Electric vehicle space-time scheduling method

Abstract

This invention relates to a time-based scheduling method for electric vehicles, comprising: establishing a road network model based on the actual traffic structure, and constructing a road impedance model and a vehicle energy consumption model as the basis for the scheduling method; obtaining the time and state-of-charge attributes of user charging decisions based on the obtained road network model, road impedance model, and vehicle energy consumption model; establishing reference points, value functions, and probability weights of cumulative prospect theory based on the time and state-of-charge attributes of the decisions, and constructing a multi-attribute charging decision model that considers the bounded rationality of electric vehicle users; obtaining the charging plans of electric vehicles arriving at charging stations based on the charging decision model, and performing orderly scheduling of electric vehicles within the station with the goal of minimizing the peak-valley difference of the total load of the distribution network.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging optimization scheduling technology, and in particular to a time-space scheduling method for electric vehicles. Background Technology

[0002] In recent years, with the continuous advancement of the goals of "carbon peaking and carbon neutrality," electric vehicles are gradually becoming an important carrier for the low-carbon transformation of the transportation sector and a crucial component of new electricity loads. The large-scale integration of electric vehicles into the power distribution network helps improve the absorption of clean energy, but its highly random and concentrated charging behavior also presents new challenges to the safe and stable operation of the power distribution network. Disorderly charging of electric vehicles can easily lead to voltage exceeding limits at distribution network nodes, transformer overload, and even overload, which in severe cases can affect power supply reliability and the quality of electricity for users.

[0003] Currently, most existing studies still employ the "perfect rationality" assumption when modeling user charging behavior, assuming that users can obtain and process complete information about all candidate charging stations and will always make the choice that maximizes utility or minimizes cost. This assumption deviates from the actual decision-making process and fails to depict users' real charging behavior under conditions of incomplete information, limited cognitive abilities, and diverse risk preferences, thus leading to a discrepancy between the charging demand derived from this assumption and the actual response.

[0004] Furthermore, current research on orderly charging largely focuses on a single spatial or temporal dimension. One approach emphasizes "charging station guidance" within the transportation network through price signals and recommended routes to alleviate congestion and spatial load concentration at some charging stations. Another approach focuses on adjusting charging power curves on the distribution network side to achieve peak shaving and valley filling, reducing the peak-valley difference. These two approaches are often disconnected, failing to grasp the complete process of electric vehicles "generating charging demand—selecting a charging station—charging at the station" at a systemic level. For the optimized scheduling of orderly charging for electric vehicles, traditional methods lack a coordinated control mechanism among the transportation network, distribution network, and user behavior, making it difficult to simultaneously address load balancing in both spatial and temporal dimensions. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to resolve the aforementioned deficiencies and propose a time-space scheduling method for electric vehicles. This method can achieve a reasonable spatial distribution of electric vehicle charging load and a reduction in peak-valley differences over time by constructing a traffic-power network model, introducing a multi-attribute charging decision model based on cumulative prospect theory, and an in-station charging optimization scheduling model. This improves the spatiotemporal balance of the overall load and provides technical support for the safe and economical operation of new power distribution networks.

[0006] The present invention adopts the following technical solution.

[0007] The time-conditioning method for electric vehicles includes the following steps:

[0008] Step 1: Establish a road network model based on the actual traffic structure, and use it to construct a road impedance model and a vehicle energy consumption model as the basis for the scheduling method;

[0009] Step 2: Based on the road network model, road impedance model and vehicle energy consumption model obtained in Step 1, obtain the time and state of charge attributes of the user's charging decision.

[0010] Step 3: Based on the time and state of charge attributes of the decision obtained in Step 2, establish the reference point, value function and probability weight of the cumulative prospect theory, and construct a multi-attribute charging decision model that considers the bounded rationality of electric vehicle users.

[0011] Step 4: Based on the charging decision model in Step 3, obtain the charging plan for electric vehicles arriving at the charging station, and schedule the electric vehicles in the station in an orderly manner with the goal of minimizing the peak-valley difference of the total load of the distribution network.

[0012] Furthermore, step 1 includes the following steps:

[0013] Step 1.1: Establish a traffic road network model using equation (1):

[0014] (1)

[0015] In equation (1), Indicates the transportation network; Represents road network nodes. Indicates the number of nodes in the road network. express The set of all road network nodes; Indicates connection to road network nodes and The section of road, express A collection of all road segments; This represents the set of times to be divided, with the entire day divided into... At that moment; Indicates road segment exist Weights at time points It is the set of weights for each road segment at each time point.

[0016] Step 1.2: Construct a road impedance model using equations (2)-(3) to obtain the road segment weight set. :

[0017] (2)

[0018] (3)

[0019] In equations (2)-(3), express Vehicle speed at all times Indicates road segment The speed of free passage, express Time and Section Traffic flow Indicates road Maximum throughput capacity Represents the empirical coefficient; , , Indicates the adaptive coefficients under different road grades; Indicates road Length, For road network nodes Traffic light waiting time.

[0020] Step 1.3: Construct a vehicle energy consumption model using equation (4):

[0021] (4)

[0022] In equation (4), , , These represent the energy consumption coefficients per unit mileage for electric vehicles traveling on main roads, secondary roads, and local roads, respectively.

[0023] Furthermore, step 2 includes the following steps:

[0024] Step 2.1: Use equations (5)-(7) to obtain the time and state-of-charge attributes for electric vehicle users' time decisions:

[0025] (5)

[0026] (6)

[0027] (7)

[0028] In equations (5)-(7), This represents the queuing time at the charging station, which follows the parameter: The exponential distribution; where, This indicates the number of charging stations inside the charging station. This indicates the average service rate of the charging pile. Indicates the average arrival rate; This indicates the shortest travel time for the vehicle from its current starting point to the target charging station. , These represent the starting position of the vehicle's journey and the location of the target charging station, respectively. This represents the total time required for an electric vehicle user to charge at the charging station numbered k.

[0029] Step 2.2: Use equation (8) to obtain the time and state-of-charge attributes for electric vehicle users' state-of-charge decisions:

[0030] (8)

[0031] In equation (8), This indicates the state of charge of the electric vehicle user upon arrival at charging station number k. This indicates the state of charge when an electric vehicle user requests charging. This represents the shortest path length between the vehicle's starting position and the target charging station.

[0032] Furthermore, step 3 includes the following steps:

[0033] Step 3.1: Use equations (9)-(11) to obtain the value functions of the time and charge state attributes for each decision:

[0034] (9)

[0035] (10)

[0036] (11)

[0037] In equations (9)-(11), , These represent the value functions for time and state of charge, respectively. , These represent the risk attitude coefficients of electric vehicle users when facing gains and losses, respectively. , These represent the aversion coefficients of electric vehicle users to losses related to time and state of charge, respectively. , These represent reference points for time and state of charge, respectively. , These represent comparisons between time, state of charge, and corresponding reference point, respectively. Their positive or negative values ​​determine whether the electric vehicle user perceives the result as a gain or a loss.

[0038] Step 3.2: Using equations (12)-(13), obtain the subjective perceived probability of electric vehicle users facing gains and losses:

[0039] (12)

[0040] (13)

[0041] In equations (12)-(13), , These represent the subjective perceived probabilities of electric vehicle users facing gains and losses, respectively. , These represent the objective probabilities corresponding to the outcomes of gain and loss, respectively. , These represent the subjective distortion coefficients of electric vehicle users in terms of gains and losses, respectively.

[0042] Step 3.3: Use equations (14)-(15) to obtain the cumulative probability weights of gains and losses for electric vehicle users:

[0043] (14)

[0044] (15)

[0045] In equations (14)-(15), , These represent the cumulative probability weights for electric vehicle users facing gains and losses, respectively; where, This represents the cumulative probability weight of the nth payoff outcome. This represents the cumulative probability weight of the m-th loss outcome.

[0046] Step 3.4: Using equations (16) and (17), we obtain the multi-attribute charging decision model that considers the bounded rationality of electric vehicle users:

[0047] (16)

[0048] (17)

[0049] In equations (16)-(17), , These represent the weighting coefficients for the time and state of charge attributes, respectively, and their sum is 1. This represents the comprehensive cumulative prospect value of charging station k, considering multiple decision-making processes and its state of charge attribute. Value functions representing time and state of charge , .

[0050] Step 3.5: Use the objective function of equation (18) to obtain the final charging station the vehicle will visit.

[0051] (18)

[0052] In equation (18), This indicates the charging station that electric vehicle users are heading to, and the overall cumulative prospect value of that charging station is at its maximum.

[0053] Furthermore, step 4 includes the following steps:

[0054] Step 4.1: Use equation (19) to obtain the total load of the distribution network nodes:

[0055] (19)

[0056] In equation (19), , Let g represent the base load and total load of the distribution network node numbered g at time t, respectively. This represents the charging power of the r-th vehicle at time t. This represents the number of electric vehicles being charged at the distribution network node numbered g.

[0057] Step 4.2: Use equation (20) to establish the objective function of the electric vehicle optimal scheduling model:

[0058] (20)

[0059] In equation (20), , denoted as g, representing the peak and valley values ​​of the total load of the distribution network node, respectively, and f, representing the peak-valley difference of the total load of the distribution network.

[0060] Step 4.3: Use equations (21)-(23) to establish the power, energy, and capacity constraints for the electric vehicle optimal scheduling model, respectively:

[0061] (twenty one)

[0062] (twenty two)

[0063] (twenty three)

[0064] In equations (21)-(23), , These represent the minimum charging power and the maximum charging power, respectively. Indicates the range of available charging time. Indicates charging efficiency. Indicates charging time. , , Let represent the state of charge of the r-th electric vehicle upon arrival, the desired state of charge, and the state of charge upon departure, respectively. Indicates the battery capacity of an electric vehicle. This indicates the transformer capacity.

[0065] Step 4.4: Use the CPLEX solver to solve the electric vehicle optimal scheduling model, obtain the corresponding charging power of the electric vehicles participating in the scheduling, and realize the orderly scheduling of electric vehicles.

[0066] The beneficial effects of the present invention are as follows: Compared with the prior art, the present invention has the following advantages:

[0067] This invention proposes a time-based scheduling method for electric vehicles. It introduces cumulative prospect theory into the charging decision model, comprehensively considers the gains and losses of time and state of charge attributes relative to the user's reference point, and describes the user's nonlinear perception of uncertainty through subjective probability weighting. This method can characterize behavioral features such as loss aversion and risk preference. Compared with models based on the assumption of perfect rationality, the resulting charging demand distribution is closer to reality, which is conducive to improving the execution effect of subsequent scheduling optimization results.

[0068] In addition, by establishing a charging decision model that considers the bounded rationality of users, the charging load is redistributed among different charging stations. By optimizing the orderly charging within the station, the load within the same charging station is smoothed over time at different times. This breaks down the boundary between the selection of charging stations in the transportation network and the scheduling within the distribution network in traditional methods, and constructs an integrated spatiotemporal collaborative optimization framework. This framework can simultaneously reduce the peak-valley difference of the total load of the distribution network and achieve overall spatiotemporal balance of the distribution network load. Attached Figure Description

[0069] Figure 1 This is a flowchart of the time-conditioning method for electric vehicles. Detailed Implementation

[0070] The present application will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention, and should not be construed as limiting the scope of protection of the present application.

[0071] This application relates to a time-based scheduling method for electric vehicles, which is a scheduling method that can accurately characterize the bounded rationality decision-making process of users and efficiently regulate the charging of electric vehicles, while overcoming the shortcomings of traditional methods in terms of regulation effect, efficiency, and applicability. This method not only obtains more accurate user charging needs, providing accurate reference for the scheduling process, but also optimizes the charging time and location of electric vehicles in the spatiotemporal dimension, effectively achieving the spatiotemporal balance of the distribution network load. Specifically, as... Figure 1 As shown, the method includes the following steps:

[0072] Step 1: Establish a road network model based on the actual traffic structure, and use this model to construct a road impedance model and a vehicle energy consumption model as the basis for the scheduling method.

[0073] Step 1.1: Establish a traffic road network model using equation (1):

[0074] (1)

[0075] In equation (1), Indicates the transportation network; Represents road network nodes. Indicates the number of nodes in the road network. express The set of all road network nodes; Indicates connection to road network nodes and The section of road, express A collection of all road segments; This represents the set of times to be divided, with the entire day divided into... At that moment; Indicates road segment exist Weights at time points It is the set of weights for each road segment at each time point.

[0076] Step 1.2: Construct a road impedance model using equations (2)-(3) to obtain the road segment weight set. :

[0077] (2)

[0078] (3)

[0079] In equations (2)-(3), express Vehicle speed at all times Indicates road segment The speed of free passage, express Time and Section Traffic flow Indicates road Maximum throughput capacity Represents the empirical coefficient; , , Indicates the adaptive coefficients under different road grades; Indicates road Length, For road network nodes Traffic light waiting time.

[0080] Step 1.3: Traffic congestion leads to a decrease in speed, which in turn increases the real-time power consumption of electric vehicles. A vehicle energy consumption model is constructed using equation (4):

[0081] (4)

[0082] In equation (4), , , These represent the energy consumption coefficients per unit mileage for electric vehicles traveling on main roads, secondary roads, and local roads, respectively.

[0083] Steps 1 and 2 establish a basic model of road traffic. However, in actual scheduling, the user's charging decision-making process also needs to be considered, including the timing and state of charge (SOC) attributes of the decision. Based on the road network model, road impedance model, and vehicle energy consumption model obtained in Step 1, the timing and SOC attributes of the user's charging decision are analyzed:

[0084] Step 2.1: Use equations (5)-(7) to obtain the time and state-of-charge attributes for electric vehicle users' time decisions:

[0085] (5)

[0086] (6)

[0087] (7)

[0088] In equations (5)-(7), This represents the queuing time at the charging station, which follows the parameter: The exponential distribution; where, This indicates the number of charging stations inside the charging station. This indicates the average service rate of the charging pile. Indicates the average arrival rate; This indicates the shortest travel time for the vehicle from its current starting point to the target charging station. , These represent the starting position of the vehicle's journey and the location of the target charging station, respectively. This represents the total time required for an electric vehicle user to charge at the charging station numbered k.

[0089] Step 2.2: Use equation (8) to obtain the time and state-of-charge attributes for electric vehicle users' state-of-charge decisions:

[0090] (8)

[0091] In equation (8), This indicates the state of charge of the electric vehicle user upon arrival at charging station number k. This indicates the state of charge when an electric vehicle user requests charging. This represents the shortest path length between the vehicle's starting position and the target charging station.

[0092] Step 3: Electric vehicle users' charging decisions are influenced by the time and state of charge attributes of each decision. Appropriate weighting coefficients are set to reflect the proportion of these attributes in each decision. Furthermore, users' charging decisions often fail to reach the optimal level; therefore, cumulative prospect theory is used to describe the bounded rationality process of user charging decisions. Based on the time and state of charge attributes of the decisions obtained in Step 2, reference points, value functions, and probability weights for cumulative prospect theory are established to construct a multi-attribute charging decision model that considers the bounded rationality of electric vehicle users.

[0093] Step 3.1: Considering that electric vehicle users with bounded rationality will have different perceived values ​​when facing gains and losses, the value functions of time and state of charge attributes for each decision are obtained using equations (9)-(11):

[0094] (9)

[0095] (10)

[0096] (11)

[0097] In equations (9)-(11), , These represent the value functions for time and state of charge, respectively. , These represent the risk attitude coefficients of electric vehicle users when facing gains and losses, respectively. , These represent the aversion coefficients of electric vehicle users to losses related to time and state of charge, respectively. , These represent reference points for time and state of charge, respectively. , These represent comparisons between time, state of charge, and corresponding reference point, respectively. Their positive or negative values ​​determine whether the electric vehicle user perceives the result as a gain or a loss.

[0098] Step 3.2: Considering that boundedly rational electric vehicle users may subjectively distort the objective probability of a certain outcome, we use equations (12)-(13) to obtain the subjective probability of electric vehicle users' perception of gains and losses:

[0099] (12)

[0100] (13)

[0101] In equations (12)-(13), , These represent the subjective perceived probabilities of electric vehicle users facing gains and losses, respectively. , These represent the objective probabilities corresponding to the outcomes of gain and loss, respectively. , These represent the subjective distortion coefficients of electric vehicle users in terms of gains and losses, respectively.

[0102] Step 3.3: Since the perception of electric vehicle users is a combination of a series of results and probabilities, the cumulative probability weights of electric vehicle users facing gains and losses are obtained using equations (14)-(15):

[0103] (14)

[0104] (15)

[0105] In equations (14)-(15), , These represent the cumulative probability weights for electric vehicle users facing gains and losses, respectively; where, This represents the cumulative probability weight of the nth payoff outcome. This represents the cumulative probability weight of the m-th loss outcome.

[0106] Step 3.4: Using equations (16) and (17), we obtain the multi-attribute charging decision model that considers the bounded rationality of electric vehicle users:

[0107] (16)

[0108] (17)

[0109] In equations (16)-(17), , These represent the weighting coefficients for the time and state of charge attributes, respectively, and their sum is 1. This represents the comprehensive cumulative prospect value of charging station k, considering multiple decision-making processes and its state of charge attribute. Value functions representing time and state of charge , .

[0110] Step 3.5: Use the objective function of equation (18) to obtain the final charging station the vehicle will visit.

[0111] (18)

[0112] In equation (18), This indicates the charging station that electric vehicle users are heading to, and the overall cumulative prospect value of that charging station is at its maximum.

[0113] Step 4: Based on the charging decision results of Step 3, obtain the charging plan of electric vehicles arriving at the charging station, and schedule the electric vehicles in the station in an orderly manner with the goal of minimizing the peak-valley difference of the total load of the distribution network.

[0114] Step 4.1: Use equation (19) to obtain the total load of the distribution network nodes:

[0115] (19)

[0116] In equation (19), , Let g represent the base load and total load of the distribution network node numbered g at time t, respectively. This represents the charging power of the r-th vehicle at time t. This represents the number of electric vehicles being charged at the distribution network node numbered g.

[0117] Step 4.2: Use equation (20) to establish the objective function of the electric vehicle optimal scheduling model:

[0118] (20)

[0119] In equation (20), , denoted as g, representing the peak and valley values ​​of the total load of the distribution network node, respectively, and f, representing the peak-valley difference of the total load of the distribution network.

[0120] Step 4.3: Use equations (21)-(23) to establish the power, energy, and capacity constraints for the electric vehicle optimal scheduling model, respectively:

[0121] (twenty one)

[0122] (twenty two)

[0123] (twenty three)

[0124] In equations (21)-(23), , These represent the minimum charging power and the maximum charging power, respectively. Indicates the range of available charging time. Indicates charging efficiency. Indicates charging time. , , Let represent the state of charge of the r-th electric vehicle upon arrival, the desired state of charge, and the state of charge upon departure, respectively. Indicates the battery capacity of an electric vehicle. This indicates the transformer capacity.

[0125] Step 4.4: Use the CPLEX solver to solve the electric vehicle optimal scheduling model to obtain the corresponding charging power of the electric vehicles participating in the scheduling, thereby realizing the orderly scheduling of electric vehicles.

[0126] Beneficial effects:

[0127] Introducing cumulative prospect theory into the charging decision model, this approach comprehensively considers the gains and losses of time and state of charge attributes relative to the user's reference point, among other factors. It also uses subjective probability weighting to describe the user's nonlinear perception of uncertainty, thus characterizing behavioral traits such as loss aversion and risk preference. Compared to models based on perfect rationality assumptions, the resulting charging demand distribution is closer to reality, improving the effectiveness of subsequent scheduling optimization. Furthermore, by establishing a charging decision model that considers users' bounded rationality, the charging load is redistributed among different charging stations. Orderly charging optimization scheduling within stations achieves temporal smoothing of the load within the same charging station across different time periods. This bridges the boundary between traditional methods of selecting charging stations in the transportation network and scheduling within the distribution network, constructing an integrated spatiotemporal collaborative optimization framework. This framework can simultaneously reduce the peak-to-valley difference of the total distribution network load, achieving overall spatiotemporal balance of the distribution network load.

[0128] The applicant of this invention has provided a detailed description of the embodiments of the invention in conjunction with the accompanying drawings. However, those skilled in the art should understand that the above embodiments are merely preferred embodiments of the invention. The detailed description is only intended to help readers better understand the spirit of the invention and is not intended to limit the scope of protection of the invention. On the contrary, any improvements or modifications made based on the inventive spirit of the invention should fall within the scope of protection of the invention.

Claims

1. A time-conditioning method for electric vehicles, characterized in that, Includes the following steps: Step 1: Establish a road network model based on the actual traffic structure, and use it to construct a road impedance model and a vehicle energy consumption model as the basis for the scheduling method; Step 2: Based on the road network model, road impedance model and vehicle energy consumption model obtained in Step 1, obtain the time and state of charge attributes of the user's charging decision. Step 3: Based on the time and state of charge attributes of the decision obtained in Step 2, establish the reference point, value function and probability weight of the cumulative prospect theory, and construct a multi-attribute charging decision model that considers the bounded rationality of electric vehicle users. Step 4: Based on the charging decision model in Step 3, obtain the charging plan for electric vehicles arriving at the charging station, and schedule the electric vehicles in the station in an orderly manner with the goal of minimizing the peak-valley difference of the total load of the distribution network.

2. The electric vehicle time-setting method considering the bounded rationality of users as described in claim 1, characterized in that, Step 1 includes the following steps: Step 1.1: Establish a traffic road network model using equation (1): (1)； In equation (1), Indicates the transportation network; Represents road network nodes. Indicates the number of nodes in the road network. express The set of all road network nodes; Indicates connection to road network nodes and The section of road, express A collection of all road segments; This represents the set of times to be divided, with the entire day divided into... At that moment; Indicates road segment exist Weights at time points It is the set of weights for each road segment at each time point; Step 1.2: Construct a road impedance model using equations (2)-(3) to obtain the road segment weight set. : (2)； (3)； In equations (2)-(3), express Vehicle speed at all times Indicates road segment The speed of free passage, express Time and Section Traffic flow Indicates road Maximum throughput capacity Represents the empirical coefficient; , , Indicates the adaptive coefficients under different road grades; Indicates road Length, For road network nodes Traffic light waiting time; Step 1.3: Construct a vehicle energy consumption model using equation (4): (4)； In equation (4), , , These represent the energy consumption coefficients per unit mileage for electric vehicles traveling on main roads, secondary roads, and local roads, respectively.

3. A time-setting method for electric vehicles that considers the bounded rationality of users, as described in claim 2, is characterized in that... Step 2 includes the following steps: Step 2.1: Use equations (5)-(7) to obtain the time and state-of-charge attributes for electric vehicle users' time decisions: (5)； (6)； (7)； In equations (5)-(7), This represents the queuing time at the charging station, which follows the parameter: The exponential distribution; where, This indicates the number of charging stations inside the charging station. This indicates the average service rate of the charging pile. Indicates the average arrival rate; This indicates the shortest travel time for the vehicle from its current starting point to the target charging station. , These represent the starting position of the vehicle's journey and the location of the target charging station, respectively. This represents the total time required for an electric vehicle user to charge at the charging station numbered k. Step 2.2: Use equation (8) to obtain the time and state-of-charge attributes for electric vehicle users' state-of-charge decisions: (8)； In equation (8), This indicates the state of charge of the electric vehicle user upon arrival at charging station number k. This indicates the state of charge when an electric vehicle user requests charging. This represents the shortest path length between the vehicle's starting position and the target charging station.

4. A time-setting method for electric vehicles that considers the bounded rationality of users, as described in claim 3, is characterized in that... Step 3 includes the following steps: Step 3.1: Use equations (9)-(11) to obtain the value functions of the time and charge state attributes for each decision: (9)； (10)； (11)； In equations (9)-(11), , These represent the value functions for time and state of charge, respectively. , These represent the risk attitude coefficients of electric vehicle users when facing gains and losses, respectively. , These represent the aversion coefficients of electric vehicle users to losses related to time and state of charge, respectively. , These represent reference points for time and state of charge, respectively. , These represent comparisons between time, state of charge, and corresponding reference point, respectively. Their positive or negative signs determine whether the electric vehicle user perceives the result as a gain or a loss. Step 3.2: Using equations (12)-(13), obtain the subjective perceived probability of electric vehicle users facing gains and losses: (12)； (13)； In equations (12)-(13), , These represent the subjective perceived probabilities of electric vehicle users facing gains and losses, respectively. , These represent the objective probabilities corresponding to the outcomes of gain and loss, respectively. , These represent the subjective distortion coefficients of electric vehicle users in terms of gains and losses, respectively. Step 3.3: Use equations (14)-(15) to obtain the cumulative probability weights of gains and losses for electric vehicle users: (14)； (15)； In equations (14)-(15), , These represent the cumulative probability weights for electric vehicle users facing gains and losses, respectively; where, This represents the cumulative probability weight of the nth payoff outcome. This represents the cumulative probability weight of the m-th loss outcome; Step 3.4: Using equations (16) and (17), we obtain the multi-attribute charging decision model that considers the bounded rationality of electric vehicle users: (16)； (17)； In equations (16)-(17), , These represent the weighting coefficients for the time and state of charge attributes, respectively, and their sum is 1. This represents the comprehensive cumulative prospect value of charging station k, considering multiple decision-making processes and its state of charge attribute. Value functions representing time and state of charge , ; Step 3.5: Use the objective function of equation (18) to obtain the final charging station the vehicle will visit. (18)； In equation (18), This indicates the charging station that electric vehicle users are heading to, and the overall cumulative prospect value of that charging station is at its maximum.

5. A time-setting method for electric vehicles that considers the bounded rationality of users, as described in claim 4, is characterized in that... Step 4 includes the following steps: Step 4.1: Use equation (19) to obtain the total load of the distribution network nodes: (19)； In equation (19), , Let g represent the base load and total load of the distribution network node numbered g at time t, respectively. This represents the charging power of the r-th vehicle at time t. This represents the number of electric vehicles being charged at the distribution network node numbered g; Step 4.2: Use equation (20) to establish the objective function of the electric vehicle optimal scheduling model: (20)； In equation (20), , denoted as g, representing the peak and valley values ​​of the total load of the distribution network node, respectively, and f is the peak-valley difference of the total load of the distribution network; Step 4.3: Use equations (21)-(23) to establish the power, energy, and capacity constraints for the electric vehicle optimal scheduling model, respectively: (21)； (22)； (23)； In equations (21)-(23), , These represent the minimum charging power and the maximum charging power, respectively. Indicates the range of available charging time. Indicates charging efficiency. Indicates charging time. , , Let represent the state of charge of the r-th electric vehicle upon arrival, the desired state of charge, and the state of charge upon departure, respectively. Indicates the battery capacity of an electric vehicle. Indicates transformer capacity; Step 4.4: Use the CPLEX solver to solve the electric vehicle optimal scheduling model, obtain the corresponding charging power of the electric vehicles participating in the scheduling, and realize the orderly scheduling of electric vehicles.

Images