Unmanned aerial vehicle electric power inspection electric energy guarantee planning method and device in multi-weather scene

Abstract

The invention provides an unmanned aerial vehicle electric power inspection electric energy guarantee planning method and device in a multi-weather scene, and aims to solve the problem of uncertainty of unmanned aerial vehicle energy consumption and renewable energy power generation in the multi-weather scene in the prior art. Weather scenes are divided into multiple types, the influence of the weather scenes on the energy consumption of the unmanned aerial vehicle power inspection system is quantified, and a system load model is established; establishing a two-stage micro-grid planning model by using the output of the power generation equipment unit; constructing a fuzzy set based on a multi-discrete scene method, and converting the micro-grid planning model into a distributed robust optimization model by using the fuzzy set; a differential evolution-column and constraint generation algorithm is utilized to solve the distributed robust optimization model, the solving time is remarkably shortened, the solution quality is ensured, simulation experiments are utilized to verify that the method can obtain an unmanned aerial vehicle electric power inspection electric energy guarantee system planning scheme considering weather uncertainty, and economy, reliability and efficiency are balanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy system planning and design, and in particular to a method and device for power supply guarantee planning for UAV power inspection under multiple weather scenarios. Background Art

[0002] With the wide application of unmanned aerial vehicles (UAVs) in the field of power inspection, their advantages of high efficiency and flexibility have significantly reduced the cost of manual inspection and improved the operation efficiency. However, the continuous operation of UAVs and their supporting ground equipment (such as control stations, charging piles, data processing terminals) poses high stability requirements for power supply. Traditional energy guarantee schemes such as tethered power supply (TUAV) are limited by the cable length, and wireless charging technologies (such as laser charging) have problems such as low transmission efficiency, making it difficult to meet the inspection requirements in remote areas or complex meteorological conditions. Microgrid systems can integrate renewable energy sources such as wind power and photovoltaic power, enabling local material utilization and local energy extraction, and thus become a feasible solution to the UAV energy guarantee problem. However, most existing technologies focus on equipment-level energy management (such as hybrid power architecture optimization) or energy supply optimization in a single scenario, lacking in-depth research on the overall planning and design of ground microgrid systems.

[0003] Although some methods for power supply guarantee of UAV systems by microgrids have been proposed in the existing technology, the impact of the uncertainty of multiple weather scenarios on the microgrid system planning has not been considered. On the one hand, severe weather such as strong wind, rainfall, and high temperature will significantly increase the hovering / flying energy consumption of UAVs (such as increased air resistance and battery performance degradation), and at the same time affect the operating load of ground equipment; on the other hand, the output of renewable energy power generation (wind power, photovoltaic power) is also restricted by meteorological condition fluctuations. Existing technologies usually adopt stochastic programming (SP) or robust optimization (RO) to handle uncertainty, but SP relies on accurate probability distributions (which are actually difficult to obtain), and RO is too conservative due to considering the worst-case scenario, resulting in a sharp increase in configuration costs or insufficient reliability. In addition, most existing technologies only consider the uncertainty of wind and light output, ignoring the coupled impact of weather on both the source and load sides, making it difficult to achieve a balance between economy and robustness.

[0004] At the level of solution methods, microgrid planning involves mixed-integer nonlinear programming (MINLP) problems, and the traditional column and constraint generation algorithm (CCG) has low computational efficiency when dealing with large-scale integer variables. Although heuristic methods can improve the search efficiency, existing research has not deeply integrated them with the distributionally robust optimization (DRO) framework, resulting in insufficient solution speed and accuracy in complex scenarios.

[0005] In summary, the existing technologies have the following defects: (1) The dual uncertainties of weather on UAV load and renewable energy generation are not systematically considered; (2) Traditional SP / RO methods cannot balance economy and robustness; (3) The low efficiency of the solution algorithm restricts the practicality of large-scale configuration problems. The present invention aims to solve the above technical defects and fill the corresponding technical gaps by designing a two-stage distributionally robust optimization model and a hybrid solution algorithm DECCG. Summary of the Invention

[0006] Aiming at the problems in the existing power supply guarantee system planning for UAV power inspection, such as the great influence of weather scenario uncertainty, the difficulty in balancing economy and reliability, and low solution efficiency, the present invention proposes a method and device for power supply guarantee planning for UAV power inspection under multiple weather scenarios. By modeling the uncertainty of multiple weather scenarios and using the differential evolution-column and constraint generation algorithm, the efficient planning and reliable operation of the microgrid system are realized.

[0007] The present invention provides a method for power supply guarantee planning for UAV power inspection under multiple weather scenarios, including the following steps: Obtain weather data of multiple weather scenarios within a time period; Based on the weather data of multiple weather scenarios, use weights to quantify the influence of multiple weather scenarios on the energy consumption of the UAV power inspection system, and establish a system load model for calculating the total energy consumption of the UAV power inspection system; Use the power generation model of the microgrid power generation equipment unit to obtain the output of the power generation equipment unit; Use the output of the power generation equipment unit to establish a microgrid planning model; the microgrid planning model includes two-stage optimization: the investment cost planning in the first stage and the operation cost optimization in the second stage, and also includes the balance constraint on the total energy consumption of the UAV power inspection system; Construct a fuzzy set based on the multi-discrete scenario method, and use the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model; the distributionally robust optimization model includes the constraints on the two stages of the microgrid planning model; Use the differential evolution-column and constraint generation algorithm to solve the distributionally robust optimization model to obtain the planning result of the UAV power inspection power supply guarantee system under multiple weather scenarios.

[0008] On the other hand, the present invention provides a device for power supply guarantee planning for UAV power inspection under multiple weather scenarios, including: The first module is used to obtain weather data of multiple weather scenarios within a time period; The second module is used to, based on the weather data of multiple weather scenarios, use weights to quantify the influence of multiple weather scenarios on the energy consumption of the UAV power inspection system, and establish a system load model for calculating the total energy consumption of the UAV power inspection system; The third module is used to obtain the output of the power generation equipment unit by using the power generation model of the microgrid power generation equipment unit; The fourth module is used to establish a microgrid planning model by using the output of the power generation equipment unit; the microgrid planning model includes two-stage optimization: the investment cost planning in the first stage and the operation cost optimization in the second stage, and also includes the balance constraint on the total energy consumption of the UAV power inspection system; The fifth module is used to construct a fuzzy set based on the multi-discrete scenario method, and use the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model; the distributionally robust optimization model includes the constraints on the two stages of the microgrid planning model; The sixth module is used to solve the distributionally robust optimization model by using the differential evolution-column and constraint generation algorithm to obtain the planning results of the UAV power inspection power supply system under multiple weather scenarios.

[0009] Compared with the prior art, the technical effects of the present invention are as follows: (1) Compared with the optimization under a single weather scenario in the past, the present invention not only covers conventional weather, but also targets multiple adverse weather scenarios. By means of a dynamic weight adjustment mechanism, a system load model is established, and the UAV power inspection power supply system established accordingly is more practical and has higher robustness.

[0010] (2) For the two-stage microgrid planning model and the distributionally robust optimization model obtained by transformation using the fuzzy set, the present invention adopts the DECCG algorithm proposed by fusing the differential evolution algorithm and the column and constraint generation algorithm to solve the distributionally robust optimization model, which can effectively shorten the solution time of large-scale configuration problems, and the quality of the solution does not decrease due to the increased speed. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on the structures shown in these drawings without creative efforts.

[0012] Figure 1 is the flowchart of the steps of a method for planning the power supply for UAV power inspection under multiple weather scenarios in the first embodiment of the present invention; Figure 2 is the algorithm framework flowchart of a method for planning the power supply for UAV power inspection under multiple weather scenarios in the first embodiment of the present invention; Figure 3It is the algorithm framework flowchart of a method for planning the power supply guarantee of UAV power inspection in multiple weather scenarios in the second embodiment of the present invention; Figure 4 It is the relevant weather data graph within one year in the simulation experiment of the present invention; Figure 5 It is the clustering scatter plot of multiple weather scenarios in the simulation experiment of the present invention; Figure 6 It is the bar chart of the power generation and load of each power generation equipment unit in the simulation experiment of the present invention. Specific implementation manners

[0013] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] In the first embodiment, as Figure 1 shown, the present invention proposes a method for planning the power supply guarantee of UAV power inspection in multiple weather scenarios, including: The first step is to obtain the weather data of multiple weather scenarios within a time period.

[0015] Since different weather scenarios have different impacts on the energy consumption and performance of UAVs, especially under harsh weather conditions, this impact is more obvious. Therefore, the weather scenarios can be classified into bad weather scenarios and ordinary weather scenarios. Bad weather scenarios mainly refer to various special weather scenarios such as strong wind (SW), rainfall (RF), snowfall (SF), high temperature (HT), and low temperature (LT), etc. Ordinary weather scenarios refer to other weather scenarios other than bad weather scenarios. Suppose there are a total of weather scenarios in multiple weather scenarios, where the th scenario is a bad weather scenario, represents an ordinary weather scenario.

[0016] The second step is to use the weather data of multiple weather scenarios to quantify the impact of multiple weather scenarios on the energy consumption of the UAV power inspection system by weights, and establish a system load model for calculating the total energy consumption of the UAV power inspection system.

[0017] The load of the UAV power inspection system includes two parts. One part is the energy consumption of the UAV , and the other part is the energy consumption of the UAV ground-related equipment 。As the weather scenario changes, the energy consumption of the UAV also changes. Therefore, the total energy consumption of the UAV power inspection system is different in adverse weather scenarios and normal weather scenarios. Assume that in the normal weather scenario, the total energy consumption of the system is ; Under the multi-weather scenario considering adverse weather scenarios, the total energy consumption of the system is 。To simplify the calculation, the load in the normal weather scenario can be calculated first, and then, based on the weather type of a certain day, weights are added. Moreover, the impacts brought by different weather types occurring on the same day can be superimposed (for example, the impacts brought by rainfall and strong wind can be cumulatively calculated). The specific calculation formula is as follows: (1) (2) Where: is the total energy consumption of the UAV power inspection system under multi-scenario weather considering adverse weather scenarios; is the total energy consumption of the UAV power inspection system in the normal weather scenario, is the time step, is the weight of the impact of each adverse weather scenario on energy consumption, ; is the total number of weather scenarios, and the weight depends on meteorological factors in the corresponding weather scenario. For example, the weight affected by rainfall weather depends on the precipitation, and the weight affected by strong wind weather depends on the wind speed, etc.; = 1 indicates that the weight impact base number for the normal weather scenario is 1; In fact, formula (2) includes the energy consumption situation of formula (1). When the impact weight values of all adverse weather scenarios in formula (2) are 0, it is transformed into the total energy consumption formula (1) of the system in the normal weather scenario.

[0018] Further, in formula (1), the UAV energy consumption is given by the following formula: (3) In the above formula, is the hovering energy consumption of the UAV, is the straight flight energy consumption of the UAV; Assume the number of UAVs in the system is , the form drag power of the UAV (the propulsion power required for the UAV to overcome its shape resistance) is , the blade induced power is , the straight flight propulsion power is , use to represent the hovering duration of the th UAV during the entire mission time period, represents the straight flight duration of the th UAV, then there is: (4) (5) Since the energy consumption of the UAV is highly correlated with that of the ground-related equipment of the UAV, for the sake of simplicity in calculation, it is assumed that the energy consumption of the ground equipment has a linear relationship with the energy consumption of the UAV. The energy consumption of the ground-related equipment of the UAV The specific value of can be given by the following formula: , (6) ; In the above formula, represents the proportionality coefficient with the energy consumption of the UAV, , , , respectively represent the proportionality coefficients of the energy consumption of the UAV charging station, the UAV control center, the UAV monitoring equipment, and the data processing device with the energy consumption of the UAV.

[0019] The respective weights of the foregoing adverse weather scenarios ( ) can all be dynamically set according to the different interval ranges to which the values of their relevant meteorological factors belong. For example, in a feasible dynamic setting method, for the rainfall weather scenario, it can be set that when the precipitation is less than the lower limit of the set interval, the weight value is taken as 0; when the precipitation falls within the interval range set by the upper limit value and the lower limit value, the weight ; when the precipitation is greater than or equal to the upper limit of the set interval, the weight is set to . Other weather scenarios are set accordingly with reference to similar rules according to different meteorological factors. By formulating this dynamic weight setting mechanism, the influence weight magnitudes under various weather types can be calculated, and then the total energy consumption in this weather scenario can be obtained, making the UAV power inspection power supply guarantee system obtained thereby more in line with the actual requirements and having higher robustness.

[0020] In the third step, using the power generation model of the microgrid power generation equipment unit, the output of the power generation equipment unit is obtained; the power generation equipment unit includes at least a wind turbine, a photovoltaic device, an energy storage device, and a gas turbine.

[0021] The power generation model of the wind turbine (WT) is as follows: (7) Wherein, is the wind speed at the altitude center, represents the output of the wind power generation equipment unit (output electric power), is the air density, is the area swept by the wind turbine rotor, is the power coefficient of the wind turbine rotor, which is a function of the wind turbine tip speed ratio and the blade pitch angle. is the overall efficiency of the wind turbine electrical components and the gearbox. is the rated power of the wind turbine. , and are the cut-out wind speed, rated wind speed, and cut-in wind speed of the wind turbine, respectively.

[0022] The photovoltaic (PV) power generation model is as follows: (8) (9) Where, represents the output of the photovoltaic power generation equipment unit, represents the solar irradiance, represents the area of the solar photovoltaic panel, represents the efficiency of the entire solar photovoltaic unit, is the temperature coefficient, usually negative, represents the current ambient temperature, is the reference temperature, generally set to , The photovoltaic power generation conversion efficiency at the reference temperature.

[0023] The energy storage (ES) power generation model is as follows: (10) Where, SOC is the state of charge, and represent the charging and discharging powers within the current time step respectively, and represent the charging efficiency and discharging efficiency respectively, represents the maximum energy capacity of a single energy storage system battery pack.

[0024] The micro gas turbine (MT) power generation model is as follows: (11) (12) Where, [[ID=7l]] is the output of the MT power generation equipment unit, is the thermal efficiency of the MT, which is related to the specific model, is the output heat of natural gas, which depends on the consumed fuel flow and the fuel calorific value (generally taken as 9.78 ).

[0025] Step 4: Using the output of the power generation equipment unit, establish a microgrid planning (DRO) model.

[0026] According to the usage characteristics of the microgrid, the microgrid planning (DRO) model is divided into two stages. The first stage is the investment cost planning stage, which mainly plans the number of each power generation equipment unit in the microgrid on a long-time scale; the second stage is the operating cost optimization stage, which mainly solves the optimization problem of the daily scheduling cost.

[0027] The total objective function of the microgrid planning model is given by the following formula: (13) where is the total investment cost of the power generation equipment, corresponding to the investment cost planning in the first stage; is the system operating cost, corresponding to the operating cost optimization in the second stage. Let the set of all power generation equipment units in the microgrid be , be the -th power generation equipment unit in the set , , , , , , then the specific calculation formula of is as follows: (14) (15) Formula (14) represents the calculation method of the total investment cost of the power generation equipment. The investment cost of each type of power generation equipment unit can be calculated by formula (15). In formula (15), is the configuration cost of a single power generation equipment unit , is the number of power generation equipment equipped in the microgrid , is 's life cycle, is the discount rate, is the planning and design time scale of this microgrid. Through formula (15), the investment cost of the power generation equipment equipped under the time scale, considering wear, repair, maintenance, etc., can be calculated.

[0028] The system operating cost can be calculated by the following formula: (16) (17) Wherein, , and respectively represent the equipment operation cost, load non - satisfaction penalty cost, and wind and light curtailment cost on a daily time scale. The sum of the three is multiplied by which represents the total operation cost on the time scale. It also includes the operation cost of each power generation equipment, and its specific calculation formula is as shown in (17). represents a single power generation equipment unit the operation cost under unit output power. represents the total operation time of the equipment in one day. represents the output of the equipment at the moment. Similarly, and are also calculated as shown in formula (17). represents the penalty cost per unit power. represents at the moment ( , unit: hour) the load curtailment amount. represents the wind and light curtailment cost per unit power. and respectively represent the wind and light curtailment situations of the wind power generation equipment and the photovoltaic power generation equipment at the moment.

[0029] After the models of each component power generation equipment unit in the system are established, the energy guarantee mode of the micro - grid for the UAV inspection task can be simulated, and then the established micro - grid planning model can be evaluated to give the optimal dispatching strategy of the micro - grid under different power supply priority conditions of each power generation equipment unit. The whole operation process is as Figure 2 shown. First, input the number of UAVs , the quantity configuration of each part of the power generation equipment unit in the micro - grid, some relevant parameters, and historical weather data. On this basis, calculate the daily power generation of the wind turbines and photovoltaic panels, and the daily total load demand on a daily basis. Then, in this embodiment, daily dispatching is carried out by setting operation dispatching rules based on power supply priority, including: calculating the relationship between the total load demand and supply; here, renewable energy (including wind energy and photovoltaic) is preferentially used for power supply, and judge the remaining power supply . If this method meets the load demand, that is, there is , then the excess power generation charges the energy storage system, and calculate , continue to judge the remaining power generation. If there is still , then calculate the cost of wind and light curtailment and return it to the total cost; if this method cannot meet the load demand, that is, it does not meet , the power supply is provided by the energy storage system discharging, and the operating cost of the energy storage system is calculated and returned to the total cost. If the load demand can still be met after charging the energy storage, the micro gas turbine is used for power generation, and its operating cost is calculated and returned to the total cost. In the UAV power inspection system, the total cost to be calculated includes the microgrid planning and design cost, the operating cost of each component, the penalty cost for unmet load, and the cost of abandoned wind and light.

[0030] The microgrid planning model also includes the balance constraint on the total energy consumption of the UAV power inspection system. Specifically, during the operation of the entire UAV power inspection system, the power balance constraint (i.e., the power generation of the microgrid is equal to the system load demand) needs to be considered, which is specifically given by the following formula: , (18) ; Among them, represents the value at the power generation equipment unit when, is the total energy consumption of the UAV power inspection system at time, which can be calculated by the total energy consumption formula of the system given by formula (2), represents the reduction of renewable energy power generation (subtracting the utilized amount from the renewable power generation).

[0031] Step 5: Construct a fuzzy set based on the multi-discrete scenario method, and use the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model. The distributionally robust optimization model includes the constraint on the total energy consumption of the UAV power inspection system and the constraints on the two stages of the microgrid planning model.

[0032] First, construct a fuzzy set based on the multi-discrete scenario method, including: (19) Among them, represents the constructed fuzzy set, represents the constructed th weather scenario, represents the th probability of the weather scenario occurring, represents the basic probability value of the th weather scenario probability, , are the probability limit range parameters under the 1-norm and norm constraints respectively.

[0033] Next, considering the uncertainty, the microgrid planning model is transformed into the following distributionally robust optimization model: (20) (21) (22) (23) (24) In the above formula (20), is the planning decision variable in the first stage, representing the number of power generation equipment units equipped, and is a vector represented by ; is the operation decision variable in the second stage. The operation decision variables include the power generation output of the gas turbine, the charge and discharge power of the energy storage system, the curtailment of renewable energy power generation, the load curtailment (total energy consumption minus total power generation), etc. represents the transpose of the investment cost coefficient vector (subsequent notations with the same upper index for vectors or matrices all represent taking the transpose); is the objective function in the first stage, i.e., the planning cost, corresponding to formula (14); is the objective function in the second stage, i.e., the operation cost, corresponding to formula (16), is the operation cost coefficient vector, is the uncertainty parameter in the th scenario; represents the feasible region of the decision variables in the second stage. Formula (21) represents the planning constraint condition in the first stage, i.e., the power generation equipment capacity constraint, is the coefficient matrix corresponding to the constraint condition in the first stage; Formula (22) represents the inequality constraint condition in the second stage, is the coefficient matrix corresponding to the inequality constraint in the second stage; Formula (23) represents the equality constraint condition in the second stage, is the coefficient matrix corresponding to the equality constraint in the second stage; Formula (24) represents the coupling constraint between the decision variables and , , are the coupling constraint matrices; , , and g are the constant terms in the corresponding constraints respectively.

[0034] Step 6: Solve the distributionally robust optimization model based on the differential evolution-column and constraint generation (DECCG) algorithm to obtain the planning results of the UAV power inspection power supply system under multiple weather scenarios considering weather scenario uncertainty.

[0035] By integrating the Differential Evolution (DE) algorithm and the Column and Constraint Generation (CCG) algorithm, the present invention proposes a new Differential Evolution - Column and Constraint Generation (DECCG) algorithm, which can effectively shorten the solution time of large-scale configuration problems such as the above-mentioned distributionally robust optimization model, and the quality of the solution is not reduced due to the increased speed. Specifically, first, the original problem in formula (20) is divided into a master problem (MP) and a sub-problem (SP), decoupling the original min-max-min optimization problem (including the objective function optimization problem of the first-stage investment cost and the objective function optimization problem of the second-stage operation cost), and then using the improved DECCG algorithm to solve MP and SP. The specific algorithm process is shown in the pseudo-code in Table 1 below: Table 1: Algorithm for Solving MP and SP Based on the DECCG Method

[0036] In the above algorithm, the inputs are the master problem, the sub-problem and related parameters, and the output is the decision variable in the first stage , that is, the capacity configuration scheme of the microgrid. First, in algorithm step 1, set the parameters of differential evolution, including the population size , the maximum number of generations of evolution , the mutation factor and the crossover rate , set the upper bound 、lower and the interval width constraint threshold of column and constraint generation, which are used to determine the boundary convergence condition of the main loop, and randomly generate the initial population within the boundary range determined by the upper and lower bounds. Then, in algorithm steps 3 - 13, use the differential evolution algorithm to solve the integer programming problem in the first stage, including: in each round of evolution ( to ), by traversing the population, apply the mutation operator and the mutation factor to the decision variable to perform the mutation operation, and apply the crossover operator with a crossover rate of to perform the crossover operation; in the selection operation, by solving the problem , for the candidate solution , obtain the objective value , if , then assign to . Then, in algorithm steps 14 - 15, return the optimal solution in the first-stage population to the second stage, and update the lower bound using , where is the first-stage cost estimation coefficient, It is a lower bound estimate of the cost in the second stage of the current problem MP. In algorithm steps 16 - 17, the second stage is solved using a commercial solver, including: fixing solving the problem , obtaining the probability value and the objective function value in the worst - case scenario, and updating the upper bound using . In algorithm steps 18 - 20, a convergence check is performed. If it is determined that holds, the algorithm is terminated, and in steps 21 - 22, new scenarios and constraints are added: updating the scenario in the worst - case scenario, adding a new variable and related constraints to problem MP, and simultaneously updating the iteration counter . Such repeated cycling and solving (the main loop of algorithm steps 3 - 22) continue until a solution that meets the termination condition is found, and then the loop is exited to obtain the optimal solution for the micro - grid planning and design, which is used as the result of the power supply guarantee planning for UAV power line inspection under multi - weather scenarios.

[0037] In the second embodiment of the present invention, a quad - rotor UAV model is selected, and the adverse weather scenarios include five special weathers: strong wind (SW), rainfall (RF), snowfall (SF), high temperature (HT), and low temperature (LT). That is, the multi - weather scenario includes a total of weather scenarios. Among them, the th scenarios respectively correspond to the adverse weather scenarios: SW, RF, SF, HT, and LT, representing the normal weather scenario.

[0038] Then, in the second step, the total energy consumption formula (2) of the UAV power line inspection system can be expressed as: ; (25) Where: is the time step, is the weight affected by rainfall weather, depending on the precipitation , is the weight affected by snowfall weather, depending on the snow intensity , and are the weights affected by high temperature and low temperature respectively, depending on the temperature , is the weight affected by strong - wind weather, depending on the wind speed . The rules for formulating each weight are as follows: Table 2: Rules for formulating weights

[0039] As shown in Table 2, each weight can be calculated according to the value range of its relevant meteorological factors. Among them, , , , , respectively represent the lower limit of precipitation, the lower limit of snowfall, the lower limit of high-temperature weather, the lower limit of low-temperature weather, and the lower limit of wind speed. When the corresponding variable values of all meteorological influencing factors on a certain day are less than the lower limit, the weight can be considered as 0, that is, the weather on that day is an ordinary weather scenario. , , , , respectively represent the upper limits of the corresponding influencing factors. When the corresponding variable value is greater than the upper limit, the weight is . When the value is between the upper and lower limits, the weight is . Through the rules of this dynamic weight adjustment mechanism, the influence weight of each weather type can be calculated, and then the total energy consumption in this weather scenario can be obtained, so that the drone power inspection power supply system obtained accordingly is more in line with the actual needs and has higher robustness.

[0040] In equation (25), the total system energy consumption in the ordinary weather scenario is still given by the following formula: ; (26) where the energy consumption of the drone is given by the aforementioned equations (3)-(5), and the energy consumption of the drone and the ground-related equipment is given by the aforementioned equation (6), and the profile drag power , the blade induced power , and the straight flight propulsion power in equations (3)-(5) are respectively given by the following formulas: ; (27) ; (28) ; (29) In the above formulas, represents the average induced velocity; represents the tip linear velocity of the rotor angle; represents the profile drag coefficient, represents the air density, represents the disk solidity, which is related to the number of blades, the blade chord length, and the rotor radius of the drone, represents the area formed when the rotor rotates, is the blade angular velocity, Represents the induced power increment correction factor, is the UAV weight, is the airframe drag ratio, is the straight flight speed of the UAV, which is a decisive variable affecting the straight flight power. Implement according to the first to sixth steps in the foregoing method to complete the power supply guarantee plan for UAV power inspection, and its corresponding algorithm framework process is as Figure 3 shown.

[0041] Specifically for the power supply guarantee planning method for UAV power inspection in multiple weather scenarios proposed in the second embodiment, the present invention verifies the effectiveness of the method proposed in the present invention by simulating and solving actual data. Select relevant weather data in a certain place (latitude 35.8°, longitude 90.6°) for a period of time, specifically the original data from 0:00 on January 1, 2022 to 0:00 on December 31, 2022 with a resolution of one hour. The specific data is as Figure 4 shown. Using the multi-scenario classification method proposed in the present invention, the clustering result of the weather scenario is Figure 5 shown. This figure shows that all historical scenarios are first reduced in dimension by principal component analysis, and then four types of weather day scenarios are obtained by clustering method. The abscissa represents the first principal component, and the ordinate represents the second principal component. Use the distributionally robust optimization method and the improved DECCG algorithm proposed in the present invention to plan and design the UAV power supply guarantee system in multiple weather scenarios, and the obtained results are shown in Table 3. It can be seen from Table 3 that the microgrid planning scheme obtained by using the two-stage microgrid planning (DRO) model and solution proposed in the present invention is reasonable, the capacity configuration is also within a reasonable range, the utilization rate of renewable energy is high, and the penalty cost for unmet load is almost 0. In an important scenario such as power inspection, it is necessary to ensure that the entire load system obtains reliable energy guarantee in order to complete the inspection task and avoid major losses.

[0042] Table 3 Solution results of the two-stage microgrid planning model

[0043] To deeply analyze the daily optimal scheduling situation, select the optimal scheduling result of a certain day in a typical day for analysis. It can be seen from the bar chart of the power generation and load of each power generation equipment unit as Figure 6 shown that when the renewable energy power generation is low, it is mainly supplied by ES and MT, and in other time periods, it is mainly supplied by WT and PV, and the excess electric energy generated by renewable energy can be stored in ES for subsequent discharge. From the relationship between the daily load and power generation, this microgrid system can fully meet the load demand of the UAV inspection system and ensure the smooth completion of the inspection task.

[0044] In a third embodiment of the present invention, a power supply guarantee planning device for UAV power inspection under multiple weather scenarios is provided, including: A first module for obtaining weather data of multiple weather scenarios within a time period; A second module for, based on the weather data of multiple weather scenarios, using weight quantization to calculate the influence of multiple weather scenarios on the energy consumption of the UAV power inspection system, establishing a system load model for calculating the total energy consumption of the UAV power inspection system; A third module for obtaining the output of the power generation equipment unit by using the power generation model of the microgrid power generation equipment unit; A fourth module for establishing a microgrid planning model by using the output of the power generation equipment unit; the microgrid planning model includes two-stage optimization: investment cost planning in the first stage and operating cost optimization in the second stage, and also includes a balance constraint on the total energy consumption of the UAV power inspection system; A fifth module for constructing a fuzzy set based on the multi-discrete scenario method and using the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model; the distributionally robust optimization model includes constraints on the two stages of the microgrid planning model; A sixth module for solving the distributionally robust optimization model by using the differential evolution-column and constraint generation algorithm to obtain the planning result of the UAV power inspection power supply guarantee system under multiple weather scenarios.

[0045] On the other hand, the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the power supply guarantee planning method for UAV power inspection under multiple weather scenarios provided in any of the above embodiments are implemented. This computer device can be a server. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store sample data. The network interface of the computer device is used to communicate with an external terminal through a network connection.

[0046] On the other hand, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the power supply guarantee planning method for UAV power inspection under multiple weather scenarios provided in any of the above embodiments are implemented.

[0047] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0048] Matters not described in this invention are well-known techniques.

[0049] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0050] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application.

[0051] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for power supply guarantee planning of drone power inspection under multiple weather scenarios, characterized in that Including: Obtain weather data of multiple weather scenarios within a time period; Based on the weather data of multiple weather scenarios, use weights to quantify the impact of multiple weather scenarios on the energy consumption of the UAV power inspection system, and establish a system load model for calculating the total energy consumption of the UAV power inspection system; Utilize the power generation model of the microgrid power generation equipment unit to obtain the output of the power generation equipment unit; Use the output of the power generation equipment unit to establish a microgrid planning model; the microgrid planning model includes two-stage optimizations: the investment cost planning in the first stage and the operation cost optimization in the second stage, and also includes the balance constraint on the total energy consumption of the UAV power inspection system; Construct a fuzzy set based on the multi-discrete scenario method, and use the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model; the distributionally robust optimization model includes the constraints on the two stages of the microgrid planning model; Use the differential evolution-column and constraint generation algorithm to solve the distributionally robust optimization model to obtain the planning result of the UAV power inspection power supply system under multiple weather scenarios.

2. The method for planning the power supply guarantee of the drone power inspection under multiple weather scenarios according to claim 1, wherein, The weather scenarios are classified into bad weather scenarios and ordinary weather scenarios.

3. The method for planning the power supply guarantee for UAV power inspection in multiple weather scenarios according to claim 2, wherein, The system load model is given by the following formula: ， ； Among them, is the total energy consumption of the UAV power inspection system under multi-scenario weather considering adverse weather scenarios; is the total energy consumption of the UAV power inspection system under normal weather scenarios, is the time step, is the energy consumption of the UAV, is the energy consumption of the UAV ground-related equipment; is the weight of the impact of each adverse weather scenario on the energy consumption, ; is the total number of weather scenarios, and the weight depends on the meteorological factors under the corresponding weather scenarios; The energy consumption of the UAV , which is obtained by summing the hovering energy consumption of the UAV and the direct flight energy consumption of the UAV ; The energy consumption of the ground-related equipment of the drone , where represents the proportionality coefficient of the energy consumption of the drone , , , respectively represent the proportionality coefficients of the energy consumption of the drone charging station, the drone control center, the drone monitoring equipment, and the data processing device to the energy consumption of the drone.

4. The method for planning the power supply guarantee for UAV power inspection in multiple weather scenarios according to claim 3, wherein, The power generation equipment unit at least includes a wind turbine, photovoltaic, energy storage, and micro gas turbine, which are represented by WT, PV, ES, and MT respectively, and are represented by to represent the set of power generation equipment units; The step of utilizing the power generation model of the microgrid power generation equipment unit to obtain the output of the power generation equipment unit includes: Obtain the output of the WT equipment unit using the wind turbine power generation model , the is a function of the altitude-centered wind speed and time ; Obtain the output of the PV power generation equipment unit using the PV power generation model ; Obtaining the output of the ES power generation equipment unit using the energy storage power generation model , the represents the state of charge of the energy storage, which is a function of time ; Obtain the output of the MT power generation equipment unit using the micro gas turbine power generation model , the said is a function of time .

5. The method for planning the power supply guarantee for UAV power inspection under multiple weather scenarios according to claim 4, wherein, The total objective function of the microgrid planning model is given by the following formula: ； Among them, is the total investment cost of the power generation equipment, corresponding to the investment cost planning in the first stage, is the system operation cost, corresponding to the operation cost optimization in the second stage, specifically: given by the following formula: ； ； In the above formula, represents a set in the th power generation equipment unit, , including: , , , ; is the configuration cost of a single power generation equipment unit , is the quantity of power generation equipment equipped in the microgrid , is 's life cycle, is the discount rate, is the planning and design time scale of the microgrid; given by the following formula: ； In the above formula, , and respectively represent the equipment operation cost, load non - satisfaction penalty cost, and curtailment cost under the daily time scale, and are given by the following formula: ， ， ； Among them, represents a single power generation equipment unit The operating cost at unit output power, represents the total operating time of the equipment within one day, represents the output of the equipment at moment; represents the penalty cost per unit power, represents within one day the load shedding amount at is in 24-hour format, with the unit of hour; represents the cost of wind and solar curtailment per unit power, and respectively represent the wind and solar curtailment situations of wind power generation equipment and photovoltaic power generation equipment at moment; The microgrid planning model also includes the balance constraint on the total energy consumption of the UAV power inspection system, which is given by the following formula: ； Among them, denotes the value at the time of the power generation equipment unit is the total energy consumption of the UAV power inspection system at the moment, which is obtained by calculating the total energy consumption formula of the UAV power inspection system under multi-scenario weather considering adverse weather scenarios. denotes the charging power within the current time step in the energy storage power generation model, denotes the discharging power within the current time step in the energy storage power generation model, denotes the reduction of renewable energy power generation, which is equal to the renewable power generation minus the utilized amount.

6. The method for planning the power supply guarantee for drone power inspection in multiple weather scenarios according to claim 5, wherein The step of constructing a fuzzy set based on the multi-discrete scenario method and using the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model includes: Based on the multi-discrete scenario method, construct the following fuzzy set: ； Among them, represents the constructed fuzzy set, represents the th weather scenario, is the total number of weather scenarios, represents the probability of the th weather scenario occurring, represents the th basic probability value of the weather scenario, and are the probability limit range parameters under the 1-norm and norm constraints respectively; Use the above fuzzy set to transform the microgrid planning model into the following distributionally robust optimization model: ， Among them, is the planning decision variable in the first stage, representing the number of power generation equipment units equipped, is the operation decision variable in the second stage, including the power generation output of gas turbines, the charge and discharge power of energy storage systems, the curtailment of renewable energy generation, and the load curtailment. The renewable energy includes wind turbines and photovoltaics, and the load curtailment is equal to the total energy consumption minus the total power generation; represents the transpose of a vector or matrix, represents the investment cost coefficient vector, is the objective function corresponding to the investment cost in the first stage; is the objective function corresponding to the operation cost in the second stage, is the operation cost coefficient vector, is the uncertainty parameter in the th scenario, represents the feasible region of the decision variables in the second stage; is the coefficient matrix corresponding to the planning constraint condition in the first stage, corresponding to the capacity constraint of the power generation equipment unit, , represents the inequality constraint condition in the second stage, is the coefficient matrix corresponding to the inequality constraint in the second stage; , represents the equality constraint condition in the second stage, is the coefficient matrix corresponding to the equality constraint in the second stage; , represents the coupling constraint of the decision variables and , , are the coupling constraint matrices; , , and g are the constant terms in the corresponding constraints respectively.

7. The method for planning the power supply guarantee of UAV power inspection in multiple weather scenarios according to claim 6, characterized in that, The step of using the differential evolution-column and constraint generation algorithm to solve the distributionally robust optimization model includes: Decompose the distributionally robust optimization model into a master problem and a sub-problem; Decouple the objective function optimization problems of the investment cost in the first stage and the operation cost in the second stage in the distributionally robust optimization model; Use the differential evolution-column and constraint generation algorithm to solve the master problem and the sub-problem respectively.

8. The method for planning power supply guarantee for UAV power inspection in multiple weather scenarios according to claim 7, characterized in that, The step of using the differential evolution-column and constraint generation algorithm to solve the master problem and the sub-problem respectively, the algorithm flow includes: Step 1.1 Input the master problem, the sub-problem and related parameters, including: Set the parameters of differential evolution, including the population size , the maximum number of generations of evolution , the mutation factor and the crossover rate ; Set the upper bound of column and constraint generation , lower and the interval width constraint threshold of the upper and lower bounds ; The initial population randomly generated within the boundary range determined by the upper and lower bounds ; Step 1.2 Use the differential evolution algorithm to solve the integer programming problem in the first stage, including: In each round of evolution, by traversing the population, for the decision variables apply the mutation operator and the mutation factor perform the mutation operation; Perform crossover operation using a crossover operator with a crossover rate of ; In the selection operation, by solving the problem , for the candidate solution , obtain the target value ; If , then assign to ; Step 1.3 Return the optimal solution in the first-stage population to the second stage, and use to update the lower bound , where is the first-stage cost estimation coefficient, is the lower bound estimation of the second-stage cost in the current problem MP; Step 1.4 Use a commercial solver to solve the second stage, including: Fixed Solve the problem to obtain the probability value in the worst case and the objective function value ; Use Update the upper bound ; Step 1.5 Perform a convergence check. If it is determined that holds, terminate the algorithm; Step 1.6 Perform adding new scenarios and constraints: update the worst-case scenario , and add new variables and related constraints to problem MP, and update the iteration counter ; Step 1.7 Repeat steps 1.2 to 1.6 until the termination condition of the main loop is reached , break out of the main loop, and obtain the optimal solution for the microgrid planning and design, which is used as the result of the power supply guarantee planning for UAV power inspection under multi-weather scenarios.

9. The method for planning the power supply guarantee for drone power inspection in multiple weather scenarios according to claim 8, wherein The UAV is a quadrotor model, and the bad weather scenarios include 5 kinds of weather: rainfall, snowfall, high temperature, low temperature and strong wind; In the system load model, the total energy consumption of the UAV power inspection system under multi-scenario weather considering bad weather scenarios is: ； Among them, is the total energy consumption of the UAV power inspection system under normal weather scenarios, is the time step, , , , and are the weights affected by rainfall, snowfall, high temperature, low temperature, and strong wind weather scenarios respectively; Let and be preset weight values, where the depends on the precipitation and is given by the following formula: ； Among them, and respectively represent the lower limit and the upper limit of the precipitation; The said depending on the snow intensity , is given by the following formula: ； wherein, and respectively represent the lower limit and the upper limit of the snowfall amount; The said depends on the temperature and is given by the following formula: ； Among them, and respectively represent the lower limit and the upper limit of the temperature in high-temperature weather; The said depends on the temperature and is given by the following formula: ； Among them, and respectively represent the lower limit and the upper limit of the temperature in low-temperature weather; depending on the wind speed , which is given by: ； Among them, and respectively represent the lower limit and the upper limit of the precipitation.

10. An electric energy guarantee planning device for UAV power inspection under multiple weather scenarios, characterized in that, Including: The first module is used to obtain the weather data of multiple weather scenarios within a time period; The second module is used to, based on the weather data of multiple weather scenarios, use weights to quantify the impact of multiple weather scenarios on the energy consumption of the UAV power inspection system, and establish a system load model for calculating the total energy consumption of the UAV power inspection system; The third module is used to obtain the output of the power generation equipment unit by using the power generation model of the microgrid power generation equipment unit; The fourth module is used to establish a microgrid planning model by using the output of the power generation equipment unit; the microgrid planning model includes two-stage optimization: the investment cost planning in the first stage and the operation cost optimization in the second stage, and also includes the balance constraint on the total energy consumption of the UAV power inspection system; The fifth module is used to construct a fuzzy set based on the multi-discrete scenario method and use the fuzzy set to transform the microgrid planning model into a distributionally robust optimization model; the distributionally robust optimization model includes the constraints on the two stages of the microgrid planning model; The sixth module is used to solve the distributionally robust optimization model by using the differential evolution-column and constraint generation algorithm to obtain the planning results of the UAV power inspection power supply system under multiple weather scenarios.

Images