An electric agricultural machine intelligent energy storage and scheduling method and system based on vehicle-network cooperation and wireless charging

Abstract

The present application belongs to the field of intelligent agriculture and smart grid technology, and relates to a kind of electric farm machinery intelligent energy storage and scheduling method and system based on vehicle-network cooperation and wireless charging;The method divides a day into multiple scheduling periods and initializes the parameters of improved sparrow search algorithm;When reaching the decision point, obtain the load and wind and light output prediction data, generate multiple candidate path sequences using the improved sparrow search algorithm, and generate the optimal movement path sequence by simulation deduction with the goal of minimizing the total cost;The optimal movement path sequence is issued to the electric farm machinery for execution;After the electric farm machinery reaches the target energy storage access point, the model predictive control algorithm is used to rollingly optimize and real-time control the wireless charging power to minimize the grid operation cost;Real-time judgment is made on whether the next decision time point is reached, and the cycle is executed until the whole day scheduling is completed.The present application realizes the two-way collaborative optimization of electric farm machinery and power grid, and improves the utilization rate of farm machinery battery and renewable energy consumption capacity.

Description

Technical Field

[0001] This invention belongs to the field of smart agriculture and smart grid technology, specifically relating to a smart energy storage and scheduling method and system for electric agricultural machinery based on vehicle-grid collaboration and wireless charging. Background Technology

[0002] With the acceleration of agricultural electrification, electric agricultural machinery is being used more and more widely.

[0003] However, existing electric agricultural machines (EAM) have only undergone basic "oil-to-electric" conversions and lack intelligent scheduling capabilities, leading to two prominent problems: First, during the busy farming season, multiple machines charge at high power simultaneously, impacting the rural power grid and easily causing grid overload and voltage exceedances; second, during the off-season, the power batteries remain idle for extended periods, with an idle rate exceeding 80%, resulting not only in the waste of expensive battery assets but also in accelerated battery performance degradation due to prolonged inactivity. Meanwhile, distributed photovoltaic power generation in rural areas is developing rapidly, but there is a serious problem of curtailment and a lack of local consumption mechanisms. The root cause of these problems lies in the lack of technical means for coordinated optimization between agricultural machinery and the power grid, and between agricultural machinery and renewable energy systems. Furthermore, existing agricultural machinery lacks V2G (Vehicle-to-Grid) bidirectional charging and discharging capabilities, relying on manual plugging and unplugging for charging, making automated scheduling difficult. This is a shortcoming of existing technology.

[0004] In view of this, it is very necessary to provide a smart energy storage and scheduling method and system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging to solve the above-mentioned defects in the prior art. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies, such as the lack of intelligent scheduling capabilities for agricultural machinery, high battery idle rates, lack of local consumption mechanisms for distributed photovoltaic power generation, and lack of synergistic optimization between agricultural machinery, the power grid, and renewable energy. This invention provides a method and system for intelligent energy storage and scheduling of electric agricultural machinery based on vehicle-grid collaboration and wireless charging to solve the aforementioned technical problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A smart energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging includes the following steps: Step S1: Divide the day into multiple scheduling periods, and set the corresponding decision time point and prediction period length for each period; initialize the parameters of the improved sparrow search algorithm; Step S2: When a decision point is reached within a certain time period, load forecast data and wind and solar power output forecast data within a preset future time domain are obtained; an improved sparrow search algorithm is used as the upper-level optimizer, and the load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences. Each candidate path sequence is simulated and deduced, and the optimal moving path sequence is generated with the goal of minimizing the total cost. The total cost includes: operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller. Step S3: The optimal movement path sequence is sent to the electric agricultural machinery for execution, and the electric agricultural machinery moves to the target energy storage access point; Step S4: Using model predictive control algorithm as the lower-level optimizer, after the electric agricultural machine arrives at the target energy storage access point, the wireless charging power of the electric agricultural machine is rolled and controlled in real time with the predicted time period length as the prediction time domain of the lower-level optimizer, so as to minimize the grid operating cost. The electric agricultural machinery has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power, realizing V2G bidirectional energy interaction between the electric agricultural machinery and the power grid. Step S5: Determine in real time whether the next decision time point has been reached. If not, return to step S4. If it has been reached, continue to determine whether the full-day scheduling has been completed. If the full-day scheduling has been completed, end the process. If the full-day scheduling has not been completed, return to step S2.

[0007] Preferably, the initialization of the improved sparrow search algorithm parameters in step S1 specifically includes: Before the first decision point, the upper-level optimizer initializes the parameters and population of the improved sparrow search algorithm: Initialize the hyperparameters of the improved sparrow search algorithm, including: sparrow population size N; the proportion of finders in the population PD; the proportion of alerters in the population SD; and the maximum number of iterations. Safety threshold ST is used by the discoverer to determine whether there is danger. Flight index parameters Used to control step size distribution; maximum value of adaptive weights. and minimum value wait; Initialize the population using the improved sparrow search algorithm by randomly generating N initial positions for sparrows.

[0008] This step can achieve the following technical effects: By employing the initialization and improvement of the sparrow search algorithm's hyperparameters and population operations, key parameters such as the sparrow population size, the ratio of discoverers to warning birds, the maximum number of iterations, and the adaptive weight range are configured before the first decision point. This lays a data foundation for the stable operation of the subsequent upper-level optimizer, ensuring that the algorithm has reasonable population diversity and search range in the early stages of iteration. It avoids premature convergence or low search efficiency caused by improper parameter settings, thereby improving the global optimality and solution speed of the path optimization results.

[0009] Preferably, step S2 specifically includes: Step S21: Reach a decision point within a certain time period and obtain load forecast data and wind and solar power output forecast data within a preset future time domain; Step S22: Set the initial value of the iteration counter to t=1; Step S23: Input the load forecast data and wind and solar power output forecast data into the upper-level optimizer algorithm; enter the upper-level optimizer algorithm iterative loop, and determine whether the maximum number of iterations has been reached before the start of each iteration. If the condition is met, the loop will exit; otherwise, the loop will continue for the next iteration. Step S24: After algorithm iteration by the upper-level optimizer, the optimal movement path sequence is generated.

[0010] This step can achieve the following technical effects: By acquiring load forecast data and wind and solar power output forecast data within a preset time domain at the decision point trigger, and inputting them into the upper-level optimizer for iterative optimization, a proactive response to the volatility of renewable energy and load uncertainty is achieved. By combining forecast information with an improved sparrow search algorithm, the planning of electric agricultural machinery movement paths can predict the peak and valley changes of the power grid and the photovoltaic power output in advance. Thus, the consideration of power grid operating costs is incorporated into the path generation stage, providing key data support for generating the optimal movement path sequence that takes into account both economic efficiency and power grid stability.

[0011] Preferably, in step S23, the upper-level optimizer algorithm iterative loop is entered, and the following steps are executed in each iteration loop: Step S231, Generate candidate path sequences: Based on the position of each sparrow in the current sparrow population, generate multiple candidate path sequences; each sparrow position corresponds to one candidate path sequence; Step S232: Calculate the operating cost of each candidate path sequence: For each candidate path sequence, call the lower-level optimizer to perform simulations within a preset time domain based on the load forecast data and wind and solar power output forecast data obtained in step S21, and calculate the operating cost according to the following expression. : , Where n is the time step index, and N is the total number of time steps in the current prediction time domain. This is the unit network loss cost coefficient. Let the network loss power be at step n. The penalty coefficient for wind and solar power curtailment. Let n be the power of wind and solar power curtailment in step n. This is the cost coefficient for battery life loss. For the battery charge / discharge power in step n, For time step; Step S233: Calculate the movement cost for each candidate path sequence. : , in, This is a path segment index, where each sparrow's location corresponds to a complete path. This represents the total number of path segments. The cost coefficient per unit distance traveled. The distance of the m-th segment of the movement path; Step S234, calculate fitness: based on the total cost corresponding to each sparrow position. The fitness value for each position; fitness value The calculation formula is: ; Step S235: Sort all sparrows according to their fitness values ​​and find the global optimal solution for the current iteration number. and the worst global solution And calculate the average location of the population. Based on PD and SD, the population is divided into discoverers, joiners, and early warning systems; Step S236, calculate adaptive weights This weight will be used in the discoverer's update formula; the expression for calculating the adaptive weight is: , in, This represents the maximum weight. The minimum weight is given, and m and n are optimization coefficients. The normalized iteration offset is calculated as follows: ; Step S237, update the finder's position in the improved sparrow search algorithm, the update expression is: , in, Let this be the position of the i-th discoverer in the j-th dimension during the t-th iteration; ∈[0,1] represents the warning value, which is a random number; ∈[0,1] represents the safety threshold; the safety threshold and the warning value together constitute the movement conditions of the discoverer; when At that time, the discoverers expanded the search area; when At that time, the discoverer leaves the current search area; For adaptive weights; ∈(0,1], represents a random number randomly selected from the range; Let i be the number of the sparrow, i = 1, 2, ..., n; j represents the latitude, j = 1, 2, ..., D; The search path is random, and its random step size follows a Lévy distribution. The dynamic step size coefficient is expressed as follows: ; The The calculation expression is: , in, This represents the step size control factor, which is usually set to 1; These are the parameters of the Lévy distribution; The Levy Flight Index parameter is typically set to 1.5; and It is a normally distributed random number; Step S238, update the joiner positions in the improved sparrow search algorithm, the update expression is: , in, Let this be the position of the participant joining in the t-th iteration; This represents the worst-case scenario globally, i.e., the position with the lowest fitness value within the algorithm's search range. Let A be the position with the lowest fitness value corresponding to the discoverer's position in the (t+1)th iteration; A is a 1*D matrix, where the values ​​of the elements in the matrix are randomly selected from 1 or -1, and D is the number of elements in the current candidate movement path sequence. + =A T (AA T ) -1 ; n is the number of followers; when When, followers expand their search range to increase their fitness value; when At this time, followers gather towards the best position among all discoverer positions, that is, they move closer to the position with the lowest fitness value among all discoverer positions; Step S239, update the position of the early warning provider in the improved sparrow search algorithm, and the update expression is: , in, Let this be the position of the early warning provider in the t-th iteration; ub This is the upper limit of the search space. lb This serves as the lower limit of the search space, which is determined by the value range of each location node in the candidate movement path sequence. A random number in the interval [0,1]; For the first t The worst global solution in the next iteration; k It is a random number within the range [-1, 1]. This represents the fitness value of the i-th sparrow position; The fitness value represents the globally optimal position. The fitness value at the worst global position; minimum parameter ε Used to avoid a denominator of 0; Step S2310, update the global optimal solution and the global worst solution: The global optimal solution update expression is: , in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; The global worst-case update expression is: , in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; Step S2311: Increment the iteration counter by t = t + 1, and return to step S24 to enter the next iteration loop.

[0012] This step can achieve the following technical effects: By employing a complete cyclical process—generating candidate path sequences, invoking the lower-level optimizer to simulate and calculate running and movement costs, evaluating fitness, and updating the positions of discoverers, joiners, and alerters, and iteratively optimizing—bidirectional collaborative optimization between the upper-level ISSA and the lower-level MPC is achieved. In this process, the running cost of each candidate path sequence is obtained through high-fidelity simulation rather than simple estimation, ensuring the accuracy of cost assessment. Through the synergistic effect of adaptive weights, Lévy fly-through, and back-learning mechanisms, the traditional sparrow algorithm's tendency to get trapped in local optima is overcome, improving the quality of the solution and the convergence speed.

[0013] Preferably, step S4 specifically includes: Step S41: After the electric agricultural machinery arrives at the target energy storage access point and completes the wireless charging docking, the lower-level optimizer reads the real-time measurement data at the current moment. The real-time measurement data includes: the voltage amplitude and voltage phase angle of each node of the distribution network, the active power and reactive power of each branch, the load power of each node, the actual output value of distributed photovoltaic and wind power, the current state of charge (SOC) of the electric agricultural machinery energy storage system, and the battery health status (SOH). Step S42: Use the prediction time period length set in step S1 as the prediction time domain length of the lower-level optimizer. Set the control step size to Then the total number of time steps in the prediction time domain is ; Step S43: Construct the objective function of the lower-level optimizer with the goal of minimizing the power grid operating cost in the current prediction time domain. , Where k is the time step index in the prediction time domain; The system network loss power at step k; Let K be the power of wind and solar power curtailment at step k; The charging and discharging power of the electric agricultural machinery energy storage system in step k is represented by a positive value indicating power feeding into the grid and a negative value indicating charging from the grid. This is the unit network loss cost coefficient; This refers to the penalty coefficient for wind and solar power curtailment. This is the cost coefficient for battery life loss. Step S44: Set the lower-level optimizer to satisfy power flow balance constraints, voltage safety operation constraints, line transmission capacity constraints, energy storage system SOC constraints, charging and discharging power limit constraints, and wireless charging power constraints during the objective function solution process; The expression for the power flow balance constraint is: , in, Inject the active power of node i in the k-th step; Inject reactive power into node i at step k; Let be the voltage amplitude at node i; and For elements of the admittance matrix; The voltage phase angle difference between node i and node l; The voltage safety operation constraint expression is as follows: , in, This represents the lower limit of the node voltage; This represents the upper limit of the node voltage; The expression for the line transmission capacity constraint is: , in, Let be the amplitude of the current flowing through line ij in the k-th step; This represents the maximum current-carrying capacity of line ij. The SOC constraint expression for the energy storage system is: , in, This is the limit of the state of charge; This represents the upper limit of the state of charge. For charging efficiency; For discharge efficiency; This refers to the rated capacity of the energy storage system. For the charging power at step k, The discharge power at step k satisfies ; The expression for the charging and discharging power limitation constraint is as follows: , in, This is the maximum charging power; This represents the maximum discharge power. and It is a binary variable. Indicates the charging status. Indicates the discharge state; The wireless charging power constraint expression is as follows:

[0014] in, This represents the actual transmission power of the wireless charging system. The minimum stable transmission power for a wireless charging system; The maximum stable transmission power for the wireless charging system; Step S45: Solve the objective function optimization problem of the lower-level optimizer using quadratic programming or interior point method to obtain the optimal charge and discharge power sequence in the current prediction time domain. Only the power command of the first control step in the sequence is executed, that is, the target value of charging and discharging power at the current moment is issued to the electric agricultural machinery; Step S46, wait for a control step size Then, new real-time measurement data is collected, the prediction time domain is rolled forward by one step, and steps S42 to S45 are repeated to achieve continuous rolling optimization control until the trigger signal of the next upper-level ISSA decision point is received.

[0015] This step can achieve the following technical effects: By employing model predictive control algorithms to perform rolling optimization and real-time control of the wireless charging power of electric agricultural machinery, and collecting real-time measurement data in each control cycle, constructing an objective function with multiple constraints, solving for the optimal power sequence, and then executing only the current step instruction, dynamic response and precise control of the power grid operation status are achieved. By matching the prediction time domain length with the upper-level scheduling period, the lower-level optimizer can make fine-grained real-time adjustments to the charging and discharging power of electric agricultural machinery within the framework of the upper-level planning, solving the problem of high-power charging impacting the power grid during the busy farming season. Peak shaving and valley filling and photovoltaic power consumption are achieved through V2G bidirectional energy interaction.

[0016] Furthermore, this invention also provides a smart energy storage and scheduling system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, comprising: The scheduling time period division module contains: Divide the day into multiple scheduling periods, and set the corresponding decision time point and prediction period length for each period; initialize the parameters of the improved sparrow search algorithm; The upper-level path optimization decision module contains: When a decision point is reached within a certain time period, load forecast data and wind and solar power output forecast data within a preset future time domain are obtained. An improved sparrow search algorithm is used as the upper-level optimizer. The load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences. Each candidate path sequence is simulated and deduced, and the optimal movement path sequence is generated with the goal of minimizing the total cost. The total cost includes: operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller. The move instruction execution module contains: The optimal movement path sequence is sent to the electric agricultural machinery for execution, and the electric agricultural machinery moves to the target energy storage access point; The lower-level real-time power control module contains: Model predictive control algorithm is used as the lower-level optimizer. After the electric agricultural machine arrives at the target energy storage access point, the wireless charging power of the electric agricultural machine is rolled and controlled in real time with the prediction time period length as the prediction time domain of the lower-level optimizer, so as to minimize the grid operation cost. The electric agricultural machinery has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power, realizing V2G bidirectional energy interaction between the electric agricultural machinery and the power grid. The loop control module contains: Real-time determination of whether the next decision time point has been reached: if not, return to the lower-level power real-time control module; if reached, continue to determine whether the full-day scheduling has been completed: if the full-day scheduling has been completed, the process ends; if the full-day scheduling has not been completed, return to the upper-level path optimization decision module.

[0017] The beneficial effects of this invention are as follows: It achieves bidirectional energy interaction between electric agricultural machinery and the power grid through V2G technology, transforming agricultural machinery from passive electrical equipment into active mobile energy storage units, thus solving the problems of existing agricultural machinery lacking intelligent scheduling capabilities and unable to participate in grid collaborative optimization; it converts idle batteries during the off-season into distributed energy storage resources, generating revenue through participation in grid services, thus solving the problems of high battery idle rates, asset waste, and accelerated performance degradation; the addition of wireless charging technology enables unmanned operation and energy replenishment of agricultural machinery throughout the entire process, solving the problems of low efficiency and difficulty in achieving automated scheduling through manual plugging and unplugging; combined with cloud-based intelligent algorithms, it promotes the local consumption of curtailed photovoltaic power, solving the problem of difficulty in absorbing distributed renewable energy in rural areas; through multi-period peak-valley price arbitrage and ancillary service revenue, it can shorten the investment payback period for agricultural machinery, provide flexible energy storage resources for rural power grids, enhance grid stability, and improve the level of agricultural intelligence.

[0018] Therefore, it is evident that the present invention has outstanding substantive features and significant progress compared with the prior art, and the beneficial effects of its implementation are also obvious. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart of a smart energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, provided by the present invention.

[0021] Figure 2 This is a schematic diagram of the intelligent energy storage and scheduling system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, provided by the present invention.

[0022] Among them, 1-Scheduling period division module, 2-Upper-layer path optimization decision module, 3-Movement command execution module, 4-Lower-layer power real-time control module, and 5-Loop control module. Detailed Implementation

[0023] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The following embodiments are explanations of the present invention, but the present invention is not limited to the following implementation methods.

[0024] Example 1: like Figure 1 As shown in the figure, this embodiment provides a smart energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, which includes the following steps: Step S1: Divide the day into four scheduling periods as shown in Table 1, execute the process in a rolling manner according to the four periods, and set the corresponding decision time point and prediction period length for each period, as well as the core objective for each period; initialize the parameters of the improved sparrow search algorithm. Table 1 Time Period Division Table

[0025] The initialization of the improved sparrow search algorithm parameters in step S1 specifically includes: Before the first decision point, the upper-level optimizer initializes the parameters and population of the improved sparrow search algorithm: Initialize the hyperparameters of the improved sparrow search algorithm, including: sparrow population size N=50; proportion of finders in the population PD=20%; proportion of early warning providers SD=10%; maximum number of iterations. =100; Safety threshold ST=0.8, used by the discoverer to determine whether it is dangerous; Flight index parameters =1.5, used to control the step size distribution; the maximum value of the adaptive weights. =1.6 and minimum value =0.8 etc.; Initialize the population using the improved sparrow search algorithm by randomly generating N initial positions for sparrows.

[0026] This step can achieve the following technical effects: By employing the initialization and improvement of the sparrow search algorithm's hyperparameters and population operations, key parameters such as the sparrow population size, the ratio of discoverers to warning birds, the maximum number of iterations, and the adaptive weight range are configured before the first decision point. This lays a data foundation for the stable operation of the subsequent upper-level optimizer, ensuring that the algorithm has reasonable population diversity and search range in the early stages of iteration. It avoids premature convergence or low search efficiency caused by improper parameter settings, thereby improving the global optimality and solution speed of the path optimization results.

[0027] Step S2, taking the decision time point of 07:00 as an example: Upon reaching 07:00, the load forecast data for each time step within the next 2 hours is obtained as [150, 180, 200, 220, 210, 190, 170, 160] (unit kW); the photovoltaic output forecast data is [80, 100, 120, 140, 150, 160, 170, 180] (unit kW); the wind power output forecast data is [30, 28, 25, 22, 20, 18, 15, 15] (unit kW); the time step is 15 minutes; an improved sparrow search algorithm is used as the upper-level optimizer, and the load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences, such as [7, 15, 33], [8, 12, 30], [5,18,25], simulate and deduce each candidate path sequence and generate the optimal movement path sequence with the goal of minimizing the total cost, for example [7,15,33]; The total cost includes: operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller. Step S2 specifically includes: Step S21: Reach a decision point within a certain time period and obtain load forecast data and wind and solar power output forecast data within a preset future time domain; Step S22: Set the initial value of the iteration counter to t=1; Step S23: Input the load forecast data and wind and solar power output forecast data into the upper-level optimizer algorithm; enter the upper-level optimizer algorithm iterative loop, and determine whether the maximum number of iterations has been reached before the start of each iteration. If the condition is met, the loop will exit; otherwise, the loop will continue for the next iteration. Step S24: After algorithm iteration by the upper-level optimizer, the optimal movement path sequence is generated.

[0028] This step can achieve the following technical effects: By acquiring load forecast data and wind and solar power output forecast data within a preset time domain at the decision point trigger, and inputting them into the upper-level optimizer for iterative optimization, a proactive response to the volatility of renewable energy and load uncertainty is achieved. By combining forecast information with an improved sparrow search algorithm, the planning of electric agricultural machinery movement paths can predict the peak and valley changes of the power grid and the photovoltaic power output in advance. Thus, the consideration of power grid operating costs is incorporated into the path generation stage, providing key data support for generating the optimal movement path sequence that takes into account both economic efficiency and power grid stability.

[0029] In step S23, the upper-level optimizer algorithm iterative loop is entered, and the following steps are executed in each iteration loop: Step S231, Generate candidate path sequences: Based on the position of each sparrow in the current sparrow population, generate multiple candidate path sequences; each sparrow position corresponds to one candidate path sequence; Step S232: Calculate the operating cost of each candidate path sequence: For each candidate path sequence, call the lower-level optimizer to perform simulations within a preset time domain based on the load forecast data and wind and solar power output forecast data obtained in step S21, and calculate the operating cost according to the following expression. : , Where n is the time step index, and N is the total number of time steps in the current prediction time domain. This is the unit network loss cost coefficient. Let the network loss power be at step n. The penalty coefficient for wind and solar power curtailment. Let n be the power of wind and solar power curtailment in step n. This is the cost coefficient for battery life loss. For the battery charge / discharge power in step n, For time step; Step S233: Calculate the movement cost for each candidate path sequence. : , in, This is a path segment index, where each sparrow's location corresponds to a complete path. This represents the total number of path segments. The cost coefficient per unit distance traveled. The distance of the m-th segment of the movement path; Step S234, calculate fitness: based on the total cost corresponding to each sparrow position. The fitness value for each position; fitness value The calculation formula is: ; Step S235: Sort all sparrows according to their fitness values ​​and find the global optimal solution for the current iteration number. and the worst global solution And calculate the average location of the population. Based on PD and SD, the population is divided into discoverers, joiners, and early warning systems; Step S236, calculate adaptive weights This weight will be used in the discoverer's update formula; the expression for calculating the adaptive weight is: , in, This represents the maximum weight. The minimum weight is given, and m and n are optimization coefficients. The normalized iteration offset is calculated as follows: ; Step S237, update the finder's position in the improved sparrow search algorithm, the update expression is: , in, Let this be the position of the i-th discoverer in the j-th dimension during the t-th iteration; ∈[0,1] represents the warning value, which is a random number; ∈[0,1] represents the safety threshold; the safety threshold and the warning value together constitute the movement conditions of the discoverer; when At that time, the discoverers expanded the search area; when At that time, the discoverer leaves the current search area; For adaptive weights; ∈(0,1], represents a random number randomly selected from the range; Let i be the number of the sparrow, i = 1, 2, ..., n; j represents the latitude, j = 1, 2, ..., D; The search path is random, and its random step size follows a Lévy distribution. The dynamic step size coefficient is expressed as follows: ; The The calculation expression is: , in, This represents the step size control factor, which is usually set to 1; These are the parameters of the Lévy distribution; The Levy Flight Index parameter is typically set to 1.5; and It is a normally distributed random number; Step S238, update the joiner positions in the improved sparrow search algorithm, the update expression is: , in, Let this be the position of the participant joining in the t-th iteration; This represents the worst-case scenario globally, i.e., the position with the lowest fitness value within the algorithm's search range. Let A be the position with the lowest fitness value corresponding to the discoverer's position in the (t+1)th iteration; A is a 1*D matrix, where the values ​​of the elements in the matrix are randomly selected from 1 or -1, and D is the number of elements in the current candidate movement path sequence. + =A T(AA T ) -1 ; n is the number of followers; when When, followers expand their search range to increase their fitness value; when At this time, followers gather towards the best position among all discoverer positions, that is, they move closer to the position with the lowest fitness value among all discoverer positions; Step S239, update the position of the early warning provider in the improved sparrow search algorithm, and the update expression is: , in, Let this be the position of the early warning provider in the t-th iteration; ub This is the upper limit of the search space. lb This serves as the lower limit of the search space, which is determined by the value range of each location node in the candidate movement path sequence. A random number in the interval [0,1]; For the first t The worst global solution in the next iteration; k It is a random number within the range [-1, 1]. This represents the fitness value of the i-th sparrow position; The fitness value represents the globally optimal position. The fitness value at the worst global position; minimum parameter ε Used to avoid a denominator of 0; Step S2310, update the global optimal solution and the global worst solution: The global optimal solution update expression is: , in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; The global worst-case update expression is: , in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; Step S2311: Increment the iteration counter by t = t + 1, and return to step S24 to enter the next iteration loop.

[0030] This step can achieve the following technical effects: By employing a complete cyclical process—generating candidate path sequences, invoking the lower-level optimizer to simulate and calculate running and movement costs, evaluating fitness, and updating the positions of discoverers, joiners, and alerters, and iteratively optimizing—bidirectional collaborative optimization between the upper-level ISSA and the lower-level MPC is achieved. In this process, the running cost of each candidate path sequence is obtained through high-fidelity simulation rather than simple estimation, ensuring the accuracy of cost assessment. Through the synergistic effect of adaptive weights, Lévy fly-through, and back-learning mechanisms, the traditional sparrow algorithm's tendency to get trapped in local optima is overcome, improving the quality of the solution and the convergence speed.

[0031] Step S3: The optimal movement path sequence [7,15,33] is sent to the electric agricultural machinery for execution. The electric agricultural machinery moves to node 7, node 15, and node 33 to access energy storage. Step S4: Using model predictive control algorithm as the lower-level optimizer, after the electric agricultural machine arrives at the target energy storage access point, the wireless charging power of the electric agricultural machine is rolled and controlled in real time with the predicted time period length as the prediction time domain of the lower-level optimizer, so as to minimize the grid operating cost. The electric agricultural machinery has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power, realizing V2G bidirectional energy interaction between the electric agricultural machinery and the power grid. Step S4 specifically includes: Step S41: After the electric agricultural machinery reaches the target energy storage access point and completes the wireless charging docking, the lower-level optimizer reads the real-time measurement data at the current moment. For example, after reaching node 7, the real-time measurement data is read as follows: the voltage amplitude of node 7 is 0.98 per unit, the current state of charge (SOC) is 60%, and the battery health status (SOH) is 95%. Step S42: Use the prediction time period length set in step S1 as the prediction time domain length of the lower-level optimizer. =2 hours, set the control step size to =15 minutes, then the total number of time steps in the prediction time domain is =8; Step S43: Construct the objective function of the lower-level optimizer with the goal of minimizing the power grid operating cost in the current prediction time domain. , Where k is the time step index in the prediction time domain; The system network loss power at step k; Let K be the power of wind and solar power curtailment at step k; The charging and discharging power of the electric agricultural machinery energy storage system in step k is represented by a positive value indicating power feeding into the grid and a negative value indicating charging from the grid. This is the unit network loss cost coefficient; This refers to the penalty coefficient for wind and solar power curtailment. This is the cost coefficient for battery life loss. Step S44: Set the lower-level optimizer to satisfy power flow balance constraints, voltage safety operation constraints, line transmission capacity constraints, energy storage system SOC constraints, charging and discharging power limit constraints, and wireless charging power constraints during the objective function solution process; The expression for the power flow balance constraint is: , in, Inject the active power of node i in the k-th step; Inject reactive power into node i at step k; Let be the voltage amplitude at node i; and For elements of the admittance matrix; The voltage phase angle difference between node i and node l; The voltage safety operation constraint expression is as follows: , in, This represents the lower limit of the node voltage; This represents the upper limit of the node voltage; The expression for the line transmission capacity constraint is: , in, Let be the amplitude of the current flowing through line ij in the k-th step; This represents the maximum current-carrying capacity of line ij. The SOC constraint expression for the energy storage system is: , in, This is the limit of the state of charge; This represents the upper limit of the state of charge. For charging efficiency; For discharge efficiency; This refers to the rated capacity of the energy storage system. For the charging power at step k, The discharge power at step k satisfies ; The expression for the charging and discharging power limitation constraint is as follows: , in, This is the maximum charging power; This represents the maximum discharge power. and It is a binary variable. Indicates the charging status. Indicates the discharge state; The wireless charging power constraint expression is as follows:

[0032] in, This represents the actual transmission power of the wireless charging system. The minimum stable transmission power for a wireless charging system; The maximum stable transmission power for the wireless charging system; Step S45: Solve the objective function optimization problem of the lower-level optimizer using quadratic programming or interior point method to obtain the optimal charge and discharge power sequence in the current prediction time domain. Only the power command of the first control step in the sequence is executed, that is, the target value of charging and discharging power at the current moment is issued to the electric agricultural machinery; Step S46, wait for a control step size Then, new real-time measurement data is collected, the prediction time domain is rolled forward by one step, and steps S42 to S45 are repeated to achieve continuous rolling optimization control until the next decision time point 09:00.

[0033] This step can achieve the following technical effects: By employing model predictive control algorithms to perform rolling optimization and real-time control of the wireless charging power of electric agricultural machinery, and collecting real-time measurement data in each control cycle, constructing an objective function with multiple constraints, solving for the optimal power sequence, and then executing only the current step instruction, dynamic response and precise control of the power grid operation status are achieved. By matching the prediction time domain length with the upper-level scheduling period, the lower-level optimizer can make fine-grained real-time adjustments to the charging and discharging power of electric agricultural machinery within the framework of the upper-level planning, solving the problem of high-power charging impacting the power grid during the busy farming season. Peak shaving and valley filling and photovoltaic power consumption are achieved through V2G bidirectional energy interaction.

[0034] Step S5: In real time, determine whether the next decision time point of 09:00 has been reached. If not, return to the rolling optimization in step S4. If 09:00 has been reached, continue to determine whether the full-day scheduling has been completed. If the full-day scheduling has been completed, end the process. If the full-day scheduling has not been completed, return to step S2. Repeat the above process until the scheduling of the four time periods of the day is completed.

[0035] Example 2: like Figure 2 As shown in the figure, this embodiment provides a smart energy storage and scheduling system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, including: Scheduling time period division module 1, in which: Divide the day into multiple scheduling periods, and set the corresponding decision time point and prediction period length for each period; initialize the parameters of the improved sparrow search algorithm; Upper-level path optimization decision module 2, in which: When a decision point is reached within a certain time period, load forecast data and wind and solar power output forecast data within a preset future time domain are obtained. An improved sparrow search algorithm is used as the upper-level optimizer. The load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences. Each candidate path sequence is simulated and deduced, and the optimal movement path sequence is generated with the goal of minimizing the total cost. The total cost includes: operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller. Movement instruction execution module 3, in which: The optimal movement path sequence is sent to the electric agricultural machinery for execution, and the electric agricultural machinery moves to the target energy storage access point; Lower-level real-time power control module 4, in which: Model predictive control algorithm is used as the lower-level optimizer. After the electric agricultural machine arrives at the target energy storage access point, the wireless charging power of the electric agricultural machine is rolled and controlled in real time with the prediction time period length as the prediction time domain of the lower-level optimizer, so as to minimize the grid operation cost. The electric agricultural machinery has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power, realizing V2G bidirectional energy interaction between the electric agricultural machinery and the power grid. Loop control module 5, in which: Real-time determination of whether the next decision time point has been reached: If not, return to the lower-level power real-time control module 4; If reached, continue to determine whether the full-day scheduling has been completed: If the full-day scheduling has been completed, the process ends; If the full-day scheduling has not been completed, return to the upper-level path optimization decision module 2.

[0036] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The methods disclosed in the embodiments are described simply because they correspond to the systems disclosed in the embodiments; relevant details can be found in the method section.

[0037] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0038] In the embodiments provided by this invention, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0039] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0040] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit.

[0041] Similarly, in the various embodiments of the present invention, each processing unit can be integrated into a functional module, or each processing unit can exist physically, or two or more processing units can be integrated into a functional module.

[0042] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0043] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0044] The above-disclosed embodiments are merely preferred embodiments of the present invention, but the present invention is not limited thereto. Any non-creative variations that can be conceived by those skilled in the art, as well as any improvements and modifications made without departing from the principles of the present invention, should fall within the protection scope of the present invention.

Claims

1. A smart energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, characterized in that, Includes the following steps: Step S1: Divide the day into multiple scheduling periods, and set the decision time point and forecast period length for each period; Initialize the parameters of the improved sparrow search algorithm; Step S2: When a decision point is reached within a certain time period, load forecast data and wind and solar power output forecast data within a preset future time domain are obtained; an improved sparrow search algorithm is used as the upper-level optimizer, and the load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences. Each candidate path sequence is simulated and deduced, and the optimal moving path sequence is generated with the goal of minimizing the total cost. Step S3: The optimal movement path sequence is sent to the electric agricultural machinery for execution, and the electric agricultural machinery moves to the target energy storage access point; Step S4: Using model predictive control algorithm as the lower-level optimizer, after the electric agricultural machine arrives at the target energy storage access point, the wireless charging power of the electric agricultural machine is rolled and controlled in real time with the predicted time period length as the prediction time domain of the lower-level optimizer to minimize the grid operating cost. Step S5: Determine in real time whether the next decision time point has been reached. If not, return to step S4. If it has been reached, continue to determine whether the full-day scheduling has been completed. If the full-day scheduling has been completed, end the process. If the full-day scheduling has not been completed, return to step S2.

2. The method for intelligent energy storage and scheduling of electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 1, characterized in that, The total cost in step S2 includes operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller.

3. The method for intelligent energy storage and scheduling of electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 1, characterized in that, The electric agricultural machinery in step S4 has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power.

4. The intelligent energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 1, characterized in that, The initialization of the improved sparrow search algorithm parameters in step S1 specifically includes: Before the first decision point, the upper-level optimizer initializes the parameters and population of the improved sparrow search algorithm: Initialize the hyperparameters of the improved sparrow search algorithm, including: sparrow population size N; the proportion of finders in the population PD; the proportion of alerters in the population SD; and the maximum number of iterations. Safety threshold ST; Flight index parameters Maximum value of adaptive weights and minimum value ; Initialize the population using the improved sparrow search algorithm by randomly generating N initial positions for sparrows.

5. The intelligent energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 1, characterized in that, Step S2 specifically includes: Step S21: Reach a decision point within a certain time period and obtain load forecast data and wind and solar power output forecast data within a preset future time domain; Step S22: Set the initial value of the iteration counter to t=1; Step S23: Input the load forecast data and wind and solar power output forecast data into the upper-level optimizer algorithm; enter the upper-level optimizer algorithm iterative loop, and determine whether the maximum number of iterations has been reached before the start of each iteration. If the condition is met, the loop will exit; otherwise, the loop will continue for the next iteration. Step S24: After algorithm iteration by the upper-level optimizer, the optimal movement path sequence is generated.

6. The method for intelligent energy storage and scheduling of electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging according to claim 5, characterized in that, In step S23, the upper-level optimizer algorithm iterative loop is entered, and the following steps are executed in each iteration loop: Step S231, Generate candidate path sequences: Based on the position of each sparrow in the current sparrow population, generate multiple candidate path sequences; each sparrow position corresponds to one candidate path sequence; Step S232: Calculate the operating cost of each candidate path sequence: For each candidate path sequence, call the lower-level optimizer to perform simulations within a preset time domain based on the load forecast data and wind and solar power output forecast data obtained in step S21, and calculate the operating cost according to the following expression. : ， Where n is the time step index, and N is the total number of time steps in the current prediction time domain. This is the unit network loss cost coefficient. Let n be the network loss power at step n. The penalty coefficient for wind and solar power curtailment. Let n be the power of wind and solar power curtailment in step n. This is the cost coefficient for battery life loss. For the battery charging and discharging power in step n, For time step; Step S233: Calculate the movement cost for each candidate path sequence. : ， in, This is a path segment index, where each sparrow's location corresponds to a complete path. This represents the total number of path segments. This is the cost coefficient per unit distance traveled. The distance of the m-th segment of the movement path; Step S234, calculate fitness: based on the total cost corresponding to each sparrow position. The fitness value for each position; fitness value The calculation formula is: ； Step S235: Sort all sparrows according to their fitness values ​​and find the global optimal solution for the current iteration number. and the worst global solution And calculate the average location of the population. Based on PD and SD, the population is divided into discoverers, joiners, and early warning systems; Step S236, calculate adaptive weights : ， in, This represents the maximum weight. The minimum weight is given, and m and n are optimization coefficients. The normalized iteration offset is calculated as follows: ； Step S237, update the finder's position in the improved sparrow search algorithm, the update expression is: ， in, Let this be the position of the i-th discoverer in the j-th dimension during the t-th iteration; ∈[0,1] represents the warning value, which is a random number; ∈[0,1] represents the safety threshold; the safety threshold and the warning value together constitute the movement conditions of the discoverer; when At that time, the discoverers expanded the search area; when At that time, the discoverer leaves the current search area; For adaptive weights; ∈(0,1], represents a random number randomly selected from the range; Let i be the number of the sparrow, i = 1, 2, ..., n; j represents the latitude, j = 1, 2, ..., D; The search path is random, and its random step size follows a Lévy distribution. The dynamic step size coefficient is expressed as follows: ； The The calculation expression is: ， in, Indicates the step size control coefficient; These are the parameters of the Lévy distribution; For the Levy flight index parameters; and It is a normally distributed random number; Step S238, update the joiner positions in the improved sparrow search algorithm, the update expression is: ， in, Let this be the position of the participant joining in the t-th iteration; The worst-case solution is the position with the lowest fitness value within the algorithm's search range. Let A be the position with the lowest fitness value corresponding to the discoverer's position in the (t+1)th iteration; A is a 1*D matrix, where the values ​​of the elements in the matrix are randomly selected from 1 or -1, and D is the number of elements in the current candidate movement path sequence. + =A T (AA T ) -1 ; n is the number of followers; when When, followers expand their search range to increase their fitness value; when At that time, the follower moves closer to the position with the lowest fitness value among all the discoverer positions; Step S239, update the position of the early warning provider in the improved sparrow search algorithm, and the update expression is: , in, Let this be the position of the early warning provider in the t-th iteration; ub This is the upper limit of the search space. lb This serves as the lower limit of the search space, which is determined by the value range of each location node in the candidate movement path sequence. A random number in the interval [0,1]; For the first t The worst global solution in the next iteration; k It is a random number within the range [-1, 1]. This represents the fitness value of the i-th sparrow position; The fitness value represents the globally optimal position. The fitness value at the worst global position; minimum parameter ε Used to avoid a denominator of 0; Step S2310, update the global optimal solution and the global worst solution: The global optimal solution update expression is: ， in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; The global worst-case update expression is: ， in, This represents the position of the i-th sparrow in the (t+1)-th iteration; Indicates fitness; Step S2311: Increment the iteration counter by t = t + 1, and return to step S24 to enter the next iteration loop.

7. The intelligent energy storage and scheduling method for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 1, characterized in that, Step S4 specifically includes: Step S41: After the electric agricultural machinery arrives at the target energy storage access point and completes the wireless charging docking, the lower-level optimizer reads the real-time measurement data at the current moment. The real-time measurement data includes: the voltage amplitude and voltage phase angle of each node of the distribution network, the active power and reactive power of each branch, the load power of each node, the actual output value of distributed photovoltaic and wind power, the current state of charge (SOC) of the electric agricultural machinery energy storage system, and the battery health status (SOH). Step S42: Use the prediction time period length set in step S1 as the prediction time domain length of the lower-level optimizer. Set the control step size to Then the total number of time steps in the prediction time domain is ; Step S43: Construct the objective function of the lower-level optimizer with the goal of minimizing the power grid operating cost in the current prediction time domain. ， Where k is the time step index in the prediction time domain; The system network loss power at step k; Let K be the power of wind and solar power curtailment at step k; The charging and discharging power of the electric agricultural machinery energy storage system in step k is represented by a positive value indicating power feeding into the grid and a negative value indicating charging from the grid. This is the unit network loss cost coefficient; This refers to the penalty coefficient for wind and solar power curtailment. This is the cost coefficient for battery life loss. Step S44: Set the lower-level optimizer to satisfy power flow balance constraints, voltage safety operation constraints, line transmission capacity constraints, energy storage system SOC constraints, charging and discharging power limit constraints, and wireless charging power constraints during the objective function solution process; Step S45: Solve the objective function optimization problem of the lower-level optimizer to obtain the optimal charge and discharge power sequence in the current prediction time domain. Only the power command of the first control step in the sequence is executed, that is, the target value of charging and discharging power at the current moment is issued to the electric agricultural machinery; Step S46, wait for a control step size Then, new real-time measurement data is collected, the prediction time domain is rolled forward by one step, and steps S42 to S45 are repeated to achieve continuous rolling optimization control until the trigger signal of the next upper-level ISSA decision point is received.

8. The method for intelligent energy storage and scheduling of electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging according to claim 7, characterized in that, The constraints satisfied during the process of solving the objective function in step S44 include: The expression for the power flow balance constraint is: ， in, Inject the active power of node i in the k-th step; Inject reactive power into node i at step k; Let be the voltage amplitude at node i; and For elements of the admittance matrix; The voltage phase angle difference between node i and node l; The voltage safety operation constraint expression is as follows: ， in, This represents the lower limit of the node voltage; This represents the upper limit of the node voltage; The expression for the line transmission capacity constraint is: ， in, Let be the amplitude of the current flowing through line ij in the k-th step; This represents the maximum current-carrying capacity of line ij. The SOC constraint expression for the energy storage system is: ， in, This is the limit of the state of charge; This represents the upper limit of the state of charge. For charging efficiency; For discharge efficiency; This refers to the rated capacity of the energy storage system. For the charging power at step k, The discharge power at step k satisfies ; The expression for the charging and discharging power limitation constraint is as follows: ， in, This is the maximum charging power; This represents the maximum discharge power. and It is a binary variable. Indicates the charging status. Indicates the discharge state; The wireless charging power constraint expression is as follows: in, This represents the actual transmission power of the wireless charging system. The minimum stable transmission power for a wireless charging system; This represents the maximum stable transmission power of the wireless charging system.

9. A smart energy storage and scheduling system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging, characterized in that, include: The scheduling time period division module contains: Divide the day into multiple scheduling periods, and set the corresponding decision time point and prediction period length for each period; initialize the parameters of the improved sparrow search algorithm; The upper-level path optimization decision module contains: When a decision point is reached within a certain time period, load forecast data and wind and solar power output forecast data within a preset future time domain are obtained. An improved sparrow search algorithm is used as the upper-level optimizer. The load forecast data and wind and solar power output forecast data are input into the upper-level optimizer to generate multiple candidate path sequences. Each candidate path sequence is simulated and deduced, and the optimal movement path sequence is generated with the goal of minimizing the total cost. The total cost includes: operating cost and movement cost. The operating cost is obtained by simulating and extrapolating the currently generated path sequence by calling the lower-level model prediction controller. The move instruction execution module contains: The optimal movement path sequence is sent to the electric agricultural machinery for execution, and the electric agricultural machinery moves to the target energy storage access point; The lower-level real-time power control module contains: Using model predictive control algorithm as the lower-level optimizer, after the electric agricultural machinery arrives at the target energy storage access point, the wireless charging power of the electric agricultural machinery is rolled and controlled in real time with the predicted time period length as the prediction time domain of the lower-level optimizer, so as to minimize the grid operation cost. The electric agricultural machinery has bidirectional charging and discharging capabilities, and the wireless charging power includes forward charging power and reverse discharging power; The loop control module contains: Real-time determination of whether the next decision time point has been reached: if not, return to the lower-level power real-time control module; if reached, continue to determine whether the full-day scheduling has been completed: if the full-day scheduling has been completed, the process ends; if the full-day scheduling has not been completed, return to the upper-level path optimization decision module.

10. A smart energy storage and scheduling system for electric agricultural machinery based on vehicle-to-grid collaboration and wireless charging as described in claim 9, characterized in that, In the lower-level real-time power control module, the prediction time domain length of the model predictive control algorithm is consistent with the prediction time period length set by the scheduling time period division module.

Images