Big Data Analytics for Large-scale Wireless Networks

Dai, Hong-Ning; Wong, Raymond Chi-Wing; Wang, Hao; Zheng, Zibin; Vasilakos, Athanasios V.

doi:10.1145/3337065

Cited by 115 publications

(60 citation statements)

References 240 publications

(242 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21], it is highlighted that ITS faces significant challenges for designing and operating the enhanced global supply chain, such as, real-time data-based control, eventually affecting the resiliency and risk. The rising significance of wireless vehicular networks indeed related to the growth and acceptance of mobile wireless communications, in which through progresses in wireless channel modelling methods and the succeeding progress of complex digital transmission approaches, providing high data rate communications is possible while following the severe QoS requirements [22], [23]. According to [24], this is imperative and data overload is experienced by modern companies due to utilizing numerous disparate innovative technologies pursuing a unified functioning picture for situational awareness.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Resource Allocation Model for Distribution Operations Using SDN

Goudarzi

Anisi

Ahmadi

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

In vehicular ad-hoc networks, autonomous vehicles generate a large amount of data prior to support in-vehicle applications. So, a big storage and high computation platform is needed. On the other hand, the computation for vehicular networks at the cloud platform requires low latency. Applying edge computation (EC) as a new computing paradigm has potentials to provide computation services while reducing the latency and improving the total utility. We propose a three-tier EC framework to set the elastic calculating processing capacity and dynamic route calculation to suitable edge servers for real-time vehicle monitoring. This framework includes the cloud computation layer, EC layer, and device layer. The formulation of resource allocation approach is similar to an optimization problem. We design a new reinforcement learning (RL) algorithm to deal with resource allocation problem assisted by cloud computation. By integration of EC and software defined networking (SDN), this study provides a new software defined networking edge (SDNE) framework for resource assignment in vehicular networks. The novelty of this work is to design a multi-agent RL-based approach using experience reply. The proposed algorithm stores the users' communication information and the network tracks' state in realtime. The results of simulation with various system factors are presented to display the efficiency of the suggested framework. We present results with a real-world case study.

show abstract

Section: Related Workmentioning

confidence: 99%

Dynamic Resource Allocation Model for Distribution Operations Using SDN

Goudarzi

Anisi

Ahmadi

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Ref. [13][14][15][16] adopted the data-driven method for learning a parameterized model from the real system trajectories. This method lessens the difficulty of theoretical analysis and learns from data directly.…”

Section: Data-driven Thickener System Identificationmentioning

confidence: 99%

A Dual-Attention Recurrent Neural Network Method for Deep Cone Thickener Underflow Concentration Prediction

Yuan

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper focuses on the time series prediction problem for underflow concentration of deep cone thickener. It is commonly used in the industrial sedimentation process. In this paper, we introduce a dual attention neural network method to model both spatial and temporal features of the data collected from multiple sensors in the thickener to predict underflow concentration. The concentration is the key factor for future mining process. This model includes encoder and decoder. Their function is to capture spatial and temporal importance separately from input data, and output more accurate prediction. We also consider the domain knowledge in modeling process. Several supplementary constructed features are examined to enhance the final prediction accuracy in addition to the raw data from sensors. To test the feasibility and efficiency of this method, we select an industrial case based on Industrial Internet of Things (IIoT). This Tailings Thickener is from FLSmidth with multiple sensors. The comparative results support this method has favorable prediction accuracy, which is more than 10% lower than other time series prediction models in some common error indices. We also try to interpret our method with additional ablation experiments for different features and attention mechanisms. By employing mean absolute error index to evaluate the models, experimental result reports that enhanced features and dual-attention modules reduce error of fitting ~5% and ~11%, respectively.

show abstract

“…Later, Reference [34] highlights the large impact that BDA may have on cellular network operators, increasing business opportunities. A recent survey of the technical solutions for the different stages of BDA in large-scale wireless networks is presented in Reference [35], identifying stream data processing as an open research area. BDA has also been recognized as a key enabling technology for 5G networks in the context of SON [6,9].…”

Section: Related Workmentioning

confidence: 99%

Complex Event Processing for Self-Optimizing Cellular Networks

de-la-Bandera

Toril

Luna-Ramírez

et al. 2020

Sensors

View full text Add to dashboard Cite

In a cellular network, signaling and data messages exchanged between network elements are an extremely valuable information for network optimization. The consideration of different types of information allows to improve the optimization results. However, the huge amount of information has made it very difficult for operators to process all the available information. To cope with this issue, in this paper, a methodology for processing cell and user connection traces to optimize a live cellular network is presented. The aim is to generate new performance indicators different from those supplied by manufacturers, taking advantage of the ability of complex event processing tools to correlate events of different nature. For illustrative purposes, an example of how a new performance indicator is created from real traces by complex event processing is given.

show abstract

Big Data Analytics for Large-scale Wireless Networks

Cited by 115 publications

References 240 publications

Dynamic Resource Allocation Model for Distribution Operations Using SDN

Dynamic Resource Allocation Model for Distribution Operations Using SDN

A Dual-Attention Recurrent Neural Network Method for Deep Cone Thickener Underflow Concentration Prediction

Complex Event Processing for Self-Optimizing Cellular Networks

Contact Info

Product

Resources

About