Game-based electric vehicle price guidance and space regulation and control method and device

Abstract

The invention provides a game-based electric vehicle price guidance and space regulation and control method and device, and belongs to the field of electric vehicle charging. The method comprises the following steps: establishing a response model of the electric vehicle user for charging price adjustment by collecting charging related historical data of the electric vehicle user, so as to obtain a selection probability prediction result of the user for each charging station; based on the selection probability prediction result, a master-slave game model of a charging station operator and an electric vehicle user is constructed, the charging station operator is a leader, and the electric vehicle user is a follower; and based on the master-slave game model, game strategy optimization among the charging station operators is carried out, and space regulation and control of charging station selection are realized by optimizing the charging price. Through price optimization and space regulation and control, space distribution optimization of the charging load is realized, the resource utilization rate of the charging station is improved, and power grid congestion is relieved.

Description

Technical Field

[0001] The present invention belongs to the field of electric vehicle charging, and particularly relates to a game-based electric vehicle price guidance and space regulation method and device for optimizing the resource allocation of electric vehicle charging stations and grid load management. Background Art

[0002] In urban population-dense areas, fast charging stations have emerged as key infrastructure, solving the growing charging demand and alleviating users' range anxiety. With the rapid expansion of fast charging infrastructure, the spatial flexibility of electric vehicles (EVs) has become the focus of research. Spatial flexibility refers to the redistribution of the charging load of electric vehicles among different charging stations by influencing users' choices of charging stations. This flexibility provides important opportunities for the power system, enabling electric vehicle users to participate in grid ancillary services such as congestion mitigation and renewable energy accommodation.

[0003] In this context, a spatial regulation method under price guidance has emerged. Electric vehicle users are somewhat sensitive to charging costs. Through price guidance, charging behavior can be effectively regulated, guiding users to choose different charging stations to disperse the charging load and avoid grid congestion. At the same time, charging station operators are also faced with the problem of how to maximize their revenue through flexible pricing strategies. A pricing model based on game theory can simulate the game relationship between charging station operators and electric vehicle users, thereby achieving the optimal regulation of spatial flexibility under price guidance during the game process.

[0004] Although some literatures have proposed electric vehicle charging pricing models based on game theory, most methods are only applicable to static pricing or single charging station scenarios and lack in-depth analysis of the game among multiple charging station operators. Therefore, how to combine the spatial flexibility of electric vehicles with price guidance in a game framework and solve the grid load problem through reasonable pricing and spatial regulation remains an urgent issue to be solved. Summary of the Invention

[0005] The object of the present invention is to overcome the deficiencies of the prior art and propose a game-based electric vehicle price guidance and space regulation method and device. The present invention optimizes price and space regulation, thereby realizing the optimization of the spatial distribution of the charging load, improving the resource utilization rate of charging stations, alleviating grid congestion, and further providing technical support for the efficient operation of the electric vehicle charging system.

[0006] The first aspect embodiment of the present invention proposes a game-based electric vehicle price guidance and space regulation method, including:

[0007] By collecting the historical charging data of electric vehicle users, a response model of electric vehicle users to charging price adjustment is established to obtain the prediction results of the selection probability of users for each charging station.

[0008] Based on the prediction results of the selection probability, a master-slave game model between the charging station operator and the electric vehicle user is constructed, where the charging station operator is the leader and the electric vehicle user is the follower; the charging station operator includes the State Grid charging station operator and the private charging station operator.

[0009] Based on the master-slave game model, the game strategies between the charging station operators are optimized, and the spatial regulation of charging station selection is realized by optimizing the charging price.

[0010] In a specific embodiment of the present invention, the obtaining of the prediction results of the selection probability of users for each charging station includes:

[0011] 1) Collect the historical charging data of electric vehicle users.

[0012] The historical data includes: historical electric vehicle trajectory data and fast charging station data; where, let y i,m,t represent the historical selection result of any user m at time period t choosing the i-th fast charging station FCS i ; if user m chooses to charge at FCS i at time period t, then y i,m,t = 1; otherwise y i,m,t = 0.

[0013] E i,m,t is the charging power information of user m at the i-th fast charging station FCS i in the historical situation at time period t. represents the distance between the location of user m at time period t and the i-th fast charging station FCS i . represents the average charging price of the predicted charging time period when user m goes to FCS i to charge. represents the number of fast charging piles at FCS i . represents the probability that user m selects FCS i among all fast charging station selections. x is the influencing factor of user m's charging station selection at time period t.

[0014] p t,pub represents the price set of all State Grid charging stations at time period t, and p t,pri represents the price set of all private charging stations at time period t.

[0015] 2) Based on the data collected in step 1), establish and solve a response model of electric vehicle users to charging price adjustment to obtain the preference coefficients for users to choose charging stations.

[0016] The response model of electric vehicle users to charging price adjustment is a logistic regression model. Among them, the expression of this logistic regression model for any user m under the influencing factor x is as follows:

[0017]

[0018] In the formula, w m is the weight coefficient reflecting the degree of importance of user m to the influencing factor x; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to ; p i,m,t represents the selection probability of user m for FCS i at time t when the influencing factor is x; b m is the constant term coefficient, which is a coefficient reflecting the degree of importance of user m to other potential influencing factors except x; w m and b m are the preference coefficients of user m;

[0019] The maximum likelihood method is used to solve the logistic regression model, and the expression is as follows:

[0020]

[0021] Solving the logistic regression model to obtain the preference coefficients w m and b m of user m;

[0022] 3) Based on the results of step 2), predict the user's charging selection probability;

[0023] Among them, substitute the w m and b m obtained in step 2 into formula (1) to obtain the selection probability p i of user m for FCS i,m,t at time t when the influencing factor is x.

[0024] In a specific embodiment of the present invention, the master-slave game model includes:

[0025] 1) The user's decision-making objective;

[0026] Among them, denote as the serial number of the charging station selected by user m at time period t, and obtain it by finding the serial number i of the charging station that maximizes p t,pub and p t,pri under the pricing; i,m,t wherein, E

[0027]

[0028] In the formula, E t,i is the charging power of the i-th fast charging station FCS i at time period t;

[0029] 2) The game objective of the charging station operator;

[0030] Among them, the game objective of the State Grid charging station operator is to maximize its own revenue:

[0031]

[0032] In the formula, U pub is the operating revenue of the State Grid charging station operator; U pub,ser and U pub,anx are the charging revenues of the State Grid charging station operator for serving electric vehicles and the revenues for participating in grid congestion elimination respectively;

[0033] Among them, the charging revenue of the State Grid charging station operator for serving electric vehicles is expressed as:

[0034]

[0035] In the formula, the start and end time periods to be regulated are t start and t end respectively, E t,pub is the charging demand power of the charging stations belonging to the State Grid operator at time period t, E t,i is the charging demand power of the i-th fast charging station at time period t, and S pub is the set of charging stations belonging to the State Grid charging station operator;

[0036] The revenue of the State Grid charging station operator for participating in grid congestion is expressed as:

[0037]

[0038] In the formula, ρ represents the revenue coefficient of congestion elimination, which is the price subsidy per kilowatt-hour determined by the grid when the State Grid charging station operator participates in congestion mitigation; ΔE t,trans is the change value of the power demand at time period t before and after the price adjustment; represents the charging demand power of the charging stations owned by the State Grid charging station operators during the time period t after the price adjustment; and are the newly set charging prices for the State Grid charging station operators and private charging station operators during the time period t after the price adjustment, respectively;

[0039] The game objective of the private charging station operator is to maximize its own revenue:

[0040]

[0041] In the formula, U pri is the operating revenue of the private charging station operator; U pri,ser and U pri,anx are the revenue from serving electric vehicle charging and the revenue from participating in grid congestion elimination of the private charging station operator, respectively;

[0042] The revenue of the private charging station operator from serving electric vehicle charging is expressed as:

[0043]

[0044] Among them, E t,pri is the charging demand power of the charging stations owned by the private charging station operator during the time period t, and S pri is the set of charging stations owned by the private charging station operator;

[0045] The revenue of the private charging station operator from participating in grid congestion is expressed as:

[0046]

[0047] Among them, this revenue is zero during non - cooperative games, and during cooperative games, the revenue values of both parties are determined according to the average marginal contribution method, and φ pri is the average marginal contribution value of the private charging station operator during cooperative games.

[0048] In a specific embodiment of the present invention, based on the master - slave game model, optimizing the game strategy between the charging station operators includes:

[0049] The game strategy includes non - cooperative games and cooperative games;

[0050] For non - cooperative games:

[0051] The State Grid charging station operator and the private charging station operator respectively control the prices p t,pub and p t,pri , and their goal is to maximize their respective revenues U pub and U pri ;

[0052] Let the sets of optional prices for State Grid charging station operators and private charging station operators be denoted as follows:

[0053] p t,pub ∈P pub ,p t,pri ∈P pri

[0054] where P pub and P pri are discrete finite sets;

[0055] The optimal pricing strategy is found by the method of marking, i.e.:

[0056]

[0057] In the formula, represents the optimal charging price of the State Grid charging station operator at time period t in the non - cooperative game, represents the optimal charging price of the private charging station operator at time period t in the non - cooperative game; and form the Nash equilibrium solution of the non - cooperative game; the revenue functions of the State Grid charging station operator and the private charging station operator in the non - cooperative game are respectively and

[0058] For the cooperative game:

[0059] The Shapley value is used to calculate the distribution method of the cooperative revenue; p' t,pub ,p′ t,pri By enumerating the discrete finite sets P pub and P pri and then maximizing the total cooperative revenue U pub +U pri is determined. p' t,pub represents the optimal charging price of the State Grid charging station operator at time period t in the cooperative game, p' t,pri represents the optimal charging price of the private charging station operator at time period t in the cooperative game; at this time, the theoretical revenue of the State Grid charging station operator is U pub (p' t,pub ,p' t,pri ), and the theoretical revenue of the private charging station operator is U pri (p' t,pub ,p' t,pri ); The Shapley value φ pub of the State Grid charging station operator is the actual distributed revenue of the State Grid charging station operator in the cooperative game scenario The Shapley value φ pri of the private charging station operator is the actual distributed revenue of the private charging station operator in the cooperative game scenario

[0060]

[0061] If then the State Grid charging station operator chooses non - cooperative game, and the optimized charging price result is and

[0062] If then the State Grid charging station operator chooses cooperative game, and the optimized charging price result is p' t,pub and p' t,pri .

[0063] The second - aspect embodiment of the present invention proposes a game - based electric vehicle price guidance and space regulation device, including:

[0064] A selection probability prediction module, configured to collect historical data related to the charging of electric vehicle users, establish a response model of electric vehicle users to charging price adjustment, so as to obtain the selection probability prediction result of users for each charging station;

[0065] A master - slave game model construction module, configured to construct a master - slave game model between the charging station operator and the electric vehicle users based on the selection probability prediction result, where the charging station operator is the leader and the electric vehicle users are the followers; the charging station operator includes the State Grid charging station operator and private charging station operators;

[0066] A charging price optimization module, configured to optimize the game strategies among the charging station operators based on the master - slave game model, and realize the space regulation of charging station selection by optimizing the charging price.

[0067] In a specific embodiment of the present invention, the obtaining of the selection probability prediction result of users for each charging station includes:

[0068] 1) Collect historical data related to the charging of electric vehicle users;

[0069] The historical data includes: historical electric vehicle trajectory data and fast charging station data; where, let y i,m,t represent the historical selection result of any user m at time period t choosing the i - th fast charging station FCS i ; if user m chooses to charge at FCS i at time period t, then y i,m,t = 1; otherwise y i,m,t = 0;

[0070] E i,m,t is the historical situation where user m at time period t is at the i - th fast charging station FCS iCharging power information; Represents the distance between the location of user m at time period t and the i-th fast charging station FCS i ; Represents the average charging price during the expected charging period when user m goes to FCS for charging at time period t i ; Represents the number of fast charging piles at FCS i ; Represents the probability that user m selects FCS among all fast charging station selections i ; x is the influencing factor for user m's charging station selection at time period t;

[0071] p t,pub Represents the price set of all State Grid charging stations at time period t, p t,pri Represents the price set of all private charging stations at time period t;

[0072] 2) Based on the data collected in step 1), establish a response model for electric vehicle users to charging price adjustment and solve to obtain the preference coefficient for users to make charging station selections;

[0073] The response model for electric vehicle users to charging price adjustment is a logistic regression model. Among them, the expression of this logistic regression model for any user m under the influencing factor x is as follows:

[0074]

[0075] In the formula, w m Is the weight coefficient reflecting the degree of importance of user m to the influencing factor x; Is 's weight coefficient, reflecting the degree of importance of user m to ; Is 's weight coefficient, reflecting the degree of importance of user m to ; Is 's weight coefficient, reflecting the degree of importance of user m to ; Is 's weight coefficient, reflecting the degree of importance of user m to ; p i,m,t Indicates the selection probability of user m for FCS at time period t when the influencing factor is x i ; m b m Is the constant term coefficient, which is the coefficient reflecting the degree of importance of user m to other potential influencing factors except x; w m And b

[0076] The maximum likelihood method is used to solve the logistic regression model, and the expression is as follows:

[0077]

[0078] The preference coefficients w m and b m ;

[0079] 3) Based on the result of step 2), predict the probability of user charging selection;

[0080] Among them, substitute w m and b m obtained in step 2) into formula (1) to obtain the selection probability p i of user m for FCS i,m,t at time t when the influencing factor is x.

[0081] In a specific embodiment of the present invention, the master-slave game model includes:

[0082] 1) User decision-making goal;

[0083] Among them, denote as the serial number of the charging station selected by user m at time t, and obtain the serial number i of the charging station that maximizes p t,pub and p t,pri under the pricing; i,m,t ;

[0084]

[0085] In the formula, E t,i is the charging power of the i-th fast charging station FCS i at time t;

[0086] 2) The game goal of the charging station operator;

[0087] Among them, the game goal of the State Grid charging station operator is to maximize its own revenue:

[0088]

[0089] In the formula, U pub is the operating revenue of the State Grid charging station operator; U pub,ser and U pub,anx are the charging revenues of the State Grid charging station operator for serving electric vehicles and the revenues for participating in the elimination of power grid congestion respectively;

[0090] Among them, the charging revenue of the State Grid charging station operator for serving electric vehicles is expressed as:

[0091]

[0092] Wherein, the start and end time periods to be regulated are \(t_{1}\) start and \(t_{2}\) end respectively, \(E_{t}\) t,pub is the charging demand power of the charging stations belonging to the grid operator during the time period \(t\), \(E_{it}\) t,i is the charging demand power of the \(i\)-th fast charging station during the time period \(t\), and \(S\) pub is the set of charging stations belonging to the grid charging station operator;

[0093] The revenue of the grid charging station operator participating in the grid congestion is expressed as:

[0094]

[0095] Wherein, \(\rho\) represents the revenue coefficient for congestion elimination, which is the per-kWh subsidy price determined by the grid when the grid charging station operator participates in congestion mitigation; \(\Delta E_{t}\) t,trans is the change value of the power demand during the time period \(t\) before and after the price adjustment; represents the charging demand power of the charging stations belonging to the grid charging station operator during the time period \(t\) after the price adjustment; and are the newly set charging prices during the time period \(t\) for the grid charging station operator and the private charging station operator respectively after the price adjustment;

[0096] The game goal of the private charging station operator is to maximize its own revenue:

[0097]

[0098] Wherein, \(U_{p}\) pri is the operating revenue of the private charging station operator; \(U_{ep}\) pri,ser and \(U_{cp}\) pri,anx are the revenue from serving electric vehicle charging and the revenue from participating in grid congestion elimination of the private charging station operator respectively;

[0099] The revenue of the private charging station operator from serving electric vehicle charging is expressed as:

[0100]

[0101] Wherein, \(E_{pt}\) t,pri is the charging demand power of the charging stations belonging to the private charging station operator during the time period \(t\), and \(S_{p}\) pri is the set of charging stations belonging to the private charging station operator;

[0102] The revenue of the private charging station operator participating in the grid congestion is expressed as:

[0103]

[0104] Among them, the benefit of this item is zero in non - cooperative games, while in cooperative games, the benefit values of both parties are determined according to the average marginal contribution method, φ pri is the average marginal contribution value of the private charging station operator in cooperative games.

[0105] In a specific embodiment of the present invention, based on the master - slave game model, optimizing the game strategies among the charging station operators includes:

[0106] The game strategies include non - cooperative games and cooperative games;

[0107] For non - cooperative games:

[0108] The state - grid charging station operator and the private charging station operator respectively control the prices p t,pub and p t,pri , and their goal is to maximize their respective benefits U pub and U pri ;

[0109] Denote the sets of optional prices of the state - grid charging station operator and the private charging station operator as:

[0110] p t,pub ∈P pub , p t,pri ∈P pri

[0111] where, P pub and P pri are discrete finite sets;

[0112] Find the optimal pricing strategy by the method of underlining, that is:

[0113]

[0114] In the formula, represents the optimal charging price of the state - grid charging station operator at time t in non - cooperative games, represents the optimal charging price of the private charging station operator at time t in non - cooperative games; and form the Nash equilibrium solution of non - cooperative games; the benefit functions of the state - grid charging station operator and the private charging station operator in non - cooperative games are respectively and

[0115] For cooperative games:

[0116] Adopt the Shapley value to calculate the distribution method of cooperative benefits; p' t,pub , p′ t,pri By enumerating the discrete finite sets P pub and Ppri Maximize the total cooperation revenue U afterwards pub +U pri Determine, p' t,pub Denote the optimal charging price of the state grid charging station operator at time period t in the cooperative game as p', t,pri and denote the optimal charging price of the private charging station operator at time period t in the cooperative game; at this time, the theoretical revenue of the state grid charging station operator is U pub (p' t,pub , p' t,pri ), and the theoretical revenue of the private charging station operator is U pri (p' t,pub , p' t,pri ); the Shapley value φ of the state grid charging station operator pub is the actual allocated revenue of the state grid charging station operator in the cooperative game scenario The Shapley value φ of the private charging station operator pri is the actual allocated revenue of the private charging station operator in the cooperative game scenario

[0117]

[0118]

[0119] If then the state grid charging station operator chooses a non - cooperative game, and the optimized result of the charging price is and

[0120] If then the state grid charging station operator chooses a cooperative game, and the optimized result of the charging price is p' t,pub and p' t,pri .

[0121] The third - aspect embodiment of the present invention proposes an electronic device, including:

[0122] At least one processor; and a memory communicatively connected to the at least one processor;

[0123] Wherein, the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the above - mentioned method for guiding the price and regulating the space of electric vehicles based on game theory.

[0124] The fourth - aspect embodiment of the present invention proposes a computer - readable storage medium, and the computer - readable storage medium stores computer instructions for causing the computer to execute the above - mentioned method for guiding the price and regulating the space of electric vehicles based on game theory.

[0125] The advantages and beneficial effects of the present invention are as follows:

[0126] The present invention introduces a price guidance mechanism among electric vehicle charging stations. By adjusting the service fees of different charging stations, it guides electric vehicle users to choose different charging stations according to the price, avoiding overloading of charging stations in a specific area, and thus improving the spatial utilization efficiency of charging resources. The present invention takes into account the charging needs of users, the spatial flexibility of charging stations, and the pricing game among charging station operators. Through the game and coordination among different types of charging station operators, it ensures the reasonable allocation of electric vehicle charging resources and optimizes the charging behavior of electric vehicles. The present invention can also improve the operation efficiency of charging stations, promote cooperation among charging station operators, achieve win-win results through reasonable price adjustment, reduce the charging cost of users, and improve the charging experience of users. At the same time, the present invention enhances the spatial flexibility of the charging network, improves the balanced distribution of charging load, and improves the adaptability of charging stations and the operation efficiency of the entire charging network. Brief Description of the Drawings

[0127] Figure 1 It is a flowchart of a game-based electric vehicle price guidance and space regulation method according to an embodiment of the present invention. Detailed Embodiments

[0128] The present invention proposes a game-based electric vehicle price guidance and space regulation method and device, which are further described in detail below with reference to the drawings and specific embodiments.

[0129] An embodiment of the present invention proposes a game-based electric vehicle price guidance and space regulation method, including:

[0130] By collecting historical charging-related data of electric vehicle users, a response model for the adjustment of charging prices by electric vehicle users is established to obtain the prediction result of the selection probability of users for each charging station;

[0131] Based on the selection probability prediction result, a master-slave game model between the charging station operator and the electric vehicle user is constructed, where the charging station operator is the leader and the electric vehicle user is the follower; the charging station operator includes the State Grid charging station operator and the private charging station operator;

[0132] Based on the master-slave game model, the game strategy optimization among the charging station operators is carried out, and the spatial regulation of charging station selection is realized by optimizing the charging price.

[0133] In a specific embodiment of the present invention, the overall process of the game-based electric vehicle price guidance and space regulation method is as Figure 1 shown, including the following steps:

[0134] 1) By collecting the historical data related to the charging of electric vehicle users, a response model for the adjustment of charging prices by users is established to obtain the prediction results of the selection probabilities of users for each charging station. The specific steps are as follows:

[0135] 1-1) Collect the historical data related to the charging of electric vehicle users.

[0136] In this embodiment, the historical data includes: historical electric vehicle trajectory data and fast charging station data. Among them, the electric vehicle trajectory data includes: time, longitude and latitude of the electric vehicle at the corresponding time, vehicle status (parked, driving, charging), and battery level; the electric vehicle trajectory data needs to have a certain time span and a suitable time interval. The time span is to ensure that multiple selection behaviors of a vehicle can be collected and obtained, and the time interval is to avoid being unable to track the state conversion of the vehicle in a timely manner. The fast charging station data includes: charging station attribution information (State Grid / private), longitude and latitude of the charging station location, time-of-use price of the charging station (charging fee + service fee), number of fast charging piles, and power of fast charging piles. Only the time-of-use price is dynamic data.

[0137] In a specific embodiment of the present invention, 170 electric vehicle trajectory data with a time interval of 10 seconds within 100 days and all fast charging station data within the driving area of the electric vehicle are obtained as the original data. Among them, let y i,m,t represent the historical selection result of any user m at time t for the i-th fast charging station FCS i : If the user m selects to charge at FCS i at time t, then y i,m,t = 1; otherwise y i,m,t = 0. E i,m,t is the charging power information of user m at the i-th fast charging station FCS i in the historical situation at time t. represents the distance between the location of user m at time t and the i-th fast charging station FCS i ; represents the average charging price of the expected charging period when user m goes to FCS i to charge; represents the number of fast charging piles of FCS i ; represents the probability that user m selects FCS i among all fast charging station selections, x is the influencing factor for user m's charging station selection at time t. p t,pub represents the price set of all State Grid charging stations at time t, and p t,pri represents the price set of all private charging stations at time t.

[0138] 1-2) Based on the data collected in step 1-1), establish a response model of electric vehicle users to charging price adjustment and solve it to obtain the preference coefficients of users for choosing charging stations.

[0139] In this embodiment, the response model of electric vehicle users to charging price adjustment is a logistic regression model. This model analyzes the sensitivity of electric vehicle users to the pricing of charging stations, quantifies the influence of different factors on users' choice of charging stations, and estimates the preference coefficients.

[0140] Among them, the expression of this logistic regression model for any user m under the influence factor x is as follows:

[0141]

[0142] In the formula, w m is the weight coefficient reflecting the degree of importance of user m to the influence factor x; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to ; is 's weight coefficient, reflecting the degree of importance of user m to . p i,m,t represents the selection probability of user m for FCS i at time t when the influence factor is x; b m is the constant term coefficient, which is the coefficient reflecting the degree of importance of user m to other potential influence factors except x; w m and b m are the preference coefficients of user m and are also the parameters to be optimized in this logistic regression model.

[0143] The maximum likelihood method is used to solve the logistic regression model, and the expression is as follows:

[0144]

[0145] Solving this model obtains the preference coefficients w m and b m of any user m.

[0146] 1-3) Based on the results of step 1-2), predict the user's charging selection probability.

[0147] In this embodiment, the w mand b m Substituting into Equation (1), the selection probability p of user m for FCS at time t when the influencing factor is x is obtained. i of i,m,t In this embodiment, based on the preference coefficients w m and b m of different users, the selection probabilities of users for each charging station under different pricing strategies are simulated, providing a quantitative basis for the charging station operator to optimize the pricing strategy.

[0148] 2) Based on the results of step 1), a master-slave game model between the charging station operator and the electric vehicle users is constructed.

[0149] Among them, the master-slave game model includes:

[0150] 2-1) User decision-making goal.

[0151] In this embodiment, p t,pub and p t,pri are respectively the price sets of all State Grid charging stations and the price sets of all private charging stations at time t, which affect the in x and thus affect p i,m,t through Equation (1). As a follower, the electric vehicle user determines the charging location according to the charging station selection probability p i,m,t calculated in step 1). After comparison, the user determines the charging location according to the principle of the largest probability. Denote as the serial number of the charging station selected by user m at time t, which is obtained by finding the serial number i of the charging station that maximizes p t,pub and p t,pri under the corresponding pricing. i,m,t

[0152]

[0153] In the formula, E t,i is the charging power of the i-th fast charging station FCS i at time t.

[0154] 2-2) Game goal of the charging station operator.

[0155] In this embodiment, as the leader, the charging station operator sets the charging price according to the principle of maximizing its own revenue, and announces the charging price and the charging station location information to the users. The charging station operators in this embodiment include State Grid charging station operators and private charging station operators, where:

[0156] 2-2-1) State Grid charging station operator.

[0157] ​As a bridge between the power grid and EV users, while serving the charging needs of EV users, the State Grid charging station operator can incorporate grid congestion alleviation into its own revenue. Therefore, its game objective is to maximize its own revenue:

[0158]

[0159] In the formula, U pub is the operating revenue of the State Grid charging station operator; U pub,ser and U pub,anx are the charging revenue from serving electric vehicles and the revenue from participating in grid congestion alleviation of the State Grid charging station operator respectively,

[0160] Among them, the charging revenue from serving electric vehicles by the State Grid charging station operator can be expressed as:

[0161]

[0162] In the formula, the start and end time periods to be regulated are t start and t end , E t,pub is the charging demand electricity of the charging stations under the State Grid operator in time period t, E t,i is the charging demand electricity of the i-th fast charging station in time period t, S pub is the set of charging stations under the State Grid charging station operator.

[0163] The revenue of the State Grid charging station operator participating in grid congestion can be expressed as:

[0164]

[0165] In the formula, ρ represents the revenue coefficient of congestion alleviation, which is the per-kWh subsidy price determined by the power grid when the State Grid charging station operator participates in congestion mitigation. ΔE t,trans is the change value of the electricity demand in time period t before and after the price adjustment. represents the charging demand electricity of the charging stations under the State Grid charging station operator in time period t after the price adjustment, and are the newly set charging prices in time period t by the State Grid charging station operator and the private charging station operator respectively after the price adjustment.

[0166] 2-1-2) Private charging station operator.

[0167] The game objective of the private charging station operator is to maximize its own revenue:

[0168]

[0169] In the formula, U pri is the operating revenue of the private charging station operator; U pri,ser and Upri,anx They are the revenue from serving electric vehicle charging and the revenue from participating in grid congestion elimination for private power station operators respectively.

[0170] The revenue from serving electric vehicle charging for private power station operators can be expressed as:

[0171]

[0172] In the formula, E t,pri is the charging demand electricity of the charging stations owned by private charging station operators in period t, and E t,i is the charging demand electricity of the i-th fast charging station in period t, and S pri is the set of charging stations owned by private charging station operators.

[0173] The revenue of private power station operators participating in grid congestion can be expressed as:

[0174]

[0175] Among them, this revenue is zero in non-cooperative games, and in cooperative games, the revenue values of both parties are determined according to the average marginal contribution method. φ pri is the average marginal contribution value of private charging station operators in cooperative games.

[0176] 3) Based on the master-slave game model constructed in step 2), optimize the game strategies among charging station operators, and realize the spatial regulation of charging station selection by optimizing the electric vehicle charging price.

[0177] In this embodiment, according to the revenue situation in different scenarios, charging station operators can choose to conduct non-cooperative games or cooperative games to achieve the goal of maximizing revenue and eliminating grid congestion.

[0178] For non-cooperative games:

[0179] During high charging demand periods, State Grid charging station operators can attract price-sensitive users by reducing prices and reduce the charging demand in congested areas. If the congested areas are operated by private charging station operators, the two parties form a non-cooperative game relationship, and each conducts pricing competition with the goal of maximizing revenue, and finally reaches a Nash equilibrium. State Grid charging station operators and private charging station operators respectively control the prices p t,pub and p t,pri , and their goal is to maximize their respective revenue functions U pub and U pri .

[0180] Let the sets of optional prices for State Grid charging station operators and private charging station operators be respectively:

[0181] p t,pub ∈P pub , pt,pri ∈P pri

[0182] where P pub and P pri are discrete finite sets.

[0183] The line-drawing method is used to find the optimal pricing strategy. Its core idea is to continuously construct constraint planes so that the solution set converges to the optimal solution.

[0184] When no player can unilaterally increase their own profit by adjusting the price, that is:

[0185]

[0186] In the formula, represents the optimal charging price of the national grid charging station operator during period t in the non-cooperative game, is the optimal charging price of the private charging station operator during period t in the non-cooperative game; and form the Nash equilibrium solution of the non-cooperative game; the profit functions of the national grid charging station operator and the private charging station operator in the non-cooperative game are respectively and

[0187] For the cooperative game:

[0188] In the case of a high demand for congestion elimination, the private charging station operator may hinder the optimization strategy of the national grid charging station operator. Therefore, it can be considered that the two form an alliance to achieve an overall profit increase. This embodiment adopts the Shapley value to calculate the distribution method of the cooperative profit, ensuring that both parties can obtain reasonable returns under cooperation and avoiding profit losses caused by non-cooperative competition. The profit of the national grid charging station operator operating alone is U pub , and the profit of the private charging station operator operating alone is U pri . p' t,pub , p′ t,pri By enumerating the discrete finite sets P pub and P pri and then maximizing the total cooperative profit U pub +U pri is determined. p' t,pub represents the optimal charging price of the national grid charging station operator during period t in the cooperative game, and p' t,pri represents the optimal charging price of the private charging station operator during period t in the cooperative game; at this time, the theoretical profit of the national grid charging station operator is U pub (p' t,pub , p' t,pri ), and the theoretical profit of the private charging station operator is Upri (p' t,pub , p' t,pri ); however, according to the distribution method of cooperative game, the Shapley value needs to be used as the actual distribution benefit. The Shapley value φ of State Grid charging station operators pub is the actual distribution benefit of State Grid charging station operators in the cooperative game scenario The Shapley value φ of private charging station operators pri is the actual distribution benefit of private charging station operators in the cooperative game scenario

[0189]

[0190]

[0191] Specifically, this embodiment helps charging station operators select the optimal strategy by analyzing the charging station benefits, electric vehicle user distribution, and grid congestion elimination effects under different game strategies (non - cooperative game vs. cooperative game); among them:

[0192] If then the State Grid charging station operator selects a non - cooperative game, and the optimized charging price result is and The State Grid charging station operator will as the pricing strategy for subordinate charging stations.

[0193] If then the State Grid charging station operator selects a cooperative game, and the optimized charging price result is p' t,pub and p' t,pri , and the State Grid charging station operator will use p' t,pub as the pricing strategy for subordinate charging stations. Dynamically adjust the pricing strategy according to real - time operation data to adapt to market changes and improve the efficiency of the overall charging network.

[0194] To implement the above - mentioned embodiment, a second - aspect embodiment of the present invention proposes a game - based electric vehicle price guidance and space regulation device, including:

[0195] A selection probability prediction module, configured to establish a response model of electric vehicle users to charging price adjustment by collecting historical data related to the charging of electric vehicle users, so as to obtain the prediction result of the selection probability of users for each charging station;

[0196] A master - slave game model construction module, configured to construct a master - slave game model between charging station operators and electric vehicle users based on the selection probability prediction result, where the charging station operator is the leader and the electric vehicle user is the follower; the charging station operator includes State Grid charging station operators and private charging station operators;

[0197] A charging price optimization module, which is used to optimize the game strategies among the charging station operators based on the master-slave game model, and realize the spatial regulation of charging station selection by optimizing the charging price.

[0198] In a specific embodiment of the present invention, the obtaining of the prediction result of the selection probability of each charging station by the user includes:

[0199] 1) Collect the historical charging-related data of electric vehicle users;

[0200] The historical data includes: historical electric vehicle trajectory data and fast charging station data; where, let y i,m,t represent the historical selection result of any user m at time period t choosing the i-th fast charging station FCS i ; if user m chooses to charge at FCS i at time period t, then y i,m,t =1; otherwise y i,m,t =0;

[0201] E i,m,t is the charging power information of user m at the i-th fast charging station FCS i in the historical situation at time period t; represents the distance between the location of user m at time period t and the i-th fast charging station FCS i ; represents the average charging price of the expected charging time period when user m goes to FCS i to charge; represents the number of fast charging piles at FCS i ; represents the probability that user m selects FCS i among all fast charging station selections, x is the influencing factor of user m's charging station selection at time period t;

[0202] p t,pub represents the price set of all State Grid charging stations at time period t, and p t,pri represents the price set of all private charging stations at time period t;

[0203] 2) Based on the data collected in step 1), establish and solve a response model of electric vehicle users to charging price adjustment to obtain the preference coefficient of users for charging station selection;

[0204] The response model of electric vehicle users to charging price adjustment is a logistic regression model. Among them, the expression of this logistic regression model for any user m under the influencing factor x is as follows:

[0205]

[0206] In the formula, w m is the weight coefficient reflecting the degree of importance that user m attaches to influencing factor x; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; p i,m,t represents the selection probability of user m for FCS at time period t when the influencing factor is x i ; b m is the constant term coefficient, which is a coefficient reflecting the degree of importance that user m attaches to other potential influencing factors except x; w m and b m are the preference coefficients of user m;

[0207] The maximum likelihood method is used to solve the above-mentioned logistic regression model, and the expression is as follows:

[0208]

[0209] The preference coefficients w m and b m of user m are obtained by solving the above-mentioned logistic regression model;

[0210] 3) Based on the results of step 2), predict the user's charging selection probability;

[0211] Among them, substituting the w m and b m obtained in step 2) into formula (1), the selection probability p i of user m for FCS at time period t when the influencing factor is x is obtained i,m,t .

[0212] In a specific embodiment of the present invention, the master-slave game model includes:

[0213] 1) User decision-making goal;

[0214] Among them, denote as the serial number of the charging station selected by user m at time period t, and by finding p t,pub and p t,pri under the pricing such that p i,m,tThe largest charging station serial number i is obtained;

[0215]

[0216] Wherein, E t,i is the charging power of the i-th fast charging station FCS i at time period t;

[0217] 2) The game objective of the charging station operator;

[0218] Among them, the game objective of the State Grid charging station operator is to maximize its own revenue:

[0219]

[0220] Wherein, U pub is the operating revenue of the State Grid charging station operator; U pub,ser and U pub,anx are the charging revenues of the State Grid charging station operator for serving electric vehicles and the revenue for participating in the elimination of power grid congestion respectively;

[0221] Among them, the charging revenue of the State Grid charging station operator for serving electric vehicles is expressed as:

[0222]

[0223] Wherein, the start and end time periods to be regulated are t start and t end , E t,pub is the charging demand power of the charging stations belonging to the State Grid operator at time period t, E t,i is the charging demand power of the i-th fast charging station at time period t, S pub is the set of charging stations belonging to the State Grid charging station operator;

[0224] The revenue of the State Grid charging station operator participating in the power grid congestion is expressed as:

[0225]

[0226] Wherein, ρ represents the revenue coefficient for congestion elimination, which is the price subsidy per kilowatt-hour determined by the power grid when the State Grid charging station operator participates in congestion mitigation; ΔE t,trans is the change value of the power demand at time period t before and after the price adjustment; represents the charging demand power of the charging stations belonging to the State Grid charging station operator at time period t after the price adjustment; and are the newly set charging prices at time period t by the State Grid charging station operator and the private charging station operator respectively after the price adjustment;

[0227] The game objective of the private charging station operator is to maximize its own revenue:

[0228]

[0229] Wherein, U pri is the operating revenue of the private charging station operator; U pri,ser and U pri,anx are the charging revenue of the private charging station operator for serving electric vehicle charging and the revenue for participating in eliminating grid congestion respectively;

[0230] The charging revenue of the private charging station operator for serving electric vehicle charging is expressed as:

[0231]

[0232] Wherein, E t,pri is the electricity demand for charging at the charging stations owned by the private charging station operator at time period t, and S pri is the set of charging stations owned by the private charging station operator;

[0233] The revenue of the private charging station operator for participating in grid congestion is expressed as:

[0234]

[0235] Wherein, this revenue is zero in the case of non - cooperative game, and in the case of cooperative game, the revenue values of both parties are determined according to the average marginal contribution method, and φ pri is the average marginal contribution value of the private charging station operator in the case of cooperative game.

[0236] In a specific embodiment of the present invention, based on the master - slave game model, optimizing the game strategies among the charging station operators includes:

[0237] The game strategies include non - cooperative game and cooperative game;

[0238] For the non - cooperative game:

[0239] The state - grid charging station operator and the private charging station operator respectively control the prices p t,pub and p t,pri , and their goal is to maximize their respective revenues U pub and U pri ;

[0240] Denote the sets of optional prices of the state - grid charging station operator and the private charging station operator as:

[0241] p t,pub ∈P pub , p t,pri ∈P pri

[0242] Wherein, P pub and P priis a discrete finite set;

[0243] The optimal pricing strategy is found by the line-drawing method, i.e.:

[0244]

[0245] wherein, represents the optimal charging price of the national grid charging station operator at time period t in the non - cooperative game, represents the optimal charging price of the private charging station operator at time period t in the non - cooperative game; and form the Nash equilibrium solution of the non - cooperative game; The revenue functions of the national grid charging station operator and the private charging station operator in the non - cooperative game are respectively and

[0246] For the cooperative game:

[0247] The Shapley value is used to calculate the distribution method of the cooperative revenue; p' t,pub , p′ t,pri By enumerating the discrete finite set P pub and P pri and then maximizing the total cooperative revenue U pub +U pri it is determined that p' t,pub represents the optimal charging price of the national grid charging station operator at time period t in the cooperative game, and p' t,pri represents the optimal charging price of the private charging station operator at time period t in the cooperative game; At this time, the theoretical revenue of the national grid charging station operator is U pub (p' t,pub , p' t,pri ), and the theoretical revenue of the private charging station operator is U pri (p' t,pub , p' t,pri );The Shapley value φ pub of the national grid charging station operator is the actual allocated revenue of the national grid charging station operator in the cooperative game scenario The Shapley value φ pri of the private charging station operator is the actual allocated revenue of the private charging station operator in the cooperative game scenario

[0248]

[0249] If then the national grid charging station operator chooses the non - cooperative game, and the optimized results of the charging price are and

[0250] If Then the operator of the State Grid charging station chooses a cooperative game, and the optimized charging price result is p' t,pub and p' t,pri .

[0251] Thus, through optimizing the price and space regulation, the optimized spatial distribution of the charging load can be achieved, the resource utilization rate of the charging station can be improved, the grid congestion can be alleviated, and further technical support can be provided for the efficient operation of the electric vehicle charging system.

[0252] To implement the above embodiments, the third aspect embodiment of the present invention proposes an electronic device, including:

[0253] At least one processor; and a memory communicatively connected to the at least one processor;

[0254] Wherein, the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the above-mentioned method for guiding the price and regulating the space of electric vehicles based on game theory.

[0255] To implement the above embodiments, the fourth aspect embodiment of the present invention proposes a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the above-mentioned method for guiding the price and regulating the space of electric vehicles based on game theory.

[0256] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0257] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; it can also exist separately without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device executes a method for guiding the price and regulating the space of an electric vehicle based on a game in the above-mentioned embodiment.

[0258] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0259] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0260] In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0261] Any process or method description in the flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0262] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0263] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0264] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0265] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist separately as individual physical units, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0266] The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A game-based electric vehicle price guidance and space regulation method, characterized in that Including: By collecting the historical charging-related data of electric vehicle users, a response model of electric vehicle users to charging price adjustment is established to obtain the prediction results of the selection probability of users for each charging station; Based on the prediction results of the selection probability, a principal-agent game model between the charging station operators and electric vehicle users is constructed, where the charging station operators are the leaders and the electric vehicle users are the followers; the charging station operators include State Grid charging station operators and private charging station operators; Based on the principal-agent game model, the game strategies between the charging station operators are optimized, and the spatial regulation of charging station selection is realized by optimizing the charging price.

2. The method according to claim 1, wherein The obtaining of the prediction results of the selection probability of users for each charging station includes: 1) Collect the historical charging-related data of electric vehicle users; The historical data includes: historical electric vehicle trajectory data and fast charging station data; among them, let y i,m,t represent the historical selection result that user m selects the i-th fast charging station FCS at time period t i ; if user m selects to charge at FCS i at time period t, then y i,m,t = 1; otherwise y i,m,t = 0; E i,m,t is the charging power information of user m at the i-th fast charging station FCS during time period t in the historical scenario i ; represents the distance between the location of user m at time period t and the i-th fast charging station FCS i ; represents the average charging price during the expected charging time period when user m goes to FCS i for charging; represents the number of fast charging piles at FCS i ; represents the probability that user m selects FCS among all fast charging station selections i ; x is the influencing factor for user m's charging station selection at time period t p t,pub represents the price set of all State Grid charging stations at time period t, p t,pri represents the price set of all private charging stations at time period t; 2) Based on the data collected in step 1), establish and solve a response model of electric vehicle users to charging price adjustment to obtain the preference coefficients of users for charging station selection; The response model of electric vehicle users to charging price adjustment is a logistic regression model. The expression of this logistic regression model for any user m under the influencing factor x is as follows: In the formula, $w_m$ is the weight coefficient reflecting the degree of importance that user m attaches to the influencing factor x; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; p i,m,t represents the selection probability of user m for FCS i at time t when the influencing factor is x; b m is the constant term coefficient, which is a coefficient reflecting the degree of importance that user m attaches to other potential influencing factors except x; w m and b m are the preference coefficients of user m; The maximum likelihood method is used to solve the logistic regression model, and the expression is as follows: Solving the logistic regression model to obtain the preference coefficients w m and b m ; 3) Based on the results of step 2), predict the charging selection probability of users; Among them, substitute the w m and b m obtained in step 2) into formula (1) to obtain the selection probability p i of user m for FCS i,m,t at time period t when the influencing factor is x.

3. The method according to claim 2, wherein The principal-agent game model includes: 1) User decision-making objectives; Among them, denote as the charging station serial number selected by user m at time period t. By finding the charging station serial number i that maximizes p t,pub and p t,pri under the pricing, we can obtain it; i,m,t ​ where E t,i is the charging power of the i-th fast charging station FCS i at time period t; 2) The game objectives of the charging station operators; Among them, the game objective of the State Grid charging station operator is to maximize its own benefits: Where, U pub is the operating income of the State Grid charging station operator; U pub,ser and U pub,anx are the charging income of the State Grid charging station operator serving electric vehicles and the income from participating in the elimination of grid congestion respectively; Among them, the income of the State Grid charging station operator for serving electric vehicle charging is expressed as: Wherein, the start and end time periods to be regulated are t start and t end , E t,pub is the charging demand power of the charging stations belonging to the national grid operator during the time period t, and E t,i is the charging demand power of the i-th fast charging station during the time period t, and S pub is the set of charging stations belonging to the national grid charging station operator; The income of the State Grid charging station operator participating in grid congestion is expressed as: In the formula, ρ represents the benefit coefficient of congestion elimination, which is the subsidy price per kWh determined by the power grid when the State Grid charging station operator participates in congestion mitigation; ΔE t,trans is the change value of the electricity demand in period t before and after the price adjustment; represents the electricity demand for charging at the charging stations owned by the State Grid charging station operator in period t after the price adjustment; and are the newly set charging prices in period t for the State Grid charging station operator and the private charging station operator after the price adjustment, respectively; The game objective of the private charging station operator is to maximize its own benefits: Where, U pri is the operating revenue of the private charging station operator; U pri,ser and U pri,anx are the charging revenue from serving electric vehicles and the revenue from participating in grid congestion elimination of the private power station operator, respectively; The income of the private charging station operator for serving electric vehicle charging is expressed as: Among them, E t,pri is the charging demand power of the charging stations owned by the private charging station operator during period t, and S pri is the set of the charging stations owned by the private charging station operator; The income of the private charging station operator participating in grid congestion is expressed as: Among them, the revenue of this item is zero in the case of non - cooperative game, while in the case of cooperative game, the revenue values of both parties are determined according to the average marginal contribution method, φ pri is the average marginal contribution value of the private charging station operator in the cooperative game.

4. The method according to claim 3, wherein The performing of the game strategy optimization between the charging station operators based on the principal-agent game model includes: The game strategies include non-cooperative games and cooperative games; For non-cooperative games: The national grid charging station operator and the private charging station operator respectively control the prices p t,pub and p t,pri with the goal of maximizing their respective revenues U pub and U pri ; Denote the optional price sets of the State Grid charging station operator and the private charging station operator as: p t,pub ∈P pub ,p t,pri ∈P pri where P pub and P pri are discrete finite sets; Find the optimal pricing strategy by the method of underlining, that is: In the formula, represents the optimal charging price of the State Grid charging station operator at time period t in the non - cooperative game, represents the optimal charging price of the private charging station operator at time period t in the non - cooperative game; and form the Nash equilibrium solution of the non - cooperative game; the revenue functions of the State Grid charging station operator and the private charging station operator in the non - cooperative game are respectively and For cooperative games: Adopt the Shapley value to calculate the distribution method of cooperative benefits; p' t,pub , p′ t,pri By enumerating the discrete finite set P pub and P pri Then maximize the total cooperative benefit U pub +U pri Determined, p' t,pub Indicates the optimal charging price of the national grid charging station operator at time period t in the cooperative game, p' t,pri Indicates the optimal charging price of the private charging station operator at time period t in the cooperative game; at this time, the theoretical benefit of the national grid charging station operator is U pub (p' t,pub , p' t,pri) , and the theoretical benefit of the private charging station operator is U pri (p' t,pub , p' t,pri) ; The Shapley value φ of the national grid charging station operator pub Is the actual distribution benefit of the national grid charging station operator in the cooperative game scenario The Shapley value φ of the private charging station operator pri Is the actual distribution benefit of the private charging station operator in the cooperative game scenario If then the operator of State Grid charging stations chooses non - cooperative game, and the optimized charging price result is and If then the grid-connected charging station operator chooses a cooperative game, and the optimized charging price result is p' t,pub and p' t,pri .

5. A game-based electric vehicle price guidance and space regulation device, characterized in that, Including: A selection probability prediction module for establishing a response model of electric vehicle users to charging price adjustment by collecting the historical charging-related data of electric vehicle users to obtain the prediction results of the selection probability of users for each charging station; A principal-agent game model construction module for constructing a principal-agent game model between the charging station operators and electric vehicle users based on the prediction results of the selection probability, where the charging station operators are the leaders and the electric vehicle users are the followers; the charging station operators include State Grid charging station operators and private charging station operators; A charging price optimization module for performing game strategy optimization between the charging station operators based on the principal-agent game model and realizing the spatial regulation of charging station selection by optimizing the charging price.

6. The transposition according to claim 5, characterized in that, The obtaining of the prediction results of the selection probability of users for each charging station includes: 1) Collect the historical charging-related data of electric vehicle users; The historical data includes: historical electric vehicle trajectory data and fast charging station data; among them, let y i,m,t represent the historical selection result that user m selects the i-th fast charging station FCS at time period t i ; if user m selects to charge at FCS i at time period t, then y i,m,t = 1; otherwise y i,m,t = 0; E i,m,t The charging power information of user m at the i-th fast charging station FCS during time period t in the historical situation i ; Represents the distance between the location of user m at time period t and the i-th fast charging station FCS i ; Represents the average charging price of the expected charging time period when user m goes to FCS i for charging; Represents the number of fast charging piles at FCS i ; Represents the probability that user m selects FCS among all fast charging station selections i ; x is the influencing factor for user m's charging station selection at time period t p t,pub represents the set of prices of all State Grid charging stations at time period t, p t,pri represents the set of prices of all private charging stations at time period t; 2) Based on the data collected in step 1), establish a response model of electric vehicle users to charging price adjustment and solve to obtain the preference coefficient of users for choosing charging stations. The response model of electric vehicle users to charging price adjustment is a logistic regression model. Among them, the expression of this logistic regression model for any user m under the influencing factor x is as follows: In the formula, w m is the weight coefficient reflecting the degree of importance that user m attaches to influencing factor x; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; is 's weight coefficient, reflecting the degree of importance that user m attaches to ; p i,m,t represents the selection probability of user m for FCS i at time period t when the influencing factor is x; b m is the constant term coefficient, which is a coefficient reflecting the degree of importance that user m attaches to other potential influencing factors except x; w m and b m are the preference coefficients of user m; The maximum likelihood method is used to solve the logistic regression model, and the expression is as follows: Solving the logistic regression model to obtain the preference coefficients w and b of user m m and b m ; 3) Based on the results of step 2), predict the probability of user charging selection. Among them, substituting the w m and b m obtained in step 2) into formula (1), the selection probability p i of user m for FCS i,m,t at time period t when the influencing factor is x is obtained.

7. The device according to claim 6, characterized in that, The master-slave game model includes: 1) User decision-making goal; Among them, denote as the charging station serial number selected by user m at time period t, and obtain it by finding the charging station serial number i that maximizes p t,pub under the pricing of p t,pri and p i,m,t ; where E t,i is the charging power of the i-th fast charging station FCS i at time period t; 2) The game goal of charging station operators; Among them, the game goal of State Grid charging station operators is to maximize their own benefits: Where, U pub is the operating revenue of the State Grid charging station operator; U pub,ser and U pub,anx are the charging revenue of the State Grid charging station operator for serving electric vehicles and the revenue from participating in the elimination of grid congestion respectively; Among them, the revenue of State Grid charging station operators from serving electric vehicle charging is expressed as: wherein, the start and end time periods to be regulated are t start and t end , E t,pub is the charging demand power of the charging stations belonging to the national grid operator during the time period t, E t,i is the charging demand power of the i-th fast charging station during the time period t, S pub is the set of charging stations belonging to the national grid charging station operator; The revenue of State Grid charging station operators participating in grid congestion is expressed as: Where ρ represents the benefit coefficient of congestion elimination, which is the per-kWh subsidy price determined by the power grid when the State Grid charging station operator participates in congestion mitigation; ΔE t,trans is the change value of the electricity demand in period t before and after the price adjustment; represents the electricity consumption demand for charging at the charging stations owned by the State Grid charging station operator in period t after the price adjustment; and are the newly set charging prices in period t for the State Grid charging station operator and the private charging station operator respectively after the price adjustment; The game goal of private charging station operators is to maximize their own benefits: Where, U pri is the operating revenue of the private charging station operator; U pri,ser and U pri,anx are the charging revenue from serving electric vehicles and the revenue from participating in the elimination of grid congestion for the private power station operator, respectively; The revenue of private charging station operators from serving electric vehicle charging is expressed as: Among them, E t,pri is the charging demand power of the charging stations belonging to the private charging station operator during period t, and S pri is the set of charging stations belonging to the private charging station operator; The revenue of private charging station operators participating in grid congestion is expressed as: Among them, the benefit of this item is zero in non - cooperative games, while in cooperative games, the benefit values of both parties are determined according to the average marginal contribution method, φ pri is the average marginal contribution value of private charging station operators in cooperative games.

8. The device according to claim 7, characterized in that, Based on the master-slave game model, optimize the game strategies among the charging station operators, including: The game strategies include non-cooperative games and cooperative games; For non-cooperative games: The national grid charging station operator and the private charging station operator respectively control the prices p t,pub and p t,pri , with the goal of maximizing their respective revenues U pub and U pri ; Denote the sets of optional prices of State Grid charging station operators and private charging station operators as: p t,pub ∈P pub ,p t,pri ∈P pri where P pub and P pri are discrete finite sets; Find the optimal pricing strategy through the method of underlining, that is: Wherein, represents the optimal charging price of the State Grid charging station operator at time period t in the non - cooperative game, represents the optimal charging price of the private charging station operator at time period t in the non - cooperative game; and form the Nash equilibrium solution of the non - cooperative game; the revenue functions of the State Grid charging station operator and the private charging station operator in the non - cooperative game are respectively and For cooperative games: Adopt the Shapley value to calculate the distribution method of cooperation benefits; p' t,pub , p′ t,pri By enumerating the discrete finite set P pub and P pri and then maximizing the total cooperation benefit U pub +U pri decide, p' t,pub represents the optimal charging price of the State Grid charging station operator at time period t in the cooperation game, p' t,pri represents the optimal charging price of the private charging station operator at time period t in the cooperation game; at this time, the theoretical benefit of the State Grid charging station operator is U pub (p' t,pub , p' t,pri ), and the theoretical benefit of the private charging station operator is U pri (p' t,pub , p' t,pri ); the Shapley value φ of the State Grid charging station operator pub is the actual distribution benefit of the State Grid charging station operator in the cooperation game scenario The Shapley value φ of the private charging station operator pri is the actual distribution benefit of the private charging station operator in the cooperation game scenario If then the operator of State Grid charging stations chooses non - cooperative game, and the optimized charging price result is and If then the grid-connected charging station operator chooses a cooperative game, and the optimized charging price result is p' t,pub and p' t,pri .

9. An electronic device, characterized in that, Include: At least one processor; And a memory communicatively connected to the at least one processor; Among them, the memory stores instructions executable by the at least one processor, and the instructions are set to execute the method according to any one of claims 1-4 above.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images