The rising adoption of plug-in electric vehicles (PEVs) leads to the temporal alignment of their electricity and mobility demands. However, mobility demand has not yet been considered in electricity planning and management. Here, we present a method to estimate individual mobility of PEV drivers at fine temporal and spatial resolution, by integrating three unique datasets of mobile phone activity of 1.39 million Bay Area residents, census data and the PEV drivers survey data. Through coupling the uncovered patterns of PEV mobility with the charging activity of PEVs in 580,000 session profiles obtained in the same region, we recommend changes in PEV charging times of commuters at their work stations and shave the pronounced peak in power demand. Informed by the tariff of electricity, we calculate the monetary gains to incentivize the adoption of the recommendations. These results open avenues for planning for the future of coupled transportation and electricity needs using personalized data.

插电式电动汽车（PEV）的采用率不断提高，导致其电力和出行需求在时间上保持一致。但是，在电力规划和管理中尚未考虑移动性需求。在这里，我们提出了一种方法，通过整合139万湾区居民手机活动，人口普查数据和PEV驾驶员调查数据的三个唯一数据集，以精细的时间和空间分辨率估算PEV驾驶员的个人流动性。通过将未发现的PEV移动性模式与在同一地区获得的580,000个会话配置文件中的PEV充电活动结合起来，我们建议更改通勤者在其工作站上的PEV充电时间，并消除功率需求的明显峰值。得知电费，我们会计算货币收益，以鼓励采纳建议。这些结果为使用个性化数据规划未来运输和电力需求耦合开辟了道路。