Electric vehicle charging station planning with dynamic prediction of elastic charging demand: a hybrid particle swarm optimization algorithm

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

Under the pressure of carbon pollution and resource scarcity, electric vehicles (EVs) have gradually replaced fuel vehicles as a new trend of low-carbon transformation. However, public charging stations (PCS) face with problems such as insufficient quantity and unreasonable distribution. By using multi-source big data, this paper analyzes the population distribution, traffic organization, infrastructure, land use and regional economy of Jinan urban area, China, and constructs a comprehensive evaluation index system to predict the spatial demand of PCS for EVs. We analyse: (1) Distribution of population activities on weekday and rest days, the closeness and betweenness of road network, high-density area, commerce, public service facilities, parks, transportation facilities, residential area, building coverage, floor area ratio, economic development area and housing price level. (2) Correlation and influence weights of 14 evaluation indexes and PCS layout. (3) Prediction of spatial demand distribution of PCS. (4) Comparison of current PCS distribution and spatial demand prediction results. This method makes up for the deficiencies of too single consideration factor, lack of intuitiveness of mathematical model and lack of urban geospatial research. This is of significance for predicting the demand distribution of PCS in the future and further promoting the whole popularity of EVs.