the rapid development of the fifthgeneration wireless communication systems, a profound revolution in terms of transmission capacity, energy efficiency, reliability, latency, and connectivity is highly expected to support a new batch of industries and applications. To achieve this goal, wireless networks are becoming extremely dynamic, heterogeneous, and complex. The modeling and optimization for the performance of realworld wireless networks are extremely challenging due to the difficulty to predict the network performance as a function of network parameters, and the prohibitively huge number of parameters to optimize. The conventional network modeling and optimization approaches rely on drive test, trial‐and‐error, and engineering experience, which are labor intensive, error‐prone, and far from optimal. On the other hand, while the research community has spent significant efforts in understanding the fundamental limits of radio channels and developing physical layer techniques to operate close to it, very little is known about the performance limits of wireless networks, where millions of radio channels interact with one another in complex manners. This paper reviews the very recent mathematical and learning based techniques for modeling and optimizing the performance of real‐world wireless networks in five aspects, including channel modeling, user demand and traffic modeling, throughput modeling and prediction, network parameter optimization, and IRS empowered performance optimization, and also presents the corresponding notable performance gains.

show abstract