New energy automobile intelligent charging control system and method

Abstract

The invention relates to the technical field of charging control, in particular to an intelligent charging control system and method for new energy vehicles, and the system comprises a demand determination unit which is used for obtaining the charging information of all new energy vehicles in a target charging station, and determining the total charging demand of the target charging station according to the charging information; and the dispatching modeling unit is used for acquiring power supply information of the power grid, determining an objective function according to the total charging demand quantity and the power supply information, and determining constraint conditions based on power balance, voltage, line capacity and distribution transformer capacity of the power grid. The charging information of all vehicles in the charging station is obtained through the demand determining unit, the total charging demand is accurately calculated, reasonable distribution of electric power resources is ensured, waste or insufficiency is avoided, factors such as power balance, voltage and line capacity of a power grid are considered through the dispatching modeling unit, and it is ensured that charging loads cannot cause too large pressure on the power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of charging control, and particularly to an intelligent charging control system and method for new energy vehicles. Background Art

[0002] New energy vehicles refer to vehicles that use unconventional vehicle fuels as the power source, integrate advanced technologies in vehicle power control and drive, and form vehicles with advanced technical principles, new technologies, and new structures.

[0003] Traditional methods lack accurate calculation of charging demand, which easily leads to uneven power distribution, resulting in power waste or insufficient charging; and traditional methods do not fully consider factors such as the power balance, voltage, and line capacity of the power grid, and the charging load may cause excessive pressure on the power grid, leading to grid instability and even failures; moreover, traditional methods lack the support of optimization algorithms and cannot generate an optimal scheduling plan, and the charging station may not obtain sufficient power, resulting in low charging efficiency and extended waiting time for users; and traditional methods cannot monitor the working status of charging piles in real time and cannot dynamically adjust the output and input loads, resulting in low operating efficiency of charging piles under different loads, unable to intelligently distribute power according to the change in load, easily leading to local overload or power shortage, affecting the overall operating efficiency of the charging station; and traditional methods lack an optimized scheduling and distribution mechanism, resulting in large power losses, increasing the power grid pressure and operating costs, unable to ensure stable power supply at the charging station, with a long charging waiting time and poor user experience, affecting the popularization of new energy vehicles. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the above-mentioned disadvantages of the prior art and provide an intelligent charging control system and method for new energy vehicles.

[0005] The technical solution adopted to solve the above technical problem is: an intelligent charging control system for new energy vehicles, comprising:

[0006] A demand determination unit, which is used to obtain the charging information of all new energy vehicles in the target charging station and determine the total charging demand of the target charging station according to the charging information;

[0007] A scheduling modeling unit, which is used to obtain the power supply information of the power grid, determine an objective function according to the total charging demand and the power supply information, and determine constraint conditions based on the power balance, voltage, line capacity, and distribution transformer capacity of the power grid;

[0008] A power dispatching unit, which is used to construct a power dispatching model of the power grid based on the objective function and the constraint conditions, solve the power dispatching model based on an optimization algorithm to obtain a power dispatching plan, and dispatch the power of the power grid to the target charging station based on the power dispatching plan;

[0009] A load determination unit, which is used to obtain the working information of all charging piles in the target charging station and determine the output load and input load of new energy vehicles charging at the charging piles based on the working information;

[0010] A power allocation unit, which is used to determine the load change amount of the charging piles according to the output load and the input load, and allocate the power of the power grid to the corresponding charging piles according to the load change amount.

[0011] Preferably, the charging information includes the expected end charging time, the charge amount before charging, the expected charge amount at the end of charging, and the maximum charging rate, the power supply information includes the power generation amount of renewable energy, the energy storage capacity of energy storage devices, and the power tradable volume of the power grid, and the calculation formula of the total charging demand is as follows:

[0012]

[0013] where Q represents the total charging demand, N represents the number of new energy vehicles in the target charging station, represents the expected charge amount at the end of charging of the new energy vehicle, and f i represents the charge amount before charging of the new energy vehicle.

[0014] Preferably, obtaining the power supply information of the power grid and determining the objective function according to the total charging demand and the power supply information includes:

[0015] Determining a first supply-demand difference according to the total charging demand and the power supply information;

[0016] When the first supply-demand difference is a positive number, determining a second supply-demand difference according to the first supply-demand difference and the power supply information;

[0017] Determining the revenue of the target charging station based on the first supply-demand difference and the second supply-demand difference, where the calculation formula of the revenue is as follows:

[0018]

[0019] where, represents the revenue of the target charging station, and T maxDenote the control period of the target charging station. Let \(Q(t)\), \(H(t)\), \(g(t)\), and \(b(t)\) represent the total charging demand, the power generation of renewable energy, the energy storage capacity of the energy storage device, and the tradable power volume of the power grid at time \(t\), and \(P\) H , \(P\) g and \(P\) b represent the electricity prices of renewable energy, the energy storage device, and the power grid transaction at time \(t\). Let \(QH\) dif represent the first supply-demand difference, and \(QH\) dif = \(Q(t)-H(t)\). Let \(QHg\) dif represent the second supply-demand difference, and \(QHg\) dif = \(Q(t)-H(t)-g(t)\);

[0020] Determine the objective function based on the revenue volume of the target charging station, where the objective function is to maximize the revenue volume of the target charging station.

[0021] Preferably, the constraint conditions include power balance constraint conditions, voltage constraint conditions, line capacity constraint conditions, and distribution transformer capacity constraint conditions. Among them, the expression of the power balance constraint condition is as follows:

[0022]

[0023] where \(j\) represents the node in the power grid that has a connected branch with node \(i\). \(P\) i , \(Q\) i and \(U\) i represent the injected active power, reactive power, and voltage amplitude of node \(i\) in the power grid. \(G\) ij and \(B\) ij represent the real part and imaginary part of the mutual admittance, and \(\theta\) ij represents the phase angle difference between the head and tail voltages of the branch;

[0024] The expression of the voltage constraint condition is as follows:

[0025] \(U\) min ≤ \(U\) i ≤ \(U\) max ;

[0026] where \(U\) min and \(U\) max represent the lower and upper limits of the node voltage;

[0027] The expression of the line capacity constraint condition is as follows:

[0028] |S ij |< \(S\) ijmax ;

[0029] where \(S\) ijmax represents the upper limit of the branch capacity \(S\) ij connecting nodes \(i\) and \(j\);

[0030] The expression of the capacity constraint condition of the distribution transformer is as follows:

[0031]

[0032] Among them, P Ti,t , P Li,t , P Ei，t and represent the total power of the distribution transformer, the conventional load power, the charging power, and the upper limit of the charging power at time t, and S i , ρ i and cosψ i represent the rated capacity, efficiency, and power factor of the distribution transformer.

[0033] Preferably, the power dispatch model is solved based on an optimization algorithm to obtain a power dispatch plan, including:

[0034] Randomly generate a group of individuals, and the position of each individual represents a combination of decision variables of the objective function;

[0035] For the combination of decision variables of the objective function represented by each individual, calculate the fitness value, where the fitness value is the value of the objective function;

[0036] Update the light intensity and attractiveness of the individual, and update the position of the individual based on the light intensity and attractiveness of the individual;

[0037] Judge whether the training error reaches the convergence value or the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the objective function is output, otherwise the number of iterations is incremented by 1.

[0038] Preferably, the update formula of the light intensity of the individual is as follows:

[0039]

[0040] Among them, and represent the light intensity of the i-th individual at the t-th iteration and the (t - 1)-th iteration, ρ represents a preset proportion, τ represents a preset proportionality coefficient, X t represents the position of the individual at the t-th iteration, and f(X t ) represents the fitness value corresponding to the position of the individual at the t-th iteration;

[0041] The update formula of the attractiveness of the individual is as follows:

[0042]

[0043] Among them, β(r) represents the attractiveness of an individual, β0 represents the maximum attractiveness, and r ij represents the distance between the i-th individual and the j-th individual, and r ij =||X i -X j ||, where X i and X j represent the positions of the i-th individual and the j-th individual;

[0044] The update formula for the position of the individual is as follows:

[0045]

[0046] Among them, and represent the positions of the i-th individual at the (t + 1)-th iteration and the t-th iteration, represents the position of the j-th individual at the t-th iteration, and ε i represents the random factor of the i-th individual, and α represents the step size scaling factor.

[0047] Preferably, determining the output load and input load of a new energy vehicle charging at the charging pile based on the working information includes:

[0048] Determining the output load of a new energy vehicle charging at the charging pile based on the working information, where the calculation formula for the output load is as follows:

[0049]

[0050] Among them, represents the output load of a new energy vehicle charging at the charging pile within a preset control period, and β knt represents whether the new energy vehicle is connected to the charging pile at time t. If it is connected to the charging pile, it takes 1; otherwise, it takes 0. represents the energy at which the new energy vehicle arrives at the charging pile and starts charging at time t, and V represents the set of new energy vehicles charging at the charging pile.

[0051] Preferably, determining the output load and input load of a new energy vehicle charging at the charging pile based on the working information further includes:

[0052] Determining the input load of a new energy vehicle charging at the charging pile based on the working information, where the calculation formula for the input load is as follows:

[0053]

[0054] Among them, represents the input load of a new energy vehicle charging at the charging pile within a preset control period.

[0055] Preferably, the calculation formula for the load change amount is as follows:

[0056]

[0057] Where E nt，V represents the load change amount of the charging pile at time t, P nt，V represents the charging power within a preset control period, η nt，V represents the charging efficiency within a preset control period, and Δt represents the preset control period.

[0058] The technical solution adopted to solve the above technical problems is: an intelligent charging control method for new energy vehicles, which is applicable to the above-mentioned intelligent charging control system for new energy vehicles, and includes:

[0059] Obtain the charging information of all new energy vehicles in the target charging station, and determine the total charging demand of the target charging station according to the charging information;

[0060] Obtain the power supply information of the power grid, determine the objective function according to the total charging demand and the power supply information, and determine the constraint conditions based on the power balance, voltage, line capacity and distribution transformer capacity of the power grid;

[0061] Construct a power dispatching model of the power grid based on the objective function and the constraint conditions, solve the power dispatching model based on an optimization algorithm to obtain a power dispatching plan, and dispatch the power of the power grid to the target charging station based on the power dispatching plan;

[0062] Obtain the working information of all charging piles in the target charging station, and determine the output load and input load of the new energy vehicles charging at the charging piles based on the working information;

[0063] Determine the load change amount of the charging pile according to the output load and the input load, and allocate the power of the power grid to the corresponding charging pile according to the load change amount.

[0064] The beneficial effects of the present invention are as follows: (1) The present invention obtains the charging information of all vehicles in the charging station through the demand determination unit, accurately calculates the total charging demand, ensures the reasonable distribution of power resources, avoids waste or shortage, and through the scheduling modeling unit, considers factors such as the power balance, voltage, and line capacity of the power grid to ensure that the charging load does not cause excessive pressure on the power grid and maintains the stable operation of the power grid; (2) The present invention passes the power scheduling unit to solve the power scheduling model through an optimization algorithm to generate an optimal scheduling plan, ensuring that the charging station obtains sufficient power, improving the charging efficiency, reducing the waiting time, and through the load determination unit, monitors the working state of the charging pile in real time, dynamically adjusts the output and input loads, and ensures the efficient operation of the charging pile under different loads; (3) The present invention passes the power distribution unit to distribute power according to the load change amount, ensures that each charging pile obtains the required power, avoids local overload or power shortage, improves the overall operation efficiency of the charging station, and through optimizing power scheduling and distribution, the system reduces power loss and power grid pressure, helps the charging station reduce operating costs, and improves economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 FIG. is a schematic diagram of the system architecture of the overall system in an embodiment proposed by the present invention;

[0066] Figure 2 FIG. is a schematic diagram of the step flow of the overall method in an embodiment proposed by the present invention.

[0067] Reference numerals: 1, demand determination unit; 2, scheduling modeling unit; 3, power scheduling unit; 4, load determination unit; 5, power distribution unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] Embodiment 1, as Figure 1 shown, a new energy vehicle intelligent charging control system proposed by the present invention includes:

[0069] A demand determination unit 1, which is used to obtain the charging information of all new energy vehicles in the target charging station and determine the total charging demand of the target charging station according to the charging information;

[0070] A scheduling modeling unit 2, which is used to obtain the power supply information of the power grid, determine the objective function according to the total charging demand and the power supply information, and determine the constraint conditions based on the power balance, voltage, line capacity, and distribution transformer capacity of the power grid;

[0071] A power scheduling unit 3, which is used to construct a power scheduling model of the power grid based on the objective function and the constraint conditions, solve the power scheduling model based on an optimization algorithm to obtain a power scheduling plan, and schedule the power of the power grid to the target charging station based on the power scheduling plan;

[0072] Load determination unit 4, which is used to obtain the working information of all charging piles in the target charging station, and determine the output load and input load of the new energy vehicles charging at the charging piles based on the working information;

[0073] Power distribution unit 5, which is used to determine the load change amount of the charging piles according to the output load and input load, and distribute the power of the power grid to the corresponding charging piles according to the load change amount.

[0074] In the present invention, the load refers to the power consumed by a device or system. The output load may refer to the power provided by the charging pile to the new energy vehicle, and the input load may refer to the power obtained by the charging pile from the power grid; the load change amount refers to the change in the load of the charging pile during the charging process, which may be caused by changes in the charging demand of the new energy vehicle or changes in the power supply conditions of the power grid; the power dispatching model is a mathematical model used to describe the power distribution in the power grid, which is constructed based on the objective function and constraint conditions and is used to determine how to optimally dispatch the power to meet the needs of the charging station.

[0075] Embodiment 2, an intelligent charging control system for new energy vehicles proposed by the present invention. Compared with Embodiment 1, this embodiment further includes: The charging information includes the expected end charging time, the charge amount before charging, the expected charge amount at the end of charging, and the maximum charging rate. The power supply information includes the power generation amount of renewable energy, the energy storage capacity of the energy storage device, and the power tradable volume of the power grid. The calculation formula for the total charging demand is as follows:

[0076]

[0077] Among them, Q represents the total charging demand, N represents the number of new energy vehicles in the target charging station, represents the expected charge amount at the end of charging of the new energy vehicle, and f i represents the charge amount before charging of the new energy vehicle.

[0078] In an optional embodiment, obtain the power supply information of the power grid, and determine the objective function according to the total charging demand and the power supply information, including:

[0079] Determine the first supply-demand difference according to the total charging demand and the power supply information;

[0080] When the first supply-demand difference is a positive number, determine the second supply-demand difference according to the first supply-demand difference and the power supply information;

[0081] Determine the revenue amount of the target charging station based on the first supply-demand difference and the second supply-demand difference. Among them, the calculation formula for the revenue amount is as follows:

[0082]

[0083] Among them, Denote the revenue of the target charging station as T max Denote the control period of the target charging station. Let Q(t), H(t), g(t), and b(t) denote the total charging demand, the power generation of renewable energy, the energy storage capacity of the energy storage device, and the electricity tradable volume of the power grid at time t, respectively. P H , P g and P b denote the electricity prices of renewable energy, the energy storage device, and the power grid trading at time t, respectively. QH dif denotes the first supply-demand difference, and OH dif =Q(t) - H(t). QHg dif denotes the second supply-demand difference, and QHg dif =Q(t) - H(t) - g(t).

[0084] In an optional embodiment, the constraint conditions include power balance constraint conditions, voltage constraint conditions, line capacity constraint conditions, and distribution transformer capacity constraint conditions. Among them, the expression of the power balance constraint condition is as follows:

[0085]

[0086] Among them, j represents the node in the power grid where there is a connected branch with node i. P i , Q i and U i denote the injected active power, reactive power, and voltage amplitude of node i in the power grid. G ij and B ij denote the real part and imaginary part of the mutual admittance. θ ij denotes the phase angle difference between the head and tail voltages of the branch;

[0087] The expression of the voltage constraint condition is as follows:

[0088] U min ≤U i ≤U max ;

[0089] Among them, U min and U max denote the lower and upper limits of the node voltage;

[0090] The expression of the line capacity constraint condition is as follows:

[0091] |S ij |<S ijmax ;

[0092] Among them, S ijmax denotes the upper limit of the branch capacity S ij connecting nodes i and j;

[0093] The expression of the distribution transformer capacity constraint condition is as follows:

[0094]

[0095] Among them, P Ti，t 、P Li，t 、P Ei，t and represent the total power of the distribution transformer, the conventional load power, the charging power, and the upper limit of the charging power during the t period, and S i 、ρ i and cosψ i represent the rated capacity, efficiency, and power factor of the distribution transformer.

[0096] In an alternative embodiment, the power dispatch model is solved based on an optimization algorithm to obtain a power dispatch scheme, including:

[0097] Randomly generate a group of individuals, where the position of each individual represents a combination of decision variables of the objective function;

[0098] For the combination of decision variables of the objective function represented by each individual, calculate the fitness value, where the fitness value is the value of the objective function;

[0099] Update the light intensity and attractiveness of the individual, and update the position of the individual based on the light intensity and attractiveness of the individual;

[0100] Judge whether the training error reaches the convergence value or the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the objective function is output; otherwise, the number of iterations is incremented by 1.

[0101] It should be noted that in the optimization algorithm, an "individual" usually represents a potential solution or candidate solution. Each individual represents a combination of a set of decision variables of the objective function, that is, a possible scheme for power grid power dispatch; decision variables are unknowns that need to be determined in the optimization problem, and they jointly determine the solution of the problem. In the power dispatch model, decision variables may include the amount of electricity allocated to each charging station, the power distribution of each line in the power grid, etc.; in some nature-inspired optimization algorithms, individuals have attributes such as "light intensity" and "attractiveness". The light intensity may represent the fitness value (i.e., the degree of excellence) of the individual, while the attractiveness determines the possibility of other individuals moving towards it.

[0102] In an alternative embodiment, the update formula for the light intensity of an individual is as follows:

[0103]

[0104] Among them, and represents the light intensity of the $i$-th individual at the $t$-th iteration and the $(t - 1)$-th iteration, $\rho$ represents the preset proportion, $\tau$ represents the preset proportionality coefficient, and $X$ t represents the position of the individual at the $t$-th iteration, and $f(X$ t ) represents the fitness value corresponding to the position of the individual at the $t$-th iteration;

[0105] The update formula for the attractiveness of the individual is as follows:

[0106]

[0107] where $\beta(r)$ represents the attractiveness of the individual, $\beta_0$ represents the maximum attractiveness, and $r$ ij represents the distance between the $i$-th individual and the $j$-th individual, and $r$ ij $= \|X$ i $- X$ j $\|$, and $X$ i and $X$ j represent the positions of the $i$-th individual and the $j$-th individual;

[0108] The update formula for the position of the individual is as follows:

[0109]

[0110] where and represent the position of the $i$-th individual at the $(t + 1)$-th iteration and the $t$-th iteration, represents the position of the $j$-th individual at the $t$-th iteration, $\varepsilon$ i represents the random factor of the $i$-th individual, and $\alpha$ represents the step size scaling factor.

[0111] In an alternative embodiment, determining the output load and input load of a new energy vehicle charging at a charging pile based on operating information includes:

[0112] Determining the output load of a new energy vehicle charging at a charging pile based on operating information, where the calculation formula for the output load is as follows:

[0113]

[0114] where represents the output load of a new energy vehicle charging at a charging pile within a preset control period, and $\beta$ knt represents whether the new energy vehicle is connected to the charging pile at time $t$. If it is connected to the charging pile, it takes 1; otherwise, it takes 0. represents the energy at which the new energy vehicle arrives at the charging pile and starts charging at time $t$, and $V$ represents the set of new energy vehicles charging at the charging pile.

[0115] In an alternative embodiment, determining the output load and input load of a new energy vehicle charging at a charging pile based on operation information further includes:

[0116] Determining the input load of a new energy vehicle charging at a charging pile based on operation information, where the calculation formula for the input load is as follows:

[0117]

[0118] Where, represents the input load of a new energy vehicle charging at a charging pile within a preset control period.

[0119] In an alternative embodiment, the calculation formula for the load change amount is as follows:

[0120]

[0121] Where E nt，V represents the load change amount of the charging pile at time t, P nt，V represents the charging power within a preset control period, η nt，V represents the charging efficiency within a preset control period, and Δt represents the preset control period.

[0122] Embodiment 3, as Figure 2 shown, a new energy vehicle intelligent charging control method proposed by the present invention, which is applicable to the described new energy vehicle intelligent charging control system, includes:

[0123] S1. Obtain the charging information of all new energy vehicles in the target charging station, and determine the total charging demand of the target charging station according to the charging information;

[0124] S2. Obtain the power supply information of the power grid, determine the objective function according to the total charging demand and the power supply information, and determine the constraint conditions based on the power balance, voltage, line capacity, and distribution transformer capacity of the power grid;

[0125] S3. Construct a power dispatching model of the power grid based on the objective function and the constraint conditions, solve the power dispatching model based on an optimization algorithm to obtain a power dispatching plan, and dispatch the power of the power grid to the target charging station based on the power dispatching plan;

[0126] S4. Obtain the operation information of all charging piles in the target charging station, and determine the output load and input load of the new energy vehicle charging at the charging pile based on the operation information;

[0127] S5. Determine the load change amount of the charging pile according to the output load and the input load, and distribute the power of the power grid to the corresponding charging pile according to the load change amount.

[0128] The embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited thereto, and various changes can be made without departing from the spirit of the present invention within the scope of knowledge possessed by those skilled in the art to which the present invention pertains.

Claims

1. An intelligent charging control system for new energy vehicles, characterized in that, Including: A demand determination unit (1) configured to obtain the charging information of all new energy vehicles in a target charging station and determine the total charging demand of the target charging station according to the charging information; A scheduling modeling unit (2) configured to obtain the power supply information of the power grid, determine an objective function according to the total charging demand and the power supply information, and determine constraint conditions based on the power balance, voltage, line capacity, and distribution transformer capacity of the power grid; A power dispatching unit (3) configured to construct a power dispatching model of the power grid based on the objective function and the constraint conditions, solve the power dispatching model based on an optimization algorithm to obtain a power dispatching plan, and dispatch the power of the power grid to the target charging station based on the power dispatching plan; A load determination unit (4) configured to obtain the working information of all charging piles in the target charging station and determine the output load and input load of new energy vehicles charging at the charging piles based on the working information; A power allocation unit (5) configured to determine the load change amount of the charging piles according to the output load and the input load, and allocate the power of the power grid to the corresponding charging piles according to the load change amount.

2. The intelligent charging control system for a new energy vehicle according to claim 1, characterized in that, The charging information includes the expected end charging time, the charge amount before charging, the expected charge amount at the end of charging, and the maximum charging rate. The power supply information includes the power generation of renewable energy, the energy storage capacity of energy storage devices, and the power tradable volume of the power grid. The calculation formula for the total charging demand is as follows: Among them, Q represents the total charging demand, and N represents the number of new energy vehicles in the target charging station. represents the expected charge amount when the charging of the new energy vehicle ends, and f i represents the charge amount before the charging of the new energy vehicle.

3. The intelligent charging control system for a new energy vehicle according to claim 2, wherein, Obtaining the power supply information of the power grid and determining the objective function according to the total charging demand and the power supply information includes: Determining a first supply-demand difference according to the total charging demand and the power supply information; When the first supply-demand difference is a positive number, determining a second supply-demand difference according to the first supply-demand difference and the power supply information; Determining the revenue amount of the target charging station based on the first supply-demand difference and the second supply-demand difference, where the calculation formula for the revenue amount is as follows: Among them, represents the revenue of the target charging station, T max represents the control period of the target charging station, Q(t), H(t), g(t), and b(t) represent the total charging demand, the power generation of renewable energy, the energy storage capacity of the energy storage device, and the power tradable volume of the power grid at time t, P H , P g and P b represent the electricity prices of renewable energy, energy storage devices, and grid transactions at time t, QH dif represents the first supply-demand difference, and QH dif =Q(t) - H(t), QHg dif represents the second supply-demand difference, and QHg dif =Q(t) - H(t) - g(t); Determining the objective function based on the revenue amount of the target charging station, where the objective function is to maximize the revenue amount of the target charging station.

4. The intelligent charging control system for a new energy vehicle according to claim 3, characterized in that, The constraint conditions include a power balance constraint condition, a voltage constraint condition, a line capacity constraint condition, and a distribution transformer capacity constraint condition. Among them, the expression of the power balance constraint condition is as follows: Among them, j represents the node where there is a connected branch with node i in the power grid, P i , Q i and U i represent the injected active power, reactive power and voltage amplitude of node i in the power grid, G ij and B ij represent the real part and imaginary part of the mutual admittance, θ ij represents the phase angle difference between the head and end voltages of the branch; The expression of the voltage constraint condition is as follows: U min ≤U i ≤U max ; where U min and U max represent the lower and upper limits of the node voltage; The expression of the line capacity constraint condition is as follows: |S ij |<S ijmax ; Among them, S ijmax represents the upper limit of the branch capacity S ij connecting nodes i and j; The expression of the distribution transformer capacity constraint condition is as follows: Among them, P Ti,t , P Li，t , P Ei，t and represent the total power of the distribution transformer, the conventional load power, the charging power, and the upper limit of the charging power during the t period. S i , ρ i and cosψ i represent the rated capacity, efficiency, and power factor of the distribution transformer.

5. The intelligent charging control system for a new energy vehicle according to claim 4, wherein Solving the power dispatching model based on an optimization algorithm to obtain a power dispatching plan includes: Randomly generating a group of individuals, where the position of each individual represents a combination of decision variables of the objective function; For the combination of decision variables of the objective function represented by each individual, calculating a fitness value, where the fitness value is the value of the objective function; Updating the light intensity and attraction degree of the individual, and updating the position of the individual based on the light intensity and attraction degree of the individual. Determine whether the training error reaches the convergence value or whether the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the objective function is output; otherwise, the number of iterations is incremented by 1.

6. The intelligent charging control system for a new energy vehicle according to claim 5, wherein The update formula for the light intensity of the individual is as follows: Among them, and represent the light intensity of the i-th individual at the t-th iteration and the (t - 1)-th iteration, ρ represents a preset proportion, τ represents a preset proportionality coefficient, X t represents the position of the individual at the t-th iteration, and f(X t ) represents the fitness value corresponding to the position of the individual at the t-th iteration; The update formula for the attractiveness of the individual is as follows: Among them, β(r) represents the attraction degree of an individual, β0 represents the maximum attraction degree, and r ij represents the distance between the i-th individual and the j-th individual, and r ij =||X i -X j ||, where X i and X j represent the positions of the i-th individual and the j-th individual; The update formula for the position of the individual is as follows: Among them, and represent the positions of the \(i\)-th individual at the \((t + 1)\)-th iteration and the \(t\)-th iteration, represents the position of the \(j\)-th individual at the \(t\)-th iteration, and \(\varepsilon\) i represents the random factor of the \(i\)-th individual, and \(\alpha\) represents the step size scaling factor.

7. An intelligent charging control system for a new energy vehicle according to claim 1, characterized in that, Determine the output load and input load of new energy vehicles charging at the charging pile based on the work information, including: Determine the output load of new energy vehicles charging at the charging pile based on the work information, where the calculation formula for the output load is as follows: Among them, represents the output load of new energy vehicles charging at the charging pile within a preset control period, and β knt represents whether the new energy vehicle is connected to the charging pile at time t. If it is connected to the charging pile, it takes 1; otherwise, it takes 0. represents the energy when the new energy vehicle arrives at the charging pile and starts charging at time t, and V represents the set of new energy vehicles charging at the charging pile.

8. The intelligent charging control system for a new energy vehicle according to claim 7, characterized in that, Determine the output load and input load of new energy vehicles charging at the charging pile based on the work information, and further include: Determine the input load of new energy vehicles charging at the charging pile based on the work information, where the calculation formula for the input load is as follows: Among them, represents the input load of new energy vehicles charging at the charging pile within a preset control period.

9. The intelligent charging control system for a new energy vehicle according to claim 8, characterized in that The calculation formula for the load change amount is as follows: Among them, E nt，V represents the load change of the charging pile at time t, and P nt，V represents the charging power within a preset control period, and η nt，V represents the charging efficiency within a preset control period, and Δt represents the preset control period.

10. A smart charging control method for a new energy vehicle, which is applicable to a smart charging control system for a new energy vehicle according to any one of claims 1-9, characterized in that, Include: Obtain the charging information of all new energy vehicles in the target charging station, and determine the total charging demand of the target charging station according to the charging information; Obtain the power supply information of the power grid, determine the objective function according to the total charging demand and the power supply information, and determine the constraint conditions based on the power balance, voltage, line capacity, and distribution transformer capacity of the power grid; Construct the power dispatching model of the power grid based on the objective function and the constraint conditions, solve the power dispatching model based on the optimization algorithm to obtain the power dispatching plan, and dispatch the power of the power grid to the target charging station based on the power dispatching plan; Obtain the work information of all charging piles in the target charging station, and determine the output load and input load of new energy vehicles charging at the charging pile based on the work information; Determine the load change amount of the charging pile according to the output load and the input load, and distribute the power of the power grid to the corresponding charging pile according to the load change amount.

Images