Electric vehicle charging scheduling method based on multi-objective optimization, medium and equipment

Abstract

The invention provides an electric vehicle charging scheduling method based on multi-objective optimization, a medium and equipment, and relates to the technical field of charging and battery swap services. Constructing an optimization model of a multi-objective function with minimum power load fluctuation and minimum power distribution cost of the regional power distribution network as targets; and solving the optimization model by using an improved artificial bee colony algorithm to obtain an optimal charging adjustment strategy, and scheduling charging of the electric vehicle according to the optimal charging adjustment strategy. According to the method, the safety and economy of electric vehicle charging scheduling can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging and swapping services, and particularly relates to an electric vehicle charging scheduling method, medium and device based on multi-objective optimization. Background Art

[0002] The charging behavior of electric vehicles is random. A large number of disorderly charging loads will have a significant impact on the planning and operation of the power grid. The reasonable and effective charging of electric vehicles plays a huge role in power demand side management. A large number of electric vehicles are connected to the power grid for disorderly charging loads, which will have a certain impact on the distribution network, including exacerbating the peak-valley difference, resulting in voltage drop, increased line losses, overloading of distribution transformers and power lines, etc. The development of V2G technology enables electric vehicles to not only charge as a load but also feed power into the power grid as an energy storage device. Combining the V2G function of electric vehicles, the power system adopts effective scheduling and regulation strategies, which becomes an important means to improve the operation safety and economy of the system. Therefore, how to effectively establish the objective function and apply the regulation strategy still needs to be studied deeply. Summary of the Invention

[0003] The purpose of the present invention is to provide an electric vehicle charging scheduling method, medium and device based on multi-objective optimization, aiming to improve the safety and economy of electric vehicle charging scheduling. The specific technical solutions are as follows:

[0004] An electric vehicle charging scheduling method based on multi-objective optimization, the method includes the following steps:

[0005] S100. Taking the initial charging time of the electric vehicle as the adjustment variable, constructing an optimization model of a multi-objective function with the minimum power load fluctuation of the regional distribution network and the lowest distribution cost as the objectives;

[0006] S200. Using an improved artificial bee colony algorithm to solve the optimization model to obtain the optimal charging adjustment strategy, and scheduling the charging of the electric vehicle according to the optimal charging adjustment strategy.

[0007] Further, the step S100 includes the following steps:

[0008] S110. Establishing an objective function for the minimum power load fluctuation of the regional distribution network:

[0009]

[0010] Among them, F1 represents the power load fluctuation of the regional distribution network, and P avg respectively represent the real-time load and average load of node i at time t, N is the number of nodes in the distribution network, and time t is divided into segments from 1 to T;

[0011] S120. Establish the objective function for minimizing the regional power distribution cost:

[0012] F2 = min{F3 + F4} (2)

[0013] Among them, F2 is the regional power distribution cost, F3 is the total operating cost of the power distribution network, and F4 represents the charging cost of electric vehicle users.

[0014]

[0015] Among them, C 1 i,t represents the operating cost of the device at node i at time t, C 2 i,t represents the energy storage cost at node i at time t, C 3 i,t represents the network loss cost at node i, C 4 i,t represents the cost of purchasing electricity from the main grid at time t.

[0016]

[0017] Among them, S is the total number of vehicles, λ s,t represents the charging state. When λ s,t is 1, it means the charging state. When λ s,t is 0, it means the non - charging state. price t is the charging electricity price, P s,t is the charging output power of the charging pile to the vehicle, and Δt represents the time difference.

[0018] S130. Establish the constraint conditions:

[0019]

[0020] Among them, S s,t+Δt is the charging level of electric vehicle s at time point t + Δt, S s，t is the charging level of electric vehicle s at time point t, η is the charging efficiency, and E s represents the battery power.

[0021] S min ≤S s,t ≤S max (6)

[0022] Among them, S min and S max are the upper and lower limits of the battery charging state.

[0023] S s,t ≥SOC f (7)

[0024] Among them, SOC f is the charging state of the electric vehicle battery, which is set by the user or selected as the system default value.

[0025] Furthermore, in the step S200, the improved artificial bee colony algorithm is as follows: It includes three groups of bees: leading bees, following bees, and observing bees; all problems in the bee colony algorithm are solved under the condition of a D-dimensional vector space, and the total number of honey sources is N;

[0026] In the leading bee stage, the initial position formula is as shown in (8):

[0027] V′ ij =R min,j +γ(R max,j -R min,j ) (8)

[0028] Among them, V' ij is the position of the initial solution, j = (1, 2,..., D), i = (1, 2,..., N), i ≠ j, γ is a number randomly generated within the range of (0, 1), R max，j and R min，j are the upper and lower limits of the x dimension;

[0029] In the following bee stage, assuming that a new high-quality nectar source is discovered, the probability of selecting this source is (9):

[0030]

[0031] Among them, f i represents the fitness value corresponding to the nectar volume of i, and can be solved by transforming it into a minimization problem through the following formula:

[0032]

[0033] Among them, F i is the previous objective function F1 or F2;

[0034] In the observing bee stage, after the loop, if there is no better solution, the leading bee becomes an observing bee, and searches for a new honey source position for neighborhood search according to (8). Each observing bee randomly selects a new solution in the solution space and updates the current optimal solution; if a new solution generated by an observing bee is better than the current optimal solution, the new solution replaces the current optimal solution:

[0035] V ij =αR ij +γ(R ij -R kj ) (12)

[0036] Among them, V ijis the new food position, R ij represents the current food source, R kj is a randomly selected food source, j is a randomly selected position index, j = (1, 2, …, D) and k = (1, 2, …, N) are randomly generated

[0037] The variation of the adaptive search factor α is shown in (13):

[0038]

[0039] where α min and α max represent the minimum and maximum values of the adaptive search factor respectively, T max represents the maximum number of hybrid iterations, and d represents the total number of iterations;

[0040] Furthermore, in the algorithm, a function subject to the Levy distribution is introduced, as shown in (14):

[0041] V″ ij = [αR ij + γ(R ij - R kj )]·L j (t) (14)

[0042] where V″ ij is the updated initial position of the improved algorithm, and L j (t) is a random function subject to the Levy distribution.

[0043] Furthermore, S200 includes the following steps:

[0044] S210. Set parameter values in the algorithm, set the number of honey sources to N1, where N1 is the number of vehicles, then the positions of the bee colony, i.e., the electric vehicle group, are V = [V1, V2, …, V N , representing the vector of all food sources, and record the charging times and optimization costs of N1 electric vehicles; randomly initialize the positions of the nectar sources, i.e., initialize the initial charging times and charging costs of each electric vehicle;

[0045] S220. Modify the positions of the nectar sources according to the constraint conditions;

[0046] S230. The leading bees search for the nectar sources to update the charging times and charging costs, and record the best positions;

[0047] S240. Determine whether there are observing bees, i.e., whether there is a better new solution to replace the current solution. If so, continue to search for the nectar sources; otherwise, enter S250;

[0048] S250. Determine whether the convergence condition is met; if so, output the best nectar source and subsequently optimize the charging behavior of N1 electric vehicles under the condition of meeting the constraints; otherwise, return to S230.

[0049] Furthermore, the number of bee colonies is set to 100, the maximum number of iterations is set to 1000, and the maximum and minimum values of the adaptive search factor are set to 1.2 and 0.8.

[0050] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned electric vehicle charging scheduling method based on multi-objective optimization are implemented.

[0051] The present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned electric vehicle charging scheduling method based on multi-objective optimization are implemented.

[0052] The electric vehicle charging scheduling method, medium, and device based on multi-objective optimization provided by the present invention have the following beneficial effects:

[0053] The electric vehicle charging scheduling method based on multi-objective optimization provided by the present invention constructs an optimization model of a multi-objective function with the minimum power load fluctuation of the regional distribution network and the lowest distribution cost as the objectives by taking the initial charging time of the electric vehicle as the adjustment variable; uses an improved artificial bee colony algorithm to solve the optimization model to obtain the optimal charging adjustment strategy, and schedules the charging of electric vehicles according to the optimal charging adjustment strategy; can improve the safety and economy of electric vehicle charging scheduling. Description of the Drawings

[0054] Figure 1 is a flowchart of an electric vehicle charging scheduling method based on multi-objective optimization provided by the present invention;

[0055] Figure 2 is the daily load curve of the system in the case of different access rates in the numerical example of the present invention;

[0056] Figure 3 is a comparison chart of the load curve results of the optimization algorithm and unordered charging when the electric vehicle access rate is 40% in the numerical example of the present invention;

[0057] Figure 4 is a structural block diagram of the computer device in the embodiment of the present invention. Detailed Embodiment

[0058] Next, in combination with the accompanying drawings provided by the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the accompanying drawings are all in a very simplified form and use non-precise scales, only for conveniently and clearly assisting in explaining the purpose of the embodiments of the present invention.

[0059] Embodiment 1

[0060] This embodiment provides an electric vehicle charging scheduling method based on multi-objective optimization. Refer to Figure 1 As shown, the method includes the following steps:

[0061] S100. Taking the initial charging time of the electric vehicle as the adjustment variable, construct an optimization model of a multi-objective function with the minimum power load fluctuation of the regional distribution network and the lowest distribution cost as the objectives.

[0062] Specifically, it includes the following steps:

[0063] S110. Establish an objective function for minimizing the power load fluctuation of the regional distribution network:

[0064]

[0065] Among them, F1 represents the power load fluctuation of the regional distribution network, and P avg respectively represent the real-time load and average load of node i at time t. N is the number of nodes in the distribution network, and time t is divided into segments from 1 to T;

[0066] S120. Establish an objective function for minimizing the regional distribution cost:

[0067] F2 = min{F3 + F4} (2)

[0068] Among them, F2 is the regional distribution cost, F3 is the total operating cost of the distribution network, and F4 represents the charging cost of electric vehicle users.

[0069]

[0070] Among them, C 1 i,t represents the operating cost of the device at node i at time t, C 2 i,t represents the energy storage cost of node i at time t, C 3 i,t represents the network loss cost of node i, C 4 i,t represents the cost of purchasing electricity from the main grid at time t.

[0071]

[0072] where S is the total number of vehicles, and λ s,t represents the charging state, and λ s,t being 1 indicates the charging state, and λ s,t being 0 indicates the non - charging state, price t is the charging electricity price, P s,t is the charging output power of the charging pile to the vehicle, and Δt represents the time difference;

[0073] S130. Establish the constraint conditions:

[0074]

[0075] where S s,t+Δt is the charging level of the electric vehicle s at time point t + Δt, and S s，t is the charging level of the electric vehicle s at time point t, η is the charging efficiency, and E s represents the battery power,

[0076] S min ≤S s,t ≤S max (6)

[0077] where S min and S max are the upper and lower limits of the battery charging state,

[0078] S s,t ≥SOC f (7)

[0079] where SOC f is the charging state of the electric vehicle battery, which is set by the user or selected as the system default value;

[0080] S200. Use the improved artificial bee colony algorithm to solve the optimization model to obtain the optimal charging regulation strategy, and schedule the charging of electric vehicles according to the optimal charging regulation strategy.

[0081] The standard artificial bee colony algorithm consists of three groups of bees: the leading bee, the following bee, and the observing bee. The ultimate goal of the bee colony is to find the richest honey source. Assume that all problems in the bee colony algorithm are solved under the condition of a D - dimensional vector space, and the total number of honey sources is N.

[0082] 1. In the leading bee stage, the initial position formula is as shown in (8):

[0083] V′ ij =R min,j +γ(R max,j -R min,j ) (8)

[0084] Among them, V' ij is the position of the initial solution, j = (1, 2, …, D), i = (1, 2, …, N), i ≠ j, γ is a randomly generated number within the range of (0, 1), R max，j and R min，j are the upper and lower limits in the x dimension.

[0085] 2. In the onlooker bee stage, assuming a new high-quality nectar source is discovered, the probability of choosing this source is (9):

[0086]

[0087] Among them, f i represents the fitness value corresponding to the nectar volume of i, and can be solved by transforming it into a minimization problem through the following formula:

[0088]

[0089] Among them, F i is the previous objective function F1 or F2.

[0090] 3. In the scout bee stage, after the loop, if there is no better solution, the leading bee becomes a scout bee, and a neighborhood search is performed to search for the position of a new honey source according to (8). Each scout bee randomly selects a new solution in the solution space and updates the current optimal solution; if the new solution generated by a scout bee is better than the current optimal solution, then the new solution replaces the current optimal solution:

[0091] V ij = R ij + γ(R ij - R kj )(11)

[0092] Among them, V ij is the new food position, R ij represents the current food source, R kj is a randomly selected food source, j is a randomly selected position index, j = (1, 2, …, D) and k = (1, 2, …, N) are randomly generated.

[0093] The improved artificial bee colony algorithm lies in:

[0094] Adding an adaptive search factor to improve the artificial bee colony algorithm to enhance the global search ability and local search ability of the algorithm,

[0095] V ij = αR ij + γ(R ij - R kj )(12)

[0096] The variation of the adaptive search factor α is shown in (13):

[0097]

[0098] Among them, α min and α max represent the minimum and maximum values of the adaptive search factor respectively, T max represents the maximum number of hybrid iterations, and d represents the total number of iterations. The purpose is to adjust the influence of the previous speed. As the iteration progresses, the parameter α decreases continuously.

[0099] Then, in the algorithm, a function obeying the Levy distribution is introduced, as shown in (14):

[0100] V″ ij = [αR ij + γ(R ij - R kj )]·L j (t) (14)

[0101] Among them, V″ ij is the updated initial position of the improved algorithm, and L j (t) is a random function obeying the Levy distribution, representing a lower possibility of a better initial position.

[0102] That is, the improved artificial bee colony algorithm is as follows: It includes three groups of bees: leading bees, following bees, and observing bees; all problems in the bee colony algorithm are solved under the condition of a D-dimensional vector space, and the total number of honey sources is N;

[0103] In the leading bee stage, the initial position formula is shown in (8):

[0104] V′ ij = R min,j + γ(R max,j - R min,j ) (8)

[0105] Among them, V' ij is the position of the initial solution, j = (1, 2,..., D), i = (1, 2,..., N), i ≠ j, γ is a number randomly generated in the range of (0, 1), and R max，j and R min，j are the upper and lower limits of the x dimension;

[0106] In the following bee stage, assuming that a new high-quality nectar source is discovered, the probability of selecting this source is (9):

[0107]

[0108] Among them, f iDenote the fitness value corresponding to the nectar volume of \(i\). It can be transformed into a minimization problem for solution by the following formula:

[0109]

[0110] where \(F\) i is the previous objective function \(F1\) or \(F2\);

[0111] In the observing bee stage, after the loop, if there is no better solution, the leading bee becomes an observing bee and conducts a neighborhood search by searching for a new honey source location according to (8). Each observing bee randomly selects a new solution in the solution space and updates the current optimal solution. If the new solution generated by an observing bee is better than the current optimal solution, the new solution replaces the current optimal solution:

[0112] \(V\) ij =\(\alpha R\) ij +\(\gamma(R\) ij -\(R\) kj ) (12)

[0113] where \(V\) ij is the new food location, \(R\) ij represents the current food source, \(R\) kj is a randomly selected food source, \(j\) is a randomly selected position index, \(j=(1,2,\ldots,D)\) and \(k=(1,2,\ldots,N)\) are randomly generated.

[0114] The change of the adaptive search factor \(\alpha\) is shown in (13):

[0115]

[0116] where \(\alpha\) min and \(\alpha\) max represent the minimum and maximum values of the adaptive search factor respectively, \(T\) max represents the maximum number of hybrid iterations, and \(d\) represents the total number of iterations;

[0117] Furthermore, in the algorithm, a function subject to the Levy distribution is introduced, as shown in (14):

[0118] \(V''\) ij =[\(\alpha R\) ij +\(\gamma(R\) ij -\(R\) kj )]\(\cdot L\) j (t) (14)

[0119] where \(V''\) ij is the updated initial position of the improved algorithm, and \(L\) j (t) is a random function subject to the Levy distribution.

[0120] Specifically, S200 includes the following steps:

[0121] S210. Set parameter values in the algorithm, set the number of honey sources as N1, where N1 is the number of vehicles. Then the positions of the bee colony, i.e., the electric vehicle group, are V = [V1, V2, …, V N , representing the vector of all food sources, and record the charging times and optimization costs of N1 electric vehicles; randomly initialize the positions of the nectar sources, i.e., initialize the initial charging times and charging costs of each electric vehicle;

[0122] S220. Modify the positions of the nectar sources according to the constraint conditions;

[0123] S230. The leading bees search for the nectar sources to update the charging times and charging costs, and record the best positions;

[0124] S240. Determine whether there are observing bees, i.e., whether there is a better new solution to replace the current solution. If so, continue to search for the nectar sources; otherwise, enter S250;

[0125] S250. Determine whether the convergence condition is satisfied; if so, output the best nectar source and subsequently optimize the charging behaviors of N1 electric vehicles under the constraint conditions; otherwise, return to S230.

[0126] In one embodiment, the number of the bee colony is set to 100, the maximum number of iterations is set to 1000, and the maximum and minimum values of the adaptive search factor are set to 1.2 and 0.8.

[0127] The electric vehicle charging scheduling method based on multi-objective optimization provided by the present invention constructs an optimization model of a multi-objective function with the minimum power load fluctuation and the lowest distribution cost of the regional distribution network by taking the initial charging time of the electric vehicle as the adjustment variable; uses an improved artificial bee colony algorithm to solve the optimization model to obtain the optimal charging adjustment strategy, and schedules the electric vehicle charging according to the optimal charging adjustment strategy; and can improve the safety and economy of the electric vehicle charging scheduling.

[0128] Verification example

[0129] The feasibility of the improved artificial bee colony algorithm is verified by the following real example:

[0130] 1. Set the example parameters:

[0131] Taking one day (24 hours) as the scheduling period, the parameters of the electric vehicle are set as follows: the full charging time is 3.7 h, the full discharging time is 2.7 h, the battery capacity is 53.5 kWh, the battery type is lithium-ion battery, the available capacity is 47.3 kWh, and the charging efficiency of the vehicle is 92.7%. The electricity price is shown in Table 1, which is divided into off-peak electricity price (00:00 - 7:00), normal electricity price (8:00 - 10:00, 16:00 - 18:00, 22:00 - 24:00), and peak electricity price (11:00 - 15:00, 19:00 - 21:00).

[0132] Table 1 Electricity price levels for each time period

[0133]

[0134] 2. Result analysis:

[0135] Taking 160 households in a certain area as an example, with an average of one car per household, when the penetration rate of electric vehicles is 0%, 40%, and 80%, the non-charging load of electric vehicles is simulated to analyze its impact on the original grid load, as Figure 2 shown.

[0136] It can be seen that the disordered charging of electric vehicles leads to an increase in the load peak. The superposition of the charging peak of electric vehicles and the peak of regional electricity consumption significantly increases the system load around 16 - 20 hours, which may cause transformer overload and further expand the peak-valley difference of the system.

[0137] On this basis, Figure 3 shows the load curve results of disordered charging when the penetration rate of electric vehicles is 40% and the proposed optimization algorithm in this paper is adopted. Table 2 shows the detailed comparison results of the costs of different charging modes when the penetration rate of electric vehicles is 40%.

[0138] From Figure 3 it can be seen that when the penetration rate of electric vehicles is 40%, they are randomly connected to the distribution network for charging, and the peak load increases significantly. By optimizing the charging access time of electric vehicles, the peak-valley difference rate of the region is significantly reduced, effectively avoiding the negative impact of random charging of electric vehicles on the power grid. It can be seen from Table 2 that when electric vehicles are connected in a disordered charging manner, the online distribution and overall operation and maintenance costs are greatly increased. However, through the proposed optimized charging mode in this paper, the impact of network loss can be reduced and the economy can be improved.

[0139] Table 2 Detailed comparison results of the costs of different charging modes when the penetration rate of electric vehicles is 40%

[0140]

[0141] Based on the comparison in the above different scenarios, for the problem of optimizing the orderly charging scheduling of electric vehicles, the present application aims to minimize the load fluctuation and distribution cost based on an improved artificial bee colony algorithm solving model, and solve the charging strategy of electric vehicles under the constraints of electric vehicle safety and meeting the load demand. It can be seen from the calculation results that this model saves the distribution optimization cost, and the maximum load fluctuation range is reduced to within 15%. It not only meets the charging needs of users, but also reduces the peak-valley difference of the load and the online distribution and overall cost of operation and maintenance, that is, demonstrates the effectiveness and practicability of the technical solution of the present disclosure.

[0142] Embodiment 2

[0143] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned electric vehicle charging scheduling method based on multi-objective optimization are implemented.

[0144] Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HardDisk Drive, abbreviation: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0145] Embodiment 3

[0146] This embodiment provides a computer device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned electric vehicle charging scheduling method based on multi-objective optimization are implemented.

[0147] Such as Figure 4As shown, the computer device may include: at least one processor 71, such as a CPU (Central Processing Unit), at least one communication interface 73, a memory 74, and at least one communication bus 72. Among them, the communication bus 72 is used to realize the connection and communication between these components. Among them, the communication interface 73 may include a display screen (Display) and a keyboard (Keyboard). Optionally, the communication interface 73 may also include a standard wired interface and a wireless interface. The memory 74 may be a high-speed RAM memory (Random Access Memory, volatile random access memory), or a non-volatile memory, such as at least one disk memory. Optionally, the memory 74 may also be at least one storage device located far from the aforementioned processor 71. Among them, application programs are stored in the memory 74, and the processor 71 calls the program code stored in the memory 74 to execute any of the above method steps.

[0148] Among them, the communication bus 72 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 72 can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 4 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0149] Among them, the memory 74 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviation: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviation: HDD) or a solid-state drive (English: solid-state drive, abbreviation: SSD); the memory 74 may also include a combination of the above types of memories.

[0150] Among them, the processor 71 may be a central processing unit (English: central processing unit, abbreviation: CPU), a network processor (English: network processor, abbreviation: NP), or a combination of a CPU and an NP.

[0151] Among them, the processor 71 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0152] Optionally, the memory 74 is further configured to store program instructions. The processor 71 may call the program instructions to implement the electric vehicle charging scheduling method based on multi-objective optimization as described in the present invention.

[0153] Those skilled in the art of the present technology should understand that the present invention may be implemented in many other specific forms without departing from the spirit and scope of the present invention. Based on the embodiments of the present invention, any changes and modifications made by those of ordinary skill in the art of the present invention according to the above disclosure shall fall within the protection scope of the claims.

Claims

1. A method for charging and scheduling electric vehicles based on multi-objective optimization, characterized in that: The method comprises the following steps: S100, taking the initial charging time of the electric vehicle as a regulating variable, constructing an optimization model of a multi-objective function with the objectives of minimizing the power load fluctuation of the regional distribution network and minimizing the distribution cost; S200: using an improved artificial bee colony algorithm to solve the optimization model to obtain an optimal charging regulation strategy, and scheduling the charging of electric vehicles according to the optimal charging regulation strategy.

2. The electric vehicle charging scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The step S100 includes the following steps: S110. Establish an objective function to minimize the fluctuation of power load in the regional distribution network: Among them, F1 represents the power load fluctuation of the regional distribution network, and P avg They represent the real-time load and average load of node i at time t, respectively. N is the number of distribution network nodes, and time t is divided into segments from 1 to T. S120. Establish the objective function of minimizing regional power distribution cost: F2=min{F3+F4} (2) Among them, F2 is the regional distribution cost, F3 is the total operating cost of the distribution network, and F4 represents the charging cost of electric vehicle users. Among them, C 1 i,t represents the operating cost of the device at node i at time t, C 2 i,t represents the energy storage cost of node i at time t, C 3 i,t represents the network loss cost of node i, C 4 i,t represents the cost of purchasing electricity from the main grid at time t, Where S is the total number of vehicles, λ s,t Indicates the charging state, λ s,t 1 indicates charging state, λ s,t 0 means non-charging state, price t is the charging electricity price, P s,t is the charging output power of the charging pile to the vehicle, and Δt represents the time difference; S130, establish constraints: Among them, S s,t+Δt is the charging level of electric vehicle s at time t+Δt, S s，t is the charging level of electric vehicle s at time t, η is the charging efficiency, E s Indicates the battery level. S min ≤S s,t ≤S max (6) Among them, S min and S max are the upper and lower limits of the battery's state of charge, S s,t ≥SOC f (7) Among them, SOC f It is the electric vehicle battery charge status, which is set by the user or selected as the system default.

3. The electric vehicle charging scheduling method based on multi-objective optimization according to claim 2 is characterized in that: In step S200, the improved artificial bee colony algorithm includes three groups of bees: leading bees, following bees and observing bees; all problems in the bee colony algorithm are solved under the condition of D-dimensional vector space, and the total number of honey sources is N; In the leading bee stage, the initial position formula is shown in (8): V′ ij =R min,j +γ(R max,j -R min,j ) (8) Among them, V' ij is the position of the initial solution, j = (1, 2, ..., D), i = (1, 2, ..., N), i ≠ j, γ is a randomly generated number in the range (0, 1), R max，j and R min，j are the upper and lower limits of the x-dimension; In the follower bee stage, assuming that a new high-quality nectar source is discovered, the probability of selecting this source is (9): Among them, f i represents the fitness value corresponding to the amount of nectar i, which can be solved by converting it into a minimization problem: Among them, F i is the previous objective function F1 or F2; In the observation bee stage, after the cycle, if there is no better solution, the leading bee becomes the observation bee and searches for a new honey source location according to (8) for a neighborhood search. Each observation bee randomly selects a new solution in the solution space and updates the current optimal solution. If a new solution generated by an observation bee is better than the current optimal solution, the new solution replaces the current optimal solution: V ij =αR ij +γ(R ij -R kj ) (12) Among them, V ij is the new food location, R ij Represents the current food source, R kj is a randomly selected food source, j is a randomly selected location index, j = (1, 2, ..., D) and k = (1, 2, ..., N) are randomly generated, The change of the adaptive search factor α is shown in (13): Among them, α min and α max Respectively represent the minimum and maximum values ​​of the adaptive search factor, T max represents the maximum number of hybrid iterations, and d represents the total number of iterations; Then, in the algorithm, a function that obeys the Levy distribution is introduced, as shown in (14): V″ ij =[αR ij +γ(R ij -R kj )]·L j (t) (14) Among them, V ij To improve the algorithm's updated initial position, L j (t) is a random function that follows the Levy distribution.

4. The electric vehicle charging scheduling method based on multi-objective optimization according to claim 3 is characterized in that: S200 includes the following steps: S210, setting parameter values ​​in the algorithm, setting the number of honey sources to N1, where N1 is the number of vehicles, then the position of the bee colony, i.e., the electric vehicle colony, is V = [V1, V2, ..., V N ], representing the vector of all food sources, and recording the charging time and optimization cost of N1 electric vehicles; randomly initializing the nectar source position, that is, initializing the initial charging time and charging cost of each electric vehicle; S220, modifying the position of the nectar source according to the constraint condition; S230, guide bees to find nectar sources to update charging time and cost, and record the best position; S240, determining whether there is an observation bee, that is, whether there is a better new solution to replace the current solution, if yes, continue searching for the nectar source, otherwise proceed to S250; S250, determining whether a convergence condition is met; If yes, output the best nectar source, and then optimize the charging behavior of N1 electric vehicles under the constraints; Otherwise, return to S230.

5. The electric vehicle charging scheduling method based on multi-objective optimization according to claim 4 is characterized in that: The number of swarms was set to 100, the maximum number of iterations was set to 1000, and the maximum and minimum values ​​of the adaptive search factor were set to 1.2 and 0.

8.

6. 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 charging scheduling method based on multi-objective optimization as described in any one of claims 1 to 5 are implemented.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the electric vehicle charging scheduling method based on multi-objective optimization as described in any one of claims 1 to 5 are implemented.

Images