Strategy determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a strategy determination method and device, electronic equipment and a storage medium. According to the specific implementation scheme, the method comprises the steps of determining a power van cluster and power van data corresponding to the power van cluster; obtaining a dual-objective optimization model based on the power supply vehicle data, and solving the dual-objective optimization model to obtain a scheduling alternative strategy set; and in response to a selection operation of a scheduling preference selection page, selecting a candidate scheduling strategy meeting a set condition from the scheduling alternative strategy set as an execution scheduling strategy. The problem that response is not timely due to existing deterministic scheduling management is solved, selectivity of scheduling strategy execution is achieved, scheduling of the power van cluster can meet scheduling requirements in various environments, and stability and reliability of operation of the power van cluster are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart grid, and particularly relates to a strategy determination method and device, electronic equipment and a storage medium. BACKGROUND

[0002] With the wide deployment of renewable energy and the accelerated construction of new power systems, power supply vehicles, as a flexible and mobile energy storage unit, are gradually becoming an important resource to support power grid operation and emergency power supply.

[0003] In recent years, the trend of cluster application of power supply vehicles is becoming more and more obvious, and it shows strong controllability and system adaptability in load regulation, standby power supplement and emergency scenarios. With the continuous promotion of distributed energy access, microgrid construction and intelligent power distribution network management, an urgent need exists for a power supply vehicle scheduling method to support the grid-connected scheduling management of power supply vehicles. Traditional energy management systems rely on deterministic scheduling management, rely on static parameters and rule-driven power distribution and access determination. Deterministic scheduling management often has problems such as lack of scheduling flexibility and delayed response, which is difficult to meet the scheduling needs in various environments and affects the stability of power supply vehicle cluster operation. SUMMARY

[0004] The present application provides a strategy determination method, device, electronic equipment and storage medium to realize real-time determination of the scheduling management of a power supply vehicle cluster, and improves the stability and reliability of the power supply vehicle cluster operation.

[0005] According to an aspect of the present application, a strategy determination method is provided, comprising:

[0006] determining a power supply vehicle cluster and power supply vehicle data corresponding to the power supply vehicle cluster, the power supply vehicle cluster including at least one power supply vehicle, and the power supply vehicle data including the state of each power supply vehicle;

[0007] obtaining a double-objective optimization model based on the power supply vehicle data, and solving the double-objective optimization model to obtain a scheduling candidate strategy set, the scheduling candidate strategy set including at least one candidate scheduling strategy, and the candidate scheduling strategy including a candidate scheduling strategy of the power supply vehicle cluster;

[0008] in response to a selection operation of a scheduling preference selection page, selecting a candidate scheduling strategy that meets a set condition from the scheduling candidate strategy set as an execution scheduling strategy, the scheduling preference selection page including a page for selecting a scheduling preference corresponding to the scheduling candidate strategy set, and the execution scheduling strategy including a scheduling strategy of the power supply vehicle cluster when the power supply vehicle cluster is scheduled.

[0009] According to another aspect of the present application, there is provided a strategy determination apparatus comprising:

[0010] a determination module configured to determine a power car cluster and power car data corresponding to the power car cluster, the power car cluster comprising at least one power car, the power car data comprising states of the power cars;

[0011] a solution module configured to obtain a double-objective optimization model based on the power car data, and solve the double-objective optimization model to obtain a set of candidate scheduling strategies, the set of candidate scheduling strategies comprising at least one candidate scheduling strategy, the candidate scheduling strategy comprising a candidate scheduling strategy of the power car cluster;

[0012] a selection module configured to select, in response to a selection operation of a scheduling preference selection page, a candidate scheduling strategy satisfying a set condition from the set of candidate scheduling strategies as an execution scheduling strategy, the scheduling preference selection page comprising a page for selecting a scheduling preference corresponding to the set of candidate scheduling strategies, the execution scheduling strategy comprising a scheduling strategy of the power car cluster when scheduling the power car cluster.

[0013] According to another aspect of the present application, there is provided an electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein

[0016] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the strategy determination method according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the strategy determination method according to any one of the embodiments of the present application when executed by the processor.

[0018] The technical scheme of the embodiment of the present application determines a power supply vehicle cluster and power supply vehicle data corresponding to the power supply vehicle cluster; obtains a double-target optimization model based on the power supply vehicle data, and solves the double-target optimization model to obtain a scheduling candidate strategy set; and in response to a selection operation of a scheduling preference selection page, selects a candidate scheduling strategy meeting a set condition from the scheduling candidate strategy set as an execution scheduling strategy. The scheduling candidate strategy set for the power supply vehicle cluster is obtained through the double-target optimization model, thereby solving the problem of untimely response caused by the existing deterministic scheduling management. The candidate scheduling strategy meeting the set condition is selected from the scheduling candidate strategy set according to the selection operation of the scheduling preference selection page, thereby realizing the selectability of the execution scheduling strategy, enabling the scheduling of the power supply vehicle cluster to meet the scheduling demand in various environments, and improving the stability and reliability of the operation of the power supply vehicle cluster.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0021] Figure 1 is a flow chart of a strategy determination method according to the first embodiment of the present application;

[0022] Figure 2 is a flow chart of a strategy selection method according to the second embodiment of the present application;

[0023] Figure 3 is a structural schematic diagram of a strategy determination device according to the third embodiment of the present application;

[0024] Figure 4 is a block diagram of an electronic device according to the fourth embodiment of the present application. DETAILED DESCRIPTION

[0025] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort should belong to the scope of the present application.

[0026] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a list of steps or units need not be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products or devices.

[0027] Embodiment one

[0028] Figure 1 is a flowchart of a strategy determination method according to the embodiment one of the present application. The embodiment can be applicable to the case of determining a scheduling strategy. The method can be performed by a strategy determination device, which can be realized in the form of hardware and / or software. The strategy determination device can be configured in an electronic device, which can include a scheduling control system, etc. As shown in Figure 1 the method includes:

[0029] S110, determining a power car cluster, and power car data corresponding to the power car cluster.

[0030] The power car cluster includes at least one power car, and the power car data includes the state of each power car.

[0031] In the embodiment, the power car can be understood as a vehicle with a power supply device, which can provide mobile power supply for electrical equipment. The power car cluster can be understood as a set composed of at least one power car, which can be responsible for the mobile power supply of a region. The power car data can be understood as the state of each power car in the power car cluster, which can include the number of each power car in the power car cluster, the state of charge, the boundary of charging or discharging capacity, and the data of the power grid where each power car is located, etc.

[0032] Specifically, for a power car cluster in a power grid, data related to the state of each power car in the power car cluster can be collected and placed in a data set. Then, data cleaning and abnormality processing can be performed on the data in the data set. Methods such as median interpolation, moving average, and 3σ rule can be used to clean and process missing values, mutation points, or non-physical abnormal data that occur in the collection process. Finally, the data after data cleaning and abnormality processing is normalized, and the power car data is obtained.

[0033] For example, the normalization method can be implemented by the following formula:

[0034]

[0035] where x o is the data after data cleaning and abnormality processing, μ is the mean of the data set, and σ is the standard deviation of the data set.

[0036] S120, based on the power car data, a double-objective optimization model is obtained, and the double-objective optimization model is solved to obtain a scheduling candidate strategy set.

[0037] The scheduling candidate strategy set includes at least one candidate scheduling strategy, and the candidate scheduling strategy includes a candidate scheduling strategy of the power car cluster.

[0038] In this embodiment, the double-objective optimization model can be understood as an optimization model related to scheduling consumption and robustness when scheduling power cars in the power car cluster. Scheduling consumption can be understood as the consumption when scheduling power cars in the power car cluster. The scheduling candidate strategy set can be understood as a set for storing candidate scheduling strategies, which can be iteratively output by the double-objective optimization model. The candidate scheduling strategy can be understood as a scheduling strategy available for the power car cluster.

[0039] Specifically, a double-objective optimization model with scheduling consumption and robustness as optimization objectives is constructed based on the data related to the operating state of each power car in the power car data and the data of the power grid where the power car cluster is located. The optimization objectives can be a scheduling consumption minimization objective and a robustness maximization objective. The constraints corresponding to the double-objective optimization model are determined based on the boundary values related to the state of each power car included in the power car data. The double-objective optimization model is solved based on the constraints corresponding to the double-objective optimization model, and the scheduling candidate strategy set is output.

[0040] S130, in response to a selection operation of the scheduling preference selection page, a candidate scheduling strategy that meets a set condition is selected from the scheduling candidate strategy set as an execution scheduling strategy.

[0041] The scheduling preference selection page comprises a page for selecting a scheduling preference corresponding to the set of scheduling candidate strategies, and the execution scheduling strategy comprises a scheduling strategy of the power vehicle cluster when the power vehicle cluster is scheduled.

[0042] In the embodiment, the scheduling preference selection page can be understood as a page for selecting a scheduling preference, and the scheduling preference can be a preference for scheduling consumption or robustness. The setting condition can be understood as being related to a score corresponding to each candidate scheduling strategy in the set of scheduling candidate strategies. The execution scheduling strategy can be understood as a candidate scheduling strategy in the set of scheduling candidate strategies, and the execution scheduling strategy can be understood as a scheduling strategy when the power vehicle cluster is scheduled.

[0043] Specifically, in response to a selection operation of the scheduling preference selection page, a scheduling preference for the set of scheduling candidate strategies is determined, for example, a preference for scheduling consumption or robustness. According to an indication of the scheduling preference, a score corresponding to each candidate scheduling strategy in the set of scheduling candidate strategies is determined. The candidate scheduling strategy with the highest score in each score can be selected as the execution scheduling strategy. The execution scheduling strategy is the execution scheduling strategy under the scheduling preference.

[0044] The technical solution of the embodiment of the application determines a power vehicle cluster and power vehicle data corresponding to the power vehicle cluster; obtains a double-target optimization model based on the power vehicle data, solves the double-target optimization model, and obtains a set of scheduling candidate strategies; and in response to a selection operation of a scheduling preference selection page, selects a candidate scheduling strategy meeting a setting condition from the set of scheduling candidate strategies as an execution scheduling strategy. The set of scheduling candidate strategies for the power vehicle cluster is obtained through the double-target optimization model, which solves the problem of untimely response caused by existing deterministic scheduling management. According to the selection operation of the scheduling preference selection page, a candidate scheduling strategy meeting the setting condition is selected from the set of scheduling candidate strategies, which realizes the selectability of the execution scheduling strategy, so that the scheduling of the power vehicle cluster can meet the scheduling demand in various environments, and the stability and reliability of the operation of the power vehicle cluster are improved.

[0045] On the basis of the above-mentioned embodiment, a variant embodiment of the above-mentioned embodiment is proposed. It should be noted that, in order to make the description brief, only the differences from the above-mentioned embodiment are described in the variant embodiment.

[0046] In one embodiment, the solving of the double-target optimization model to obtain the set of scheduling candidate strategies comprises:

[0047] The power supply vehicle charging and discharging boundary constraint, the state of charge constraint and the power balance condition in the power supply vehicle data are combined to form a robust constraint set, the power supply vehicle charging and discharging boundary constraint indicates the condition when the power supply vehicle exchanges power with the outside world, the state of charge constraint indicates the constraint of the remaining power corresponding to the power supply vehicle, and the power balance condition indicates the load capacity of the power grid area where the power supply vehicle is located.

[0048] Based on the robust constraint set, the double-objective optimization model is iterated to obtain an iteration result.

[0049] In a case where the iteration result indicates that the double-objective optimization model converges, a scheduling candidate strategy set is output.

[0050] In the embodiment, the power supply vehicle charging and discharging boundary constraint indicates the condition when the power supply vehicle exchanges power with the outside world, and the power supply vehicle charging and discharging boundary can include a boundary value when the power supply vehicle discharges power to the outside and a boundary value when the power supply vehicle is charged. The state of charge constraint indicates the constraint of the remaining power corresponding to the power supply vehicle, and the state of charge can indicate the percentage of the remaining power of the power supply vehicle. The power balance condition indicates the load capacity of the power grid area where the power supply vehicle is located. The robust constraint set can be understood as the constraint set corresponding to the double-objective optimization model.

[0051] For example, the power supply vehicle charging and discharging boundary constraint is: wherein P i,t is the power supply vehicle charging and discharging power, is the minimum charging power, is the maximum discharging power.

[0052] The state of charge constraint includes a state of charge update constraint and a state of charge boundary constraint, and the state of charge update constraint is wherein SOC i,t is the state of charge of the power supply vehicle, η dis is the discharging efficiency of the power supply vehicle, η ch is the charging efficiency of the power supply vehicle, is the power supply vehicle discharging power, is the power supply vehicle charging power; and the state of charge boundary constraint is wherein is the minimum state of charge, is the maximum state of charge.

[0053] The power balance condition is wherein D t is the load demand of the power grid area where the power supply vehicle is located, and R t is the new energy power supply (indicating the available new energy power supply within a time t).

[0054] The power supply vehicle charging and discharging boundary constraint, the state of charge constraint, and the power balance condition form a robustness constraint set. Based on the robustness constraint set, the double-objective optimization model is iterated, and the Pareto front is generated by searching and iteration of the multi-objective genetic algorithm, so that the double-objective optimization model gradually converges, and an iteration result is obtained. In the case that the iteration result indicates that the double-objective optimization model converges, a Pareto optimal solution set, i.e., a scheduling candidate strategy set, is output. Each candidate scheduling strategy in the scheduling candidate strategy set can be used as a scheduling strategy of the power supply vehicle cluster.

[0055] In one embodiment, the double-objective optimization model is obtained based on the power supply vehicle data, including:

[0056] The power supply vehicle discharging power in the power supply vehicle data is determined, and the product of the power supply vehicle discharging power and the electric energy value attribute value is integrated to obtain a scheduling consumption objective function. The power supply vehicle discharging power indicates the power output provided by the power supply vehicle when supplying power to the outside world.

[0057] In the case that the disturbance condition is met, a robustness objective function is constructed according to the grid side data in the power supply vehicle data. The grid side data indicates the data corresponding to the grid where the power supply vehicle is located, and the disturbance condition indicates the interference condition when the power supply vehicle cluster is scheduled.

[0058] The scheduling consumption objective and the robustness objective are taken as double objectives, the scheduling consumption objective function and the robustness objective function are combined to obtain a double-objective optimization model. The scheduling consumption objective is related to the consumption amount when the power supply vehicle cluster is scheduled, and the robustness objective is related to the robustness when the power supply vehicle cluster is scheduled.

[0059] In this embodiment, the power supply vehicle discharging power can be understood as the power output provided by the power supply vehicle when supplying power to the electric device in the outside world. The electric energy value attribute value can be understood as the attribute value corresponding to the electric energy value, which can change over time. The scheduling consumption objective function can be understood as a function constructed for the scheduling consumption target, which can be a function with the optimization objective of minimizing the scheduling consumption.

[0060] In this embodiment, the disturbance condition can be understood as the interference condition of the power supply vehicle cluster in various uncertain environments. The grid side data can be understood as various data of the grid where the power supply vehicle is located, which can include the load demand, the new energy power supply power, and the start-stop control variable of the grid area where the power supply vehicle is located. The robustness objective function can be understood as a function constructed for the robustness target, which can be a function with the optimization objective of maximizing the index corresponding to the robustness.

[0061] For the double-objective optimization model, an example sets a joint optimization variable, including: where ΔT k is the length of the scheduling time block, is the power supply vehicle charging and discharging power of each power supply vehicle at each time, is the power supply vehicle schedulable state, is the power supply vehicle location information. Each joint optimization variable corresponds to a specific candidate scheduling strategy, and the optimization process of the double-objective optimization model is to search for the optimal scheme under the double objectives.

[0062] The scheduling consumption objective function is: where M is the number of power supply vehicles in the power supply vehicle cluster, ΔT k is the time interval covered by the kth scheduling time block, K represents the total number of scheduling time blocks, is the power supply vehicle discharging power of the ith power supply vehicle at time t, λ t is the power value attribute value corresponding to the scheduling time block t, and x is the joint optimization variable.

[0063] The robustness objective function is max x R(x)=min ξ∈Ξ Feasibility(x,ξ). Where Ξ is the disturbance condition, and Feasibility(x,ξ) represents the feasibility of the joint optimization variable x under the interference ξ. The disturbance condition can include: the load prediction error disturbance is where is the predicted load demand of the power supply vehicle in the power grid area at time t, is the Gaussian disturbance, is the volatility intensity, which is determined by statistical analysis of historical load demand prediction errors; the new energy output error disturbance is where is the predicted new energy power supply at time t; the execution disturbance is where u i,t is the start-stop control variable, is a binary random variable of execution deviation, which follows a Bernoulli distribution, and the probability parameter p d represents the probability of occurrence of execution deviation, Bernoulli is the Bernoulli distribution, indicating that the start-stop control variable takes the value 1 (execution deviation occurs) or 0 (no deviation). Finally, the disturbance set Ξ={ξ (1) ,ξ (2) ,…,ξ (n)} is constructed by historical data analysis, and each ξ (1) corresponds to a complete disturbance vector combination, i.e.

[0064] A dual-target optimization model is obtained by jointly scheduling the consumption target function and the robustness target function with the dual-target of scheduling consumption target and robustness target:

[0065]

[0066] In one embodiment, the power car cluster is determined, and the power car data corresponding to the power car cluster is determined.

[0067] A task granularity is obtained, the task granularity being related to a time granularity corresponding to fluctuation of the electric energy value attribute value;

[0068] The scheduling period is divided into at least one scheduling time block according to the task granularity, the scheduling period including a total time length during which the power car cluster needs to be scheduled;

[0069] For each scheduling time block, the power car cluster in the scheduling time block is determined, and the power car data corresponding to the power car cluster is determined.

[0070] In this embodiment, the task granularity can be understood as being related to fluctuation of the electric energy value attribute value over time and being set based on engineering experience. The scheduling period can be understood as a total time length during which the power car cluster needs to be scheduled. The scheduling time block can be understood as a minimum time block for updating the scheduling strategy corresponding to the power car cluster.

[0071] For example, the task granularity ΔT0 can be set as a regular granularity such as 15 minutes, 30 minutes, or 60 minutes. According to the length value indicated by ΔT0, the scheduling period is divided into at least one scheduling time block, and the length of each scheduling time block is ΔT k . The starting time point of each ΔT k may be generated by an optimization algorithm. wherein T is the scheduling period, ΔT k is the time span of the kth scheduling time block, K is the number of scheduling time blocks, [ΔT min , ΔT max ] is the range of acceptable time blocks. For example, if the power car charging and discharging response time is 10 minutes, ΔT min cannot be lower than 10 minutes, and ΔT max is the maximum time unit, such as 60 minutes.

[0072] Embodiment Two

[0073] Figure 2 is a flowchart of a strategy selection method according to Embodiment Two of the present application. This embodiment is directed to the method of selecting and executing a scheduling strategy in the above-mentioned embodiments. As shown in Figure 2 , the method comprises:

[0074] S210, determine a power car cluster and power car data corresponding to the power car cluster.

[0075] S220, obtain a double-objective optimization model based on the power car data, and solve the double-objective optimization model to obtain a set of scheduling candidate strategies.

[0076] S230, in response to a selection operation of a scheduling preference selection page, determine a scheduling preference result corresponding to the set of scheduling candidate strategies.

[0077] In this embodiment, the scheduling preference result can be understood as a selection result of scheduling consumption or robustness.

[0078] Specifically, in response to a selection operation of a scheduling preference selection page, a scheduling preference result for the set of scheduling candidate strategies is determined. The scheduling preference result can be a preference for scheduling consumption or robustness, and the scheduling preference result indicates the degree of attention to scheduling consumption and robustness of the power car cluster in the current running scenario.

[0079] S240, obtain a tunable weight factor corresponding to the scheduling preference result.

[0080] In this embodiment, the tunable weight factor can be understood as a parameter set according to the scheduling preference result, and the tunable weight factor can be used to indicate the influence of scheduling consumption and robustness on the score corresponding to each candidate scheduling strategy.

[0081] Specifically, after the scheduling preference result is determined, a tunable weight factor is set according to the scheduling preference result.

[0082] For example, the range of the tunable weight factor can be: α∈[0,1]. If the selection of the scheduling preference result is a preference for scheduling consumption, the value of the tunable weight factor can be set to be greater than 0.5, and if the selection of the scheduling preference result is a preference for robustness, the value of the tunable weight factor can be set to be less than 0.5.

[0083] S250, for each candidate scheduling strategy in the set of scheduling candidate strategies, determine candidate scheduling data corresponding to the candidate scheduling strategy, input the candidate scheduling data and the tunable weight factor into a scoring index function to obtain a scheduling strategy score corresponding to the candidate scheduling strategy.

[0084] The candidate scheduling data includes data generated when the power car cluster executes the candidate scheduling strategy.

[0085] In the embodiment, the candidate scheduling data can be understood as data generated when the candidate scheduling strategy is executed on the cluster of power supply vehicles, and the candidate scheduling data can include data of scheduling consumption and robustness generated when the candidate scheduling strategy is executed. The scheduling strategy score can be understood as a comprehensive score of the candidate scheduling strategy under the scheduling preference result.

[0086] Specifically, for each candidate scheduling strategy in the set of scheduling candidate strategies, the scheduling strategy score corresponding to the candidate scheduling strategy needs to be determined based on the scheduling preference result. The scheduling strategy score corresponding to the candidate scheduling strategy can be obtained by determining the candidate scheduling data corresponding to the candidate scheduling strategy, and inputting the candidate scheduling data and the adjustable weight factor indicated by the scheduling preference result into the scoring index function. The scoring index model can be a model for combining the scores corresponding to the scheduling consumption and the robustness based on the adjustable weight factor.

[0087] Optionally, the determining the candidate scheduling data corresponding to the candidate scheduling strategy, the inputting the candidate scheduling data and the adjustable weight factor into the scoring index function, and the obtaining the scheduling strategy score corresponding to the candidate scheduling strategy, comprise:

[0088] determining the candidate scheduling data corresponding to the candidate scheduling strategy, the candidate scheduling data comprising scheduling consumption data and scheduling robustness data, the scheduling consumption data indicating a consumption amount corresponding to the candidate scheduling strategy, and the scheduling robustness data indicating a robustness score of the candidate scheduling strategy;

[0089] determining a consumption score corresponding to the scheduling consumption data and a robustness score corresponding to the scheduling robustness data;

[0090] inputting the consumption score, the robustness score, and the adjustable weight factor into the scoring index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy.

[0091] In the embodiment, the scheduling consumption data can be understood as a scheduling consumption amount corresponding to the cluster of power supply vehicles when the cluster of power supply vehicles is scheduled by the candidate scheduling strategy. The scheduling robustness data can be understood as a robustness score corresponding to the cluster of power supply vehicles when the cluster of power supply vehicles is scheduled by the candidate scheduling strategy.

[0092] For example, the candidate scheduling data corresponding to the candidate scheduling strategy is determined, and the candidate scheduling data includes scheduling consumption data C(x) and scheduling robustness data R(x). The consumption score and the robustness score can be calculated by the candidate scheduling data including the scheduling consumption data C(x) and the scheduling robustness data R(x). min , C maxrespectively, are the minimum and maximum of the scheduling consumption data in the scheduling candidate strategy set, R min , respectively, are the minimum and maximum robustness in the scheduling candidate strategy set. Finally, the consumption score max robustness score and the adjustable weight factor are input into the score index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy.

[0093] Optionally, the method of inputting the consumption score, the robustness score, and the adjustable weight factor into the score index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy comprises:

[0094] The difference between the set value and the adjustable weight factor is taken as a residual weight factor, the adjustable weight factor indicating the proportion of the consumption score in the scheduling strategy score, and the residual weight factor indicating the proportion of the robustness score in the scheduling strategy score;

[0095] The product of the adjustable weight factor and the consumption score is taken as a first score;

[0096] The product of the residual weight factor and the robustness score is taken as a second score;

[0097] The sum of the first score and the second score is taken as the scheduling strategy score corresponding to the candidate scheduling strategy.

[0098] In this embodiment, the adjustable weight factor can be understood as the weight proportion corresponding to the scheduling consumption. The residual weight factor can be understood as the weight proportion corresponding to the robustness. The first score can be understood as the score corresponding to the scheduling consumption under the scheduling preference result, and the second score can be understood as the score corresponding to the robustness under the scheduling preference result.

[0099] For example, the set value can be set as 1, and the difference between the set value and the adjustable weight factor a is taken as a residual weight factor 1-a. The product of the adjustable weight factor and the consumption score is taken as a first score, i.e. The product of the residual weight factor and the robustness score is taken as a second score, i.e. Finally, the sum of the first score and the second score is taken as the scheduling strategy score corresponding to the candidate scheduling strategy, i.e. the scheduling strategy score According to the above method, the scheduling strategy score corresponding to each candidate scheduling strategy in the scheduling candidate strategy set is calculated.

[0100] S260, the candidate scheduling strategy corresponding to the scheduling strategy score satisfying the set condition in the scheduling strategy score is determined as the execution scheduling strategy. ​

[0101] The set condition is related to the numerical value of each of the scheduling strategy scores.

[0102] Specifically, among the scheduling strategy scores, the candidate scheduling strategy corresponding to the scheduling strategy score that meets the set condition is determined as the execution scheduling strategy. The set condition can be that the candidate scheduling strategy corresponding to the scheduling strategy score with the highest score is selected from the scheduling strategy scores and determined as the execution scheduling strategy.

[0103] For example, the scheduling strategy score with the highest score is selected from the scheduling strategy scores, and the candidate scheduling strategy corresponding to the scheduling strategy score is taken as the execution scheduling strategy of the current scheduling time block, i.e. * = argmax x∈POF Score(x), i.e. * as the execution scheduling scheme. The execution scheduling scheme includes the instructions of the power supply vehicle charging and discharging power of each power supply vehicle in the power supply vehicle cluster in the scheduling time block, the start-stop state indication of whether the power supply vehicle participates in scheduling, and the corresponding time division, etc. Finally, the execution scheduling scheme is sent to each power supply vehicle in the power supply vehicle cluster.

[0104] According to the above scheduling strategy determination method, there are the following exemplary schemes:

[0105] Scheme 1: S1, the data collection module collects the data of 5 power supply vehicles in the power supply vehicle cluster as the power supply vehicle data, the scheduling period is 8:00-20:00, and the task granularity is set to 15 minutes.

[0106] S2, the default basic granularity is 15 minutes, a double-objective optimization model is obtained based on the power supply vehicle data, and then the double-objective optimization model is solved to generate multiple candidate scheduling strategies, thereby obtaining a set of scheduling candidate strategies.

[0107] S3, the scheduling preference result of the scheduling preference selection page is set to "scheduling consumption priority", the adjustable weight factor α is set to 0.8, each candidate scheduling strategy x in the set of scheduling candidate strategies is comprehensively evaluated according to the scoring index function, and the candidate scheduling strategy x with the highest score is selected. * as the execution scheduling strategy.

[0108] S4, after the execution scheduling strategy x * is selected, the scheduling execution phase is entered. The x *The control variables (such as the charging and discharging power of each power car in the scheduling time block, the start and stop state, the access command) contained in x are packaged into control instructions and issued to the 10 power cars in the power car cluster through wireless communication or wired interface. After receiving the control instructions, the power cars perform corresponding charging, discharging or standby operations, while monitoring their key operating parameters in real time. If an abnormality (such as state of charge < 15% or > 95%) or power response deviation exceeding the threshold value is detected in a power car, the candidate scheduling strategy with the highest robustness score in the scheduling candidate strategy set is immediately called for quick switching to avoid system operation abnormalities.

[0109] Scheme two: S1, the data of the 10 power cars in the power car cluster are collected in real time as power car data, the scheduling period is 6:00-20:00, and the task granularity is set to 10 minutes.

[0110] S2, the default 10-minute basic granularity, a double-objective optimization model is obtained based on the power car data, then the double-objective optimization model is solved to generate multiple candidate scheduling strategies, and a scheduling candidate strategy set is obtained.

[0111] S3, the scheduling preference result of the scheduling preference selection page is set to "robustness priority", the adjustable weight factor a is set to 0.2, each candidate scheduling strategy x in the scheduling candidate strategy set is comprehensively evaluated according to the scoring index function, and the candidate scheduling strategy x with the highest score is selected. * as the execution scheduling strategy.

[0112] S4, after selecting the execution scheduling strategy x * , the scheduling execution phase is entered. x * The control variables (such as the charging and discharging power of each power car in the scheduling time block, the start and stop state, the access command) contained in x are packaged into control instructions and issued to the 10 power cars in the power car cluster through wireless communication or wired interface. After receiving the control instructions, the power cars perform corresponding charging, discharging or standby operations, while monitoring their key operating parameters in real time. If an abnormality (such as state of charge < 15% or > 95%) or power response deviation exceeding the threshold value is detected in a power car, the candidate scheduling strategy with the highest robustness score in the scheduling candidate strategy set is immediately called for quick switching to avoid system operation abnormalities.

[0113] The technical scheme of the embodiment of the application is: in response to a selection operation of a scheduling preference selection page, a scheduling preference result corresponding to a scheduling candidate strategy set is determined; a adjustable weight factor corresponding to the scheduling preference result is obtained; for each candidate scheduling strategy in the scheduling candidate strategy set, candidate scheduling data corresponding to the candidate scheduling strategy is determined, and the candidate scheduling data and the adjustable weight factor are input into a scoring index function to obtain a scheduling strategy score corresponding to the candidate scheduling strategy; a candidate scheduling strategy corresponding to a scheduling strategy score that meets the set condition in each scheduling strategy score is determined as an execution scheduling strategy. According to the scheduling preference result, the scheduling strategy score corresponding to each candidate scheduling strategy in the scheduling candidate strategy set is determined, flexible scheduling of the candidate scheduling strategy is realized, scheduling consumption and robustness are taken into account, and the execution scheduling strategy is determined according to each scheduling strategy score, thereby improving the practicality and controllability of the execution scheduling strategy.

[0114] Embodiment three

[0115] Figure 3 is a structural schematic diagram of a strategy determination apparatus provided according to the embodiment three of the application. As shown in the figure, the apparatus includes: Figure 3

[0116] A determination module 310 is configured to determine a power vehicle cluster and power vehicle data corresponding to the power vehicle cluster, the power vehicle cluster including at least one power vehicle, and the power vehicle data including a state of each power vehicle.

[0117] A solving module 320 is configured to obtain a double-target optimization model based on the power vehicle data, and solve the double-target optimization model to obtain a scheduling candidate strategy set, the scheduling candidate strategy set including at least one candidate scheduling strategy, and the candidate scheduling strategy including a candidate scheduling strategy of the power vehicle cluster.

[0118] A selection module 330 is configured to select, in response to a selection operation of a scheduling preference selection page, a candidate scheduling strategy that meets a set condition from the scheduling candidate strategy set as an execution scheduling strategy, the scheduling preference selection page including a page for selecting a scheduling preference corresponding to the scheduling candidate strategy set, and the execution scheduling strategy including a scheduling strategy of the power vehicle cluster when the power vehicle cluster is scheduled.

[0119] ​The strategy determination apparatus provided by the embodiment of the present application determines the power supply vehicle cluster through a determination module, and determines the power supply vehicle data corresponding to the power supply vehicle cluster; obtains a double-target optimization model based on the power supply vehicle data through a solving module, and solves the double-target optimization model to obtain a scheduling candidate strategy set; and selects a candidate scheduling strategy meeting a set condition from the scheduling candidate strategy set as an execution scheduling strategy in response to a selection operation of a scheduling preference selection page through a selection module. Through the mutual cooperation of the modules, the scheduling candidate strategy set for the power supply vehicle cluster is obtained through the double-target optimization model, and the problems such as untimely response caused by the existing deterministic scheduling management are solved. The candidate scheduling strategy meeting the set condition is selected from the scheduling candidate strategy set in accordance with the selection operation of the scheduling preference selection page, the selectability of the execution scheduling strategy is realized, the scheduling of the power supply vehicle cluster can meet the scheduling demand in various environments, and the stability and reliability of the operation of the power supply vehicle cluster are improved.

[0120] In one embodiment, the selection module 330 includes:

[0121] The first determination unit is configured to determine a scheduling preference result corresponding to the scheduling candidate strategy set in response to a selection operation of a scheduling preference selection page.

[0122] The acquisition unit is configured to acquire an adjustable weight factor corresponding to the scheduling preference result.

[0123] The input unit is configured to determine candidate scheduling data corresponding to each candidate scheduling strategy in the scheduling candidate strategy set, input the candidate scheduling data and the adjustable weight factor into a scoring index function to obtain a scheduling strategy score corresponding to the candidate scheduling strategy, and the candidate scheduling data includes data generated when the power supply vehicle cluster executes the candidate scheduling strategy.

[0124] The second determination unit is configured to determine a candidate scheduling strategy corresponding to a scheduling strategy score meeting the set condition as an execution scheduling strategy in each scheduling strategy score, and the set condition is related to the numerical value of each scheduling strategy score.

[0125] In one embodiment, the input unit includes:

[0126] The first determination subunit is configured to determine candidate scheduling data corresponding to the candidate scheduling strategy, and the candidate scheduling data includes scheduling consumption data and scheduling robustness data, the scheduling consumption data indicates the consumption amount corresponding to the candidate scheduling strategy, and the scheduling robustness data indicates the robustness score of the candidate scheduling strategy.

[0127] a second determining sub-unit, configured to determine a consumption score corresponding to the scheduling consumption data and a robustness score corresponding to the scheduling robustness data;

[0128] an inputting sub-unit, configured to input the consumption score, the robustness score and the adjustable weight factor into a score index function to obtain a scheduling strategy score corresponding to the candidate scheduling strategy.

[0129] In one embodiment, the inputting sub-unit is specifically configured to:

[0130] determine a difference between a set value and the adjustable weight factor as a residual weight factor, the adjustable weight factor indicating a proportion of the consumption score in the scheduling strategy score, and the residual weight factor indicating a proportion of the robustness score in the scheduling strategy score;

[0131] multiply the adjustable weight factor by the consumption score to obtain a first score;

[0132] multiply the residual weight factor by the robustness score to obtain a second score;

[0133] add the first score and the second score to obtain the scheduling strategy score corresponding to the candidate scheduling strategy.

[0134] In one embodiment, the solving module 320 is specifically configured to:

[0135] compose a robustness constraint set from a power vehicle charging / discharging boundary constraint, a state of charge constraint and a power balance condition in the power vehicle data, the power vehicle charging / discharging boundary constraint indicating a condition when the power vehicle exchanges power with the outside world, the state of charge constraint indicating a constraint on a residual power corresponding to the power vehicle, and the power balance condition indicating a load capacity of a power grid region where the power vehicle is located;

[0136] perform iteration on the double-objective optimization model based on the robustness constraint set to obtain an iteration result;

[0137] in a case where the iteration result indicates that the double-objective optimization model converges, output a scheduling candidate strategy set.

[0138] In one embodiment, the solving module 320 is specifically configured to:

[0139] determine a power vehicle discharging power in the power vehicle data, and integrate a product of the power vehicle discharging power and an electric energy value attribute value to obtain a scheduling consumption objective function, the power vehicle discharging power indicating an electric power output provided by the power vehicle when supplying power to the outside world;

[0140] In the case of meeting a disturbance condition, a robustness target function is constructed according to grid side data in the power car data, the grid side data indicating data corresponding to a grid where the power car is located, and the disturbance condition indicating an interference condition when the power car cluster is scheduled.

[0141] With the scheduling consumption target and the robustness target as double targets, a double target optimization model is obtained by combining the scheduling consumption target function and the robustness target function, the scheduling consumption target being related to consumption when the power car cluster is scheduled, and the robustness target being related to robustness when the power car cluster is scheduled.

[0142] In one embodiment, the determining module 310 is specifically configured to:

[0143] Obtain a task granularity, the task granularity being related to a time granularity corresponding to fluctuation of the electric energy value attribute value;

[0144] Divide a scheduling period according to the task granularity to obtain at least one scheduling time block, the scheduling period including a total time length during which the power car cluster needs to be scheduled;

[0145] For each scheduling time block, determine a power car cluster in the scheduling time block and power car data corresponding to the power car cluster.

[0146] The strategy determination apparatus provided in the embodiments of the present application can execute the strategy determination method provided in any of the embodiments of the present application, and through mutual cooperation and collaborative work among the modules, the determination of the scheduling strategy is completed, and the corresponding function modules and beneficial effects of the execution method are possessed.

[0147] Embodiment four

[0148] According to the embodiments of the present application, the present application further provides an electronic device and a computer readable storage medium.

[0149] Figure 4 is a block diagram of an electronic device according to the electronic device provided in embodiment four of the present application, and the electronic device can implement the strategy determination method described in the embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (such as headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0150] AsFigure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., which is communicatively connected to the at least one processor 411. The memory stores a computer program that can be executed by the at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0151] Various components in the electronic device are connected to the I / O interface 415, including an input unit 416, such as a keyboard, a mouse, etc., an output unit 417, such as various types of displays, a speaker, etc., a storage unit 418, such as a magnetic disk, an optical disk, etc., and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0152] The processor 411 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 performs various methods and processes described above, such as the policy determination method.

[0153] In some embodiments, the policy determination method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded onto the RAM 413 and executed by the processor 411, one or more steps of the policy determination method described above can be performed. Alternatively, in other embodiments, the processor 411 can be configured to perform the policy determination method by any other appropriate means, such as by means of firmware.

[0154] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0155] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented on the computer or other programmable apparatus. The computer programs can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0156] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0157] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0158] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0159] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0160] The technical scheme of the embodiment of the present application is a strategy determination method, device, electronic equipment and storage medium. The technical scheme of the embodiment of the present application determines a power supply vehicle cluster and power supply vehicle data corresponding to the power supply vehicle cluster; obtains a double-target optimization model based on the power supply vehicle data, and solves the double-target optimization model to obtain a scheduling candidate strategy set; and in response to a selection operation of a scheduling preference selection page, selects a candidate scheduling strategy meeting a set condition from the scheduling candidate strategy set as an execution scheduling strategy. The double-target optimization model is used to obtain the scheduling candidate strategy set for the power supply vehicle cluster, thereby solving the problem of untimely response caused by the existing deterministic scheduling management. According to the selection operation of the scheduling preference selection page, the candidate scheduling strategy meeting the set condition is selected from the scheduling candidate strategy set, thereby realizing the selectability of the execution scheduling strategy, and making the scheduling of the power supply vehicle cluster meet the scheduling demand in various environments, and improving the stability and reliability of the operation of the power supply vehicle cluster.

[0161] It should be understood that the various forms of flow shown above can be reordered, steps added or removed. For example, the steps described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical scheme of the present application can be achieved, which is not limited herein.

[0162] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A strategy determination method, characterized in that, include: Determine the power supply vehicle cluster and the power supply vehicle data corresponding to the power supply vehicle cluster, wherein the power supply vehicle cluster includes at least one power supply vehicle and the power supply vehicle data includes the status of each power supply vehicle. Based on the power vehicle data, a dual-objective optimization model is obtained, and the dual-objective optimization model is solved to obtain a set of scheduling candidate strategies. The set of scheduling candidate strategies includes at least one candidate scheduling strategy, and the candidate scheduling strategy includes the candidate scheduling strategy of the power vehicle cluster. In response to the selection operation on the scheduling preference selection page, a candidate scheduling strategy that meets the set conditions is selected from the set of scheduling candidate strategies and used as the execution scheduling strategy. The scheduling preference selection page includes a page for selecting the scheduling preference corresponding to the set of scheduling candidate strategies. The execution scheduling strategy includes the scheduling strategy of the power vehicle cluster when scheduling the power vehicle cluster.

2. The method according to claim 1, characterized in that, The step of responding to the selection operation on the scheduling preference selection page by selecting a candidate scheduling strategy that meets the set conditions from the set of alternative scheduling strategies as the execution scheduling strategy includes: In response to the selection operation on the scheduling preference selection page, determine the scheduling preference result corresponding to the set of scheduling candidate strategies; Obtain the adjustable weight factor corresponding to the scheduling preference result; For each candidate scheduling strategy in the set of alternative scheduling strategies, candidate scheduling data corresponding to the candidate scheduling strategy is determined. The candidate scheduling data and the adjustable weight factor are input into the scoring index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy. The candidate scheduling data includes the data generated when the candidate scheduling strategy is executed on the power vehicle cluster. Among the scores of each scheduling strategy, the candidate scheduling strategy corresponding to the score of the scheduling strategy that meets the set conditions is determined as the execution scheduling strategy. The set conditions are related to the numerical value of each scheduling strategy score.

3. The method according to claim 2, characterized in that, The step of determining the candidate scheduling data corresponding to the candidate scheduling strategy, and inputting the candidate scheduling data and the adjustable weight factor into the scoring index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy, includes: Determine the candidate scheduling data corresponding to the candidate scheduling strategy. The candidate scheduling data includes scheduling consumption data and scheduling robustness data. The scheduling consumption data indicates the consumption amount corresponding to the candidate scheduling strategy, and the scheduling robustness data indicates the robustness score of the candidate scheduling strategy. Determine the consumption score corresponding to the scheduling consumption data and the robustness score corresponding to the scheduling robustness data; The consumption score, the robustness score, and the adjustable weight factor are input into the scoring index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy.

4. The method according to claim 3, characterized in that, The step of inputting the consumption score, the robustness score, and the adjustable weight factor into the scoring index function to obtain the scheduling strategy score corresponding to the candidate scheduling strategy includes: The difference between the set value and the adjustable weight factor is used as the remaining weight factor. The adjustable weight factor indicates the proportion of the consumption score in the scheduling strategy score, and the remaining weight factor indicates the proportion of the robustness score in the scheduling strategy score. The product of the adjustable weighting factor and the consumption score is taken as the first score; The product of the remaining weight factor and the robustness score is taken as the binary score; The sum of the first score and the second score is taken as the scheduling strategy score corresponding to the candidate scheduling strategy.

5. The method according to claim 1, characterized in that, Solving the bi-objective optimization model yields a set of scheduling candidate strategies, including: The power vehicle charging and discharging boundary constraints, state of charge constraints, and power balance conditions in the power vehicle data are combined into a robust constraint set. The power vehicle charging and discharging boundary constraints indicate the conditions when the power vehicle exchanges power with the outside world. The state of charge constraints indicate the constraints on the remaining power of the power vehicle. The power balance conditions indicate the load capacity of the power grid area where the power vehicle is located. Based on the robustness constraint set, the bi-objective optimization model is iterated to obtain the iterative results; If the iteration results indicate that the bi-objective optimization model has converged, output a set of scheduling alternative strategies.

6. The method according to claim 1, characterized in that, The dual-objective optimization model obtained based on the power vehicle data includes: The discharge power of the power vehicle in the power vehicle data is determined, and the product of the discharge power of the power vehicle and the energy value attribute value is integrated to obtain the scheduling consumption objective function. The discharge power of the power vehicle indicates the power output provided by the power vehicle when supplying power to the outside world. Under the condition of disturbance, a robust objective function is constructed based on the grid-side data in the power vehicle data. The grid-side data indicates the data corresponding to the power grid where the power vehicle is located, and the disturbance condition indicates the interference situation when the power vehicle cluster is scheduled. By taking scheduling consumption target and robustness target as dual objectives, and combining the scheduling consumption target function and the robustness target function, a dual-objective optimization model is obtained. The scheduling consumption target is related to the consumption during the scheduling of the power vehicle cluster, and the robustness target is related to the robustness during the scheduling of the power vehicle cluster.

7. The method according to claim 1, characterized in that, The determination of the power supply vehicle cluster and the power supply vehicle data corresponding to the power supply vehicle cluster includes: Obtain the task granularity, which is related to the time granularity corresponding to the fluctuation of the electrical energy value attribute value; According to the task granularity, the scheduling period is divided to obtain at least one scheduling time block. The scheduling period includes the total duration for scheduling the power vehicle cluster. For each scheduling time block, determine the power vehicle cluster under the scheduling time block, and the power vehicle data corresponding to the power vehicle cluster.

8. A strategy determination device, characterized in that, include: The determination module is used to determine the power vehicle cluster and the power vehicle data corresponding to the power vehicle cluster. The power vehicle cluster includes at least one power vehicle, and the power vehicle data includes the status of each power vehicle. The solution module is used to obtain a dual-objective optimization model based on the power vehicle data, and to solve the dual-objective optimization model to obtain a set of scheduling candidate strategies. The set of scheduling candidate strategies includes at least one candidate scheduling strategy, and the candidate scheduling strategy includes the candidate scheduling strategy of the power vehicle cluster. The selection module is used to select a candidate scheduling strategy that meets the set conditions from the set of scheduling candidate strategies in response to the selection operation of the scheduling preference selection page, and to execute the scheduling strategy. The scheduling preference selection page includes a page for selecting the scheduling preference corresponding to the set of scheduling candidate strategies. The executed scheduling strategy includes the scheduling strategy of the power vehicle cluster when scheduling the power vehicle cluster.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the strategy determination method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the strategy determination method according to any one of claims 1-7.

Images