Electric vehicle cluster multi-package master-slave game ordered charging optimization method

Abstract

The invention discloses an electric vehicle cluster multi-package master-slave game ordered charging optimization method, and relates to the technical field of charging optimization, and the method comprises the following steps: collecting charging information, and fitting the probability distribution of the charging demands of different charging piles in each time period based on a probability prediction method; setting an electric vehicle charging package according to the probability distribution of the charging demand and the power purchase and sale price of the power distribution network; and constructing a charging cost model according to the charging information, and forming an electric vehicle charging load package selection method in combination with an electric vehicle charging package. Road network information, vehicle owner behavior tracks and power grid topological structure information are comprehensively considered, probability distribution of charging requirements of different charging piles in each time period is fitted based on an improved LightGBM model method, and a fixed electricity price package mode, a peak-valley electricity price package mode and a step electricity price package mode are formulated according to personalized charging requirements of the electric vehicle. And the charging load of the electric vehicle performs package selection according to the charging demand of the electric vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of charging optimization, and in particular to a method for optimizing the orderly charging of electric vehicle clusters using a multi-package master-slave game. Background Art

[0002] Large-scale development of new energy has become the core direction of my country's energy and power industry. The dual-carbon strategic goal has further promoted the development of new energy. The proportion of installed capacity of renewable energy such as wind power and photovoltaic power has continued to rise, which has given the power system green attributes while increasing the uncertainty of safe and stable operation. Electric vehicles are considered to be "new energy" on the load side. Compared with traditional fuel vehicles, electric vehicles operate through charging and discharging of battery systems, which effectively responds to the country's dual-carbon strategy.

[0003] The number of electric vehicles in my country continues to rise, and the large-scale charging load of electric vehicles will bring a series of challenges and opportunities to the distribution network. The charging load of electric vehicles is affected by factors such as the number of vehicles, type, charging time, charging duration, and charging frequency, and is random in time and space distribution. During disordered charging, the peak of the charging load often overlaps with the peak of the residential electricity load, resulting in an increase in the peak-to-valley difference in electricity load, increasing the peak-shaving pressure of the power grid, and reducing the investment efficiency of the distribution network. With the large-scale access of new energy power sources, their volatility and randomness are superimposed on the randomness of the charging load, making the dispatch of the power system more complicated. The orderly charging of electric vehicles has positive effects such as peak shaving and valley filling, and promoting the consumption of clean energy, which can effectively alleviate the peak-shaving pressure of the power grid.

[0004] Electricity price control is an effective means to guide the orderly charging of electric vehicles. It refers to the use of electricity price incentives such as time-of-use electricity prices, real-time electricity prices and peak electricity prices to increase charging costs when the load is large and reduce charging costs when the load is small. It takes advantage of the user's desire to save electricity and guides users to charge during low-load periods. At the same time, the real-time electricity price and tiered electricity price mechanism can also guide users' demand periods to coincide with periods when new energy power generation is sufficient, which is in line with the intermittent nature of new energy output, reduces wind and solar power abandonment, improves grid reliability, and maintains a balance between supply and demand in the electricity market.

[0005] Residential communities are high-frequency charging areas for electric vehicles, and face many problems such as a surge in charging load and limited transformer capacity, which lead to conflicts between residents' electricity consumption and electric vehicle charging needs. It is necessary to guide electric vehicles to charge in an orderly manner to alleviate the problem of tight electricity supply and demand in residential communities, which is conducive to delaying the high cost of replacing transformers in residential communities and further meeting the personalized charging needs of different electric vehicle users. Summary of the invention

[0006] In view of the problems existing in the existing electric vehicle cluster multi-package master-slave game orderly charging optimization method, the present invention is proposed.

[0007] Therefore, the problem to be solved by the present invention is that the charging time of electric vehicles cannot be guided, which will lead to an increase in the peak-to-valley difference of power load and increase the peak-shaving pressure of the power grid.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, an embodiment of the present invention provides a method for optimizing the orderly charging of a multi-package master-slave game of an electric vehicle cluster, which comprises the following steps:

[0010] Collect charging information and fit the probability distribution of charging demand at different charging piles in different time periods based on the probability prediction method;

[0011] Set up electric vehicle charging packages based on the probability distribution of charging demand and the price of electricity purchased and sold by the distribution network;

[0012] A charging cost model is constructed based on the charging information, and combined with the electric vehicle charging package, a method for selecting the electric vehicle charging load package is formed.

[0013] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, wherein: the charging information includes the road network information around the community, the behavior trajectory of the car owner, and the topology of the power grid;

[0014] The road network information around the community includes road network nodes, road connection conditions, road grades, real-time traffic, and congestion conditions;

[0015] The owner's behavior trajectory includes the probability distribution of travel time, road section travel time, destination stay time, trip departure time, user power status, and charging time;

[0016] The grid topology structure includes transformer capacity, parameters of different branches in the community, node locations, and node parameters.

[0017] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, the probability distribution fitting method of charging demand of different charging piles in different time periods includes:

[0018] Based on the improved LightGBM model, the single-point prediction objective function is set, and the mathematical formula is expressed as:

[0019]

[0020] Where L represents the objective function of the LightGBM model. Represented as the predicted value of the charging pile in the tth period With the true value x t The error relationship between Ω(f k) is represented as the regular term of the LightGBM model, γ and γ are both represented as penalty coefficients, A is represented as the number of nodes in the kth tree of the LightGBM model, ω a Represented as the weight of the ath node of the kth tree of the LightGBM model;

[0021] Use the forward distribution algorithm to derive the objective function after the i-th iteration and solve the weight number ω a The minimum value of is obtained to obtain the objective function. The specific formula is expressed as:

[0022]

[0023] I a ={iq(x i )=a}

[0024] Where, L (i) It is represented as the objective function after the derivative of the i-th iteration of the LightGBM model, I is represented as the total number of iterations of the LightGBM model, ω is represented as the weight of the k-th tree of the LightGBM model, and g is represented as i and h i They are respectively represented as the coefficients of the derivative of the i-th iteration and are both penalty coefficients, f i (x i ) represents the iterative derivation of the actual value of the charging pile in each period of the LightGBM model, I a It is represented as the set of nodes of each tree, and ω is represented as the weight of the i-th iteration derivative of the k-th tree of the LightGBM model;

[0025] The non-parametric kernel density estimation model is used to establish a probability distribution model for the prediction error of charging demand in each period faced by charging piles. The mathematical formula is expressed as follows:

[0026]

[0027] In the formula, It is represented by the predicted value of the charging pile in each period, and x′ is represented by the predicted error value of the charging pile in each period. It is represented as the probability distribution model of charging demand prediction error in each period, and σ is represented as the free parameter of the probability distribution model.

[0028] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, the electric vehicle charging package includes a fixed electricity price package mode, a peak-valley electricity price package mode and a ladder electricity price package mode;

[0029] The fixed electricity price package mode is a fixed electricity price for the whole day with no limit on the charging amount;

[0030] The peak-valley electricity price package model is to formulate peak-valley electricity prices to guide the charging load of electric vehicles and participate in peak-shaving and valley-filling of the power grid;

[0031] The step electricity price package model sets the charging amount of the electric vehicle charging load to N levels, implements different electricity quantity standards and electricity price standards in each level of the step-by-step electricity price, and guides the agent electric vehicle charging load to charge reasonably.

[0032] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, in which: in the fixed electricity price package mode, the electricity sales revenue of the mth charging pile is expressed as:

[0033]

[0034] In the formula, It is expressed as the fixed electricity price package mode revenue of the charging pile in the dth day and time period t, It is represented as the fixed electricity price of the charging pile at time t on day d, It is represented by the electricity sales of the charging pile at time period t on day d;

[0035] In the peak-valley electricity price package model, the electricity sales revenue of the mth charging pile is expressed as:

[0036]

[0037] In the formula, It is expressed as the revenue of the charging pile in the peak-valley electricity price package mode at time t on day d, It is expressed as the peak, valley and normal period electricity price, T P , T M and T V Represents the peak, valley and average time periods. and It is expressed as the settlement price of charging piles during peak, valley and normal periods;

[0038] In the tiered electricity price package model, the electricity sales revenue of the mth charging pile is expressed as:

[0039]

[0040] In the formula, It is expressed as the income of the tiered electricity price package model in the dth day and time period t, It is represented by the tiered electricity price of the charging pile in time period t, and They represent the electricity prices of charging piles under different electricity standards. It is represented by the sales volume of the charging pile in the tiered electricity price package at time t on day d, and Indicates the boundaries for different electrical quantity standards.

[0041] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, the charging cost model includes a power purchase cost model, an investment and construction cost model, and an operation and maintenance cost model, wherein the power purchase cost model is expressed by a mathematical formula as follows:

[0042]

[0043] The investment and construction cost model is expressed by a mathematical formula:

[0044]

[0045] The operation and maintenance cost model is expressed by a mathematical formula:

[0046]

[0047] The charging pile economic benefit model is calculated through the charging cost model, which is specifically expressed as follows:

[0048]

[0049] F up =I ev -C inv -C yw -C gs

[0050] In the formula, F up Expressed as the economic benefit of the charging pile, I ev It is represented by the revenue from electricity sales of charging pile packages, C inv It is the investment and construction cost of charging pile, C yw Expressed as the charging pile operation and maintenance cost, C gs It is represented by the cost of purchasing electricity from the distribution network for charging piles, M is represented by the total number of charging piles, ψ E It is represented by the investment and construction cost of charging piles per unit capacity, γ is represented by the discount rate of all charging piles, It is represented as the life cycle of the mth charging pile. It is represented by the rated capacity of the mth charging pile. It is expressed as the unit capacity operation and maintenance cost of the mth charging pile, It is represented by the power purchased by the charging pile from the distribution network at time t on day d, It is represented by the electricity selling price of the charging pile in the distribution network at time period t on day d;

[0051] The calculation formula of the charging cost of electric vehicle charging load is expressed as:

[0052] F down =Cev +C loss

[0053] Among them, the charging cost includes the package charging cost and loss cost. The package charging cost is expressed as:

[0054]

[0055] The loss cost is expressed as:

[0056]

[0057] In the formula, F down It is represented by the charging cost of electric vehicle charging load, C ev Denotes the charging cost of the electric vehicle package, C loss Expressed as the loss cost of electric vehicles, k 1 , k 2 and k 3 are all expressed as 0-1 parameters and satisfy k 1 +k 2 +k 3 =1, i represents the i-th charging package of the charging pile, and λ represents the unit charging power cost loss of the electric vehicle charging load.

[0058] As a preferred solution of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages of the present invention, the method for selecting a charging load package for electric vehicles includes: adopting a master-slave game model to characterize the power interaction and dynamic game between the charging pile and the charging load of the electric vehicle, and obtaining a Nash equilibrium solution by nesting the CPLEX commercial solver through the cuckoo optimization algorithm;

[0059] The master-slave game model between the charging pile and the electric vehicle charging load is expressed as:

[0060] G={N;S 充电桩 ; S 充电负荷 ; F up ; F down}

[0061] Among them, N represents the participants, whose set is N = {charging pile ∪ electric vehicle charging load}

[0062] S 充电桩 It is represented as the main charging pile strategy, and its set is:

[0063]

[0064] S 充电负荷 It is represented as the charging load strategy of the slave electric vehicle, and its set is:

[0065]

[0066] In the formula, G represents the game setting model;

[0067] Finally, the obtained Nash equilibrium solution is used to form the charging pile package pricing results and the electric vehicle charging load package selection method.

[0068] In a second aspect, an embodiment of the present invention provides an electric vehicle cluster multi-package master-slave game orderly charging optimization system, which includes a charging data acquisition module, a charging package design module, a cost model construction module, and an optimization decision module;

[0069] The charging data acquisition module is used to obtain real-time data related to charging, including the charging demand of the electric vehicle, the location information of the vehicle, the status of the power grid and the electricity price information;

[0070] The charging package design module designs a variety of charging packages for electric vehicle users to choose from based on the power purchase and sale prices of the power grid and the probability distribution of charging demand;

[0071] The cost model building module is used to estimate and analyze the cost of the entire charging system, including electricity purchase cost, infrastructure construction cost, and operation and maintenance cost;

[0072] The optimization decision module adopts the master-slave game model in game theory and the cuckoo search algorithm to nest the business solver to provide optimization decisions for charging pile pricing and charging load management.

[0073] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned electric vehicle cluster multi-package master-slave game orderly charging optimization method is implemented.

[0074] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned electric vehicle cluster multi-package master-slave game orderly charging optimization method is implemented.

[0075] The beneficial effects of the present invention are as follows: by comprehensively considering road network information, car owner behavior trajectory and power grid topology information, the probability distribution of charging demand of different charging piles in different time periods is fitted based on the improved LightGBM model method, and fixed electricity price package mode, peak and valley electricity price package mode and step electricity price package mode are formulated according to the personalized charging needs of electric vehicles. The electric vehicle charging load selects the package according to its own charging needs. The charging piles and the electric vehicle charging load form a master-slave game based on autonomy and profit-seeking. Through interactive games and repeated iterations, different package prices of charging piles and electric vehicle charging load package selection results are formed, which can reduce the charging cost while meeting the personalized charging needs of the electric vehicle charging load, and is conducive to guiding electric vehicles to charge in an orderly manner to alleviate the power supply shortage in some periods of the community. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0077] Figure 1 Flow chart of the master-slave game orderly charging optimization method for electric vehicle clusters with multiple packages. DETAILED DESCRIPTION

[0078] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0079] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0080] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0081] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0082] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0083] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0084] Example 1

[0085] Reference Figure 1 , which is the first embodiment of the present invention, and provides an electric vehicle cluster multi-package master-slave game orderly charging optimization method, comprising the following steps:

[0086] S1. Collect charging information and fit the probability distribution of charging demand of different charging piles in different time periods based on the probability prediction method.

[0087] Charging information includes road network information around the community, vehicle owner behavior trajectory, and grid topology;

[0088] Among them, the road network information around the community includes road network nodes, road connections, road grades, real-time traffic, and congestion conditions;

[0089] The owner's behavior trajectory includes the probability distribution of travel time, road section travel time, destination stay time, trip departure time, user power status, and charging time;

[0090] The grid topology includes transformer capacity, parameters of different branches in the community, node locations, and node parameters.

[0091] The probability distribution fitting methods for charging demand of different charging piles in different time periods include:

[0092] Based on the improved LightGBM model, the single-point prediction objective function is set, and the mathematical formula is expressed as:

[0093]

[0094] Where L represents the objective function of the LightGBM model. Represented as the predicted value of the charging pile in the tth period With the true value x t The error relationship between Ω(f k ) is represented as the regular term of the LightGBM model, which is used to optimize the model parameters. γ and γ are both represented as penalty coefficients. A is represented as the number of nodes in the kth tree of the LightGBM model. ω a Represented as the weight of the ath node of the kth tree of the LightGBM model;

[0095] Use the forward distribution algorithm to derive the objective function after the i-th iteration and solve the weight number ω a The minimum value of is obtained to obtain the objective function. The specific formula is expressed as:

[0096]

[0097] I a ={iq(x i )=a}

[0098] Where, L (i) It is represented as the objective function after the derivative of the i-th iteration of the LightGBM model, I is represented as the total number of iterations of the LightGBM model, ω is represented as the weight of the k-th tree of the LightGBM model, and g is represented as i and h i They are respectively represented as the coefficients of the derivative of the i-th iteration and are both penalty coefficients, f i (x i ) represents the iterative derivation of the actual value of the charging pile in each period of the LightGBM model, I a It is represented as the set of nodes of each tree, and ω is represented as the weight of the i-th iteration derivative of the k-th tree of the LightGBM model;

[0099] The non-parametric kernel density estimation model is used to establish a probability distribution model for the prediction error of charging demand in each period faced by charging piles. The mathematical formula is expressed as follows:

[0100]

[0101] In the formula, It is represented by the predicted value of the charging pile in each period, and x′ is represented by the predicted error value of the charging pile in each period. It is represented as the probability distribution model of charging demand prediction error in each period, and σ is represented as the free parameter of the probability distribution model.

[0102] S2. Set up electric vehicle charging packages based on the probability distribution of charging demand and the price of electricity purchased and sold on the distribution network.

[0103] Electric vehicle charging packages include fixed electricity price package mode, peak and valley electricity price package mode and tiered electricity price package mode;

[0104] Among them, the fixed electricity price package mode is a fixed electricity price for the whole day, with no limit on charging volume;

[0105] The peak-valley electricity price package model is to set peak-valley electricity prices to guide the charging load of electric vehicles and participate in peak-shaving and valley-filling of the power grid;

[0106] The tiered electricity price package model sets the charging amount of electric vehicle charging load to N levels, and implements different electricity quantity standards and electricity price standards at each level of the tiered increasing electricity price, guiding the agent electric vehicle charging load to charge reasonably.

[0107] In the fixed electricity price package model, the electricity sales revenue of the mth charging pile is expressed as:

[0108]

[0109] In the formula, It is expressed as the fixed electricity price package mode revenue of the charging pile in the dth day and time period t, It is represented as the fixed electricity price of the charging pile at time t on day d, It is represented by the electricity sales of the charging pile at time period t on day d;

[0110] In the peak-valley electricity price package model, the electricity sales revenue of the mth charging pile is expressed as:

[0111]

[0112]

[0113] In the formula, It is expressed as the revenue of the charging pile in the peak-valley electricity price package mode at time t on day d, It is expressed as the peak, valley and normal period electricity price, T P , T M and T V Represents the peak, valley and average time periods. and It is expressed as the settlement price of charging piles during peak, valley and normal periods;

[0114] In the tiered electricity price package model, the electricity sales revenue of the mth charging pile is expressed as:

[0115]

[0116] In the formula, It is expressed as the income of the tiered electricity price package model in the dth day and time period t, It is represented by the tiered electricity price of the charging pile in time period t, and They represent the electricity prices of charging piles under different electricity standards. It is represented by the sales volume of the charging pile in the tiered electricity price package at time t on day d, and Indicates the boundaries for different electrical quantity standards.

[0117] S3. Construct a charging cost model based on the charging information, and combine it with the electric vehicle charging package to form an electric vehicle charging load package selection method.

[0118] The charging cost model includes the electricity purchase cost model, the investment and construction cost model, and the operation and maintenance cost model. The electricity purchase cost model is expressed by a mathematical formula:

[0119]

[0120] The investment and construction cost model is expressed by mathematical formula:

[0121]

[0122] The operation and maintenance cost model is expressed by mathematical formula:

[0123]

[0124] The economic benefit model of the charging pile is calculated through the charging cost model, which is specifically expressed as follows:

[0125]

[0126] F up =I ev -C inv -C yw -C gs

[0127] In the formula, F up Expressed as the economic benefit of the charging pile, I ev It is represented by the revenue from electricity sales of charging pile packages, C inv It is the investment and construction cost of charging pile, C yw Expressed as the charging pile operation and maintenance cost, C gs It is represented by the cost of purchasing electricity from the distribution network for charging piles, M is represented by the total number of charging piles, ψ E It is represented by the investment and construction cost of charging piles per unit capacity, γ is represented by the discount rate of all charging piles, It is represented as the life cycle of the mth charging pile. It is represented by the rated capacity of the mth charging pile. It is expressed as the unit capacity operation and maintenance cost of the mth charging pile, It is represented by the power purchased by the charging pile from the distribution network at time t on day d, It is represented by the electricity selling price of the charging pile in the distribution network at time period t on day d;

[0128] The calculation formula of the charging cost of electric vehicle charging load is expressed as:

[0129] F down =C ev +C loss

[0130] Among them, the charging cost includes the package charging cost and loss cost. The package charging cost is expressed as:

[0131]

[0132] The loss cost is expressed as:

[0133]

[0134] In the formula, F down It is represented by the charging cost of electric vehicle charging load, C ev Denotes the charging cost of the electric vehicle package, C loss Expressed as the loss cost of electric vehicles, k 1 , k 2 and k 3 are all expressed as 0-1 parameters and satisfy k 1 +k 2 +k 3 =1, i represents the i-th charging package of the charging pile, and λ represents the unit charging power cost loss of the electric vehicle charging load.

[0135] The method for selecting an electric vehicle charging load package includes: using a master-slave game model to characterize the power interaction and dynamic game between charging piles and electric vehicle charging loads, and obtaining a Nash equilibrium solution by nesting a CPLEX commercial solver through a cuckoo optimization algorithm;

[0136] The master-slave game model between the charging pile and the electric vehicle charging load is expressed as:

[0137] G={N;S 充电桩 ; S 充电负荷 ; F up ; F down}

[0138] Among them, N represents the participants, whose set is N = {charging pile ∪ electric vehicle charging load}

[0139] S 充电桩 It is represented as the main charging pile strategy, and its set is:

[0140]

[0141] S 充电负荷 It is represented as the charging load strategy of the slave electric vehicle, and its set is:

[0142]

[0143] In the formula, G represents the game setting model;

[0144] Finally, the obtained Nash equilibrium solution is used to form the charging pile package pricing results and the electric vehicle charging load package selection method.

[0145] In summary, by comprehensively considering road network information, car owner behavior trajectory and power grid topology information, the probability distribution of charging demand in different charging piles in different time periods is fitted based on the improved LightGBM model method, and fixed electricity price package mode, peak and valley electricity price package mode and step electricity price package mode are formulated according to the personalized charging needs of electric vehicles. The electric vehicle charging load selects the package according to its own charging needs. The charging piles and the electric vehicle charging load form a master-slave game based on autonomy and profit-seeking. Through interactive games and repeated iterations, different package prices for charging piles and electric vehicle charging load package selection results are formed, which can reduce the charging cost while meeting the personalized charging needs of electric vehicle charging loads, and is conducive to guiding electric vehicles to charge in an orderly manner to alleviate power supply shortages in some periods of the community.

[0146] Example 2

[0147] On the basis of the first embodiment, this embodiment further provides an electric vehicle cluster multi-package master-slave game orderly charging optimization system, including a charging data collection module, a charging package design module, a cost model construction module, and an optimization decision module;

[0148] The charging data acquisition module is used to obtain real-time data related to charging, including the charging demand of the electric vehicle, the location information of the vehicle, the status of the power grid and the electricity price information;

[0149] The charging package design module designs a variety of charging packages for electric vehicle users to choose from based on the power purchase and sale prices of the power grid and the probability distribution of charging demand;

[0150] The cost model building module is used to estimate and analyze the cost of the entire charging system, including electricity purchase cost, infrastructure construction cost, and operation and maintenance cost;

[0151] The optimization decision module adopts the master-slave game model in game theory and the cuckoo search algorithm to nest the business solver to provide optimization decisions for charging pile pricing and charging load management.

[0152] This embodiment also provides a computer device, which is suitable for the case of an electric vehicle cluster multi-package master-slave game orderly charging optimization method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the electric vehicle cluster multi-package master-slave game orderly charging optimization method proposed in the above embodiment.

[0153] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0154] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing orderly charging of electric vehicle clusters using multi-package master-slave game is implemented as proposed in the above embodiment.

[0155] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0156] Example 3

[0157] On the basis of the previous two embodiments, this embodiment provides an electric vehicle cluster multi-package master-slave game orderly charging optimization method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0158] Table 1: Schematic diagram of the effects of different electric vehicle charging methods

[0159]

[0160] Comparative Example 1: Static load limitation is adopted, and no guidance is given to charging electric vehicles;

[0161] It can be seen from Table 1 that because there is no guidance on electric vehicle charging, the charging time of electric vehicles conflicts with residential electricity consumption, which leads to a significant increase in load during peak hours, and even reaches the load. In contrast, in the case of Example 1, when charging a car, it may face charging restrictions or higher fees during peak hours, and the waiting time will also increase, resulting in a satisfaction level that is significantly lower than that of Example 1.

[0162] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the orderly charging of electric vehicle clusters with multiple packages by master-slave game, characterized in that: The following steps are included: Collect charging information and fit the probability distribution of charging demand at different charging piles in different time periods based on the probability prediction method; Set up electric vehicle charging packages based on the probability distribution of charging demand and the price of electricity purchased and sold by the distribution network; A charging cost model is constructed based on the charging information, and combined with the electric vehicle charging package, a method for selecting the electric vehicle charging load package is formed.

2. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game according to claim 1, characterized in that: The charging information includes the road network information around the community, the owner's behavior trajectory, and the power grid topology; The road network information around the community includes road network nodes, road connection conditions, road grades, real-time traffic, and congestion conditions; The owner's behavior trajectory includes the probability distribution of travel time, road section travel time, destination stay time, trip departure time, user power status, and charging time; The grid topology structure includes transformer capacity, parameters of different branches in the community, node locations, and node parameters.

3. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game as claimed in claim 2, characterized in that: The probability distribution fitting methods for charging demand of different charging piles in different time periods include: Based on the improved LightGBM model, the single-point prediction objective function is set, and the mathematical formula is expressed as: Where L represents the objective function of the LightGBM model. Represented as the predicted value of the charging pile in the tth period With the true value x t The error relationship between Ω(f k ) is represented as the regular term of the LightGBM model, γ and γ are both represented as penalty coefficients, A is represented as the number of nodes in the kth tree of the LightGBM model, ω a Represented as the weight of the ath node of the kth tree of the LightGBM model; Use the forward distribution algorithm to derive the objective function after the i-th iteration and solve the weight number ω a The minimum value of is obtained to obtain the objective function. The specific formula is expressed as: Where, L (i) It is represented as the objective function after the derivative of the i-th iteration of the LightGBM model, I is represented as the total number of iterations of the LightGBM model, ω is represented as the weight of the k-th tree of the LightGBM model, and g is represented as i and h i They are respectively represented as the coefficients of the derivative of the i-th iteration and are both penalty coefficients, f i (x i ) represents the iterative derivation of the actual value of the charging pile in each period of the LightGBM model, I a It is represented as the set of nodes of each tree, and ω is represented as the weight of the i-th iteration derivative of the k-th tree of the LightGBM model; The non-parametric kernel density estimation model is used to establish a probability distribution model for the prediction error of charging demand in each period faced by charging piles. The mathematical formula is expressed as follows: In the formula, It is represented by the predicted value of the charging pile in each period, and x′ is represented by the predicted error value of the charging pile in each period. It is represented as the probability distribution model of charging demand forecast error in each period, and σ is represented as the free parameter of the probability distribution model.

4. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game as claimed in claim 3 is characterized by: The electric vehicle charging packages include fixed electricity price package mode, peak and valley electricity price package mode and tiered electricity price package mode; The fixed electricity price package mode is a fixed electricity price for the whole day with no limit on the charging amount; The peak-valley electricity price package model is to formulate peak-valley electricity prices to guide the charging load of electric vehicles and participate in peak-shaving and valley-filling of the power grid; The step electricity price package model sets the charging amount of the electric vehicle charging load to N levels, implements different electricity quantity standards and electricity price standards in each level of the step-by-step electricity price, and guides the agent electric vehicle charging load to charge reasonably.

5. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game as claimed in claim 4, characterized in that: In the fixed electricity price package model, the electricity sales revenue of the mth charging pile is expressed as: In the formula, It is expressed as the fixed electricity price package mode revenue of the charging pile in the dth day and time period t, It is represented as the fixed electricity price of the charging pile at time t on day d, It is represented by the electricity sales of the charging pile at time period t on day d; In the peak-valley electricity price package model, the electricity sales revenue of the mth charging pile is expressed as: In the formula, It is expressed as the revenue of the charging pile in the peak-valley electricity price package mode at time t on day d, It is expressed as the peak, valley and normal period electricity price, T P 、T M and T V Represents the peak, valley and average time periods. and It is expressed as the settlement price of charging piles during peak, valley and normal periods; In the tiered electricity price package model, the electricity sales revenue of the mth charging pile is expressed as: In the formula, It is expressed as the income of the tiered electricity price package model in the dth day and time period t, It is represented by the tiered electricity price of the charging pile in time period t, and They represent the electricity prices of charging piles under different electricity standards. It is represented by the sales volume of the charging pile in the tiered electricity price package at time t on day d, and Indicates the boundaries for different electrical quantity standards.

6. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game as claimed in claim 5, characterized in that: The charging cost model includes a power purchase cost model, an investment and construction cost model, and an operation and maintenance cost model, wherein the power purchase cost model is expressed by a mathematical formula as follows: The investment and construction cost model is expressed by a mathematical formula: The operation and maintenance cost model is expressed by a mathematical formula: The charging pile economic benefit model is calculated through the charging cost model, which is specifically expressed as follows: F up =I ev -C inv -C yw -C gs In the formula, F up Expressed as the economic benefit of the charging pile, I ev It is represented by the revenue from electricity sales of charging pile packages, C inv It is the investment and construction cost of charging pile, C yw Expressed as the charging pile operation and maintenance cost, C gs It is represented by the cost of purchasing electricity from the distribution network for charging piles, M is represented by the total number of charging piles, ψ E It is represented by the investment and construction cost of charging piles per unit capacity, γ is represented by the discount rate of all charging piles, It is represented as the life cycle of the mth charging pile. It is represented by the rated capacity of the mth charging pile. It is expressed as the unit capacity operation and maintenance cost of the mth charging pile, It is represented by the power purchased by the charging pile from the distribution network at time t on day d, It is represented by the electricity selling price of the charging pile in the distribution network at time period t on day d; The calculation formula of the charging cost of electric vehicle charging load is expressed as: F down =C ev +C loss Among them, the charging cost includes the package charging cost and loss cost. The package charging cost is expressed as: The loss cost is expressed as: In the formula, F down It is represented by the charging cost of electric vehicle charging load, C ev Denotes the charging cost of the electric vehicle package, C loss It is represented as the loss cost of electric vehicles, k1, k2 and k3 are all represented as 0-1 parameters, and satisfy k1+k2+k3=1, i represents the i-th charging package of the charging pile, and λ represents the unit charging power cost loss of the electric vehicle charging load.

7. The method for optimizing the orderly charging of electric vehicle cluster multi-package master-slave game as claimed in claim 6, characterized in that: The method for selecting an electric vehicle charging load package includes: using a master-slave game model to characterize the power interaction and dynamic game between charging piles and electric vehicle charging loads, and obtaining a Nash equilibrium solution by nesting a CPLEX commercial solver through a cuckoo optimization algorithm; The master-slave game model between the charging pile and the electric vehicle charging load is expressed as: G={N;S 充电桩 ;S 充电负荷 ;F up ;F down } Among them, N represents the participants, whose set is N = {charging pile ∪ electric vehicle charging load} S 充电桩 It is represented as the main charging pile strategy, and its set is: S 充电负荷 It is represented as the charging load strategy of the slave electric vehicle, and its set is: In the formula, G represents the game setting model; Finally, the obtained Nash equilibrium solution is used to form the charging pile package pricing results and the electric vehicle charging load package selection method.

8. An electric vehicle cluster multi-package master-slave game orderly charging optimization system, based on the electric vehicle cluster multi-package master-slave game orderly charging optimization method according to any one of claims 1 to 7, characterized in that: It includes charging data collection module, charging package design module, cost model building module, and optimization decision module; The charging data acquisition module is used to obtain real-time data related to charging, including the charging demand of the electric vehicle, the location information of the vehicle, the status of the power grid and the electricity price information; The charging package design module designs a variety of charging packages for electric vehicle users to choose from based on the power purchase and sale prices of the power grid and the probability distribution of charging demand; The cost model building module is used to estimate and analyze the cost of the entire charging system, including electricity purchase cost, infrastructure construction cost, and operation and maintenance cost; The optimization decision module adopts the master-slave game model in game theory and the cuckoo search algorithm to nest the business solver to provide optimization decisions for charging pile pricing and charging load management.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the electric vehicle cluster multi-package master-slave game orderly charging optimization method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electric vehicle cluster multi-package master-slave game orderly charging optimization method described in any one of claims 1 to 7 are implemented.

Images