FedGeoSwap++:A Novel Context-Aware and Privacy-Preserving Sensor Substitution Framework for Fault Tolerance in Metaverse-Driven Smart Cities
محورهای موضوعی : Computer Engineering
Seyed Mosarreza Mosavisadr
1
,
Maryam Kheirabadi
2
,
Hossein Monshizadeh Naeen
3
1 - Department of Computer Engineering, Ne.C.,Islamic Azad University,Neyshabur,Iran
2 - Department of Computer Engineering, Ne.C.,Islamic Azad University,Neyshabur,Iran
3 - Department of Computer Engineering, Ne.C., Islamic Azad University, Neyshabur, Iran
کلید واژه: Metaverse, Fault Tolerance, Edge Computing, IoT,
چکیده مقاله :
The integration of the Metaverse with real-time physical data from Internet of Things (IoT) sensors introduces stringent requirements for system reliability and continuity. Sensor failures at the network edge can disrupt immersive experiences due to data loss or inconsistency. To address this challenge, we propose FedGeoSwap++, a novel fault-tolerant framework that combines spatio-temporal indexing, federated learning, transfer learning, and an intelligent Dynamic Resource Adaptation (DRA) agent based on Double Q-Learning to enable intelligent, privacy-preserving sensor substitution in Metaverse applications. FedGeoSwap++ leverages a cloud-based spatio-temporal database with R-tree indexing to identify the geographically closest and data-wise most similar sensor upon failure. A Double Q-Learning agent dynamically adjusts the trade-off between spatial proximity and temporal correlation based on network load and environmental dynamics. Furthermore, a hard correlation threshold (ρ ≥ 0.6) ensures semantic consistency by filtering out spatially close but data-wise dissimilar sensors. We evaluate the framework using a simulated smart city environment with 50 sensors and 100 timesteps over 300 simulation runs. Results show that FedGeoSwap++ achieves a Mean Absolute Error (MAE) of 0.615°C, outperforming Nearest (0.624°C), CorrOnly (0.955°C), MeanImpute (3.029°C), and LSTM-Predict (1.299°C), while maintaining low latency (0.16 ms). Paired t-test confirms the statistical significance of this improvement (p < 0.0001). This work advances fault tolerance in Metaverse systems by ensuring seamless continuity, high accuracy, and robustness under sensor failures.
[1] Y. K. Dwivedi et al., "Metaverse: Understanding the implications for business and society," International Journal of Information Management, vol. 66, p. 102542, 2022. DOI: 10.1016/j.ijinfomgt.2022.102542
[2] S. Shaikh and M. Jammal, "Survey of fault management techniques for edge-enabled distributed metaverse applications," Computer Networks, vol. 254, p. 110803, 2024. DOI: 10.1016/j.comnet.2024.110803.
[3] Q. Yang et al., "Federated Machine Learning: Concept and Applications," ACM TIST, vol. 10, no. 2, pp. 1–19, 2019. DOI: 10.1145/3298981
[4] Y. Zhang et al., "Transfer Learning in Internet of Things: A Survey," IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 885–918, 2021. DOI: 10.1109/COMST.2021.3053817
[5] H. van Hasselt, A. Guez, and D. Silver, "Deep Reinforcement Learning with Double Q-Learning," in Proc. AAAI, vol. 30, no. 1, 2016. DOI: 10.1609/aaai.v30i1.10256.
[6] M. Mudassar et al., "Adaptive fault-tolerant strategy for latency-aware IoT application executing in edge computing environment," IEEE IoT-J, vol. 9, no. 15, pp. 13250–13262, 2022. DOI: 10.1109/JIOT.2022.3143572.
[7] S. Tuli et al., "PreGAN: Predictive task migration," IEEE Trans. Parallel Distrib. Syst., 2023.
[8] K. Ray et al., "Prioritized fault recovery for MEC," IEEE Trans. Dependable Secure Comput., 2023.
[9] Y. Jia et al., "Fault tolerance of stateful microservices," IEEE J. Cloud Comput., 2023.
[10] P. Zhao and G. Dán, "A benders decomposition approach for resilient placement of virtual process control functions in mobile edge clouds," IEEE TNSM, vol. 15, no. 4, pp. 1460–1472, 2018. DOI: 10.1109/TNSM.2018.2867878
[11] R. Siyadatzadeh et al., "ReLIEF: RL-based task assignment," IEEE IoT-J, 2023.
[12] Y. Gao et al., "FIBFT: Fast speculative Byzantine consensus," IEEE Trans. Parallel Distrib. Syst., 2023.
[13] X. Wu et al., "Reja: Secure storage and consistency," IEEE Trans. Dependable Secure Comput., 2023.
[14] Y. Du et al., "CRACAU: False update identification," IEEE Trans. Inf. Forensics Security, 2023.
[15] J. Cheng, D.T. Nguyen, V.K. Bhargava, Resilient edge service placement under demand and node failure uncertainties, IEEE Trans. Netw. Serv. Manag. 21 (1)
(2024) 558–573
[16] H. Taka, F. He, E. Oki, Service placement and user assignment in multi-access edge computing with base-station failure, in: 2022 IEEE/ACM 30th International
Symposium on Quality of Service (IWQoS), 2022, pp. 1–10
[17] Tuli, S., Tuli, S., & Buyya, R. (2023). CAROL: Context-aware resource optimization and learning for edge computing. IEEE Transactions on Cloud Computing, 11(1), 456–468. https://doi.org/10.1109/TCC.2022.3178901
