Deep Learning in Mobile and Wireless Networking: A Survey

Zhang, Chaoyun; Patras, Paul; Haddadi, Hamed

doi:10.1109/comst.2019.2904897

Cited by 1,242 publications

(780 citation statements)

References 491 publications

Supporting

Mentioning

777

Contrasting

Unclassified

Order By: Relevance

“…The progress of optimization techniques in the field of artificial intelligence allows deep neural network algorithms to extract information from raw data. Deep neural networks have various layers of nonlinear processing blocks . These networks can learn complex relationships in raw data to predict the next values based on input data.…”

Section: Deep Learning–based Predictions Of Time Seriesmentioning

confidence: 99%

“…Deep neural networks have various layers of nonlinear processing blocks. 11 These networks can learn complex relationships in raw data to predict the next values based on input data. The main advantage of deep learning over machine learning is its ability to extract features automatically, which in turn saves us from designing expensive handcrafted features.…”

Section: Deep Learning-based Predictions Of Time Seriesmentioning

confidence: 99%

“…On the other hand, deep learning demonstrates remarkable performance to solve the problems of wireless communication. 11,12 Deep learning neural networks can learn and predict the unknown values of data at a certain time instant, provided known data values for previous time periods. This learning method always requires prior training on a specific form of data for best prediction results.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep‐DRX: A framework for deep learning–based discontinuous reception in 5G wireless networks

Memon

Maheshwari

Shin

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The tremendous advancement in various types of mobile devices with distinct services demands emerging 5G networks to deal with different kinds of traffic. The high data rates along with beam searching operation in 5G increase user equipment (UE) energy expenses. Discontinuous reception (DRX) is used in long‐term evolution network to save the power of UE. The DRX conserves the energy at the cost of increased latency. On the other hand, long short‐term memory (LSTM), a deep neural network, has shown incredible results in learning time‐varying sequences from data sets. In this article, we propose a novel idea to train LSTM network for prediction of next packet arrival time based on real wireless traffic trace (dataset). Then, we use the trained LSTM model to predict dynamic sleep time in DRX for 5G networks. Our proposed algorithm, deep learning–based DRX (Deep‐DRX) is able to make dynamic sleep cycle in 5G communications. Deep‐DRX achieves 10% and 30% of power saving with a mean delay of 1.006 ms and 1.05 ms for Trace 1 and Trace 2, respectively.

show abstract

Section: Deep Learning–based Predictions Of Time Seriesmentioning

confidence: 99%

Section: Deep Learning-based Predictions Of Time Seriesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep‐DRX: A framework for deep learning–based discontinuous reception in 5G wireless networks

Memon

Maheshwari

Shin

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…ML models enable us to replace heuristics with more robust and general alternatives. In this paper, we propose observing the Wi-Fi AP energy values during LTE-U OFF duration and using the data to train different ML models [14]. We also apply the models in an online experiment to detect the number of Wi-Fi APs.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Enabled Spectrum Sharing in Dense LTE-U/Wi-Fi Coexistence Scenarios

Dziedzic

Sathya

Rochman

et al. 2020

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

1 Abstract-The application of Machine Learning (ML) techniques to complex engineering problems has proved to be an attractive and efficient solution. ML has been successfully applied to several practical tasks like image recognition, automating industrial operations, etc. The promise of ML techniques in solving non-linear problems influenced this work which aims to apply known ML techniques and develop new ones for wireless spectrum sharing between Wi-Fi and LTE in the unlicensed spectrum. In this work, we focus on the LTE-Unlicensed (LTE-U) specification developed by the LTE-U Forum, which uses the duty-cycle approach for fair coexistence. The specification suggests reducing the duty cycle at the LTE-U base-station (BS) when the number of co-channel Wi-Fi basic service sets (BSSs) increases from one to two or more. However, without decoding the Wi-Fi packets, detecting the number of Wi-Fi BSSs operating on the channel in real-time is a challenging problem. In this work, we demonstrate a novel ML-based approach which solves this problem by using energy values observed during the LTE-U OFF duration. It is relatively straightforward to observe only the energy values during the LTE-U BS OFF time compared to decoding the entire Wi-Fi packet, which would require a full Wi-Fi receiver at the LTE-U base-station. We implement and validate the proposed ML-based approach by real-time experiments and demonstrate that there exist distinct patterns between the energy distributions between one and many Wi-Fi AP transmissions. The proposed ML-based approach results in a higher accuracy (close to 99% in all cases) as compared to the existing auto-correlation (AC) and energy detection (ED) approaches.

show abstract

“…Hence, the performance of TLBO algorithm is better than MTLBO and performance of MTLBO algorithm is better than SA. Equation26 gives a mathematical representation of the relationship between number of fog caches and execution time in case of MTLBO. This relationship is derived using curve-fitting technique64,65…”

mentioning

confidence: 99%

Efficient content retrieval in fog zone using Nano‐Caches

Singh

Kumar

Sharma

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary It is always desired to improve the response time from cloud servers, which deliver contents without buffering. As the penetration of mobile/fog devices is increasing, the limits of cellular ranges come under question. This question arises in spite of the fact that the current Internet Service Providers and data operators are adding cellular towers frequently to reduce delay and enhance performance. This performance can be improved by increasing Nano‐Cache(s) at the edges of the network for forwarding interrelated contents to remote corner of the earth. In this research work, Nano‐Caches are integrated for delivering contents efficiently, using search‐based optimization techniques, which are energy and response aware in nature. An algorithm, namely, Modified Teaching Learning‐Based Optimization(MTLBO), is devised and implemented in fog zone to find efficient route for forwarding contents using Nano‐Caches and subsequently to improve content retrieval time. Mathematical distribution model of traffic is used for simulation process. MTLBO is compared with existing algorithms, namely, Teaching Learning‐Based Optimization (TLBO) Algorithm and Simulated Annealing (SA) Algorithm. The design of experiments (DOE) was carried out to observe number of iterations, learning rate, and by changing the network size. Java library was used for observing values of memory and execution time. The results show that Modified Teaching Learning‐Based Optimization (MTLBO) approach is better than Teaching Learning‐Based Optimization (TLBO) approach as it has less overheads in terms of memory (considering number of fog caches) and network size for delivering contents at remote areas. In comparison to the Simulated Annealing (SA) algorithm, MTLBO performs better in terms of execution time, overhead in terms of memory, and scalability as function of network size.

show abstract

Deep Learning in Mobile and Wireless Networking: A Survey

Cited by 1,242 publications

References 491 publications

Deep‐DRX: A framework for deep learning–based discontinuous reception in 5G wireless networks

Deep‐DRX: A framework for deep learning–based discontinuous reception in 5G wireless networks

Machine Learning Enabled Spectrum Sharing in Dense LTE-U/Wi-Fi Coexistence Scenarios

Efficient content retrieval in fog zone using Nano‐Caches

Contact Info

Product

Resources

About