Energy Management of Electric Vehicle Integrated Home in a Time-of-Day Regime

Two‐layer optimal charging strategy for electric vehicles in old residential areas

“…As mentioned in section 3, the set departure time is generated by uniformly adding a certain error with an absolute value of 0.5/1/1.5, and so on, to the actual value. A user's target SOC is generated according to a uniform distribution U(0.8,1), and considering that users' daily mileage has a logarithmic normal distribution, the initial SOC is generated according to formula (22).…”

“…To reduce the charging cost while ensuring safe operation, the charging and noncharging times of each EV were arranged according to a time-sharing electricity price mechanism. 22 A smart-charging hardware system was designed to simultaneously optimize the charging cost and time. 23 Researchers 24 have proposed a market framework that includes three entities: the EV owner, fleet operator, and distribution system operator.…”

“…As mentioned above, the objective functions of most charging strategies are associated primarily with cost, charging time, peak-to-average ratio, and so on. [22][23][24][25][26][27][28][29][30][31] However, with the increase in the number of EVs, the most urgent problem to be solved in the future is incomplete charging, which may increase the EV users' mileage anxiety. Therefore, this study proposes an index called the total user satisfaction, which is treated as an objective function in the proposed charging strategies.…”

“…Therefore, this study proposes an index called the total user satisfaction, which is treated as an objective function in the proposed charging strategies. In addition, with existing methods, the departure time is set by the user, [19][20][21][22][23][24][28][29][30] who can control the charging process by advancing the set departure time, which may cause unfair electricity distribution and even undesired competition. Therefore, to fully consider the differences among users, a long short-term memory (LSTM) prediction model is used to predict the departure time of each user.…”

Electric Vehicles Scale Evolution Model Considering Social Attributes

“…The facts are that the electric vehicle industry is in its infancy in China, thus, the poor historical data support for electric vehicles and the different policies of various countries lead to the low reference value of international data [4]- [5], which bring challenges to the electric vehicle scale prediction [6]- [7]. Current studies mostly use new product diffusion models to predict the development trend of electric vehicles [8]- [10].…”