Federated learning is a distributed learning paradigm that enables learning on multiple clients to solve the data privacy problem. This study proposes a multi-variable input traffic model based on federated learning, which predicts fuel consumption and emissions based on speed, acceleration, temperature, and seasons, and apply real-world vehicle history data for simulation. To avoid affecting predicting effect, auto-encoder is introduced to traffic model to remove outliers. The results show that the MSE after the outlier removal is at least 10% lower than the raw data, and this traffic model compared with the existing non-federal learning methods, the prediction loss value in MAE in winter only increase by about 0.2%–3.8%, the MSE in summer decrease by about 3%–17.8%. It is proved this model still have a favorable prediction performance while protecting privacy.
Traffic Prediction Model of Fuel Consumption and Carbon Emissions with Integration of Machine Learning and Federated Learning
22nd COTA International Conference of Transportation Professionals ; 2022 ; Changsha, Hunan Province, China
CICTP 2022 ; 832-843
2022-09-08
Conference paper
Electronic Resource
English
Multi-period traffic prediction method based on federated learning
European Patent Office | 2025
|Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation
ArXiv | 2024
|