The spatio-temporal distribution of electric vehicle charging loads is affected by the high uncertainty of road network traffic conditions. Therefore, the accuracy of prediction of charging load can be improved by combining the real-time road network traffic condition, which can provide a basis for the distribution network to cope with the charging load. We present a spatio-temporal charging load prediction method based on cellular traffic simulation. First, joint vehicle-road-network modeling and travel chain principles simulate user travel patterns. Next, a metacellular transmission model integrates traffic flow simulation to represent urban road dynamics, including vehicle behaviors (e.g., following, lane changes) and adaptive traffic flow updates. Road traffic indexes are derived, and an EV energy consumption model incorporating traffic parameters predicts charging load distribution. Simulation in a Hunan urban area validates the method’s feasibility.
A spatio-temporal prediction method for charging load considering metric traffic flow simulation
2025-04-18
1429950 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2022
|Traffic flow prediction method for traffic flow spatio-temporal data information
European Patent Office | 2024
|Spatio-Temporal AutoEncoder for Traffic Flow Prediction
IEEE | 2023
|Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features
IET | 2021
|