Abstract

The speedy evolution of IoT ecosystems has produced major challenges in resource allocation, with a focus on scalability, energy efficiency, and making decisions effectively in real time. This research documents the integration of the Pyramid Quantum Neural Network (Py-QNN) with Deep Learning Long Short-Term Memory (DLSTM) to solve these challenges. Py-QNN makes use of quantum computing's superposition and entanglement to boost computational speed and simultaneously cut energy usage. About CNNs, RNNs, and hybrid models, Py-QNN offers better performance each time. It delivers reductions in latency ranging from 30-50%, energy consumption decreases of 60-70%, and up to 25% improvement in throughput across several iterations. The results suggest that Py-QNN has the potential to greatly improve resource allocation in vast IoT networks, while continuing to provide real-time responsiveness and scalability.