A Hybrid Quantum-Inspired Deep Reinforcement Learning Framework for Adaptive Scheduling and Energy-Efficient LoRaWAN in Smart IoT Networks

Shaista Tarannum; Usha Shiramally Mallappa

doi:10.48084/etasr.14958

Authors

Shaista Tarannum Department of Electronics and Communication Engineering, JSSATE, Bengaluru, Karnataka, India | Visvesvaraya Technological University, Belagavi, India | Department of Computer Science and Engineering, MSRUAS, Bengaluru, Karnataka, India
Usha Shiramally Mallappa Department of Electronics and Communication Engineering, JSSATE, Bengaluru, Karnataka, India | Visvesvaraya Technological University, Belagavi, India

Volume: 16 | Issue: 3 | Pages: 35143-35153 | June 2026 | https://doi.org/10.48084/etasr.14958

Received: 20 September 2025 | Revised: 31 October 2025 | Accepted: 10 November 2025 | Online: 6 June 2026

Corresponding author: Shaista Tarannum

Abstract

The rapid deployment of Internet-of-Things (IoT) applications in smart city environments has significantly increased the demand for energy-aware and reliable long-range communication solutions. Long-Range Wide-Area Network (LoRaWAN) is one of the most promising IoT technologies and is widely adopted in low-power wide area networks for large-scale deployments. However, LoRaWAN faces scalability issues due to the large number of nodes connected to the same gateway or sharing the same channel. Conventional adaptive data rate and channel allocation strategies often fail to balance scalability, reliability, and energy consumption in highly dynamic LoRaWAN networks. This study, therefore, introduces a quantum-inspired hybrid Double Deep Q-Network (DDQN) and Variational Quantum Circuit (VQC) framework to perform intelligent transmission scheduling and adaptive policy optimization in large-scale LoRaWAN networks. The framework initially leverages a DDQN-based learning agent to select optimal transmission configurations, where it jointly optimizes the spreading factors, channel assignments, and wait actions to reduce energy consumption while maintaining a high Packet Delivery Ratio (PDR). The framework further integrates a quantum-enhanced policy adaptation module that employs a VQC-based decision layer to encode network states into a high-dimensional Hilbert space, enabling improved exploration of the action space and superior adaptation to varying traffic congestion conditions. Comprehensive simulation results show that the proposed hybrid framework outperforms classical Deep Reinforcement Learning (DRL) strategies for adaptive resource scheduling. The results further demonstrate that the hybrid DDQN+VQC achieves up to 28.4% reduction in energy consumption and a 21.7% improvement in PDR under dense IoT deployments. In addition, the proposed hybrid policy positively influences latency performance in LoRaWAN. Overall, the results demonstrate the effectiveness of integrating quantum-inspired policy adaptation with DRL for scalable, energy-efficient, and reliable LoRaWAN optimization.

Keywords:

Double Deep Q-Networks (DDQNs), Variational Quantum Circuit (VQC), LoRaWAN optimization, adaptive transmission scheduling, reliability-aware resource allocation, energy efficiency

References

"Ericsson Mobility Report." Ericsson. https://www.ericsson.com/en/reports-and-papers/mobility-report.

F. Cuomo, M. Campo, A. Caponi, G. Bianchi, G. Rossini, and P. Pisani, "EXPLoRa: Extending the performance of LoRa by suitable spreading factor allocations," in 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, Rome, Italy, 2017, pp. 1–8.

A. Khalifeh, K. A. Aldahdouh, K. A. Darabkh, and W. Al-Sit, "A Survey of 5G Emerging Wireless Technologies Featuring LoRaWAN, Sigfox, NB-IoT and LTE-M," in 2019 International Conference on Wireless Communications Signal Processing and Networking, Chennai, India, 2019, pp. 561–566.

M. A. Gava, H. R. O. Rocha, M. J. Faber, M. E. V. Segatto, H. Wörtche, and J. A. L. Silva, "Optimizing Resources and Increasing the Coverage of Internet-of-Things (IoT) Networks: An Approach Based on LoRaWAN," Sensors, vol. 23, no. 3, Jan. 2023, Art. no. 1239.

K. Lin, M. A. Ullah, H. Alves, K. Mikhaylov, and T. Hao, "Energy Efficiency Optimization for Subterranean LoRaWAN Using a Reinforcement Learning Approach: A Direct-to-Satellite Scenario," IEEE Wireless Communications Letters, vol. 13, no. 2, pp. 308–312, Feb. 2024.

V. Balyan, "Priority-based resource allocation in layering LoRaWAN," International Journal on Smart Sensing and Intelligent Systems, vol. 17, no. 1, Nov. 2024, Art. no. 34.

G. Park, W. Lee, and I. Joe, "Network resource optimization with reinforcement learning for low power wide area networks," EURASIP Journal on Wireless Communications and Networking, vol. 2020, no. 1, Sept. 2020, Art. no. 176.

E. I. Shayo, A. T. Abdalla, and A. J. Mwambela, "Dynamic multi-frame multi-spreading factor scheduling algorithm for LoRaWAN," Journal of Electrical Systems and Information Technology, vol. 10, no. 1, Feb. 2023, Art. no. 11.

P. Maurya, A. Hazra, P. Kumari, T. B. Sørensen, and S. K. Das, "A Comprehensive Survey of Data-Driven Solutions for LoRaWAN: Challenges and Future Directions," ACM Transactions on Internet of Things, vol. 6, no. 1, Feb. 2025, Art. no. 6.

M. Chen, L. Mokdad, J. Ben-Othman, and J.-M. Fourneau, "Dynamic Parameter Allocation With Reinforcement Learning for LoRaWAN," IEEE Internet of Things Journal, vol. 10, no. 12, pp. 10250–10265, June 2023.

S. Madhavan, R. Riad Al-Fatlawy, MD. Mujahid Irfan, K. Neeraj, and R. Dineshkumar, "Improving LoRa Low-Power Wide-Area Networks with Double Deep-Q Learning-Based Resource Allocation," in 2024 Third International Conference on Distributed Computing and Electrical Circuits and Electronics, Ballari, India, 2024, pp. 1–5.

A. Núñez and E. María, "Parametrized Quantum Circuits for Reinforcement Learning," Ph.D. dissertation, Universidad de Granada, Granada, Spain, 2024.

M. Cerezo et al., "Variational quantum algorithms," Nature Reviews Physics, vol. 3, no. 9, pp. 625–644, Sept. 2021.

Z. Yan, R. Tanikella, and H. Tabassum, "Optimizing Vehicular Networks with Variational Quantum Circuits-Based Reinforcement Learning," in IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops, Vancouver, Canada, 2024, pp. 1–2.

K. Zhang, C. K. M. Lee, Y. P. Tsang, and C. H. Wu, "Variational Quantum Reinforcement Learning for Joint Resource Allocation of Blockchain-Based Vehicular Edge Computing and Quantum Internet," IEEE Transactions on Vehicular Technology, vol. 74, no. 10, pp. 15831–15847, Oct. 2025.

S. Gao, Y. Zou, and L. Feng, "A Lightweight Double-Deep Q-Network for Energy Efficiency Optimization of Industrial IoT Devices in Thermal Power Plants," Electronics, vol. 14, no. 13, June 2025, Art. no. 2569.

S. Parween and S. Z. Hussain, "Efficient collision control and auction-based resource allocation mechanism in dense LoRaWAN network via TCP using DRL technique," International Journal of Information Technology, vol. 16, no. 7, pp. 4039–4057, Oct. 2024.

A. Tellache, A. Mekrache, A. Bradai, R. Boussaha, and Y. Pousset, "Deep Reinforcement Learning based Resource Allocation in Dense Sliced LoRaWAN Networks," in 2022 IEEE International Conference on Consumer Electronics, Las Vegas, NV, USA, 2022, pp. 1–6.

G. Zhao, K. Lin, D. Chapman, N. Metje, and T. Hao, "Optimizing energy efficiency of LoRaWAN-based wireless underground sensor networks: A multi-agent reinforcement learning approach," Internet of Things, vol. 22, July 2023, Art. no. 100776.

A. Li, "Deep Reinforcement Learning Based Resource Allocation for LoRaWAN," in 2022 IEEE 96th Vehicular Technology Conference, London, UK, 2022, pp. 1–4.

J. Mhatre, M. Nguyen, A. Lee, and H. Lee, "Experimental Analysis of LoRaWAN for Optimizing Water Quality Monitoring with Reinforcement Learning-Driven Scheduling," in 2024 IEEE International Performance, Computing, and Communications Conference, Orlando, FL, USA, 2024, pp. 1–6.

J. Mhatre, A. Lee, and H. Lee, "Frequency Hopping Scheduling Algorithm in Green LoRaWAN: Reinforcement Learning Approach," in 2023 IEEE Conference on Standards for Communications and Networking, Munich, Germany, 2023, pp. 216–221.

M. Catak and B. Celikkaya, "Limits of Number of Motes at Smart City Scenarios for LoRaWAN," Engineering, Technology & Applied Science Research, vol. 9, no. 3, pp. 4116–4119, June 2019.