The deployment of a charging infrastructure to cover the increasing demand of electric vehicles (EVs) has become a crucial problem in smart cities. Additionally, the penetration of the EV will increase once the users can have enough charging stations. In this work, we tackle the problem of locating a set of charging stations in a smart city considering heterogeneous data sources such as open data city portals, geo-located social network data, and energy transformer substations. We use a multi-objective genetic algorithm to optimize the charging station locations by maximizing the utility and minimizing the cost. Our proposal is validated through a case study and several experimental results.

在智能城市中，部署充电基础设施来满足不断增长的电动汽车（EV）需求已成为一个关键问题。此外，一旦用户拥有足够的充电站，电动汽车的普及率就会提高。在这项工作中，我们解决了在智能城市中设置一组充电站的问题，该充电站需要考虑异构数据源，例如开放数据城市门户，地理定位的社交网络数据和能源变电站。我们使用多目标遗传算法，通过最大化效用和最小化成本来优化充电站的位置。我们的建议通过案例研究和一些实验结果得到了验证。