Search

Copyright © 2022 The Author(s). 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%. 10.13039/501100007914-Brunel University London, U.K.

© Copyright 2021, The Author(s). An Intelligent Internet of Things network based on an Artificial Intelligent System, can substantially control and reduce the congestion effects in the network. In this paper, an artificial intelligent system is proposed for eliminating the congestion effects in traffic load in an Intelligent Internet of Things network based on a deep learning Convolutional Recurrent Neural Network with a modified Element-wise Attention Gate. The invisible layer of the modified Element-wise Attention Gate structure has self-feedback to increase its long short-term memory. The artificial intelligent system is implemented for next step ahead traffic estimation and clustering the network. In the proposed architecture, each sensing node is adaptive and able to change its affiliation with other clusters based on a deep learning modified Element-wise Attention Gate. The modified Element-wise Attention Gate has the ability to handle the buffer capacity in all the network, thereby enriching the Quality of Service. A deep learning modified training algorithm is proposed to learn the artificial intelligent system allowing the neurons to have greater concentration ability. The simulation results demonstrate that the Root Mean Square error is minimized by 37.14% when using modified Element-wise Attention Gate when compared with a Deep Learning Recurrent Neural Network. Also, the Quality of Service of the network is improved, for example, the network lifetime is enhanced by 12.7% more than with Deep Learning Recurrent Neural Network.

The utilization of conventional modeling strategies in the identification and control of a nonlinear dynamical system suffers from some weaknesses. These include absence of precise, conventional knowledge about the system, a high degree of uncertainty, strongly nonlinear and time-varying behavior. In this paper, a modified training algorithm for the identification and control of a nonlinear system using a soft-computing approach is proposed. Specifically, a modified structure of the Elman neural network with spike neural networks is proposed. This modified structure includes self-feedback, which provides a dynamic trace of the training algorithm. This self-feedback has weights, which can be trained during the training process. The simulation results show that the modified structure with the modified training algorithm is capable of the identification and control of a dynamic system in a more robust manor than when solely applying the other types of neural networks by 70% in terms of minimization of the percentage of error.

An intelligent software defined network (ISDN) based on an intelligent controller can manage and control the network in a remarkable way. In this article, a methodology is proposed to estimate the packet flow at the sensing plane in the software defined network-Internet of Things based on a partial recurrent spike neural network (PRSNN) congestion controller, to predict the next step ahead of packet flow and thus, reduce the congestion that may occur. That is, the proposed model (spike ISDN-IoT) is enhanced with a congestion controller. This controller works as a proactive controller in the proposed model. In addition, we propose another intelligent clustering controller based on an artificial neural network, which operates as a reactive controller, to manage the clustering in the sensing area of the spike ISDN-IoT. Hence, an intelligent queuing model is introduced to manage the flow table buffer capacity of the spike ISDN-IoT network, such that the quality of service (QoS) of the whole network is improved. A modified training algorithm is introduced to train the PRSNN to adjust its weight and threshold. The simulation results demonstrate that the QoS is improved by (14.36%) when using the proposed model as compared with a convolutional neural network.