Small cell is a key enabler for massive connectivity and higher data rate in the future generation of a cellular communication system. Few challenges in heterogeneous networks (HetNets) are effective resource utilization and de- ployment of optimal small base stations (SBSs) under dynamic mobile traffic patterns. In this paper, we design a traffic adaptive small cell planning (TASCP) schema to minimize the deployment of SBSs, enhancing the network energy efficiency without compromising the user equipment’s QoS (UEs). The proposed TASCP consists of two phases: small cell formation (SCF) and small Cell optimization (SCO). SCF creates the initial association between the UEs and SBS. The SCF operates the modes (active/sleep) of SBSs according to the dynamic traffic load. Changing the mode of SBS from an active mode to a sleep mode is based on the traffic load shared by other neighboring SBSs, cooperatively. The proposed TASCP method is compared with state-of-the-art algorithms, i.e., the Self-organized SBS Deployment Strategy (SSDS) and UE Association and SBS On/Off (USOF) algorithm. The network performance is calculated in terms of network energy efficiency, throughput, convergence time, and active small base stations. The performance of the proposed TASCP significantly increases as compared to state-of-the-art algorithms.

In recent Artificial Intelligence developments, large datasets as knowledge are a prime requirement for analysis and prediction. To manage the knowledge of the network, the Data Center Network (DCN) has been considered a global data storage facility on edge servers and cloud servers. In recent research trends, knowledge-defined networking (KDN) architecture is considered, where the management plane works as the knowledge plane. The major network management task in the DCN is to control traffic congestion. To improve network management, i.e., optimized resource management, enhanced Quality of Service (QoS), we propose a path prediction technique by combining the convolution layer with the RNN deep learning model, i.e., Convolution-Long short-term memory network as Convolution-LSTM and the bi-directional long short-term memory (BiLSTM) network as Convolution-BiLSTM. The experimental results demonstrate that, in terms of many metrics, i.e., network latency, packet loss ratio, network throughput, and overhead, our proposed methodologies perform better than the existing works, i.e., OSPF, FlowDCN, modified discrete PSO, ANN, CNN, and LSTM-based routing approaches. The proposed approach improves the network throughput by approximately 30% and 12% as compared to existing CNN and LSTM-based routing approaches, respectively.