Highly Accurate and Reliable Wireless Network Slicing in 5th Generation Networks: A Hybrid Deep Learning Approach

Khan, Sulaiman; Khan, Suleman; Ali, Yasir; Khalid, Muhammad Irfan; Ullah, Zahid; Mumtaz, Shahid

doi:10.1007/s10922-021-09636-2

Cited by 24 publications

(6 citation statements)

References 30 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN supports accurate slice assignment to both known and unknown devices and copes with slice failure. LSTM is used to predict slice requests, the workload of the network and the probable slice failure [100]. Simulation on NS2 validates the performance of the proposed model.…”

mentioning

confidence: 85%

Deep Learning in the Ubiquitous Human–Computer Interactive 6G Era: Applications, Principles and Prospects

et al. 2023

View full text Add to dashboard Cite

With the rapid development of enabling technologies like VR and AR, we human beings are on the threshold of the ubiquitous human-centric intelligence era. 6G is believed to be an indispensable cornerstone for efficient interaction between humans and computers in this promising vision. 6G is supposed to boost many human-centric applications due to its unprecedented performance improvements compared to 5G and before. However, challenges are still to be addressed, including but not limited to the following six aspects: Terahertz and millimeter-wave communication, low latency and high reliability, energy efficiency, security, efficient edge computing and heterogeneity of services. It is a daunting job to fit traditional analytical methods into these problems due to the complex architecture and highly dynamic features of ubiquitous interactive 6G systems. Fortunately, deep learning can circumvent the interpretability issue and train tremendous neural network parameters, which build mapping relationships from neural network input (status and specific requirements of a 6G application) to neural network output (settings to satisfy the requirements). Deep learning methods can be an efficient alternative to traditional analytical methods or even conquer unresolvable predicaments of analytical methods. We review representative deep learning solutions to the aforementioned six aspects separately and focus on the principles of fitting a deep learning method into specific 6G issues. Based on this review, our main contributions are highlighted as follows. (i) We investigate the representative works in a systematic view and find out some important issues like the vital role of deep reinforcement learning in the 6G context. (ii) We point out solutions to the lack of training data in 6G communication context. (iii) We reveal the relationship between traditional analytical methods and deep learning, in terms of 6G applications. (iv) We identify some frequently used efficient techniques in deep-learning-based 6G solutions. Finally, we point out open problems and future directions.

show abstract

mentioning

confidence: 85%

Deep Learning in the Ubiquitous Human–Computer Interactive 6G Era: Applications, Principles and Prospects

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For achieving optimum resource utilization and traffic control, the researchers proposed sliced-based solutions for different research problems such as Khan et al (2021b); Khan et al (2022) suggested a sliced design for network communication systems to efficiently control the congestion and network traffic. They proposed a convolution neural network (CNN) for classification purposes, while LSTM and SVM for statistical analysis.…”

Section: Related Workmentioning

confidence: 99%

Efficient Power Grid Management Using Sliced-Based Mechanism for Systematic Allocation of Solar Energy Resources: A Conceptual Framework

Khan

Nazir

2022

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

The over-population and the limited energy resources have puzzled the government and private organizations to think about the providence of non-stop energy resources to the industries, hospitals, smart homes, and shopping malls to ensure normal routine activities. To accept this challenge, some researchers put their efforts into generating energy from renewable energy resources (solar, fossil fuels, wind turbines, geothermal energy, and many others) to fulfill the needs of life. While some researchers worked on the efficient utilization of the available energy resources to save the energy for future generations. Inspiring from the second approach, this research work has proposed a systematic allocation of energy resources using the slice-based mechanism in a smart grid environment. This research framework using a hybrid model comprises long short-term memory (LSTM), and a support vector machine (SVM), where the LSTM classifies different energy requests (for allocation of energy resources) while the SVM accomplishes the statistical analysis (to estimate the number of solar energy resources allocated and for a specific interval of time). This need-based allocation of energy resources will not only assist in saving energy resources for future use, but will also improve the life of the power grid and other electric appliances (due to over-usage and burning). The applicability of this model is validated by testing it on a real-time scenario like slice failure conditions, slice overflow conditions, a huge number of requests, and alternate slice allocation conditions. Furthermore, the incoming request classification is also validated based on its accurate identification using a confusion matrix, varying number of hidden layers, accuracy, and time consumption. The outperformance of the selected based on these scenarios and validation metrics reflects the applicability of this framework. Moreover, this framework will assist in reducing overbilling charges and energy savage for future generations due to its need-based allocation of energy resources assignment capabilities.

show abstract

“…allocation mechanism [1]. Network slicing refers to selecting 7 appropriate slices for the specific traffic type to provide 8 better-performing and cost-efficient services.…”

Section: Introductionmentioning

confidence: 99%

Moderately Multispike Return Neural Network for SDN Accurate Traffic Awareness in Effective 5G Network Slicing

2022

View full text Add to dashboard Cite

Due to the huge variety of 5G services, Network slicing is promising mechanism for dividing the physical network resources in to multiple logical network slices according to the requirements of each user. Highly accurate and fast traffic classification algorithm is required to ensure better Quality of Service (QoS) and effective network slicing. Fine-grained resource allocation can be realized by Software Defined Networking (SDN) with centralized controlling of network resources. However, the relevant research activities have concentrated on the deep learning systems which consume enormous computation and storage requirements of SDN controller that results in limitations of speed and accuracy of traffic classification mechanism. To fill this gap, this paper proposes intelligent SDN Multi Spike Neural System (IMSNS) by implementing Moderately Multi-Spike Return Neural Networks (MMSRNN) controller with time based coding achieving remarkable reduction on energy consumption and accurate traffic identification to predict the most appropriate network slice. In addition, this paper proposes another intelligent Recurrent Neural Network (RNN) controller for load balancing and slice failure condition. The current researchers have adopted the: accuracy, precision, recall and F1-Score, the simulation results revealed that the proposed model could provide the accurate 5G network slicing as compared with a convolutional neural network (CNN) by 5%.INDEX TERMS Slicing; 5G; Return Neural Networks ; Intelligent Multi spike neural network.

show abstract

Highly Accurate and Reliable Wireless Network Slicing in 5th Generation Networks: A Hybrid Deep Learning Approach

Cited by 24 publications

References 30 publications

Deep Learning in the Ubiquitous Human–Computer Interactive 6G Era: Applications, Principles and Prospects

Deep Learning in the Ubiquitous Human–Computer Interactive 6G Era: Applications, Principles and Prospects

Efficient Power Grid Management Using Sliced-Based Mechanism for Systematic Allocation of Solar Energy Resources: A Conceptual Framework

Moderately Multispike Return Neural Network for SDN Accurate Traffic Awareness in Effective 5G Network Slicing

Contact Info

Product

Resources

About