Summary Software Defined‐DCN (SD‐DCN) is a layered topology with logically centralized control which provides intelligence thro‐ugh programmability. The controller in SD‐DCN provides different network management skills by decoupling of control plane and data plane. However, the controller applies traditional artificial intelligence approaches and neural network approaches for routing strategies in recent systems. To manage dynamic changes in the network, deep learning approaches provide deep analysis and prediction to enhance the existing network performance. In convolutional neural network (CNN) deep learning model, the learning process executes based on present traffic data and forgets the inputs for the future learning phase. To overcome CNN limitation, in this article, different recurrent neural network (RNN) deep learning models are used to improve the routing computation for SD‐DCN topology. The long short‐term memory (LSTM)‐ RNN and bi‐directional long short‐term memory (BiLSTM)‐RNN deep learning models provide forget gate to analyze periodic network traffic datasets and improve routing by delivering dynamic and intelligent routing paths in the network. The proposed system is implemented in a simulation scenario, and the proposed work improves the network performance in hot‐spot traffic as compared to the existing mechanisms. Moreover, error analysis of different deep learning models is presented in the evaluation results.

The 5G ultra-dense small cell network plays a key role in the future generation of mobile networks. It provides high data rate, seamless coverage and reliable services for wireless communication in an ultra-dense network. The dense deployment of small cells is needed to control forthcoming traffic demands which leads to enhance the operational cost and reduces the energy efficiency. One way to improve the energy efficiency is by using the sleeping strategy of small cell by transferring the traffic load of a small cell to other small cells. This work proposes an Initial Connection algorithm for establishing an initial association between the UEs and small base stations (s-BSs) while considering the UE preference. The Initial Connection algorithm creates a connected network. Moreover, the proposed Load Sharing Based Sleep Approach (LSBSA) algorithm performs small cells sleeping on the connected network which results in the deployment of s-BSs. The proposed Initial Connection and LSBSA algorithms are implemented and evaluated in MATLAB for different mobile data traffic. Also, various UEs distribution scenarios are considered. The results are demonstrated that the proposed approaches improve network performance in terms of energy efficiency of the small cell network by deploying the optimal number of active s-BSs.

5G will require a number of Key Technological Components to meet its very ambitious goals, including Heterogeneous Networks a nd Small Cells. The Dense Deployme nt of Small Cell Base Stations (SBSs) will play a major role as they can be installed in a more targeted manner to relieve traffic in hot spot areas, increase coverage, and spectral efficiency. However, the current deployment of the SBS is static (examples include Femto, Pico, and Nano cells), normally deployed on demand around hotspots. In the scenario of unpredictable crowd movement, these static deployment of small cell can be inefficient with high CAPEX and OPEX. This paper focuses on the scenario where UE-based Virtual Small Cell Base Stations (UE-VBSs) can be dynamically selected among UEs to deal effectively with the non-stationary, non-uniform distribution of mobile traffic with respect to time and space domain. To implement this concept, we propose an efficient clustering technique (Affinity Propagation Clustering) to select the best set of UE-VBSs to supplement an overlay loaded SBS. Simulative evaluation highlights salient features of the technique, as well as its limitations with regard to scalability. Further, we discuss the modification of the algorithm according to our objec tive sc enario focusing on red ucing the message passing procedure to and from only a number of eligible UE-VBSs using the power received by a UE from the eligible UE-VBSs as a parameter. The algorithm is implemented and evaluated in MATLAB and, also validated using NS3 simulator.

The IEEE 802.11 standard for wireless local area networks defines a power management algorithm for Independent Basic Service Set (IBSS) allowing it to save critical battery energy in low powered wireless devices. The power management algorithm for IBSS uses beacon intervals (BIs) as the time unit, where every BI consists of an Announcement Traffic Indication Message (ATIM) window and a data window. The stations that have data to send need to go through a handshaking procedure in the ATIM window. If this handshaking is successful, the station remains awake in the data window and participates in the data communication. Otherwise, it goes into the sleep mode. This paper presents an analytical model to compute the throughput, expected delay and expected power consumption in an IEEE 802.11 IBSS in power save mode (PSM) for different traffic conditions in the network. The impact of data arrival rate, network size, and size of the BI on the performance of the IEEE 802.11 DCF in PSM is also analyzed. This analysis reveals a clear trade-off among throughput, delay, and average power consumption. The trade-off analysis is useful for designing efficient power consumption algorithms while maintaining the consistence performance of the network in terms of throughput and delay.

The service selection for automatic dynamic service composition with client's requirements oriented service selection becomes more intense. The existing planning and selection algorithms are mostly designed for service discovery. Further, to our knowledge, there are only a few works that incorporate end-user requirements into service composition. In this paper, we propose a graph based multi-grain clustering and selection model for service composition.