Unmanned equipment-oriented mobile energy storage vehicle path planning method and device

Abstract

The invention discloses a mobile energy storage vehicle path planning method and device for unmanned equipment. According to the method, a path planning problem of a mobile energy storage vehicle is constructed into a two-stage mathematical planning model; respectively setting a first stage constraint condition and a second stage constraint condition according to the decision variables of the first stage and the second stage; and solving the two-stage mathematical planning model through an evolutionary algorithm to obtain path planning of the mobile energy storage vehicle. According to the method, the planning efficiency and rationality of the path are effectively improved, the energy complementing efficiency is improved, and support is provided for comprehensive use of unmanned equipment in the future.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle scheduling, and particularly relates to a path planning method and device for a mobile energy storage vehicle for unmanned equipment. Background Art

[0002] Unmanned equipment, as a new emerging technology of unmanned operation, can be widely applied to scenarios such as disaster relief and rescue where human execution is extremely dangerous. Currently, the power system of unmanned equipment mainly uses electric energy as the core energy source, which is based on its significant advantages of high efficiency, cleanliness, and easy maintenance. However, this power mode also leads to a key problem: the continuous working ability and activity range of unmanned equipment in scenarios such as disaster relief and rescue are directly limited by the capacity of the battery pack it carries.

[0003] Currently, traditional power supply methods are difficult to implement under such conditions and cannot meet the rapid and flexible energy supply requirements of unmanned equipment. In this context, using a mobile energy storage vehicle to supply electric energy to unmanned equipment has become a highly practical solution.

[0004] Therefore, how to invent a path planning method for a mobile energy storage vehicle, effectively improve the planning efficiency and rationality of the path, improve the energy supply efficiency, and provide support for the full use of future unmanned equipment has become an urgent problem to be solved. Summary of the Invention

[0005] For this reason, the present invention provides a path planning method and device for a mobile energy storage vehicle for unmanned equipment. By constructing a two-stage mathematical programming model and solving the two-stage mathematical programming model through an evolutionary algorithm, the path planning of the mobile energy storage vehicle is obtained, effectively improving the planning efficiency and rationality of the path, enhancing the energy supply efficiency, and providing support for the full use of future unmanned equipment.

[0006] To achieve the above object, the present invention provides the following technical solutions: A path planning method for a mobile energy storage vehicle for unmanned equipment, comprising:

[0007] Construct the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model;

[0008] According to the decision variables of the first stage and the second stage, set the first-stage constraint conditions and the second-stage constraint conditions respectively;

[0009] Solve the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

[0010] As a preferred solution of a path planning method for a mobile energy storage vehicle for unmanned equipment, the objective function expression of the two-stage mathematical programming model is:

[0011]

[0012] Wherein, K is the number of mobile energy storage vehicles; n k is the number of tasks required to be executed by the k-th mobile energy storage vehicle; is the time for the k-th mobile energy storage vehicle to complete the i-th task; is the i-th task completed by the k-th mobile energy storage vehicle; is the lower edge of the time window of the i-th task.

[0013] As an optimal solution of a path planning method for mobile energy storage vehicles for unmanned equipment, the first-stage constraint conditions are:

[0014]

[0015] Wherein, x ijk and y jk are 0-1 decision variables; x ijk means that the k-th mobile energy storage vehicle executes the j-th task after executing the i-th task; y jk means that the j-th task is executed by the k-th mobile energy storage vehicle;

[0016] The second-stage constraint conditions are:

[0017]

[0018]

[0019] Wherein, E i is the energy required for the i-th task; l i is the upper edge of the time window of the i-th task; is the initial location of the k-th mobile energy storage vehicle; p k is the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; d ij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are respectively the time and energy when the k-th mobile energy storage vehicle enters its i-th task node; and are respectively the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node; is the waiting time for the k-th mobile energy storage vehicle to enter its i-th task; The number of times the k-th mobile energy storage vehicle needs to return to the charging center when performing its i-th task.

[0020] As an optimal solution of a path planning method for mobile energy storage vehicles for unmanned equipment, the steps of solving the two-stage mathematical programming model through the evolutionary algorithm are as follows:

[0021] Initialize the chromosome population through chromosome coding to obtain an initial population; initialize the parameters of the evolutionary algorithm to obtain initial parameters;

[0022] Calculate the fitness of the initial population through an improved 2-opt operator to obtain the initial fitness;

[0023] Starting from the first chromosome in the initial population, execute the self-crossing operator to generate a crossed population;

[0024] Starting from the first chromosome in the initial population, execute the mutation operator to generate a mutated population;

[0025] Select elite individuals from the initial population, the crossed population, and the mutated population according to the elite population ratio in the initial parameters and add them to the new population;

[0026] Randomly select several individuals from the initial population, the crossed population, and the mutated population and add them to the new population;

[0027] Use the new population as the next-round initial population, and sequentially execute the self-crossing operator and the mutation operator to iteratively generate the next-round new population until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual;

[0028] Decode the optimal individual to obtain the path planning scheme of the mobile energy storage vehicle.

[0029] As an optimal solution of a path planning method for mobile energy storage vehicles for unmanned equipment, in the process of calculating the fitness of the initial population through the improved 2-opt operator, decode the chromosome into the tasks that each energy storage vehicle needs to perform; calculate the best task execution order and the corresponding fitness of each mobile energy storage vehicle through the improved 2-opt operator; sum up the fitness of each mobile energy storage vehicle to obtain the overall fitness of the chromosome.

[0030] The present invention also provides a path planning device for mobile energy storage vehicles for unmanned equipment. Based on the above path planning method for mobile energy storage vehicles for unmanned equipment, it includes:

[0031] A two-stage mathematical programming model construction module for constructing the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model;

[0032] A constraint condition setting module, configured to set first-stage constraint conditions and second-stage constraint conditions respectively according to the decision variables in the first stage and the second stage;

[0033] A two-stage mathematical programming model solving module, configured to solve the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

[0034] As an optimal solution of a path planning device for a mobile energy storage vehicle for unmanned equipment, in the two-stage mathematical programming model construction module, the objective function expression of the two-stage mathematical programming model is:

[0035]

[0036] In the formula, K is the number of mobile energy storage vehicles; n k is the number of tasks that the k-th mobile energy storage vehicle needs to execute; is the time for the k-th mobile energy storage vehicle to complete the i-th task; is the i-th task completed by the k-th mobile energy storage vehicle; is the lower edge of the time window of the i-th task.

[0037] As an optimal solution of a path planning device for a mobile energy storage vehicle for unmanned equipment, in the constraint condition setting module, the first-stage constraint conditions are:

[0038]

[0039] In the formula, x ijk and y jk are 0-1 decision variables; x ijk means that the k-th mobile energy storage vehicle executes the j-th task after executing the i-th task; y jk means that the j-th task is executed by the k-th mobile energy storage vehicle;

[0040] The second-stage constraint conditions are:

[0041]

[0042]

[0043] In the formula, E i is the energy required for the i-th task; l i is the upper edge of the time window of the i-th task; is the initial position where the k-th mobile energy storage vehicle is located; p kis the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; d ij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are the time and energy when the k-th mobile energy storage vehicle enters its i-th task node respectively; and are the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node respectively; is the waiting time when the k-th mobile energy storage vehicle enters its i-th task; is the number of times the k-th mobile energy storage vehicle needs to return to the charging center when performing its i-th task.

[0044] As an optimal solution of a path planning device for mobile energy storage vehicles for unmanned equipment, in the two-stage mathematical programming model solving module, the sub-module for solving the two-stage mathematical programming model through the evolutionary algorithm includes:

[0045] A population initialization sub-module, used to initialize the chromosome population through chromosome coding to obtain an initial population; and initialize the parameters of the evolutionary algorithm to obtain initial parameters;

[0046] An initial fitness calculation sub-module, used to calculate the fitness of the initial population through an improved 2-opt operator to obtain the initial fitness;

[0047] A cross population generation sub-module, used to start from the first chromosome in the initial population, execute the self-cross operator to generate a cross population;

[0048] A mutation population generation sub-module, used to start from the first chromosome in the initial population, execute the mutation operator to generate a mutation population;

[0049] An elite individual selection sub-module, used to select elite individuals from the initial population, the cross population and the mutation population according to the elite population ratio in the initial parameters and add them to the new population;

[0050] A new population supplementation sub-module, used to randomly select several individuals from the initial population, the cross population and the mutation population and add them to the new population;

[0051] A new population iterative generation sub-module is used to take the new population as the initial population for the next round, and successively execute the self-cross operator and the mutation operator to iteratively generate the new population for the next round until the number of iterations reaches the maximum number of iterations in the initial parameters, completing the iteration and outputting the optimal individual;

[0052] A path planning scheme acquisition sub-module is used to decode the optimal individual to obtain the path planning scheme of the mobile energy storage vehicle.

[0053] As an optimal scheme of a path planning device for a mobile energy storage vehicle for unmanned equipment, in the initial fitness calculation sub-module of the two-stage mathematical programming model solving module, during the process of calculating the fitness of the initial population through the improved 2-opt operator, the chromosome is decoded into the tasks that each energy storage vehicle needs to execute; the best task execution order and the corresponding fitness of each mobile energy storage vehicle are calculated through the improved 2-opt operator; the fitness of each mobile energy storage vehicle is summed to obtain the overall fitness of the chromosome.

[0054] The present invention has the following advantages: The path planning problem of the mobile energy storage vehicle is constructed as a two-stage mathematical programming model; according to the decision variables of the first stage and the second stage, the constraint conditions of the first stage and the second stage are set respectively; the two-stage mathematical programming model is solved by an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle. The steps of the solution are as follows: The chromosome population is initialized through chromosome coding to obtain an initial population; the parameters of the evolutionary algorithm are initially set to obtain initial parameters; the fitness of the initial population is calculated through an improved 2-opt operator to obtain an initial fitness; starting from the first chromosome in the initial population, a self-cross operator is executed to generate a cross population; starting from the first chromosome in the initial population, a mutation operator is executed to generate a mutant population; elite individuals are selected from the initial population, the cross population, and the mutant population according to the elite population ratio in the initial parameters and added to a new population; several individuals are randomly selected from the initial population, the cross population, and the mutant population and added to the new population; the new population is used as the next-round initial population, and the self-cross operator and the mutation operator are sequentially executed to iteratively generate the next-round new population until the number of iterations reaches the maximum number of iterations in the initial parameters, completing the iteration and outputting the optimal individual; the optimal individual is decoded to obtain the path planning scheme of the mobile energy storage vehicle. The present invention is more suitable for the path planning problem of the mobile energy storage vehicle for unmanned equipment. The operators designed in the algorithm are more suitable for the characteristics of this problem: open, multiple charging centers, with time window constraints and considering material loss. Among them, the cross operator is different from the individual-to-individual cross in the traditional genetic algorithm, and a cross of gene fragment to gene fragment, which is more suitable for the structure of the problem solution, is selected, making the evolution of the population more efficient. The present invention effectively improves the efficiency and rationality of path planning, enhances the energy replenishment efficiency, and provides support for the full use of future unmanned equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, without creative efforts, other implementation drawings can also be obtained according to the provided drawings.

[0056] The structures, ratios, sizes, etc. shown in this specification are only used to cooperate with the content disclosed in the specification for those who are familiar with this technology to understand and read, and are not used to limit the limited conditions under which the present invention can be implemented. Therefore, they do not have technical substance significance. Any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0057] Figure 1 It is a schematic flowchart of a path planning method for a mobile energy storage vehicle for unmanned equipment provided in Embodiment 1 of the present invention;

[0058] Figure 2 It is a schematic flowchart of an evolutionary algorithm in a path planning method for a mobile energy storage vehicle for unmanned equipment provided in Embodiment 1 of the present invention;

[0059] Figure 3 It is a schematic diagram of the architecture of a path planning device for a mobile energy storage vehicle for unmanned equipment provided in Embodiment 2 of the present invention. Detailed implementation manners

[0060] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0061] Embodiment 1

[0062] See Figure 1 , Embodiment 1 of the present invention provides a path planning method for a mobile energy storage vehicle for unmanned equipment, including the following steps:

[0063] S1. Construct the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model;

[0064] S2. Set the first-stage constraint conditions and the second-stage constraint conditions respectively according to the decision variables of the first stage and the second stage;

[0065] S3. Solve the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

[0066] In this embodiment, in step S1, the path planning problem of the mobile energy storage vehicle is constructed into a two-stage mathematical programming model;

[0067] Specifically, the present invention defines the path planning problem of the mobile energy storage vehicle for unmanned equipment. In this problem, the transported material is the electric energy that will be consumed on the way, and the task to be performed is to supply electric energy to the unmanned equipment, which is a completely new vehicle routing problem. Specifically, in the case of knowing the energy requirements and locations of the unmanned equipment, several mobile energy storage vehicles are scheduled to supply energy to the unmanned equipment within a specified time window.

[0068] Based on the above definitions, this problem is modeled as a two-stage mathematical programming model.

[0069] Among them, the objective function expression of the two-stage mathematical programming model is:

[0070]

[0071] In the formula, K is the number of mobile energy storage vehicles; n k is the number of tasks that the k-th mobile energy storage vehicle needs to execute; is the time for the k-th mobile energy storage vehicle to complete the i-th task; is the i-th task completed by the k-th mobile energy storage vehicle; is the lower edge of the time window of the i-th task.

[0072] In this embodiment, in step S2, according to the decision variables of the first stage and the second stage, the first-stage constraint conditions and the second-stage constraint conditions are respectively set;

[0073] Specifically, in the first stage, the decision variable is the task that each mobile energy storage vehicle needs to execute; in the second stage, the decision variable is the order of tasks that each mobile energy storage vehicle needs to execute.

[0074] The first-stage constraint conditions are:

[0075]

[0076] In the formula, x ijk and y jk are 0-1 decision variables; x ijk means that the k-th mobile energy storage vehicle executes the j-th task after executing the i-th task; y jk means that the j-th task is executed by the k-th mobile energy storage vehicle;

[0077] The second-stage constraint conditions are:

[0078]

[0079]

[0080] In the formula, E i is the energy required for the i-th task; l i is the upper edge of the time window of the i-th task; is the initial location of the k-th mobile energy storage vehicle; p k is the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; dij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are respectively the time and energy when the k-th mobile energy storage vehicle enters its i-th task node; and are respectively the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node; is the waiting time for the k-th mobile energy storage vehicle to enter its i-th task; is the number of times the k-th mobile energy storage vehicle needs to return to the charging center when performing its i-th task.

[0081] In this embodiment, in step S3, the two-stage mathematical programming model is solved by an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

[0082] Specifically, as Figure 2 shown, the steps of solving the two-stage mathematical programming model by the evolutionary algorithm are as follows:

[0083] S31. Initialize the chromosome population through chromosome coding to obtain an initial population; initialize the parameters of the evolutionary algorithm to obtain initial parameters;

[0084] Specifically, the coding method of the chromosome is integer coding. In the case of a task scale of n, the size of the chromosome is 1×n, and the value at each position is an integer from 1 to K, indicating that the task at the corresponding position is completed by the mobile energy storage vehicle with the number corresponding to the value at the corresponding position. The initial parameters include: population size, maximum number of iterations, and elite population ratio.

[0085] S32. Calculate the fitness of the initial population through an improved 2-opt operator to obtain the initial fitness;

[0086] Specifically, first decode the chromosome into the tasks that each energy storage vehicle needs to execute, then use the improved 2-opt operator to find the best task execution order and the corresponding fitness of each mobile energy storage vehicle, and sum the fitness of each mobile energy storage vehicle as the fitness of the entire chromosome. The basic steps of the improved 2-opt operator are as follows: randomly generate several neighborhood solutions in the neighborhood of the current solution, compare the fitness of these solutions with that of the current solution, if there is a neighborhood solution better than the current solution, then use this neighborhood solution as the current solution, otherwise use the current solution as the optimal solution. The improved 2-opt operator is encapsulated in the fitness function. At the same time, start iterating the population from the loop variable t = 1.

[0087] S33. Starting from the first chromosome in the initial population, execute the self-cross operator to generate a cross population;

[0088] Specifically, starting from the first chromosome, execute the self-cross operator, randomly select two mobile energy storage vehicle numbers m and n, generate a random integer r, where r is between 1 and the minimum number of tasks of the two mobile energy storage vehicles, and cross r tasks of the two mobile energy storage vehicles.

[0089] Specifically, first generate two different random integers m and n between 1 and K, obtain the number of tasks of the mobile energy storage vehicles numbered m and n under the current chromosome, and then generate another random number r, which is between 1 and the smaller of the number of tasks of the two mobile energy storage vehicles. This can avoid the number of crossed tasks exceeding the number of tasks of a certain mobile energy storage vehicle. After that, cross r random tasks of these two mobile energy storage vehicles.

[0090] S34. Starting from the first chromosome in the initial population, execute the mutation operator to generate a mutant population;

[0091] Specifically, starting from the first chromosome, execute the mutation operator, select the mobile energy storage vehicle number with the worst fitness, and select the task number with the worst fitness among them, and randomly assign this task to the task list of the mobile energy storage vehicle with the same initial charging center. If there is no mobile energy storage vehicle with the same initial center, it is randomly assigned to other mobile energy storage vehicles.

[0092] Specifically, this mutation operator is similar to the single-point mutation operator. Directionally select the mobile energy storage vehicle number with the worst fitness and select the task number with the worst fitness among them. However, the mutated value is random. Randomly select a mobile energy storage vehicle with the same initial charging center or other mobile energy storage vehicles.

[0093] S35. Select elite individuals from the initial population, the cross population, and the mutant population according to the elite population ratio in the initial parameters and add them to the new population;

[0094] Specifically, sort the initial population, the cross population, and the mutant population together according to fitness, and start selecting elite individuals with the elite population ratio from the individual with the best fitness and add them to the new population.

[0095] S36. Randomly select several individuals from the initial population, the cross population, and the mutant population and add them to the new population;

[0096] Specifically, the remaining individuals in the new population are randomly selected from the initial population, the cross population, and the mutant population. This can not only retain certain excellent individuals but also enrich the diversity of the population.

[0097] S37. Take the new population as the initial population for the next round, and sequentially execute the self-crossing operator and the mutation operator to iteratively generate a new population for the next round until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual.

[0098] Specifically, take the new population as the initial population for the next round of iteration, and loop through steps S33 - S37 with the loop variable t = t + 1 to iteratively generate a new population for the next round until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual.

[0099] S38. Decode the optimal individual to obtain the path planning scheme for the mobile energy storage vehicle.

[0100] In a possible embodiment, a comparison example between the present invention and the traditional genetic algorithm is provided as follows:

[0101] The first example has 50 task nodes, that is, 50 unmanned equipment. The second example has 100 task nodes.

[0102]

[0103]

[0104] Table 1 Comparison results between the present invention and the traditional genetic algorithm

[0105] From the results in Table 1, it can be seen that the present invention is superior to the traditional genetic algorithm in terms of the quality of the optimal solution, convergence speed, and stability, but the running time is slightly longer than that of the traditional algorithm.

[0106] In summary, the present invention constructs the path planning problem of the mobile energy storage vehicle as a two-stage mathematical programming model; according to the decision variables of the first stage and the second stage, the constraint conditions of the first stage and the second stage are respectively set; the two-stage mathematical programming model is solved by an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle. The steps of the solution are as follows: the chromosome population is initialized through chromosome coding to obtain an initial population; the parameters of the evolutionary algorithm are initially set to obtain initial parameters; the fitness of the initial population is calculated by an improved 2-opt operator to obtain an initial fitness; starting from the first chromosome in the initial population, a self-crossing operator is executed to generate a crossed population; starting from the first chromosome in the initial population, a mutation operator is executed to generate a mutated population; elite individuals are selected from the initial population, the crossed population and the mutated population according to the elite population ratio in the initial parameters and added to a new population; several individuals are randomly selected from the initial population, the crossed population and the mutated population and added to the new population; the new population is used as the next-round initial population, and the self-crossing operator and the mutation operator are sequentially executed to iteratively generate the next-round new population until the number of iterations reaches the maximum number of iterations in the initial parameters, the iteration is completed, and the optimal individual is output; the optimal individual is decoded to obtain the path planning scheme of the mobile energy storage vehicle. The present invention is more suitable for the path planning problem of the mobile energy storage vehicle for unmanned equipment. The operators designed in the algorithm are more suitable for the characteristics of this problem: open, multiple charging centers, with time window constraints and considering material loss. Among them, the crossing operator is different from the individual-to-individual crossing of the traditional genetic algorithm, and a crossing of gene segments that is more suitable for the structure of the problem solution is selected, which makes the evolution of the population more efficient. The present invention effectively improves the path planning efficiency and rationality, enhances the energy replenishment efficiency, and provides support for the full use of future unmanned equipment.

[0107] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario, and multiple devices cooperate with each other to complete it. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will interact with each other to complete the method.

[0108] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the above embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] Embodiment 2

[0110] Referring to Figure 3 , Embodiment 2 of the present invention further provides a path planning device for a mobile energy storage vehicle for unmanned equipment, including:

[0111] A two-stage mathematical programming model construction module 001 for constructing the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model;

[0112] A constraint condition setting module 002 for setting the first-stage constraint conditions and the second-stage constraint conditions respectively according to the decision variables of the first stage and the second stage;

[0113] A two-stage mathematical programming model solving module 003 for solving the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

[0114] In this embodiment, in the two-stage mathematical programming model construction module 001, the objective function expression of the two-stage mathematical programming model is:

[0115]

[0116] In the formula, K is the number of mobile energy storage vehicles; n k is the number of tasks that the kth mobile energy storage vehicle needs to execute; is the time for the kth mobile energy storage vehicle to complete the ith task; is the ith task completed by the kth mobile energy storage vehicle; is the lower edge of the time window of the ith task.

[0117] In this embodiment, in the constraint condition setting module 002, the first-stage constraint conditions are:

[0118]

[0119]

[0120] In the formula, x ijk and y jk are 0-1 decision variables; xijk For the k-th mobile energy storage vehicle to execute the j-th task after completing the i-th task; y jk For the j-th task to be executed by the k-th mobile energy storage vehicle;

[0121] The second-stage constraint conditions are as follows:

[0122]

[0123]

[0124] In the formula, E i is the energy required for the i-th task; l i is the upper edge of the time window of the i-th task; is the initial location of the k-th mobile energy storage vehicle; p k is the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; d ij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are the time and energy when the k-th mobile energy storage vehicle enters its i-th task node respectively; and are the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node respectively; is the waiting time for the k-th mobile energy storage vehicle to enter its i-th task; is the number of times the k-th mobile energy storage vehicle needs to return to the charging center when executing its i-th task.

[0125] In this embodiment, in the two-stage mathematical programming model solving module 003, the sub-module for solving the two-stage mathematical programming model through the evolutionary algorithm includes:

[0126] The population initialization sub-module 031 is used to initialize the chromosome population through chromosome coding to obtain an initial population; and initialize the parameters of the evolutionary algorithm to obtain initial parameters;

[0127] The initial fitness calculation sub-module 032 is used to calculate the fitness of the initial population through an improved 2-opt operator to obtain the initial fitness;

[0128] The cross-population generation sub-module 033 is used to start from the first chromosome in the initial population, execute the self-cross operator to generate a cross population;

[0129] The mutant population generation sub-module 034 is used to start from the first chromosome in the initial population, execute the mutation operator, and generate a mutant population;

[0130] The elite individual selection sub-module 035 is used to select elite individuals from the initial population, the crossover population, and the mutant population according to the elite population ratio in the initial parameters, and add them to the new population;

[0131] The new population supplementation sub-module 036 is used to randomly select several individuals from the initial population, the crossover population, and the mutant population, and add them to the new population;

[0132] The new population iterative generation sub-module 037 is used to use the new population as the next-round initial population, sequentially execute the self-crossover operator and the mutation operator, iteratively generate the next-round new population until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual;

[0133] The path planning scheme acquisition sub-module 038 is used to decode the optimal individual to obtain the path planning scheme of the mobile energy storage vehicle.

[0134] In this embodiment, in the initial fitness calculation sub-module 032 of the two-stage mathematical programming model solving module 003, during the process of calculating the fitness of the initial population through the improved 2-opt operator, the chromosome is decoded into the tasks that each energy storage vehicle needs to execute; the best task execution order and the corresponding fitness of each mobile energy storage vehicle are calculated through the improved 2-opt operator; the fitness of each mobile energy storage vehicle is summed to obtain the overall fitness of the chromosome.

[0135] It should be noted that the information interaction, execution process, etc. among the above system modules, due to being based on the same concept as the method embodiment in Embodiment 1 of the present application, the technical effects brought by them are the same as those of the method embodiment of the present application. The specific content can be seen in the description of the method embodiment shown in the foregoing of the present application, and will not be elaborated here.

[0136] Embodiment 3

[0137] The embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code of a path planning method for a mobile energy storage vehicle for unmanned equipment is stored, and the program code includes instructions for executing a path planning method for a mobile energy storage vehicle for unmanned equipment according to Embodiment 1 or any possible implementation manner thereof.

[0138] A computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that incorporates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0139] Embodiment 4

[0140] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0141] The processor and the memory communicate with each other via a bus; the memory stores program instructions executable by the processor, and the processor can execute a path planning method for a mobile energy storage vehicle for unmanned equipment according to Embodiment 1 or any possible implementation manner thereof by invoking the program instructions.

[0142] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor, which is implemented by reading software code stored in the memory. The memory can be integrated in the processor or can exist independently outside the processor.

[0143] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center to another website, computer, server, or data center by wire (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.).

[0144] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing system. They can be centralized on a single computing system or distributed on a network composed of multiple computing systems. Optionally, they can be implemented by program codes executable by the computing system. Thus, they can be stored in the storage system and executed by the computing system. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0145] Although the present invention has been described in detail with general descriptions and specific embodiments above, based on the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of the present invention claimed.

Claims

1. A path planning method for a mobile energy storage vehicle for unmanned equipment, characterized in that, Including: Construct the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model; According to the decision variables of the first stage and the second stage, set the first stage constraint conditions and the second stage constraint conditions respectively; Solve the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

2. The path planning method for a mobile energy storage vehicle for unmanned equipment according to claim 1, wherein The objective function expression of the two-stage mathematical programming model is: Where K is the number of mobile energy storage vehicles; n k is the number of tasks to be performed by the k-th mobile energy storage vehicle; is the time for the k-th mobile energy storage vehicle to complete the i-th task; is the i-th task completed by the k-th mobile energy storage vehicle; L ti(k) is the lower edge of the time window for the i-th task.

3. The path planning method of a mobile energy storage vehicle for unmanned equipment according to claim 2, characterized in that The first stage constraint conditions are: where x ijk and y jk are 0-1 decision variables; x ijk represents that the k-th mobile energy storage vehicle executes the j-th task after completing the i-th task; y jk represents that the j-th task is executed by the k-th mobile energy storage vehicle; The second stage constraint conditions are: where E i is the energy required for the i-th task; l i is the upper bound of the time window for the i-th task; is the initial location of the k-th mobile energy storage vehicle; p k is the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; d ij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are the time and energy when the k-th mobile energy storage vehicle enters its i-th task node, respectively; and are the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node, respectively; is the waiting time when the k-th mobile energy storage vehicle enters its i-th task; is the number of times the k-th mobile energy storage vehicle needs to return to the charging center when performing its i-th task.

4. The path planning method for a mobile energy storage vehicle for unmanned equipment according to claim 3, characterized in that, The steps of solving the two-stage mathematical programming model through the evolutionary algorithm are: Initialize the chromosome population through chromosome coding to obtain the initial population; initialize the parameters of the evolutionary algorithm to obtain the initial parameters; Calculate the fitness of the initial population through the improved 2-opt operator to obtain the initial fitness; Starting from the first chromosome in the initial population, execute the self-cross operator to generate a cross population; Starting from the first chromosome in the initial population, execute the mutation operator to generate a mutant population; Select elite individuals from the initial population, the cross population and the mutant population according to the elite population ratio in the initial parameters and add them to the new population; Randomly select several individuals from the initial population, the cross population and the mutant population and add them to the new population; Take the new population as the next round of initial population, and sequentially execute the self-cross operator and the mutation operator to iteratively generate the next round of new population until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual; Decode the optimal individual to obtain the path planning scheme of the mobile energy storage vehicle.

5. A path planning method for a mobile energy storage vehicle for unmanned equipment according to claim 4, characterized in that, In the process of calculating the fitness of the initial population through the improved 2-opt operator, decode the chromosome into the tasks that each energy storage vehicle needs to execute; calculate the best task execution order and the corresponding fitness of each mobile energy storage vehicle through the improved 2-opt operator; sum up the fitness of each mobile energy storage vehicle to obtain the overall fitness of the chromosome.

6. A path planning device for a mobile energy storage vehicle for unmanned equipment, adopting a path planning method for a mobile energy storage vehicle for unmanned equipment according to any one of claims 1-5, characterized in that, Including: A two-stage mathematical programming model construction module for constructing the path planning problem of the mobile energy storage vehicle into a two-stage mathematical programming model; A constraint condition setting module for setting the first stage constraint conditions and the second stage constraint conditions respectively according to the decision variables of the first stage and the second stage; A two-stage mathematical programming model solving module for solving the two-stage mathematical programming model through an evolutionary algorithm to obtain the path planning of the mobile energy storage vehicle.

7. The path planning device for a mobile energy storage vehicle for unmanned equipment according to claim 6, characterized in that, In the two-stage mathematical programming model construction module, the objective function expression of the two-stage mathematical programming model is: Where K is the number of mobile energy storage vehicles; n k is the number of tasks to be executed by the k-th mobile energy storage vehicle; is the time for the k-th mobile energy storage vehicle to complete the i-th task; is the i-th task completed by the k-th mobile energy storage vehicle; is the lower edge of the time window for the i-th task.

8. The path planning device for a mobile energy storage vehicle for unmanned equipment according to claim 7, characterized in that, In the constraint condition setting module, the first stage constraint conditions are: where x ijk and y jk are 0-1 decision variables; x ijk means that the k-th mobile energy storage vehicle executes the j-th task after completing the i-th task; y jk means that the j-th task is executed by the k-th mobile energy storage vehicle; The second stage constraint conditions are: Where E i is the energy required for the i-th task; l i is the upper bound of the time window for the i-th task; is the initial location of the k-th mobile energy storage vehicle; p k is the charging center where the k-th mobile energy storage vehicle is initially located; ρ is the power consumption per unit distance of the mobile energy storage vehicle; v is the driving speed of the mobile energy storage vehicle; M is the maximum capacity of the mobile energy storage vehicle; P is the discharge power of the mobile energy storage vehicle; Q is the charging power of the mobile energy storage vehicle; d ij is the distance between the i-th node and the j-th node; b i is the number of the charging center closest to the i-th task node; and are the time and energy when the k-th mobile energy storage vehicle enters its i-th task node, respectively; and are the time and energy when the k-th mobile energy storage vehicle leaves its i-th task node, respectively; is the waiting time when the k-th mobile energy storage vehicle enters its i-th task; is the number of times the k-th mobile energy storage vehicle needs to return to the charging center when performing its i-th task.

9. The path planning device for a mobile energy storage vehicle for unmanned equipment according to claim 8, characterized in that, In the two-stage mathematical programming model solving module, the sub-module for solving the two-stage mathematical programming model through the evolutionary algorithm includes: A population initialization sub-module for initializing the chromosome population through chromosome coding to obtain the initial population; initializing the parameters of the evolutionary algorithm to obtain the initial parameters; The initial fitness calculation sub-module is used to calculate the fitness of the initial population through the improved 2-opt operator to obtain the initial fitness; The cross population generation sub-module is used to start from the first chromosome in the initial population, execute the self-cross operator to generate a cross population; The mutation population generation sub-module is used to start from the first chromosome in the initial population, execute the mutation operator to generate a mutation population; The elite individual selection sub-module is used to select elite individuals from the initial population, the cross population and the mutation population according to the elite population ratio in the initial parameters and add them to the new population; The new population supplement sub-module is used to randomly select several individuals from the initial population, the cross population and the mutation population and add them to the new population; The new population iterative generation sub-module is used to use the new population as the next round of initial population, successively execute the self-cross operator and the mutation operator, iteratively generate the next round of new population until the number of iterations reaches the maximum number of iterations in the initial parameters, complete the iteration, and output the optimal individual; The path planning scheme acquisition sub-module is used to decode the optimal individual to obtain the path planning scheme of the mobile energy storage vehicle.

10. The path planning device for a mobile energy storage vehicle for unmanned equipment according to claim 9, characterized in that, In the initial fitness calculation sub-module of the two-stage mathematical programming model solving module, in the process of calculating the fitness of the initial population through the improved 2-opt operator, the chromosome is decoded into the tasks that each energy storage vehicle needs to execute; the best task execution order and the corresponding fitness of each mobile energy storage vehicle are calculated through the improved 2-opt operator; the fitness of each mobile energy storage vehicle is summed to obtain the overall fitness of the chromosome.

Images