Work

Quantum enabled cloud IOT collaboration for ultra low latency data processing in cyber physical systems

Year: 2026

Type: article

Abstract: Cyber-Physical Systems (CPS) are evolving in a new era of intelligent infrastructures that combine sensing and computing. However, as quantum computing and ultra-dense IoT networks tends to get expanded, traditional encrypting data and optimizing systems are insufficient to secure the data in real time. Artificial Intelligence (AI) with post-quantum cryptography and edge intelligence transforms CPS into self-adaptive ecosystems that is capable of handling threats. However, the modern systems struggle with latency management and high computational complexity that occur after quantum computing. Hence, this paper research develops an AI-Driven Quantum-Resilient Cyber-Physical System (AI-QRCPS) framework that combines three novel layers and this includes: (i) a Post-Quantum Security Layer employing lattice-based cryptography and quantum key distribution for end-to-end confidentiality, (ii) an Adaptive Intelligence Layer using Reinforcement Learning (RL) and Firefly Optimization for dynamic resource orchestration and anomaly detection, and (iii) an IoT-Edge Coordination Layer for latency-aware task scheduling using double deep Q-learning. Experimental evaluation shows that the proposed framework achieves an average latency as low as 7.9–10.7 ms, throughput up to 94.5 tasks/s, energy consumption as low as 3.3–4.8 J/task, and task completion rates exceeding 98% across varying edge/IoT node densities and bandwidths. The research designs a unified AI-driven quantum-resilient Cyber-Physical System (AI-QRCPS) framework. The results show an enhanced edge-IoT data transfer efficiency and intelligent load balancing, which gets maximized with relevance to the number of tasks processed per second under high-bandwidth conditions. The results show that the proposed framework is a flexible to build next-generation CPS networks.

Source: Discover Internet of Things

DOI: 10.1007/s43926-026-00316-8

Authors: S. Nalini, Syed Mohd. Saqib, Md. Mazharunnisa, Shailesh P. Bendale, Faiz Akram, P. Murugan