Resource Allocation in IoT Using Pyramid Quantum Neural Network (Py-QNN): A Deep Learning Approach

Main Article Content

S R K Raju Vegesna, P Lakshmi Sruthi, A Mahalakshmi

Abstract

Internet of Things (IoT) is growing at an accelerated pace where more and more connected smart devices are collecting enormous data. The management of resources is another significant issue because IoT networks are often founded and formed dynamically and are extremely diverse. This paper introduces a new type of deep learning model, the Pyramid Quantum Neural Network (Py-QNN,), that is intended for solving the problem of resource allocation in Internet of Things systems. Py-QNN builds on quantum computing for improving Deep Learning’s computation performance, scalability and accuracy. Pyramid structure helps to control the hierarchy of the IoT networks; additionally, QNNs increase learning abilities due to the existence of superposition and entanglement, which in turn increases the generalization capabilities and ensures faster convergence. In this way, Py-QNN utilizes simulated resource and network requirements to anticipate proficient resource assignment, and implement this quickly to minimize delay and maximize efficiency. Experimental findings reveal that Py-QNN yields better performance over baseline traditional deep learning models especially in large and complex IoT networks by averting resource wastage while offering online solutions.

Article Details

Section
Articles