Predicting the spatial demand for public charging stations for EVs using multi-source big data: an example from jinan...

Area of Science:

• Urban Planning and Transportation Science
• Environmental Science and Sustainability
• Geospatial Data Analysis

Background:

• Growing adoption of electric vehicles (EVs) driven by carbon pollution and resource scarcity.
• Current challenges in public charging station (PCS) deployment include insufficient numbers and poor spatial distribution.
• Need for data-driven approaches to optimize PCS placement for widespread EV adoption.

Purpose of the Study:

• To develop a comprehensive evaluation index system for predicting the spatial demand of PCS for EVs.
• To analyze key urban factors influencing PCS demand in Jinan urban area.
• To provide a scientific basis for optimizing PCS distribution and planning.

Main Methods:

• Utilized multi-source big data analysis of population distribution, traffic, infrastructure, land use, and economy.
• Constructed a comprehensive evaluation index system incorporating 14 distinct factors.
• Employed geospatial analysis to predict PCS spatial demand and compared it with current distribution.

Main Results:

• Identified critical factors influencing PCS demand, including population activity, road network characteristics, and land use patterns.
• Developed a predictive model for spatial PCS demand distribution based on integrated urban data.
• Highlighted discrepancies between current PCS distribution and predicted demand, indicating areas for improvement.

Conclusions:

• The proposed multi-factor, geospatial approach offers a more intuitive and comprehensive method for PCS planning than traditional models.
• Accurate prediction of PCS spatial demand is crucial for supporting the widespread adoption of electric vehicles.
• Findings provide valuable insights for urban planners and policymakers to enhance EV charging infrastructure.