Reaching carbon neutrality needs global actions in various industry sectors. Building energy systems and electric vehicles (EV) are two main contributors to the decarbonization in the energy and transportation sectors, and the distributed building energy system with EV charging driven by renewable energy can greatly reduce carbon emissions. However, in the research about distributed building energy systems with EVs, the time-of-use (TOU) pricing of the grid and uncertain EVs charging loads (caused by random daily miles, departure/return time, and charging modes) are not considered simultaneously, which will influence the performances of the system. In this research, a distributed building energy system with EV is studied under the uncertain EV charging behaviors and TOU pricing of electricity, and the corresponding operation strategy is designed. The economic, environment, renewable energy penetration, and power trading performances are analyzed, and the crucial parameters of the system are optimized with three goals of minimum electricity cost, maximum renewable energy utilization ratio, and minimum net power purchase from the grid simultaneously based on the nondominated sorting genetic algorithm II (NSGA-II). The optimal system is analyzed from the perspective of energy flow and typical daily operation. The influences of the EV fast charging ratio and carbon tax on the optimal system are also studied. According to the results, the electricity cost, renewable energy utilization ratio, and net power purchase can be 0.0773 $ kWh⁻¹, 54.3%, and 172.65 MWh year⁻¹ simultaneously.

实现碳中和需要各个行业部门的全球行动。建筑能源系统和电动汽车（EV）是能源和交通领域脱碳的两个主要贡献者，而可再生能源驱动的电动汽车充电的分布式建筑能源系统可以大大减少碳排放。然而，在对带有电动汽车的分布式建筑能源系统的研究中，没有考虑电网的使用时间（TOU）定价和不确定的电动汽车充电负载（由随机的每日里程、出发/返回时间和充电模式引起）同时，这将影响系统的性能。本研究针对电动汽车充电行为和电费分时定价的不确定性，研究了电动汽车分布式建筑能源系统，并设计了相应的运行策略。分析了经济、环境、可再生能源渗透率和电力交易性能，以最小电力成本、最大可再生能源利用率和最小净购电三个目标同时优化系统的关键参数。非支配排序遗传算法 II (NSGA-II)。从能量流和典型日常运行的角度分析了最优系统。还研究了电动汽车快速充电率和碳税对优化系统的影响。根据结果​​，电力成本、可再生能源利用率和净购电可以为 0.0773 $ kWh 并基于非支配排序遗传算法II（NSGA-II）同时优化系统的关键参数，以最小电力成本、最大可再生能源利用率和最小净购电量三个目标。从能量流和典型日常运行的角度分析了最优系统。还研究了电动汽车快速充电率和碳税对优化系统的影响。根据结果​​，电力成本、可再生能源利用率和净购电可以为 0.0773 $ kWh 并基于非支配排序遗传算法II（NSGA-II）同时优化系统的关键参数，以最小电力成本、最大可再生能源利用率和最小净购电量三个目标。从能量流和典型日常运行的角度分析了最优系统。还研究了电动汽车快速充电率和碳税对优化系统的影响。根据结果​​，电力成本、可再生能源利用率和净购电可以为 0.0773 $ kWh 从能量流和典型日常运行的角度分析了最优系统。还研究了电动汽车快速充电率和碳税对优化系统的影响。根据结果​​，电力成本、可再生能源利用率和净购电可以为 0.0773 $ kWh 从能量流和典型日常运行的角度分析了最优系统。还研究了电动汽车快速充电率和碳税对优化系统的影响。根据结果​​，电力成本、可再生能源利用率和净购电可以为 0.0773 $ kWh^-1、54.3 % 和 172.65 MWh 年^-1同时。