Value prediction method of retired power battery, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a value prediction method of a decommissioned power battery, electronic equipment and a storage medium, and the method comprises the steps: inputting a group of randomly generated decommissioned power battery values into a sub-problem model through first iteration, obtaining the number of decommissioned power batteries and an overall charging and discharging plan according to an upper-layer model, and transmitting the number and the overall charging and discharging plan to a lower-layer decommissioned power battery model; solving to obtain a charging and discharging plan of each decommissioned power battery individual, judging whether the charging and discharging plan meets the constraint of the decommissioned power battery individual or not, determining the number of the decommissioned power batteries as the final number of the decommissioned power batteries of the iteration, and feeding back the final number to the main problem model; and adjusting the value of the retired power batteries by using an adjustment algorithm according to the retailer income, returning the value of a group of retired power batteries with the highest income to the sub-problem model to carry out second iteration, carrying out loop iteration until an equilibrium solution is obtained, and outputting the final quantity of the retired power batteries and the value of the retired power batteries. And the accuracy of value prediction and quantity prediction of the retired power batteries is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of retired battery transaction pricing, and in particular to a value prediction method, electronic device and storage medium for retired power batteries. Background Art

[0002] While promoting economic development, industrial parks have also become major carbon emitters. Emission reduction in industrial parks is the key to achieving carbon neutrality goals. Therefore, industrial parks have broad market prospects for using retired power batteries to achieve low-carbon energy management. However, the accuracy of the prediction of the number of retired power batteries and the prediction of the value of retired power batteries in related technologies needs to be improved. Summary of the invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] The purpose of the present invention is to solve one of the technical problems existing in the related art to at least a certain extent. The embodiments of the present invention provide a value prediction method for retired power batteries, an electronic device and a storage medium, which can obtain a balanced solution for the number of retired power batteries and the value of retired power batteries, thereby improving the accuracy of retailers' predictions on the value of retired power batteries and parks' predictions on the number of retired power batteries.

[0005] An embodiment of the first aspect of the present invention provides a method for predicting the value of a retired power battery, comprising:

[0006] Randomly generate a set of different retired power battery values;

[0007] In a first iteration, a set of different retired power battery values ​​are input into a sub-problem model, wherein the sub-problem model includes an upper model and a lower retired power battery model;

[0008] Obtain the number of retired power batteries and the overall charge and discharge plan according to the upper model, and pass them to the lower retired power battery model;

[0009] Obtaining a charge and discharge plan for each individual retired power battery according to the lower retired power battery model;

[0010] Determine whether the charge and discharge plan of each retired power battery individual satisfies the constraints corresponding to each retired power battery individual; if so, determine the number of retired power batteries as the final number of retired power batteries of this iteration, and obtain a set of the final number of retired power batteries of this iteration; otherwise, re-solve the upper model until the final number of retired power batteries of this iteration is determined;

[0011] Feeding back the final number of retired power batteries of the group in this iteration to the main problem model;

[0012] The main problem model solves the retailer profit according to the final number of retired power batteries and the retired power battery value, adjusts the retired power battery value according to the retailer profit using an adjustment algorithm, takes a group of retired power battery values ​​with the highest corresponding profit as a different group of retired power battery values ​​for the next iteration, and returns the group to the sub-problem model for a second iteration;

[0013] The loop is iterated until a balanced solution is obtained, and the final number of retired power batteries and the value of the retired power batteries are output.

[0014] According to certain embodiments of the first aspect of the present invention, obtaining the number of retired power batteries and the overall charge and discharge plan according to the upper model includes:

[0015] The upper model is solved using a column and constraint generation algorithm in a two-stage robust optimization method;

[0016] The first stage is a mixed integer programming model, which uses the master problem MP to solve and obtain energy management plans for different scenarios;

[0017] The second stage is a two-level optimization model, which uses the dual sub-problem SP to determine whether the current energy management plan is the energy management plan for the worst scenario, and obtains the energy management plan for the worst scenario;

[0018] The number of retired power batteries and the overall charge and discharge plan are determined according to the energy management plan for the worst scenario.

[0019] According to some embodiments of the first aspect of the present invention, the main problem MP is:

[0020] min x Ax+ψ

[0021]

[0022] Where A, B, F, f, G, g, U, V, C, and D are the parameter matrices of the actual model, x is the output plan of the non-renewable energy output units and retired power batteries, y is the specific output of the non-renewable energy output units and retired power batteries, and μ is an uncertainty variable;

[0023] The dual subproblem SP is:

[0024]

[0025] According to certain embodiments of the first aspect of the present invention, obtaining a charge and discharge plan for each individual retired power battery according to the lower retired power battery model includes:

[0026] Group the retired power batteries and determine the number of retired power batteries in each retired power battery group;

[0027] Determine a charge and discharge plan for each retired power battery pack according to the overall charge and discharge plan transmitted by the upper model;

[0028] According to the charge and discharge plan of each of the retired power battery groups, the charge and discharge plan of each of the retired power batteries is determined.

[0029] According to certain embodiments of the first aspect of the present invention, grouping the retired power batteries comprises:

[0030] Retired power batteries are grouped according to their individual parameters.

[0031] According to some embodiments of the first aspect of the present invention, the main problem model is:

[0032] D = (ac)S;

[0033] In the formula, D is the retailer's revenue, a is the value of retired power batteries, S is the number of retired power batteries, and c is the recycling cost per unit of retired power batteries, which is a known parameter.

[0034] According to some embodiments of the first aspect of the present invention, the adjustment algorithm is a genetic algorithm or a particle swarm algorithm.

[0035] An embodiment of the second aspect of the present invention is an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the value prediction method of retired power batteries as described above.

[0036] An embodiment of the third aspect of the present invention is a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the value prediction method of a retired power battery as described above is implemented.

[0037] The above scheme has at least the following beneficial effects: a set of randomly generated retired power battery values ​​is input into the sub-problem model including the upper model and the lower retired power battery model to start the first iteration; the number of retired power batteries and the overall charge and discharge plan are obtained according to the upper model, and passed to the lower retired power battery model; the lower retired power battery model calculates the charge and discharge plan of each individual retired power battery; it is determined whether the charge and discharge plan of each individual retired power battery satisfies the constraints corresponding to each individual retired power battery, and if so, the number of retired power batteries is determined as the final number of retired power batteries for this iteration, and a set of final numbers of retired power batteries for this iteration is obtained; otherwise, the upper model is solved again. The sub-problem model is used until the final number of retired power batteries in this iteration is determined; a group of final numbers of retired power batteries in this iteration is fed back to the main problem model; the main problem model solves the retailer's profit according to the final number of retired power batteries and the value of retired power batteries, adjusts the value of retired power batteries according to the retailer's profit using the adjustment algorithm, takes a group of retired power battery values ​​with the highest corresponding profit as a group of different retired power battery values ​​for the next iteration, and returns them to the sub-problem model for the second iteration; iterates repeatedly until an equilibrium solution is obtained, outputs the final number of retired power batteries and the value of retired power batteries, thereby improving the accuracy of retailers' predictions on the value of retired power batteries and the park's predictions on the number of retired power batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0039] The present invention is further described below in conjunction with the accompanying drawings and embodiments;

[0040] Figure 1 An optional flow chart of a method for predicting the value of a retired power battery provided in an embodiment of the present invention;

[0041] Figure 2 The embodiment of the present invention provides Figure 1 An optional flowchart of step 103;

[0042] Figure 3 The embodiment of the present invention provides Figure 1 An optional flowchart of step 104 in FIG. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0044] It should be noted that the terms "first", "second", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0046] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0047] Reference Figure 1 As shown, Figure 1 An optional flow chart of a method for predicting the value of a retired power battery provided in an embodiment of the present invention. The method for predicting the value of a retired power battery includes but is not limited to steps 101 to 108. Each step is introduced in turn below.

[0048] Step S101: randomly generate a group of different retired power battery values.

[0049] Specifically, the value of retired power batteries can be the sales price of retired power batteries. The value range of retired power batteries is determined based on the historical transaction price data of retired power batteries. The number of retired power battery values ​​is set, and within the retired power battery value range, a retired power battery value is randomly generated, and then a second retired power battery value is randomly generated. If repeated, the value is discarded and regenerated until there is no repetition, and the second retired power battery value is obtained. Then, the retired power battery value is randomly generated until the number of retired power battery values ​​set is met, and a group of different retired power battery values ​​is obtained.

[0050] Step S102: In the first iteration, a set of different retired power battery values ​​are input into the sub-problem model.

[0051] Specifically, in the first iteration, a set of different retired power battery values ​​generated randomly are input into the sub-problem model, which includes an upper-level model and a lower-level retired power battery model.

[0052] Step S103: Obtain the number of retired power batteries and the overall charge and discharge plan according to the upper-layer model, and pass them to the lower-layer retired power battery model.

[0053] Specifically, the number of retired power batteries can be the number of retired power batteries purchased by the park. The overall charge and discharge plan can be the overall charge and discharge plan for retired power batteries. When the upper model is established, the number of non-renewable energy output units and renewable energy output units in the park is determined, and the output size, capacity and other constraints of each unit and retired power batteries are determined. Variables such as the one-day output plan of non-renewable energy output units, the one-day output plan of renewable energy output units, the one-day output plan of retired power batteries, and the number of retired power batteries are established. Based on the renewable energy output data of the park in previous years, the output fluctuation range of the renewable energy output units is determined. The one-day output plan of the unit refers to whether the unit is outputting at a certain moment, the output size, etc.

[0054] In this embodiment, the non-renewable energy output unit can be a thermal power unit, a fuel cell, etc., and the renewable energy output unit can be a wind power unit, a photovoltaic power unit, etc. In actual application, the upper model parameters will be different for different parks. For example, for different parks, there will be different numbers of non-renewable energy output units and renewable energy output units; in practice, the park does not necessarily use thermal power units and fuel cells, but other non-renewable energy output units. It can be set according to actual conditions, and this embodiment does not impose specific restrictions on it.

[0055] Reference Figure 2 As shown, Figure 2 The embodiment of the present invention provides Figure 1 An optional flowchart of step 103 in the figure, wherein step 103 includes but is not limited to the following steps 201 to 204.

[0056] Step 201: The upper model is solved using the column and constraint generation algorithm in the two-stage robust optimization method;

[0057] Step 202: The first stage is a mixed integer programming model, which uses the master problem MP to solve and obtain energy management plans for different scenarios;

[0058] Step 203: The second stage is a two-level optimization model, which uses the dual sub-problem SP to determine whether the current energy management plan is the energy management plan for the worst scenario, and obtains the energy management plan for the worst scenario;

[0059] Step 204: Determine the number of retired power batteries and the overall charging and discharging plan based on the energy management plan for the worst-case scenario.

[0060] Specifically, robust optimization is an optimization method to deal with data uncertainty, but single-stage robust optimization is too conservative. Using two-stage robust optimization can reduce conservatism and improve robustness. The principle of the column and constraint generation algorithm is to divide the two-stage robust optimization into a main problem and a sub-problem. In the main problem, the influence of uncertain variables is first ignored and solved as a deterministic optimization. On the basis of the deterministic optimization solution, relatively harsh scenarios and corresponding sub-problem decision variables and constraints are continuously added to continuously improve the upper and lower bounds of the objective function until the algorithm converges, thereby ensuring the robustness of the final solution.

[0061] Specifically, the energy management plans for different scenarios can be output plans for non-renewable energy output units and retired power batteries when the output fluctuations of renewable energy output units are different. The specific outputs of non-renewable energy output units and retired power batteries are obtained according to the output plans of non-renewable energy output units and retired power batteries. The output fluctuation range of renewable energy output units is determined based on the renewable energy output data of the park in previous years, and the output fluctuation of renewable energy output units is limited within the output fluctuation range.

[0062] Specifically, photovoltaic power generation and wind power generation cannot be determined artificially, so the output of wind turbines and photovoltaic generators will fluctuate randomly. The worst scenario refers to the situation where the output fluctuation of renewable energy output units is the largest, or it can be the situation where the output fluctuation of wind turbines and photovoltaic generators is the largest. The energy management plan for the worst scenario can be the output plan of non-renewable energy output units and retired power batteries when the output fluctuation of renewable energy output units is the largest, where the number of retired power batteries participating in the scheduling should minimize the cost. The upper model is solved using the column and constraint generation algorithm in the two-stage robust optimization method, and finally the output plan of thermal power units, fuel cells and retired power batteries is obtained when the output fluctuation of wind turbines and photovoltaic generators is the largest, where the number of retired power batteries participating in the scheduling should minimize the cost. According to the energy management plan for the worst scenario, the number of retired power batteries purchased by the park and the overall charging and discharging plan of retired power batteries are determined.

[0063] In some embodiments, the main question MP is:

[0064] min x Ax+ψ

[0065]

[0066] Where A, B, F, f, G, g, U, V, C, and D are the parameter matrices of the actual model, x is the output plan of non-renewable energy output units and retired power batteries, y is the specific output of non-renewable energy output units and retired power batteries, and μ is an uncertainty variable.

[0067] The dual subproblem SP is:

[0068]

[0069] Specifically, in the main problem MP, the uncertainty variable is the output of renewable energy with uncertainty due to the influence of climate conditions. Uncertain variables can be photovoltaic power generation and wind power generation affected by climate conditions. The upper model is a two-stage robust optimization model, which is solved using the column and constraint generation algorithm in the two-stage robust optimization method, and is divided into a main problem and sub-problems. The first stage is a mixed integer programming model. In the first stage, the main problem MP is used to solve the output plan x of the corresponding thermal power unit, fuel cell and retired power battery under different output fluctuations of wind power units and photovoltaic power units. According to the output plan x of the thermal power unit, fuel cell and retired power battery, the specific output y of the thermal power unit, fuel cell and retired power battery is obtained.

[0070] Specifically, the second stage is a two-layer optimization model. The subproblem is a max-min two-layer optimization problem. The inner min problem is transformed into a max problem through duality, and the dual subproblem SP is used to solve it. Each output plan x has a corresponding specific output y. When the output fluctuation of wind turbines and photovoltaic generators is the largest, the specific output y of thermal power units, fuel cells and retired power batteries should minimize the cost. Finally, the output plan of thermal power units, fuel cells and retired power batteries is solved when the output fluctuation of wind turbines and photovoltaic generators is the largest. According to the output plan of retired power batteries, the number of retired power batteries and the overall charge and discharge plan are obtained. The number of retired power batteries is the number of retired power batteries purchased by the park, and the overall charge and discharge plan is the overall charge and discharge plan of retired power batteries.

[0071] Specifically, the output fluctuation range of wind turbines and photovoltaic generators is determined based on the output data of wind turbines and photovoltaic generators in previous years. When solving the upper model, the output fluctuation of wind turbines and photovoltaic generators is limited to the output fluctuation range.

[0072] Step S104: obtaining a charge and discharge plan for each individual retired power battery according to the lower retired power battery model.

[0073] Specifically, when the lower-level retired power battery model is established, variables such as the number of retired power batteries and the number of retired power battery groups are set, and the output size, capacity and other constraints of retired power battery groups and retired power battery individuals are determined. When formulating the objective function, the goal is to minimize the sum of the fluctuation ranges of retired power batteries, so as to reduce the loss of retired power batteries and extend the service life of retired power batteries.

[0074] Reference Figure 3 As shown, Figure 3 The embodiment of the present invention provides Figure 1 An optional flowchart of step 104 in the figure, wherein step 104 includes but is not limited to the following steps 301 to 303.

[0075] Step 301: grouping the retired power batteries and determining the number of retired power batteries in each retired power battery group;

[0076] Step 302: Determine a charge and discharge plan for each retired power battery pack according to the overall charge and discharge plan transmitted by the upper model;

[0077] Step 303: Determine the charge and discharge plan of each retired power battery according to the charge and discharge plan of each retired power battery group.

[0078] Specifically, the overall charge and discharge plan transmitted by the upper model is the overall charge and discharge plan of the retired power batteries. All retired power batteries constitute the retired power battery aggregation layer PBA in the upper model. In the lower retired power battery model, the retired power battery aggregation layer PBA is divided into the first layer, which is the retired power battery group layer, and the second layer is the retired power battery individual layer. Each layer is a mixed integer linear programming problem, which can be solved using the cplex solver. The lower retired power battery model is solved in layers to avoid the dimensional disaster caused by bringing massive retired power batteries into the lower retired power battery model and improve computing efficiency.

[0079] In some embodiments, grouping retired power batteries includes: grouping according to the parameters of individual retired power batteries. For example, retired power batteries with the same capacity, maximum output, and minimum output can be grouped together to ensure the consistency of model constraints. After grouping according to the parameters of individual retired power batteries, the number of retired power batteries in each retired power battery group is determined, and the number of retired power battery groups is determined. After grouping the retired power batteries, the charge and discharge plan of each retired power battery group is determined according to the overall charge and discharge plan of the retired power batteries transmitted by the upper model. According to the charge and discharge plan of each retired power battery group, the charge and discharge plan of each individual retired power battery is determined.

[0080] Step S105: Determine whether the charge and discharge plan of each retired power battery individual satisfies the constraints corresponding to each retired power battery individual. If so, determine the number of retired power batteries as the final number of retired power batteries for this iteration, and obtain a set of final numbers of retired power batteries for this iteration; otherwise, re-solve the upper model until the final number of retired power batteries for this iteration is determined.

[0081] Specifically, the constraints corresponding to the retired power battery individuals may be the output size, capacity and other constraints of the retired power battery individuals. It is determined whether the charge and discharge plan of each retired power battery individual meets the output size, capacity and other constraints of each retired power battery individual. If so, the number of retired power batteries is determined as the final number of retired power batteries for this iteration, and a set of final number of retired power batteries for this iteration is obtained; otherwise, the upper model is solved again until the final number of retired power batteries for this iteration is determined.

[0082] Step S106: Feedback a set of final retired power battery quantities of this iteration to the main problem model.

[0083] In some embodiments, the main problem model is:

[0084] D = (ac)S;

[0085] In the formula, D is the retailer's revenue, a is the value of retired power batteries, S is the number of retired power batteries, and c is the recycling cost per unit of retired power batteries, which is a known parameter.

[0086] Specifically, the value of retired power batteries can be the selling price of retired power batteries set by retailers, and the retailer's profit can be calculated based on the number of retired power batteries, the recycling cost per unit of retired power batteries and the selling price of retired power batteries.

[0087] Step S107: The main problem model solves the retailer's profit based on the final number of retired power batteries and the value of retired power batteries, adjusts the value of retired power batteries using an adjustment algorithm based on the retailer's profit, takes a group of retired power battery values ​​with the highest corresponding profit as a different group of retired power battery values ​​for the next iteration, and returns it to the sub-problem model for a second iteration.

[0088] Specifically, the main problem model solves the retailer's profit based on the final number of retired power batteries, the recycling cost per unit of retired power batteries, and the value of retired power batteries. In some embodiments, the adjustment algorithm can use a genetic algorithm or a particle swarm algorithm to improve the solving efficiency. The retired power battery value is adjusted using a genetic algorithm or a particle swarm algorithm according to the retailer's profit, and a group of retired power battery values ​​with the highest corresponding profit is taken as a group of different retired power battery values ​​for the next iteration, and returned to the sub-problem model for the second iteration.

[0089] Step S108: loop iterate until a balanced solution is obtained, and output the final number of retired power batteries and the value of retired power batteries.

[0090] Specifically, as the number of iterations increases, the number of retired power battery values ​​in a group of retired power battery values ​​will decrease, and the number of retired power battery quantities in a corresponding group of retired power battery quantities will also decrease until a balanced solution is obtained, and a final number of retired power batteries and a corresponding retired power battery value are output. The iteration is repeated until a balanced solution is obtained, and the final number of retired power batteries and the value of retired power batteries are output, which improves the accuracy of retailers' predictions of retired power battery values ​​and parks' predictions of retired power battery quantities.

[0091] In one possible implementation, a method for predicting the value of retired power batteries in an embodiment of the present invention is configured in a main control unit of a battery automatic trading machine. A plurality of retired power batteries are stored in the battery automatic trading machine. After outputting the number of retired power batteries and the value of retired power batteries, the output number of retired power batteries and the value of retired power batteries can be transmitted to a battery conveying device of the battery automatic trading machine. The battery conveying device can convey a corresponding number of retired power batteries based on the number of retired power batteries, and configure a corresponding retired power battery selling price based on the value of the retired power batteries, thereby realizing a quick transaction.

[0092] It can be seen that the first iteration starts by inputting a set of randomly generated retired power battery values ​​into the sub-problem model including the upper model and the lower retired power battery model; the number of retired power batteries and the overall charge and discharge plan are obtained according to the upper model and passed to the lower retired power battery model; the lower retired power battery model calculates the charge and discharge plan of each individual retired power battery; it is judged whether the charge and discharge plan of each individual retired power battery satisfies the constraints corresponding to each individual retired power battery; if so, the number of retired power batteries is determined as the final number of retired power batteries for this iteration, and a set of final numbers of retired power batteries for this iteration is obtained; otherwise, the upper model is solved again until it is confirmed. Determine the final number of retired power batteries in this iteration; feed back a group of final numbers of retired power batteries in this iteration to the main problem model; the main problem model solves the retailer's profit based on the final number of retired power batteries and the value of retired power batteries, adjusts the value of retired power batteries using an adjustment algorithm based on the retailer's profit, takes a group of retired power battery values ​​with the highest corresponding profit as a group of different retired power battery values ​​for the next iteration, and returns them to the sub-problem model for a second iteration; iterates repeatedly until an equilibrium solution is obtained, outputs the final number of retired power batteries and the value of retired power batteries, thereby improving the accuracy of retailers' predictions on the value of retired power batteries and the park's predictions on the number of retired power batteries.

[0093] The embodiment of the present invention further provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned method for predicting the value of retired power batteries when executing the computer program. The electronic device can be any intelligent terminal including a computer.

[0094] An embodiment of the present invention further provides a storage medium storing a computer program, which implements the above-mentioned method for predicting the value of retired power batteries when executed by a processor.

[0095] The terms "first", "second", "third", "fourth", etc. (if any) in the description of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate to describe embodiments of the present invention, such as being able to be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0096] It should be understood that in the present invention, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0097] It should be understood that in the description of the embodiments of the present invention, the meaning of multiple (or multiple items) is more than two, greater than, less than, exceed, etc. are understood to exclude the number, and above, below, within, etc. are understood to include the number.

[0098] It should also be understood that the various implementations provided in the embodiments of the present invention can be combined arbitrarily to achieve different technical effects.

[0099] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for predicting the value of retired power batteries, characterized in that: include: Randomly generate a set of different retired power battery values; In a first iteration, a set of different retired power battery values ​​are input into a sub-problem model, wherein the sub-problem model includes an upper model and a lower retired power battery model; Obtain the number of retired power batteries and the overall charge and discharge plan according to the upper model, and pass them to the lower retired power battery model; Obtaining a charge and discharge plan for each individual retired power battery according to the lower retired power battery model; Determine whether the charge and discharge plan of each retired power battery individual satisfies the constraints corresponding to each retired power battery individual; if so, determine the number of retired power batteries as the final number of retired power batteries of this iteration, and obtain a set of the final number of retired power batteries of this iteration; otherwise, re-solve the upper model until the final number of retired power batteries of this iteration is determined; Feeding back the final number of retired power batteries of the group in this iteration to the main problem model; The main problem model solves the retailer profit according to the final number of retired power batteries and the retired power battery value, adjusts the retired power battery value according to the retailer profit using an adjustment algorithm, takes a group of retired power battery values ​​with the highest corresponding profit as a different group of retired power battery values ​​for the next iteration, and returns the group to the sub-problem model for a second iteration; The loop is iterated until a balanced solution is obtained, and the final number of retired power batteries and the value of the retired power batteries are output.

2. The method for predicting the value of retired power batteries according to claim 1, characterized in that: The obtaining of the number of retired power batteries and the overall charge and discharge plan according to the upper model includes: The upper model is solved using a column and constraint generation algorithm in a two-stage robust optimization method; The first stage is a mixed integer programming model, which uses the master problem MP to solve and obtain energy management plans for different scenarios; The second stage is a two-level optimization model, which uses the dual sub-problem SP to determine whether the current energy management plan is the energy management plan for the worst scenario, and obtains the energy management plan for the worst scenario; The number of retired power batteries and the overall charge and discharge plan are determined according to the energy management plan for the worst scenario.

3. The method for predicting the value of retired power batteries according to claim 2, characterized in that: The main problem MP is: minutes x Ax+ψ Where A, B, F, f, G, g, U, V, C, and D are the parameter matrices of the actual model, x is the output plan of the non-renewable energy output units and retired power batteries, y is the specific output of the non-renewable energy output units and retired power batteries, and μ is an uncertainty variable; The dual subproblem SP is:

4. The method for predicting the value of retired power batteries according to claim 1, characterized in that: The obtaining of a charge and discharge plan for each individual retired power battery according to the lower retired power battery model includes: Group the retired power batteries and determine the number of retired power batteries in each retired power battery group; Determine a charge and discharge plan for each retired power battery pack according to the overall charge and discharge plan transmitted by the upper model; According to the charge and discharge plan of each of the retired power battery groups, the charge and discharge plan of each of the retired power batteries is determined.

5. The method for predicting the value of retired power batteries according to claim 4, characterized in that: The grouping of retired power batteries includes: Retired power batteries are grouped according to their individual parameters.

6. The method for predicting the value of retired power batteries according to claim 1, characterized in that: The main problem model is: D = (ac)S; In the formula, D is the retailer's revenue, a is the value of retired power batteries, S is the number of retired power batteries, and c is the recycling cost per unit of retired power batteries, which is a known parameter.

7. The method for predicting the value of retired power batteries according to claim 1, characterized in that: The adjustment algorithm is a genetic algorithm or a particle swarm algorithm.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the value prediction method of a retired power battery as described in any one of claims 1 to 7 when executing the computer program.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a value prediction method for retired power batteries according to any one of claims 1 to 7 is implemented.

Images