Charging pile configuration method and device based on cuckoo algorithm, equipment and medium

Abstract

The invention discloses a Cuckoo algorithm-based charging pile configuration method, apparatus and device, and a medium. The method comprises the steps of predicting charging demand data of a target area; substituting the charging demand data, preset energy storage data of the energy storage system and the attribute data of the power distribution network into a preset configuration model to obtain a to-be-solved model; the to-be-solved model is solved through a preset multi-target cuckoo search algorithm, a charging pile configuration strategy in the target area is obtained, a step parameter in the preset multi-target cuckoo search algorithm is set as a constant, and the step parameter is inversely proportional to the number of iterations of the preset multi-target cuckoo search algorithm. The efficiency of locating and sizing of the charging pile is improved through the preset multi-target cuckoo search algorithm, the charging demand data of the electric vehicle, the preset energy storage data of the energy storage system and the attribute data (including the electric vehicle, the energy storage system and the power distribution network) of the power distribution network are considered, and the configuration of the charging pile is more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization, and in particular to a charging pile configuration method, device, equipment and medium based on a cuckoo algorithm. Background Art

[0002] With the rapid development of my country's economy, the number of electric vehicles (EVs) has increased significantly. Due to the sharp increase in EV charging demand, a large number of charging stations (EVCS stations) need to be connected to the power grid. However, the random construction of EVCS not only fails to meet the sharp increase in EV charging demand, but also may have an adverse impact on the stability and economy of the power grid.

[0003] In the prior art, the configuration of charging stations (EVCS stations) often only considers the charging demand. Building EVCS only based on the charging demand not only fails to meet the sharp increase in EV charging demand, but also may have an adverse impact on the stability and economy of the power grid. At the same time, although building EVCS based on charging demand can directly meet the car use needs of EV owners, it is often not friendly to the investors of charging stations (EVCS stations), making the construction cost of charging stations (EVCS stations) too high. That is, the prior art has limitations on the configuration of charging stations (EVCS stations), resulting in unreasonable configuration of charging stations (EVCS stations). Summary of the invention

[0004] In view of this, the present invention provides a charging pile configuration method, device, equipment and medium based on the cuckoo algorithm, which is used to solve the problem that the configuration of the charging station (EVCS station) in the prior art is limited, resulting in unreasonable configuration of the charging station (EVCS station).

[0005] To achieve one or part or all of the above purposes or other purposes, the present invention proposes a charging pile configuration method based on the cuckoo algorithm, comprising:

[0006] Predicting charging demand data of the target area by using historical electric vehicle traffic data of each intersection in the target area and characteristic data of electric vehicles;

[0007] Bringing the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved;

[0008] The model to be solved is solved by a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step length parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step length parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0009] Optionally, the step of predicting charging demand data of the target area by using historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles includes:

[0010] Establishing a probability distribution model based on the historical electric vehicle traffic data;

[0011] By using the Monte Carlo simulation method and the probability distribution model, the average traffic flow data of each intersection in the target area within the target time is predicted;

[0012] The charging demand data of the target area is predicted based on the average vehicle flow data and the characteristic data of the electric vehicle.

[0013] Optionally, the characteristic data at least includes total mileage data, starting travel time data and starting remaining power data, and the step of predicting the charging demand data of the target area based on the average vehicle flow data and the characteristic data of the electric vehicle includes:

[0014] Establishing a first probability density function according to the mathematical characteristics of the total mileage data in the characteristic data, and acquiring first probability distribution data based on the first probability density function;

[0015] constructing a second probability density function for the starting driving time data by analogy, and acquiring second probability distribution data based on the second probability density function;

[0016] By using a preset probability density function for the initial remaining power data, taking the initial remaining power data as a random variable, obtaining third probability distribution data;

[0017] The charging demand data of the target area is predicted based on the average vehicle flow data, the first probability distribution data, the second probability distribution data, and the third probability distribution data.

[0018] Optionally, the step of predicting the charging demand data of the target area based on the average vehicle flow data, the first probability distribution data, the second probability distribution data and the third probability distribution data includes:

[0019] Obtaining initial charging demand data of the target area according to the first probability distribution data, the second probability distribution data, and the third probability distribution data through a charging demand model based on a decision tree;

[0020] The charging demand data of the target area is predicted based on the average vehicle flow data and the initial charging demand data.

[0021] Optionally, before the step of bringing the charging demand data, the preset energy storage data of the energy storage system and the distribution network attribute data into a preset configuration model to obtain a model to be solved, the step further includes:

[0022] Constructing a first objective function based on the first preset condition, wherein the first objective function is a function that characterizes that the comprehensive cost of the charging pile combined with the energy storage system meets the first preset condition;

[0023] Constructing a second objective function based on the second preset condition, wherein the second objective function is a function that characterizes whether the waiting time of the electric vehicle meets the second preset condition;

[0024] Constructing a third objective function based on the third preset condition, wherein the third objective function is a function that characterizes that the voltage fluctuation of the distribution network meets the third preset condition;

[0025] Combining the first objective function, the second objective function and the third objective function to obtain a function equation group in the preset configuration model;

[0026] Acquire preset constraints, and obtain the preset configuration model based on the preset constraints and the functional equation group.

[0027] Optionally, the preset constraints include at least: distance constraints, charging station capacity constraints, node voltage constraints, energy storage system power constraints, and energy storage system charging and discharging power constraints.

[0028] Optionally, the step of solving the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area includes:

[0029] The model to be solved is solved by a preset multi-objective cuckoo search algorithm, the preset position of the charging pile to be configured in the target area, the first attribute data of the charging pile to be configured and the second attribute data of the preset energy storage system, and the charging pile configuration strategy in the target area is generated according to the preset position, the first attribute data and the second attribute data.

[0030] On the other hand, an embodiment of the present application provides a charging pile configuration device based on a cuckoo algorithm, the device comprising:

[0031] A prediction module, used to predict charging demand data of the target area based on historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles;

[0032] A first calculation module is used to bring the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved;

[0033] The second calculation module is used to solve the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0034] On the other hand, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the charging pile configuration method based on the cuckoo algorithm are performed as described above.

[0035] On the other hand, an embodiment of the present application provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the charging pile configuration method based on the cuckoo algorithm as described above are executed.

[0036] Implementing the embodiments of the present invention will have the following beneficial effects:

[0037] The charging demand data of the target area is predicted by the historical electric vehicle traffic data of each intersection in the target area and the characteristic data of electric vehicles; the charging demand data, the preset energy storage data of the energy storage system and the attribute data of the distribution network are brought into the preset configuration model to obtain the model to be solved; the model to be solved is solved by the preset multi-objective cuckoo search algorithm to obtain the charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm. The efficiency of the site selection and capacity determination of the charging piles is improved by the preset multi-objective cuckoo search algorithm, taking into account the charging demand data of electric vehicles, the preset energy storage data of the energy storage system and the attribute data of the distribution network (three aspects of electric vehicles, energy storage systems and distribution networks), so that the configuration of the charging piles is more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0039] in:

[0040] Figure 1It is a flow chart of a charging pile configuration method based on the cuckoo algorithm provided in an embodiment of the present application;

[0041] Figure 2 It is a state task network diagram in another charging pile configuration method based on the cuckoo algorithm provided in an embodiment of the present application;

[0042] Figure 3 It is a structural schematic diagram of a charging pile configuration device based on a cuckoo algorithm provided in an embodiment of the present application;

[0043] Figure 4 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0044] Figure 5 It is a structural schematic diagram of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] like Figure 1 As shown, the embodiment of the present application provides a charging pile configuration method based on the cuckoo algorithm, including:

[0047] S101, predicting charging demand data of the target area based on historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles;

[0048] Exemplarily, the number of all cars passing the target intersection (any intersection within the target area) within a preset time is counted, and the number of electric vehicles passing the target intersection within the preset time (historical electric vehicle flow data) is obtained based on the number of all cars through probabilistic statistical data. Specifically, the number of all cars passing the target intersection (any intersection within the target area) within the preset time is 100, and the probabilistic statistical data shows that the proportion of new energy vehicles in the target area is 4%, of which electric vehicles account for 70%. Then the number of electric vehicles passing the target intersection within the preset time (historical electric vehicle flow data) is calculated to be 100*4%*70%=2.8. After rounding, it is determined that the number of electric vehicles passing the target intersection within the preset time is 3.

[0049] Exemplarily, the characteristic data represents the driving characteristics of the electric vehicle, and the characteristic data at least includes total mileage data, starting driving time data, and starting remaining power data (SOC) of any electric vehicle on the same day.

[0050] S102, bringing the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved;

[0051] Exemplarily, a BESS is an energy storage system consisting of a battery and a parallel voltage converter, which can transfer loads and has the ability to regulate the exchange (output or absorption) of power (active or reactive) with the AC system, and thus has functions such as smooth transition, peak shaving and valley filling, frequency regulation and voltage regulation. The preset energy storage data is a mathematical model used to describe the charging and discharging characteristics of the BESS, specifically:

[0052]

[0053] In the formula, B λ The subscript indicates the λth BESS; P cha Indicates charging power; α cha Indicates charging efficiency; represents the capacity of the λth BESS; represents the rated capacity of the λth BESS; P dis Represents discharge power; α dis Indicates the discharge efficiency, Δt bess is the working time of the energy storage system (BESS), t bess is the time when the BESS starts to operate; in addition, the self-discharge rate of BESS is negligible.

[0054] Exemplarily, the preset configuration model includes a function for characterizing the minimum total economic cost of building a charging station, a function for characterizing the minimum waiting time cost of a user (electric vehicle), and a function for the minimum voltage fluctuation of the distribution network where the charging station is located; the preset configuration model also includes distance constraints, charging station capacity constraints, node voltage constraints, energy storage system power constraints, and energy storage system charging and discharging power constraints.

[0055] S103. Solve the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0056] Exemplarily, the multi-objective cuckoo search algorithm is an algorithm that effectively solves the optimization problem by simulating the Brood Parasitism of certain species of cuckoos.

[0057] Exemplarily, by adjusting the step size parameter of the Levy flight in the multi-objective cuckoo search algorithm, the balance between the global search and the local search of the algorithm can be controlled, and then the step size parameter is set to a constant, and the step size parameter decreases as the number of iterations increases, thereby improving the search efficiency, that is, improving the efficiency of solving the model to be solved.

[0058] The charging demand data of the target area is predicted by the historical electric vehicle traffic data of each intersection in the target area and the characteristic data of electric vehicles; the charging demand data, the preset energy storage data of the energy storage system and the attribute data of the distribution network are brought into the preset configuration model to obtain the model to be solved; the model to be solved is solved by the preset multi-objective cuckoo search algorithm to obtain the charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm. The efficiency of the site selection and capacity determination of the charging piles is improved by the preset multi-objective cuckoo search algorithm, taking into account the charging demand data of electric vehicles, the preset energy storage data of the energy storage system and the attribute data of the distribution network (three aspects of electric vehicles, energy storage systems and distribution networks), so that the configuration of the charging piles is more reasonable.

[0059] In a possible implementation, the step of predicting charging demand data of the target area by using historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles includes:

[0060] Establishing a probability distribution model based on the historical electric vehicle traffic data;

[0061] By using the Monte Carlo simulation method and the probability distribution model, the average traffic flow data of each intersection in the target area within the target time is predicted;

[0062] The charging demand data of the target area is predicted based on the average vehicle flow data and the characteristic data of the electric vehicle.

[0063] Exemplarily, a probability distribution model is established based on historical traffic flow data, and a Monte Carlo simulation method is used to simulate the traffic flow conditions at each intersection in the next 30 days (target time) to calculate an average traffic flow index, which is used to predict the number of vehicles passing through the intersection in the next 30 days (target time).

[0064] Exemplarily, when the problem to be solved is the probability of a random event occurring, or the expected value of a random variable, the Monte Carlo simulation method is a method of estimating the probability of the random event by the frequency of occurrence of the event through experiments, or obtaining certain numerical features of the random variable and using them as the solution to the problem.

[0065] In a possible implementation manner, the characteristic data at least includes total mileage data, starting travel time data, and starting remaining power data, and the step of predicting the charging demand data of the target area based on the average vehicle flow data and the characteristic data of the electric vehicle includes:

[0066] Establishing a first probability density function according to the mathematical characteristics of the total mileage data in the characteristic data, and acquiring first probability distribution data based on the first probability density function;

[0067] constructing a second probability density function for the starting driving time data by analogy, and acquiring second probability distribution data based on the second probability density function;

[0068] By using a preset probability density function for the initial remaining power data, taking the initial remaining power data as a random variable, obtaining third probability distribution data;

[0069] The charging demand data of the target area is predicted based on the average vehicle flow data, the first probability distribution data, the second probability distribution data, and the third probability distribution data.

[0070] For example, the total mileage of an electric vehicle (EV) in a day follows a log-normal distribution (mathematical property), i.e. The first probability density function is:

[0071]

[0072] Where s is the total mileage of the EV in one day, in km; μ b and σ b Respectively represent the mean and standard deviation of the total mileage of the vehicle in a day, where μ b =3.3,σ b =0.88, π and e are mathematical constants. The probability distribution diagram of the total mileage of an EV in one day (first probability distribution data) is obtained through the first probability density function.

[0073] For example, the daily behavior of EV users, seasonal changes, traffic conditions and other factors may affect the starting driving time of EV. The starting driving time of EV also presents the characteristics of bimodal distribution. Therefore, the analogy method is adopted, that is, analogy with human behavior (daily travel mode), and the probability density function is used to describe the distribution of the starting driving time of EV, and the second probability density function is obtained:

[0074]

[0075] Where t is the travel time in minutes. s,1 and σ s,1 represents the mean and standard deviation of the first peak, μ s,2 and σ s,2 represents the mean and standard deviation of the second peak, where μ s,1 =8,σ s,1 =3,μ s,2 =18,σ s,2 =2.25. The probability distribution diagram of the starting driving time of the EV at each time (second probability distribution data) is obtained from the second probability density function.

[0076] For example, the starting SOC affects the user's charging time and the charging demand of the EV. If the starting SOC of the EV is a random variable, the preset probability density function is:

[0077]

[0078] In the formula, SOC EV is the starting SOC of EV, μ soc is the mean value of SOC, σ soc is the standard deviation of SOC, where μ soc =0.3,σ soc = 0.15. A probability diagram of the initial SOC (third probability distribution data) is obtained according to a preset probability density function.

[0079] In a possible implementation, the step of predicting the charging demand data of the target area based on the average vehicle flow data, the first probability distribution data, the second probability distribution data, and the third probability distribution data includes:

[0080] Obtaining initial charging demand data of the target area according to the first probability distribution data, the second probability distribution data, and the third probability distribution data through a charging demand model based on a decision tree;

[0081] The charging demand data of the target area is predicted based on the average vehicle flow data and the initial charging demand data.

[0082] For example, considering the total mileage of EV in one day (first probability distribution data), the starting SOC (second probability distribution data), and the starting driving time (third probability distribution data), a decision tree-based charging demand model can be used to predict the charging demand, and the data is divided into four ranges according to the total mileage of EV in one day. In each range, the possibility of charging demand is judged according to the conditions of the starting SOC and the starting driving time: if the mileage is greater than 100 kilometers, and the SOC is less than 20%, and the starting driving time is during the peak period, charging is required; if the mileage is greater than 200 kilometers, and the SOC is less than 30%, and the starting driving time is during the peak period, charging is required; if the mileage is greater than 150 kilometers, and the SOC is less than 25%, and the starting driving time is during the non-peak period, charging is required; in other cases, charging is not required.

[0083] In a possible implementation manner, before the step of bringing the charging demand data, the preset energy storage data of the energy storage system, and the distribution network attribute data into the preset configuration model to obtain the model to be solved, the step further includes:

[0084] Constructing a first objective function based on the first preset condition, wherein the first objective function is a function that characterizes that the comprehensive cost of the charging pile combined with the energy storage system meets the first preset condition;

[0085] Constructing a second objective function based on the second preset condition, wherein the second objective function is a function that characterizes whether the waiting time of the electric vehicle meets the second preset condition;

[0086] Constructing a third objective function based on the third preset condition, wherein the third objective function is a function that characterizes that the voltage fluctuation of the distribution network meets the third preset condition;

[0087] Combining the first objective function, the second objective function and the third objective function to obtain a function equation group in the preset configuration model;

[0088] Acquire preset constraints, and obtain the preset configuration model based on the preset constraints and the functional equation group.

[0089] Exemplarily, the first preset condition is to characterize that the comprehensive cost of the charging pile combined with the energy storage system is the lowest, then the first objective function is:

[0090] minF1=W1+W2+W3

[0091] Among them, F1 refers to the comprehensive cost of EVCS combined with BESS, that is, the total economic cost of establishing a charging station; W1 represents the annualized total cost of investing in the construction of EVCS; W2 is the full life cycle cost of investing in the construction of BESS; and W3 is the power loss cost.

[0092] Exemplarily, the second preset condition is that the waiting time of the electric vehicle is the shortest, then the second objective function is:

[0093]

[0094] Where n EV Indicates the number of EVs; represents the shortest distance for the i-th vehicle to reach the j-th EVCS; v is the average driving speed; W(i) represents the waiting time of the i-th vehicle in the queue at the j-th EVCS.

[0095] Exemplarily, the third preset condition is that the voltage fluctuation of the distribution network is the lowest, then the third objective function is:

[0096]

[0097] N node represents the number of nodes; T represents time; V ij represents the voltage of node i at time j; It refers to the average voltage of node i during the period [1,T].

[0098] Exemplarily, the preset constraints include at least: distance constraints, charging station capacity constraints, node voltage constraints, energy storage system power constraints, and energy storage system charging and discharging power constraints.

[0099] Specifically, the distance constraint is:

[0100] R EVCS ≤D EVCS ≤2R EVCS

[0101] In the formula, R EVCS represents the service radius of the charging station; D EVCS Indicates the distance between two charging stations.

[0102] Charging station capacity constraints:

[0103]

[0104]

[0105] Indicates the maximum value of charging demand in this area; T max Indicates the maximum service time of the charging station.

[0106] Node voltage constraints:

[0107]

[0108] In the formula, and They are the upper and lower limits of voltage after node k is connected to EVCS.

[0109] Energy storage system power constraints:

[0110]

[0111] In the formula, and They represent the minimum and maximum SOC of the electric energy storage system respectively.

[0112] Energy storage system charging and discharging power constraints:

[0113]

[0114] In the formula, Respectively represent the rated charging and discharging power of BESS.

[0115] In a possible implementation, the step of solving the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area includes:

[0116] The model to be solved is solved by a preset multi-objective cuckoo search algorithm, the preset position of the charging pile to be configured in the target area, the first attribute data of the charging pile to be configured and the second attribute data of the preset energy storage system, and the charging pile configuration strategy in the target area is generated according to the preset position, the first attribute data and the second attribute data.

[0117] Exemplarily, the MCS algorithm follows the following principles: for each cuckoo, an egg is generated according to the current nest state, that is, a new solution is generated; the cuckoo randomly selects a parasitic nest for incubation; if the quality of the newly generated egg is better than the eggs in the parasitic nest, the new egg is kept in the parasitic nest. Otherwise, the original egg is retained; under certain probability conditions (determined by the parameter P, P∈[0,1]), the host bird may find the egg. If the host bird finds the egg, it destroys the egg or looks for a new nest; the cuckoo will randomly select a nest location to lay eggs, that is, the change of the nest location is achieved through Levy flight:

[0118]

[0119] In the formula, is the nest position of the kth bird in the it+1th generation; m is the total number of parasitic nests; s is the step size parameter; Levy (ψ) is the Levy flight, which is essentially a Markov chain. The position of the next generation nest depends on the transition probability

[0120] Specifically, by adjusting the step size parameter s of the Levy flight, the balance between the global search and the local search of the control algorithm is achieved. That is, the step size parameter is set to a constant to improve the search efficiency. The step size s will decrease as the number of iterations increases, as shown in the following formula:

[0121]

[0122] Among them, s i is the step length parameter of the i-th iteration; s0 is the initial step length parameter of the Levy flight, and the preset multi-objective cuckoo search algorithm is obtained.

[0123] In a possible implementation, Figure 2 As shown, an embodiment of the present application provides a charging pile configuration method based on the cuckoo algorithm, including: inputting historical traffic data; predicting the traffic flow at each intersection through a traffic flow prediction model, and outputting the prediction results; inputting the prediction results into a charging demand calculation model, and outputting the charging demand; setting initialization parameters such as upper and lower limits of decision variables, number of iterations, and number of populations; initializing the MCS algorithm to generate a cuckoo population; evaluating individual fitness and finding the best nest; updating the Levy flight step; selecting the best individual, and updating the positions of the remaining cuckoos; selecting and iterating to generate a new generation of optimal individuals; whether the maximum number of iterations has been reached; generating the optimal solution, and outputting the EVCS position and capacity as well as the BESS capacity and charging and discharging power.

[0124] In a possible implementation, Figure 3 As shown, an embodiment of the present application provides a charging pile configuration device based on a cuckoo algorithm, the device comprising:

[0125] Prediction module 201, used to predict charging demand data of the target area based on historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles;

[0126] A first calculation module 202 is used to bring the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved;

[0127] The second calculation module 203 is used to solve the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step length parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step length parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0128] In a possible implementation, the prediction module 201 is used to:

[0129] Establishing a probability distribution model based on the historical electric vehicle traffic data;

[0130] By using the Monte Carlo simulation method and the probability distribution model, the average traffic flow data of each intersection in the target area within the target time is predicted;

[0131] The charging demand data of the target area is predicted based on the average vehicle flow data and the characteristic data of the electric vehicle.

[0132] In a possible implementation, the prediction module 201 is used to:

[0133] Establishing a first probability density function according to the mathematical characteristics of the total mileage data in the characteristic data, and acquiring first probability distribution data based on the first probability density function;

[0134] constructing a second probability density function for the starting driving time data by analogy, and acquiring second probability distribution data based on the second probability density function;

[0135] By using a preset probability density function for the initial remaining power data, taking the initial remaining power data as a random variable, obtaining third probability distribution data;

[0136] The charging demand data of the target area is predicted based on the average vehicle flow data, the first probability distribution data, the second probability distribution data, and the third probability distribution data.

[0137] In a possible implementation, the prediction module 201 is used to:

[0138] Obtaining initial charging demand data of the target area according to the first probability distribution data, the second probability distribution data, and the third probability distribution data through a charging demand model based on a decision tree;

[0139] The charging demand data of the target area is predicted based on the average vehicle flow data and the initial charging demand data.

[0140] In a possible implementation manner, the first calculation module 202 is used to:

[0141] Constructing a first objective function based on the first preset condition, wherein the first objective function is a function that characterizes that the comprehensive cost of the charging pile combined with the energy storage system meets the first preset condition;

[0142] Constructing a second objective function based on the second preset condition, wherein the second objective function is a function that characterizes whether the waiting time of the electric vehicle meets the second preset condition;

[0143] Constructing a third objective function based on the third preset condition, wherein the third objective function is a function that characterizes that the voltage fluctuation of the distribution network meets the third preset condition;

[0144] Combining the first objective function, the second objective function and the third objective function to obtain a function equation group in the preset configuration model;

[0145] Acquire preset constraints, and obtain the preset configuration model based on the preset constraints and the functional equation group.

[0146] In a possible implementation, the preset constraints include at least: distance constraints, charging station capacity constraints, node voltage constraints, energy storage system power constraints, and energy storage system charging and discharging power constraints.

[0147] In a possible implementation manner, the second calculation module 203 is used to:

[0148] The model to be solved is solved by a preset multi-objective cuckoo search algorithm, the preset position of the charging pile to be configured in the target area, the first attribute data of the charging pile to be configured and the second attribute data of the preset energy storage system, and the charging pile configuration strategy in the target area is generated according to the preset position, the first attribute data and the second attribute data.

[0149] The charging demand data of the target area is predicted by the historical electric vehicle traffic data of each intersection in the target area and the characteristic data of electric vehicles; the charging demand data, the preset energy storage data of the energy storage system and the attribute data of the distribution network are brought into the preset configuration model to obtain the model to be solved; the model to be solved is solved by the preset multi-objective cuckoo search algorithm to obtain the charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm. The efficiency of the site selection and capacity determination of the charging piles is improved by the preset multi-objective cuckoo search algorithm, taking into account the charging demand data of electric vehicles, the preset energy storage data of the energy storage system and the attribute data of the distribution network (three aspects of electric vehicles, energy storage systems and distribution networks), so that the configuration of the charging piles is more reasonable.

[0150] In a possible implementation, Figure 4As shown, an embodiment of the present application provides an electronic device 300, including: a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it implements: predicting the charging demand data of the target area through the historical electric vehicle traffic data at each intersection in the target area and the characteristic data of the electric vehicles; bringing the charging demand data, the preset energy storage data of the energy storage system, and the distribution network attribute data into a preset configuration model to obtain a model to be solved; solving the model to be solved by a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0151] The charging demand data of the target area is predicted by the historical electric vehicle traffic data of each intersection in the target area and the characteristic data of electric vehicles; the charging demand data, the preset energy storage data of the energy storage system and the attribute data of the distribution network are brought into the preset configuration model to obtain the model to be solved; the model to be solved is solved by the preset multi-objective cuckoo search algorithm to obtain the charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm. The efficiency of the site selection and capacity determination of the charging piles is improved by the preset multi-objective cuckoo search algorithm, taking into account the charging demand data of electric vehicles, the preset energy storage data of the energy storage system and the attribute data of the distribution network (three aspects of electric vehicles, energy storage systems and distribution networks), so that the configuration of the charging piles is more reasonable.

[0152] In a possible implementation, Figure 5 As shown, an embodiment of the present application provides a computer-readable storage medium 400 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it implements: predicting the charging demand data of the target area through the historical electric vehicle flow data at each intersection in the target area and the characteristic data of the electric vehicles; bringing the charging demand data, the preset energy storage data of the energy storage system and the distribution network attribute data into a preset configuration model to obtain a model to be solved; solving the model to be solved by a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

[0153] The charging demand data of the target area is predicted by the historical electric vehicle traffic data of each intersection in the target area and the characteristic data of electric vehicles; the charging demand data, the preset energy storage data of the energy storage system and the attribute data of the distribution network are brought into the preset configuration model to obtain the model to be solved; the model to be solved is solved by the preset multi-objective cuckoo search algorithm to obtain the charging pile configuration strategy in the target area, and the step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm. The efficiency of the site selection and capacity determination of the charging piles is improved by the preset multi-objective cuckoo search algorithm, taking into account the charging demand data of electric vehicles, the preset energy storage data of the energy storage system and the attribute data of the distribution network (three aspects of electric vehicles, energy storage systems and distribution networks), so that the configuration of the charging piles is more reasonable.

[0154] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0155] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0156] The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, etc., or any suitable combination of the foregoing.

[0157] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0158] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0159] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described above, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

[0160] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A charging pile configuration method based on the cuckoo algorithm, characterized in that: The method comprises: Predicting charging demand data of the target area by using historical electric vehicle traffic data of each intersection in the target area and characteristic data of electric vehicles; Bringing the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved; The model to be solved is solved by a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step length parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step length parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

2. The charging pile configuration method based on the cuckoo algorithm according to claim 1 is characterized in that: The step of predicting charging demand data of the target area by using historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles comprises: Establishing a probability distribution model based on the historical electric vehicle traffic data; By using the Monte Carlo simulation method and the probability distribution model, the average traffic flow data of each intersection in the target area within the target time is predicted; The charging demand data of the target area is predicted based on the average vehicle flow data and the characteristic data of the electric vehicle.

3. The charging pile configuration method based on the cuckoo algorithm according to claim 2 is characterized in that: The characteristic data at least includes total mileage data, starting travel time data and starting remaining power data. The step of predicting the charging demand data of the target area based on the average vehicle flow data and the characteristic data of the electric vehicle includes: Establishing a first probability density function according to the mathematical characteristics of the total mileage data in the characteristic data, and acquiring first probability distribution data based on the first probability density function; constructing a second probability density function for the starting driving time data by analogy, and acquiring second probability distribution data based on the second probability density function; By using a preset probability density function for the initial remaining power data, taking the initial remaining power data as a random variable, obtaining third probability distribution data; The charging demand data of the target area is predicted based on the average vehicle flow data, the first probability distribution data, the second probability distribution data, and the third probability distribution data.

4. The charging pile configuration method based on the cuckoo algorithm according to claim 3 is characterized in that: The step of predicting the charging demand data of the target area based on the average vehicle flow data, the first probability distribution data, the second probability distribution data and the third probability distribution data comprises: Obtaining initial charging demand data of the target area according to the first probability distribution data, the second probability distribution data, and the third probability distribution data through a charging demand model based on a decision tree; The charging demand data of the target area is predicted based on the average vehicle flow data and the initial charging demand data.

5. The charging pile configuration method based on the cuckoo algorithm according to claim 1, characterized in that: Before the step of bringing the charging demand data, the preset energy storage data of the energy storage system and the distribution network attribute data into the preset configuration model to obtain the model to be solved, the step further includes: Constructing a first objective function based on the first preset condition, wherein the first objective function is a function that characterizes that the comprehensive cost of the charging pile combined with the energy storage system meets the first preset condition; Constructing a second objective function based on the second preset condition, wherein the second objective function is a function that characterizes whether the waiting time of the electric vehicle meets the second preset condition; Constructing a third objective function based on the third preset condition, wherein the third objective function is a function that characterizes that the voltage fluctuation of the distribution network meets the third preset condition; Combining the first objective function, the second objective function and the third objective function to obtain a function equation group in the preset configuration model; Acquire preset constraints, and obtain the preset configuration model based on the preset constraints and the functional equation group.

6. The charging pile configuration method based on the cuckoo algorithm according to claim 5 is characterized in that: The preset constraints include at least: distance constraints, charging station capacity constraints, node voltage constraints, energy storage system power constraints, and energy storage system charging and discharging power constraints.

7. The charging pile configuration method based on the cuckoo algorithm according to claim 1, characterized in that: The step of solving the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area includes: The model to be solved is solved by a preset multi-objective cuckoo search algorithm, the preset position of the charging pile to be configured in the target area, the first attribute data of the charging pile to be configured and the second attribute data of the preset energy storage system, and the charging pile configuration strategy in the target area is generated according to the preset position, the first attribute data and the second attribute data.

8. A charging pile configuration device based on the cuckoo algorithm, characterized in that: The device comprises: A prediction module, used to predict charging demand data of the target area based on historical electric vehicle flow data of each intersection in the target area and characteristic data of electric vehicles; A first calculation module is used to bring the charging demand data, preset energy storage data of the energy storage system and distribution network attribute data into a preset configuration model to obtain a model to be solved; The second calculation module is used to solve the model to be solved by using a preset multi-objective cuckoo search algorithm to obtain a charging pile configuration strategy in the target area, wherein a step size parameter in the preset multi-objective cuckoo search algorithm is set to a constant, and the step size parameter is inversely proportional to the number of iterations of the preset multi-objective cuckoo search algorithm.

9. An electronic 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 computer program, the steps of the charging pile configuration method based on the cuckoo algorithm as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the charging pile configuration method based on the cuckoo algorithm as described in any one of claims 1 to 7 are implemented.

Images