@article{Tightiz2026, 
author = {Lilia Tightiz and L. Minh Dang and Hyosik Yang},
title = {QFedFormer: A Privacy-Preserving Federated Transformer with Blockchain-Anchored Incentives for Dynamic EV Charging Pricing},
year = {2026},
journal = {Computer Modeling in Engineering & Sciences},
volume = {147},
number = {3},
pages = {46},
keywords = {Blockchain, federated learning, EV charging, dynamic pricing, differential privacy, SHAP, tokenized incentives},
url = {https://www.sciopen.com/article/10.32604/cmes.2026.081849},
doi = {10.32604/cmes.2026.081849},
abstract = {We present QFedFormer, a federated transformer for dynamic electric vehicle (EV)-charging price prediction that combines quantization-aware training, SHAP-guided explainability, and blockchain-based incentives. The framework trains across distributed charging stations without centralizing user data, and programmable contracts set tariffs from forecasted demand and user-declared flexibility, while token rewards are derived from SHAP-based utility scores and anchored on-chain via Merkle proofs. On a real-world dataset, QFedFormer attains an energy-demand RMSE of  1.82±0.02 kWh and a tariff RMSE of  11.83±0.10 KRW/kWh (MAPE  2.7±0.2%) in the non-private baseline, outperforming FedAvg and Block-FeDL by  14.1% and  9.5%, respectively. Under client-level differential privacy (DP) with  (σ=1.6,C=1,p=0.1,δDP=10−5), QFedFormer achieves  (ε=2.0,δDP=10−5) after 50 rounds under a Rényi accountant, with forecast accuracy degrading modestly to  1.95 kWh RMSE ( ∼7.1% relative increase vs. non-private baseline). Blockchain evaluation shows an average audit latency of  58 ms per audit round, while a permissioned Ethereum-compatible deployment sustains more than  500 client updates per minute with gas costs of  ∼$0.039/client per audit round. These results indicate that QFedFormer enables accurate, privacy-preserving, and auditable coordination of EV–grid interactions, offering both regulators and service providers a practical deployment pathway.}
}