An Energy Efficient Network Slicing with Data Aggregation Technique for Wireless Sensor Networks

Wireless Sensor Network (WSNs) is considered as a vital part in the design of Internet of Things (IoT). Network slicing and data aggregation problems are considered as the major sissues in the design of WSN. The main aim of the study is to improve the network efficiency with the presence of restricted resources. In this way, this paper aims to design an energy-efficient deep learning-based network slicing with data aggregation (EENS-DA) technique which allocates the needed physical resources to the specific application clearly and efficiently. Besides, the EENS-DA model uses convolutional long short term memory (Conv-LSTM) based network slicing and tree-based data aggregation techniques. The EENS-DA technique improves the effectiveness of data slicing, improves the accuracy, and sustain privacy preservation in the network. The outcome of the EENS-DA model is compared to the existing techniques interms of distinct measure. The comparison results reveals that the solutions obtained by the EENS-DA model is better than the other models.