Study on Clustering of Free-Floating Bike-Sharing Parking Time Series in Beijing Subway Stations

摘要: In recent years, the free-floating bike-sharing (FFBS) system has become a significant mode of travel to satisfy urban residents’ demands. However, with rapid development FFBS, many problems have arisen, among which parking problem is most prominent. To solve FFBS around subways, firstly, time series pattern and subway station classification in Beijing were constructed based on intensity, showing spatial distribution stations different intensity levels. Second, hierarchical clustering method dynamic warping (DTW) was proposed cluster series. Subway grouped into 11 clusters, purity reached 0.939, achieved expected effect. Then, peak off-peak period features extracted discuss results. Finally, two-level early-warning index for monitoring constructed, took real-time quantity land use capacity consideration. And management strategies indices put forward. It very important sustainable cities.