Prediction method and device and computer readable storage medium

Abstract

The embodiment of the invention provides a prediction method and device and a computer readable storage medium. The reliability of predicting a discharge behavior can be improved. The method comprises: according to a first parameter, determining the market inventory of an electric device within a preset time period, the first parameter comprising at least one of the price of the electric device within the preset time period and a policy for the electric device; and predicting the discharge behavior of the electric device according to the market inventory.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicles, and particularly to a prediction method, device, and computer-readable storage medium. Background Art

[0002] Energy conservation and emission reduction are the keys to the sustainable development of the automotive industry. In this context, electric vehicles have become an important part of the sustainable development of the automotive industry due to their advantages of energy conservation and environmental protection.

[0003] In the energy aggregation mode, as a mobile power source, an electric vehicle can indirectly participate in the power market through a swapping station aggregation to achieve profits, such as energy arbitrage. From the perspective of an aggregator, the charging and discharging behavior of an electric vehicle directly affects its strategy for participating in the power market. Especially for the discharging behavior, due to the influence of human subjective factors, its prediction is extremely challenging. Therefore, how to predict the discharging behavior is an urgent problem to be solved. Summary of the Invention

[0004] Embodiments of the present application provide a prediction method, device, and computer-readable storage medium, which can improve the reliability of predicting the discharging behavior.

[0005] In a first aspect, a prediction method is provided. The method includes: determining the market retention of an electrical device within a preset time period according to a first parameter, where the first parameter includes at least one of the price of the electrical device within the preset time period and the policy for the electrical device; predicting the discharging behavior of the electrical device according to the market retention.

[0006] Since the price and / or policy of an electrical device will, to a large extent, affect the market retention of the electrical device. For example, if the price of the electrical device is high, its market retention may decrease. Therefore, in the embodiments of the present application, the influence of the price of the electrical device and / or the policy for the electrical device on the market retention is considered in the process of determining the market retention of the electrical device, and the discharging behavior of the electrical device is predicted based on the market retention, so that the accuracy of the determined market retention is relatively high, and thus the reliability of the prediction result can be effectively improved.

[0007] In some possible implementation manners, the first parameter includes the policy. Determining the market holding quantity of the electrical device within a preset time period according to the first parameter includes: determining the market holding quantity according to at least one of a first policy strength, a second policy strength, a first acceptance degree, and a second acceptance degree; wherein, the first policy strength is the policy strength for users who spontaneously purchase the electrical device, the second policy strength is the policy strength for users who follow the trend to purchase the electrical device, the first acceptance degree is the acceptance degree of the policy by users who spontaneously purchase the electrical device, and the second acceptance degree is the acceptance degree of the policy by users who follow the trend to purchase the electrical device.

[0008] In the above technical solution, since the first policy strength for users who spontaneously purchase the electrical device, the second policy strength for users who follow the trend to purchase the electrical device, the first acceptance degree of the policy by users who spontaneously purchase the electrical device, and the second acceptance degree of the policy by users who follow the trend to purchase the electrical device respectively have a great influence on the market holding quantity. Therefore, the accuracy of the market holding quantity determined according to at least one of the first policy strength, the second policy strength, the first acceptance degree, and the second acceptance degree is relatively high.

[0009] In some possible implementation manners, the first parameter includes the price. Determining the market holding quantity of the electrical device within a preset time period according to the first parameter includes: determining the market holding quantity according to the difference between the price of the electrical device and the price of the fuel device.

[0010] Generally, the higher the price of the electrical device, that is, the greater the difference between the price of the electrical device and the price of the fuel device, the fewer the duration holding quantities of the electrical device may be. Therefore, in the above technical solution, determining the duration holding quantity according to the difference between the two can improve the reliability of the result to a certain extent.

[0011] In some possible implementation manners, the price of the electrical device is determined based on the purchase price of the electrical device and the maintenance cost of the electrical device.

[0012] In some possible implementation manners, the method further includes: determining the purchase price of the electrical device according to at least one of the service life of the electrical device, the depreciation rate of the electrical device, the selling price of the electrical device, and the subsidy amount of the electrical device.

[0013] Since the service life, depreciation rate, selling price, and subsidy amount of the electrical device are closely related to the purchase price of the electrical device. For example, the higher the subsidy amount, the lower the purchase price may be. Therefore, in the above technical solution, at least one of the service life, depreciation rate, selling price, and subsidy amount of the electrical device is considered in the process of determining the purchase price of the electrical device, making the determined purchase price more accurate.

[0014] In some possible implementation manners, the method further includes: determining the maintenance cost of the electrical device according to at least one of the cost per unit mileage fuel consumption of the electrical device, the annual maintenance cost of the electrical device, the annual mileage of the electrical device, and the depreciation rate of the electrical device.

[0015] Since the cost per unit mileage fuel consumption, annual maintenance cost, annual mileage, and depreciation rate of the electrical device are closely related to the maintenance cost of the electrical device. Therefore, in the above technical solution, at least one of the cost per unit mileage fuel consumption, annual maintenance cost, annual mileage, and depreciation rate of the electrical device is considered in the process of determining the maintenance cost of the electrical device, making the determined maintenance cost more accurate.

[0016] In some possible implementation manners, the determining the market retention volume of the electrical device within a preset time period according to the first parameter includes: determining the market retention volume according to the first parameter and a first model, where the first model is the Bass model.

[0017] In the above technical solution, the market retention volume of the electrical device is determined according to the Bass model, that is, the long-term retention volume of the electrical device is dynamically modeled through the Bass model, and on this basis, the discharge behavior is predicted, greatly improving the reliability of the long-term prediction result. Further, relatively speaking, the Bass model is more mature, thus being able to improve the prediction efficiency.

[0018] In some possible implementation manners, the first parameter further includes the discharge amount of the electrical device within the preset time period; the predicting the discharge behavior of the electrical device according to the market retention volume includes: predicting the discharge behavior of the electrical device according to the market retention volume and the discharge amount of the electrical device.

[0019] In the above technical solution, in addition to based on the market retention volume of the electrical device, the discharge behavior of the discharge device is predicted based on the discharge amount of the electrical device. On the one hand, predicting the discharge behavior based on more parameters makes the obtained prediction result more reliable; on the other hand, the discharge amount of the electrical device can also affect its discharge behavior to a certain extent, and considering the discharge amount of the electrical device in the prediction process further improves the accuracy of the prediction result.

[0020] In some possible implementation manners, the method further includes: determining the discharge amount of each power consumption device based on the subjective factors of the users of each power consumption device in the power consumption devices.

[0021] Since the subjective factors of users greatly affect the discharge amount of power consumption devices. For example, users with "battery anxiety" may tend to discharge less, and thus the discharge amount of this power consumption device may be relatively small. Users who prefer to make a profit may tend to discharge more, and thus the discharge amount of this power consumption device may be relatively large. Therefore, the above technical solution can effectively improve the accuracy of determination by determining the discharge amount of the power consumption device based on the subjective factors of the users.

[0022] In some possible implementation manners, the determining the discharge amount of each power consumption device based on the subjective factors of the users of each power consumption device in the power consumption devices includes: determining the discharge amount of each power consumption device based on the preference degree of the user for the subjective factors and the satisfaction degree of the swapping station for the subjective factors.

[0023] The above technical solution determines the discharge amount of each power consumption device based on the preference degree of the user for the subjective factors and the satisfaction degree of the swapping station for the subjective factors. Since the preference degree of the user for the subjective factors and the satisfaction degree of the swapping station for the subjective factors are closely related to the discharge amount of the power consumption device, the determined discharge amount is more accurate.

[0024] In some possible implementation manners, the method further includes: determining the preference degree of the user for the subjective factors based on the subjective factors of the user and the intuitionistic fuzzy set; wherein, the power consumption device includes a first power consumption device, the user of the first power consumption device is a first user, the subjective factor of the first user includes a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to represent the preference degree of the first user for the first subjective factor.

[0025] The above technical solution determines the preference degree of the user for the subjective factors by introducing the intuitionistic fuzzy set, that is, it synthesizes the certainty, fuzziness and uncertainty of the subjective factors, so that the finally determined result can better reflect the preference degree of the user for the subjective factors.

[0026] In some possible implementation manners, the method further includes: determining the satisfaction degree of the swapping station for the subjective factors based on the subjective factors of the user and the intuitionistic fuzzy decision matrix; wherein, the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to represent the satisfaction degree of swapping station g for the subjective factors, and i and g are positive integers.

[0027] In the above technical solution, by introducing an intuitionistic fuzzy decision matrix to determine the satisfaction degree of the swapping station with respect to subjective factors, that is, by integrating certainty, fuzziness, and uncertainty, the finally determined result can better reflect the satisfaction degree of the swapping station with respect to subjective factors.

[0028] In some possible implementation manners, determining the discharge amount of each electrical device based on the preference degree of the user for the subjective factors and the satisfaction degree of the swapping station with respect to the subjective factors includes: obtaining an approximation matrix based on the preference degree of the subjective factors and the satisfaction degree of the swapping station with respect to the subjective factors, where the element in the m-th row and n-th column of the approximation matrix represents the preference degree of user m for swapping station n; determining a target swapping station in the swapping stations according to the approximation matrix; and determining the discharge amount based on the target swapping station.

[0029] In the above technical solution, by introducing an approximation matrix to characterize the preferences of users for different swapping stations, that is, by considering the spatio-temporal dimensional features in the prediction process, the determined discharge amount is more accurate, and thus the prediction result obtained based on the discharge amount is more reliable.

[0030] In some possible implementation manners, determining the discharge amount based on the target swapping station includes: determining the discharge amount based on the distance between the electrical device at the current moment and the target swapping station and / or the discharge time of the electrical device for discharging at the target swapping station.

[0031] Generally, the farther the electrical device is from the target swapping station at the current moment, the more power is consumed for the electrical device to reach the target swapping station, and thus the discharge amount may be less. On the contrary, the closer the electrical device is to the target swapping station at the current moment, the less power is consumed for the electrical device to reach the target swapping station, and thus the discharge amount may be more. In addition, since the electricity price may be different at different times, for example, the electricity price may be higher during peak hours and lower during off-peak hours. If the electrical device discharges during peak hours, the discharge amount may be more, so as to better profit from the electricity market. If the electrical device discharges during off-peak hours, the discharge amount may be less. Therefore, the above technical solution determines the discharge amount based on the distance between the electrical device at the current moment and the target swapping station and / or the discharge time of the electrical device for discharging at the target swapping station, and the determined discharge amount has a high accuracy rate.

[0032] In a second aspect, a prediction device is provided, including: a determination unit, configured to determine the market holding amount of an electrical device within a preset time period according to a first parameter, where the first parameter includes at least one of the price of the electrical device within the preset time period and the policy for the electrical device; and a prediction unit, configured to predict the discharge behavior of the electrical device according to the market holding amount.

[0033] In some possible implementation manners, the determining unit is specifically configured to: determine the market retention based on at least one of a first policy strength, a second policy strength, a first acceptance degree, and a second acceptance degree; wherein, the first policy strength is the policy strength for users who spontaneously purchase the electric device, the second policy strength is the policy strength for users who follow the trend to purchase the electric device, the first acceptance degree is the acceptance degree of the users who spontaneously purchase the electric device for the policy, and the second acceptance degree is the acceptance degree of the users who follow the trend to purchase the electric device for the policy.

[0034] In some possible implementation manners, the first parameter includes the price, and the determining unit is specifically configured to: determine the market retention according to the difference between the price of the electric device and the price of the fuel device.

[0035] In some possible implementation manners, the price of the electric device is determined based on the purchase price of the electric device and the maintenance cost of the electric device.

[0036] In some possible implementation manners, the determining unit is further configured to: determine the purchase price of the electric device according to at least one of the service life of the electric device, the depreciation rate of the electric device, the selling price of the electric device, and the subsidy amount of the electric device.

[0037] In some possible implementation manners, the determining unit is further configured to: determine the maintenance cost of the electric device according to at least one of the cost per unit mileage fuel consumption of the electric device, the annual maintenance cost of the electric device, the annual driving mileage of the electric device, and the depreciation rate of the electric device.

[0038] In some possible implementation manners, the determining unit is specifically configured to: determine the market retention according to the first parameter and a first model, and the first model is the Bass model.

[0039] In some possible implementation manners, the first parameter further includes the discharge amount of the electric device within the preset time period; the prediction unit is specifically configured to: predict the discharge behavior of the electric device according to the market retention and the discharge amount of the electric device.

[0040] In some possible implementation manners, the determining unit is further configured to: determine the discharge amount of each electric device based on the subjective factors of the users of each electric device in the electric device.

[0041] In some possible implementation manners, the determining unit is specifically configured to: determine the discharge amount of each power consumption device based on the preference degree of the user for the subjective factor and the satisfaction degree of the swapping station for the subjective factor.

[0042] In some possible implementation manners, the determining unit is further configured to: determine the preference degree of the user for the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy set; wherein, the power consumption device includes a first power consumption device, the user of the first power consumption device is a first user, the subjective factor of the first user includes a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to represent the preference degree of the first user for the first subjective factor.

[0043] In some possible implementation manners, the determining unit is further configured to: determine the satisfaction degree of the swapping station for the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy decision matrix; wherein, the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to represent the satisfaction degree of swapping station g for the subjective factor, and i and g are positive integers.

[0044] In some possible implementation manners, the determining unit is specifically configured to: obtain an approximation matrix based on the preference degree of the subjective factor and the satisfaction degree of the swapping station for the subjective factor, where the element in the m-th row and n-th column of the approximation matrix represents the preference degree of user m for swapping station n; determine a target swapping station from the swapping stations according to the approximation matrix; and determine the discharge amount based on the target swapping station.

[0045] In some possible implementation manners, the determining unit is specifically configured to: determine the discharge amount based on the distance between the power consumption device at the current moment and the target swapping station and / or the discharge time of the power consumption device for discharging at the target swapping station.

[0046] In a third aspect, a prediction device is provided, including a processor and a memory, where the memory is used to store a computer program, and the processor is used to call the computer program to execute the method in the first aspect or its various implementation manners.

[0047] In a fourth aspect, a computer-readable storage medium is provided, which is used to store a computer program, and the computer program enables a computer to execute the method in the first aspect or its various implementation manners. Description of the Drawings

[0048] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments of the present application. Obviously, the following described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the drawings.

[0049] In the drawings, the drawings are not drawn to actual scale.

[0050] Figure 1 It is a schematic flowchart of a prediction method according to an embodiment of the present application.

[0051] Figure 2 It is a specific flowchart of a prediction method according to an embodiment of the present application.

[0052] Figure 3 It is a schematic block diagram of a prediction device according to an embodiment of the present application.

[0053] Figure 4 It is a schematic block diagram of a prediction device according to an embodiment of the present application. Detailed implementation manners

[0054] The following will further describe the implementation manners of the present application in detail in combination with the drawings and embodiments. The detailed description and drawings of the following embodiments are used to exemplarily illustrate the principle of the present application, but cannot be used to limit the scope of the present application, that is, the present application is not limited to the described embodiments.

[0055] In the description of the present application, it should be noted that unless otherwise specified, the meaning of "a plurality" is two or more; the orientation or positional relationships indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation to the present application. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] Unless otherwise defined, all technical and scientific terms used in the present application have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs; the terms used in the description of the present application in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the description and claims of the present application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the description and claims of the present application or the above drawings are used to distinguish different objects and are not used to describe a specific order or primary-secondary relationship.

[0057] In this application, the mention of "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of this application. The occurrence of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0058] In the energy aggregation mode, electric vehicles, as mobile power sources, can indirectly participate in the electricity market through aggregators at swap stations to achieve profits, such as energy arbitrage. From the perspective of aggregators, the charging and discharging behaviors of electric vehicles affect their strategies for participating in the electricity market, especially the discharging behavior. Due to the influence of human subjective factors, the prediction of the discharging behavior is extremely challenging.

[0059] Common time series prediction methods, such as Markov chains, face the problem of error propagation. Specifically, Markov chains predict future states based on the current state, and the current state is determined by historical states. Since there are inevitable errors in each state prediction, in medium- and long-term predictions, the errors will accumulate as the current state is updated, resulting in extremely poor prediction effects.

[0060] The discharging behavior of electric vehicles is affected by multi-dimensional factors of time and space. The commonly used long short-term memory network focuses on time-dimensional features and ignores spatial factors. Moreover, there are obvious differences in the number of electric vehicles in different regions, resulting in differences in the aggregable energy of regional swap stations.

[0061] In addition, the fuzziness and uncertainty of the subjective cognition of vehicle owners make the interpretability of the discharging behavior of electric vehicles more complex. Different from charging, the discharging behavior of electric vehicles depends on the subjective cognition of vehicle owners. In the energy aggregation mode, vehicle owners with "range anxiety" may tend to discharge less to ensure the vehicle's endurance, while vehicle owners who prefer to make a profit may tend to discharge more to participate in the electricity market for profit. This subjective factor has obvious individual differences and is a fuzzy concept that is difficult to quantify with precise numbers.

[0062] In view of this, an embodiment of the present application proposes a prediction method, which determines the market retention of an electrical device within a preset time period based on a first parameter, and predicts the discharge behavior of the electrical device according to the market retention. The first parameter includes at least one parameter of the price of the electrical device within the preset time period and the policy for the electrical device. Since the price and / or policy of the electrical device will largely affect the market retention of the electrical device. For example, if the price of the electrical device is high, its market retention may be reduced. Therefore, in the embodiment of the present application, the influence of the price of the electrical device and / or the policy for the electrical device on the market retention is considered during the process of determining the market retention of the electrical device, and the discharge behavior of the electrical device is predicted based on the market retention, so that the accuracy of the determined market retention is relatively high, and thus the reliability of the prediction result can be effectively improved.

[0063] Figure 1 FIG. 4 shows a schematic flowchart of a prediction method 100 according to an embodiment of the present application. Exemplarily, the method 100 can be applied to vehicle-to-grid (V2G) technology.

[0064] As Figure 1 shown, the method 100 may include at least some of the following content.

[0065] S110: Determine the market retention of the electrical device within a preset time period according to the first parameter, where the first parameter includes at least one parameter of the price of the electrical device within the preset time period and the policy for the electrical device.

[0066] S120: Predict the discharge behavior of the electrical device according to the market retention.

[0067] Among them, the electrical device can be an electric vehicle, or a ship or a spacecraft, etc. The electric vehicle can be, for example, a passenger car or a heavy truck, etc.

[0068] The preset time period can be, for example, 1 year, 2 years, 5 years, etc. The policy for the electrical device can be constantly changing.

[0069] Since the price and / or policy of the electrical device will largely affect the market retention of the electrical device. For example, if the price of the electrical device is high, its market retention may be reduced. Therefore, in the embodiment of the present application, the influence of the price of the electrical device and / or the policy for the electrical device on the market retention is considered during the process of determining the market retention of the electrical device, and the discharge behavior of the electrical device is predicted based on the market retention, so that the accuracy of the determined market retention is relatively high, and thus the reliability of the prediction result can be effectively improved.

[0070] In the case where the first parameter includes a policy for the electrical device, S110 may specifically include: determining the market retention volume according to at least one of the first policy strength, the second policy strength, the first acceptance degree, and the second acceptance degree. Wherein, the first policy strength is the policy strength for users who spontaneously purchase electrical devices, the second policy strength is the policy strength for users who follow the trend to purchase electrical devices, the first acceptance degree is the acceptance degree of users who spontaneously purchase electrical devices for the policy, and the second acceptance degree is the acceptance degree of users who follow the trend to purchase electrical devices for the policy.

[0071] Optionally, the policy strength may be determined based on parameters such as the subsidy amount or the duration of the policy.

[0072] In the above technical solution, due to the first policy strength for users who spontaneously purchase electrical devices and the second policy strength for users who follow the trend to purchase electrical devices, as well as the first acceptance degree of users who spontaneously purchase electrical devices for the policy and the second acceptance degree of users who follow the trend to purchase electrical devices for the policy respectively, the impact on the market retention volume is relatively large. Therefore, the accuracy of the market retention volume determined according to at least one of the first policy strength, the second policy strength, the first acceptance degree, and the second acceptance degree is relatively high.

[0073] In the case where the first parameter includes the price of the electrical device, since if the price of the electrical device is relatively high, its market share may decline. Therefore, S110 may specifically include: determining the market retention volume of the electrical device according to the difference between the price of the electrical device and the price of the fuel device.

[0074] Generally, the higher the price of the electrical device, that is, the greater the difference between the price of the electrical device and the price of the fuel device, the fewer the duration retention volumes of the electrical device may be. Therefore, in the above technical solution, determining the duration retention volume according to the difference between the two can improve the reliability of the result to a certain extent.

[0075] Optionally, the price of the electrical device may be determined based on the purchase price of the electrical device and the maintenance cost of the electrical device.

[0076] For example, the higher the purchase price of the electrical device, the higher the price of the electrical device may be; if the maintenance cost of the electrical device is higher, the price of the electrical device may also be higher.

[0077] Multiple factors need to be considered for the purchase price of the electrical device. In some embodiments, the purchase price of the electrical device may be determined according to at least one of the service life of the electrical device, the depreciation rate of the electrical device, the selling price of the electrical device, and the subsidy amount of the electrical device.

[0078] Since the service life, depreciation rate, selling price, and subsidy amount of an electrical device are closely related to the purchase price of the electrical device. For example, the higher the subsidy amount, the lower the purchase price may be. Therefore, in the above technical solution, at least one of the service life, depreciation rate, selling price, and subsidy amount of the electrical device is considered during the process of determining the purchase price of the electrical device, making the determined purchase price more accurate.

[0079] Similar to the purchase price of an electrical device, the maintenance cost of the electrical device also needs to be considered from multiple aspects. Optionally, the maintenance cost of the electrical device can be determined based on at least one of the fuel consumption cost per unit mileage of the electrical device, the annual maintenance cost of the electrical device, the annual mileage of the electrical device, and the depreciation rate of the electrical device.

[0080] Since the fuel consumption cost per unit mileage, annual maintenance cost, annual mileage, and depreciation rate of an electrical device are closely related to the maintenance cost of the electrical device. Therefore, in the above technical solution, at least one of the fuel consumption cost per unit mileage, annual maintenance cost, annual mileage, and depreciation rate of the electrical device is considered during the process of agreeing on the maintenance cost of the electrical device, making the determined maintenance cost more accurate.

[0081] After determining the first parameter, in one implementation, the market retention volume of the electrical device can be determined based on the first parameter and the first model.

[0082] The first model can be some common models used for power load forecasting. Optionally, the first model can be a diffusion model. For example, the first model can be the Bass model.

[0083] The Bass model is a diffusion model that can model the dynamic evolution of the market retention volume of electrical devices from a macroscopic perspective. The original expression of the Bass model is as follows:

[0084]

[0085] Where Q(t) is the proportion of the market retention volume of electrical devices at time t in the total market potential, ranging from 0 to 1. q(t) is the change rate of the market share of electrical devices at time t, that is, dQ / dt. m is the innovation coefficient, representing the number of users who spontaneously purchase electrical devices. n is the imitation coefficient, representing the number of users who follow the trend to purchase electrical devices.

[0086] In the above technical solution, the market retention volume of the electrical device is determined according to the Bass model, that is, the medium- and long-term retention volume of the electrical device is dynamically modeled through the Bass model, and on this basis, the discharge behavior is predicted, greatly improving the reliability of the long-term prediction results. Further, relatively speaking, the Bass model is more mature, thus improving the prediction efficiency.

[0087] To describe the embodiments of the present application more clearly, the embodiments of the present application will be described in detail below by taking the first model as the Bass model as an example.

[0088] As described above, although the Bass model describes the diffusion effect of the market share of electrical devices, it does not consider the influence of multiple factors, especially the influence of policies and the prices of electrical devices. Therefore, the embodiments of the present application can redefine the innovation coefficient m and the imitation coefficient n.

[0089] First, introduce the influence of policies on the market retention of electrical devices, that is, the first parameter includes policies for electrical devices, so the following relational expression can be obtained:

[0090] m(t + 1) = m(t) + Mγ M (2)

[0091] n(t + 1) = n(t) + Nγ N (3)

[0092] Among them, M represents the policy strength for users who spontaneously purchase electrical devices, and its value range is [0, 1]. N represents the policy strength for users who follow the trend to purchase electrical devices, and its value range is also [0, 1]. That is to say, the embodiments of the present application quantify the policy strength, and M and N can be respectively understood as a coefficient. γ M represents the acceptance degree of users who spontaneously purchase electrical devices for policies, and γ N represents the acceptance degree of users who follow the trend to purchase electrical devices for policies.

[0093] It can be seen from the above expressions (2) and (3) that the redefined m and n are time-varying parameters, which can reflect the influence of policies on the market retention.

[0094] Furthermore, in the case where the first parameter includes the price of electrical devices, introduce a correction factor μ(t) to reflect the influence of price on the market retention of electrical devices, that is, the following expression is obtained:

[0095]

[0096]

[0097] Among them, α is a price influence factor, which is a positive value. p EV (t), p CV (t) respectively represent the prices of electrical devices and fuel devices at time t. It can be seen that a high price of electrical devices will cause its market share to decline.

[0098] The price of electrical devices is related to the purchase price of electrical devices and the maintenance cost of electrical devices. Therefore, expressions (6)-(8) can be obtained:

[0099]

[0100]

[0101]

[0102] Among them, x ∈ {EV, CV}, representing different types of devices, EV represents an electric device, and CV represents a fuel device. Represents the purchase price of device x at time t. ω is the discount rate, τ is the service life of the device, and r is the depreciation rate of the device. C x，p (t), C x，s (t) represent the selling price and subsidy amount of the device respectively. Represents the maintenance cost of device x at time t. C x，c (k), C x，l represent the fuel consumption cost per unit mileage in the k-th year and the annual maintenance cost of the device respectively. d annual is the annual mileage. (k - t) can represent a preset time period, that is, t can represent the time of purchasing an electric device, and k can represent the time of maintaining the electric device. For example, if a user purchases an electric device in 2003 and maintains it in 2008, then t is 2003, k is 2008, and the preset time period is 5 years.

[0103] It can be seen that the improved Bass model comprehensively considers the influence of policies and prices on the market share of electric devices, so that the long-term inventory of electric devices can be predicted based on the improved Bass model.

[0104] In addition to the price of the electric device and / or the policy for the electric device, the first parameter may further include the discharge amount of the electric device within a preset time period. At this time, S120 may specifically include: predicting the discharge behavior of the electric device according to the market inventory and the discharge amount of the electric device.

[0105] In the above technical solution, in addition to based on the market inventory of the electric device, the discharge behavior of the discharge device is predicted based on the discharge amount of the electric device. On the one hand, predicting the discharge behavior based on more parameters makes the obtained prediction result more reliable; on the other hand, the discharge amount of the electric device can also affect its discharge behavior to a certain extent, and considering the discharge amount of the electric device in the prediction process further improves the accuracy of the prediction result.

[0106] Considering that the fuzziness and uncertainty of the user's subjective cognition of the electric device may result in different discharge amounts for different electric devices. Therefore, in some embodiments, the discharge amount of each electric device can be determined based on the subjective factors of the users of each electric device.

[0107] Since the subjective factors of users greatly affect the discharge amount of the electrical device, determining the discharge amount of the electrical device based on the subjective factors of users can effectively improve the accuracy of the determination.

[0108] Exemplarily, as described above, the subjective factors may include whether the user has "battery anxiety" or prefers to make a profit. Users with "battery anxiety" may tend to discharge less, and thus the discharge amount of the electrical device may be relatively small. Users who prefer to make a profit may tend to discharge more, and thus the discharge amount of the electrical device may be relatively large.

[0109] Exemplarily again, the subjective factors may also include the staying time of the user in a certain area. If the staying time in this area is long, the discharge amount of the electrical device may be large; if the staying time of the user in this area is short, the discharge amount of the electrical device may be small or even zero.

[0110] Exemplarily again, the subjective factors of the user may also include the user's preference for different local battery swap stations. For example, there may be multiple battery swap stations in an area, and which battery swap station the user specifically chooses for discharging is affected by the subjective human factors of the user.

[0111] Therefore, the discharge amount of each electrical device can be determined based on the preference degree of the user for the subjective factors and the satisfaction degree of the battery swap station for the subjective factors.

[0112] In this technical solution, the discharge amount of each electrical device is determined based on the preference degree of the user for the subjective factors and the satisfaction degree of the battery swap station for the subjective factors. Since the preference degree of the user for the subjective factors and the satisfaction degree of the battery swap station for the subjective factors are closely related to the discharge amount of the electrical device, the determined discharge amount is more accurate.

[0113] In the embodiments of the present application, a discharge behavior model based on fuzzy multi-attribute decision-making can be used to simulate the discharge behaviors of different users in different regions.

[0114] Optionally, method 100 may further include: determining the preference degree of the user for the subjective factors based on the subjective factors of the user and the intuitionistic fuzzy set. Among them, the electrical device includes a first electrical device, the user of the first electrical device is a first user, the subjective factors of the first user include a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the preference degree of the first user for the first subjective factor.

[0115] Suppose there are K car owners, and the I subjective factors affecting the discharge behavior are z 1 …z i , then the intuitionistic fuzzy set of car owner k is:

[0116]

[0117] Among them, u k (z i ), υ k (z i ) are the membership degree and non-membership degree of the subjective factor z i for the intuitionistic fuzzy set e k , representing the preference degree of the car owner k for the subjective factor z i . The membership degree indicates the degree to which the subjective factor z i belongs to the intuitionistic fuzzy set e k , and the value range of the membership degree is between 0 and 1. The non-membership degree indicates the degree to which the subjective factor z i does not belong to the intuitionistic fuzzy set e k , and its value range is also between 0 and 1.

[0118] In the above technical solution, by introducing the intuitionistic fuzzy set to determine the user's preference degree for the subjective factor, that is, by integrating the certainty, fuzziness and uncertainty of the subjective factor, the finally determined result can better reflect the user's preference degree for the subjective factor.

[0119] Furthermore, the method 100 may further include: determining the satisfaction degree of the swapping station for the subjective factor based on the user's subjective factor and the intuitionistic fuzzy decision matrix. Among them, the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of the swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to represent the satisfaction degree of the swapping station g for the subjective factor, where i and g are positive integers.

[0120] Suppose there are G swapping stations, and the intuitionistic fuzzy decision matrix can be expressed as the following matrix:

[0121]

[0122] Among them, the g-th row of this matrix can form the intuitionistic fuzzy set d g of the swapping station g, and d gi = <u gi (z i ), υ gi (z i )> are the membership degree and non-membership degree of the subjective factor z i for the intuitionistic fuzzy set d g , representing the satisfaction degree of the swapping station g for the subjective factor z i .

[0123] In the above technical solution, by introducing the intuitionistic fuzzy decision matrix to determine the satisfaction degree of the swapping station for the subjective factor, that is, by integrating the certainty, fuzziness and uncertainty, the finally determined result can better reflect the satisfaction degree of the swapping station for the subjective factor.

[0124] Considering that different subjective factors may have different membership degrees and non-membership degrees, therefore, for unified representation, the embodiment of the present application introduces connection numbers. Then, the intuitionistic fuzzy set of user k can be transformed into a corresponding connection number set, that is:

[0125] e′ k ={<z i , a k (z i ) + b k (z i )j 1 + c k (z i )j 2 >|z i ∈Z} (11)

[0126] a k (z i ) = u k (z i )(1 - υ k (z i )) (12)

[0127] b k (z i ) = 1 - u k (z i )(1 - υ k (z i )) - υ k (z i )(1 - u k (z i )) (13)

[0128] c k (z i ) = υ k (z i )(1 - u k (z i )) (14)

[0129] j 1 ∈[-1, 1], j 2 = -1 (15)

[0130] Among them, a k (z i ), b k (z i ), c k (z i ) can represent consistency, difference, and opposition respectively. Through the weighted combination of the three, the certainty, fuzziness, and uncertainty of subjective factors are integrated.

[0131] Similarly, the intuitionistic fuzzy decision matrix of the battery swapping station can be transformed into:

[0132]

[0133] d′ gi =a gi (z i )+b gi (z i )j 1 +c gi (z i )j 2 (17)

[0134] Among them, the g-th row of the matrix can form the connection number set d′ of the battery swapping station g g .

[0135] After that, based on the user's preference degree for subjective factors and the satisfaction degree of the battery swapping station for subjective factors, an approximate matrix can be obtained, and the target battery swapping station can be determined among the battery swapping stations according to the approximate matrix, and then the discharge amount can be determined based on the target battery swapping station.

[0136] Among them, the element in the m-th row and n-th column of the approximate matrix can represent the preference degree of user m for the battery swapping station n.

[0137] For example, the approximate matrix S′ can be expressed as:

[0138]

[0139]

[0140] Among them, θ i is the weight of the subjective factor z i . S′ kg represents the preference degree of vehicle owner k for the battery swapping station g.

[0141] In the above technical solution, by introducing an approximate matrix to characterize the user's preference for different battery swapping stations, that is, considering the spatio-temporal dimension characteristics in the prediction process, the determined discharge amount is more accurate, and thus the prediction result obtained based on the discharge amount is more reliable.

[0142] Specifically, the discharge amount can be determined based on the distance between the current moment of the electrical device and the target battery swapping station and / or the discharge time of the electrical device for discharging at the target battery swapping station.

[0143] For example, the farther the electrical device is from the target battery swapping station at the current moment, the more power is consumed for the electrical device to reach the target battery swapping station, and the discharge amount may be less. On the contrary, the closer the electrical device is to the target battery swapping station at the current moment, the less power is consumed for the electrical device to reach the target battery swapping station, and the discharge amount may be more.

[0144] Since the electricity price may vary at different times, for example, the electricity price may be higher during peak hours (such as 17:00 - 23:00) and lower during off-peak hours (such as 23:00 - 7:00 the next day). Then, the discharge amount can be determined based on the discharge time when the electrical device discharges at the target swapping station.

[0145] For example, if the electrical device discharges during peak hours, the discharge amount may be relatively large, so as to better profit from the electricity market. If the electrical device discharges during off-peak hours, the discharge amount may be relatively small.

[0146] Based on the distance of the electrical device from the target swapping station at the current moment and / or the discharge time when discharging at the target swapping station, the above technical solution determines the discharge amount, and the accuracy of the determined discharge amount is relatively high.

[0147] After determining the discharge amount of each electrical device, the overall discharge behavior of the electrical devices in the target area can be predicted based on the market retention of the electrical devices.

[0148] Figure 2 The flowchart of an embodiment of the present application is shown. Among them, the preset time period is T, for example, T is 5 years. The number of users of the electrical device is K. The first parameter is the policies and prices within the preset number of years T.

[0149] First, let t = 1, and deduce the number of electrical devices in each region within 1 year. And let k = 1, and select the target swapping station according to the approximate matrix.

[0150] After that, sample the driving distance and the discharge time to calculate the discharge amount. Among them, the driving distance is the distance of the electrical device from the target swapping station at the current moment, and the discharge time is the discharge time when the electrical device discharges at the target swapping station.

[0151] Next, determine whether k is greater than K.

[0152] If k is greater than K, continue to determine whether t is greater than T. If t is greater than T, the entire process ends. If t is less than T, then let t = t + 1, and continue to deduce the number of electrical devices in each region within t years.

[0153] If k is less than K, then let k = k + 1, and continue to select the target swapping station according to the approximate matrix. Iterate in this way until k is greater than K and t is greater than T.

[0154] That is to say, by alternately deducing the market retention of the electrical devices and the discharge behavior of the users, the spatio-temporal distribution of the discharge behavior of the medium- and long-term electrical devices can be predicted.

[0155] In the embodiments of the present application, the magnitudes of the serial numbers of the above processes do not imply the sequence of execution. The execution sequence of each process should be determined according to its function and internal logic, and should not impose any limitation on the implementation process of the embodiments of the present application.

[0156] Moreover, on the premise of no conflict, the various embodiments described in the present application and / or the technical features in the various embodiments can be arbitrarily combined with each other, and the technical solutions obtained after the combination should also fall within the protection scope of the present application.

[0157] The prediction method in the embodiments of the present application is described in detail above. Next, the prediction device in the embodiments of the present application will be described. It should be understood that the prediction device in the embodiments of the present application can execute the prediction method in the embodiments of the present application.

[0158] Figure 3 The schematic block diagram of the prediction device 300 in the embodiments of the present application is shown. Among them, as Figure 3 shown, the prediction device 300 may include:

[0159] A determination unit 310, configured to determine the market retention of the electrical device within a preset time period according to a first parameter, where the first parameter includes at least one parameter of the price of the electrical device within the preset time period and the policy for the electrical device.

[0160] A prediction unit 320, configured to predict the discharge behavior of the electrical device according to the market retention.

[0161] Optionally, in the embodiments of the present application, the determination unit 310 is specifically configured to: determine the market retention according to at least one of a first policy strength, a second policy strength, a first acceptance degree, and a second acceptance degree; where the first policy strength is the policy strength for users who spontaneously purchase the electrical device, the second policy strength is the policy strength for users who follow the trend to purchase the electrical device, the first acceptance degree is the acceptance degree of the policy by users who spontaneously purchase the electrical device, and the second acceptance degree is the acceptance degree of the policy by users who follow the trend to purchase the electrical device.

[0162] Optionally, in the embodiments of the present application, the first parameter includes the price, and the determination unit 310 is specifically configured to: determine the market retention according to the difference between the price of the electrical device and the price of the fuel device.

[0163] Optionally, in the embodiments of the present application, the price of the electrical device is determined based on the purchase price of the electrical device and the maintenance cost of the electrical device.

[0164] Optionally, in the embodiments of the present application, the determining unit 310 is further configured to: determine the purchase price of the electrical device according to at least one of the service life of the electrical device, the depreciation rate of the electrical device, the selling price of the electrical device, and the subsidy amount of the electrical device.

[0165] Optionally, in the embodiments of the present application, the determining unit 310 is further configured to: determine the maintenance cost of the electrical device according to at least one of the cost per unit mileage fuel consumption of the electrical device, the annual maintenance cost of the electrical device, the annual mileage of the electrical device, and the depreciation rate of the electrical device.

[0166] Optionally, in the embodiments of the present application, the determining unit 310 is specifically configured to: determine the market retention volume according to the first parameter and the first model, and the first model is the Bass model.

[0167] Optionally, in the embodiments of the present application, the first parameter further includes the discharge amount of the electrical device within the preset time period; the predicting unit 320 is specifically configured to: predict the discharge behavior of the electrical device according to the market retention volume and the discharge amount of the electrical device.

[0168] Optionally, in the embodiments of the present application, the determining unit 310 is further configured to: determine the discharge amount of each electrical device based on the subjective factors of the users of each electrical device in the electrical device.

[0169] Optionally, in the embodiments of the present application, the determining unit 310 is specifically configured to: determine the discharge amount of each electrical device based on the preference degree of the user for the subjective factors and the satisfaction degree of the swapping station for the subjective factors.

[0170] Optionally, in the embodiments of the present application, the determining unit 310 is further configured to: determine the preference degree of the user for the subjective factors based on the subjective factors of the user and the intuitionistic fuzzy set; wherein, the electrical device includes a first electrical device, the user of the first electrical device is a first user, the subjective factor of the first user includes a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the preference degree of the first user for the first subjective factor.

[0171] Optionally, in the embodiments of the present application, the determining unit 310 is further configured to: determine the satisfaction degree of the swapping station for the subjective factors based on the subjective factors of the user and the intuitionistic fuzzy decision matrix; wherein, the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of the swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the satisfaction degree of the swapping station g for the subjective factors, and i and g are positive integers.

[0172] Optionally, in the embodiment of the present application, the determining unit 310 is specifically configured to: obtain an approximation matrix based on the preference degree of the subjective factors and the satisfaction degree of the swap station with respect to the subjective factors, where the element in the m-th row and n-th column of the approximation matrix represents the preference degree of user m for swap station n; determine a target swap station from the swap stations according to the approximation matrix; and determine the discharge amount based on the target swap station.

[0173] Optionally, in the embodiment of the present application, the determining unit 310 is specifically configured to: determine the discharge amount based on the distance between the power consumption device and the target swap station at the current moment and / or the discharge time of the power consumption device when discharging at the target swap station.

[0174] It should be understood that the prediction device 300 can implement the corresponding operations in the method 100. For the sake of brevity, details are not described herein again.

[0175] Figure 4 FIG. 10 is a schematic hardware structure diagram of a prediction device 400 according to an embodiment of the present application. The prediction device 400 includes a memory 401, a processor 402, a communication interface 403, and a bus 404. Among them, the memory 401, the processor 402, and the communication interface 403 are communicatively connected to each other through the bus 404.

[0176] The memory 401 may be a read-only memory (ROM), a static storage device, and a random access memory (RAM). The memory 401 may store a program. When the program stored in the memory 401 is executed by the processor 402, the processor 402 and the communication interface 403 are used to execute the respective steps of the prediction method according to the embodiment of the present application.

[0177] The processor 402 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, and is used to execute relevant programs to implement the functions required by the units in the device according to the embodiment of the present application, or to execute the prediction method according to the embodiment of the present application.

[0178] The processor 402 may also be an integrated circuit chip with signal processing capabilities. In the implementation process, the respective steps of the prediction method according to the embodiment of the present application may be completed by the integrated logic circuit in the hardware of the processor 402 or by instructions in software form.

[0179] The above-mentioned processor 402 can also be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware processor, or can be executed and completed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 401, and the processor 402 reads the information in the memory 401 and combines its hardware to complete the functions required to be executed by the units included in the prediction device 400 in the embodiments of the present application, or executes the prediction method of the embodiments of the present application.

[0180] The communication interface 403 uses a transceiver device such as, but not limited to, a transceiver to implement the communication between the prediction device 400 and other devices or communication networks.

[0181] The bus 404 can include a path for transmitting information between various components of the prediction device 400 (for example, the memory 401, the processor 402, the communication interface 403).

[0182] It should be noted that although the above-mentioned prediction device 400 only shows a memory, a processor, and a communication interface, in the specific implementation process, those skilled in the art should understand that the prediction device 400 can also include other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the prediction device 400 can also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the prediction device 400 can also only include the devices necessary for implementing the embodiments of the present application, and does not necessarily include Figure 4 all the devices shown in

[0183] The embodiments of the present application also provide a computer-readable storage medium for storing a computer program, and the computer program is used to execute the methods of the various embodiments of the present application described above.

[0184] The above-mentioned computer-readable storage medium can be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0185] An embodiment of the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to execute the above-described prediction method.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A prediction method, characterized in that, the method includes: determining the market retention volume of an electrical device within a preset time period according to a first parameter, where the first parameter includes at least one parameter of the price of the electrical device and the policy for the electrical device within the preset time period; predicting the discharge behavior of the electrical device according to the market retention volume.

2. The method according to claim 1, characterized in that, the first parameter includes the policy, and determining the market retention volume of the electrical device within the preset time period according to the first parameter includes: determining the market retention volume according to at least one of a first policy strength, a second policy strength, a first acceptance degree, and a second acceptance degree; wherein, the first policy strength is the policy strength for users who spontaneously purchase the electrical device, the second policy strength is the policy strength for users who follow the trend to purchase the electrical device, the first acceptance degree is the acceptance degree of the policy by users who spontaneously purchase the electrical device, and the second acceptance degree is the acceptance degree of the policy by users who follow the trend to purchase the electrical device.

3. The method according to claim 1 or 2, characterized in that, the first parameter includes the price, and determining the market retention volume of the electrical device within the preset time period according to the first parameter includes: determining the market retention volume according to the difference between the price of the electrical device and the price of the fuel device.

4. The method according to any one of claims 1 to 3, characterized in that, the price of the electrical device is determined based on the purchase price of the electrical device and the maintenance cost of the electrical device.

5. The method according to claim 4, characterized in that, the method further includes: determining the purchase price of the electrical device according to at least one of the service life of the electrical device, the depreciation rate of the electrical device, the selling price of the electrical device, and the subsidy amount of the electrical device.

6. The method according to claim 4 or 5, characterized in that, the method further includes: determining the maintenance cost of the electrical device according to at least one of the fuel consumption cost per unit mileage of the electrical device, the annual maintenance cost of the electrical device, the annual driving mileage of the electrical device, and the depreciation rate of the electrical device.

7. The method according to any one of claims 1 to 6, characterized in that, determining the market retention volume of the electrical device within the preset time period according to the first parameter includes: determining the market retention volume according to the first parameter and a first model, where the first model is the Bass model.

8. The method according to any one of claims 1 to 7, characterized in that, the first parameter further includes the discharge amount of the electrical device within the preset time period; predicting the discharge behavior of the electrical device according to the market retention volume includes: predicting the discharge behavior of the electrical device according to the market retention volume and the discharge amount of the electrical device.

9. The method according to claim 8, characterized in that, the method further includes: Determine the discharge amount of each electrical device based on the subjective factors of the users of each electrical device in the electrical device.

10. The method according to claim 9, wherein, the determining the discharge amount of each electrical device based on the subjective factors of the users of each electrical device in the electrical device includes: Determine the discharge amount of each electrical device based on the preference degree of the user for the subjective factor and the satisfaction degree of the swapping station for the subjective factor.

11. The method according to claim 10, wherein, the method further includes: Determine the preference degree of the user for the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy set; wherein, the electrical device includes a first electrical device, the user of the first electrical device is a first user, the subjective factor of the first user includes a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the preference degree of the first user for the first subjective factor.

12. The method according to claim 10 or 11, wherein, the method further includes: Determine the satisfaction degree of the swapping station for the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy decision matrix; wherein, the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the satisfaction degree of swapping station g for the subjective factor, and i and g are positive integers.

13. The method according to any one of claims 10 to 12, wherein, the determining the discharge amount of each electrical device based on the preference degree of the user for the subjective factor and the satisfaction degree of the swapping station for the subjective factor includes: Obtain an approximation matrix based on the preference degree of the subjective factor and the satisfaction degree of the swapping station for the subjective factor, and the element in the m-th row and n-th column of the approximation matrix represents the preference degree of user m for swapping station n; Determine a target swapping station among the swapping stations according to the approximation matrix; Determine the discharge amount based on the target swapping station.

14. The method according to claim 13, wherein, the determining the discharge amount based on the target swapping station includes: Determine the discharge amount based on the distance between the electrical device at the current moment and the target swapping station and / or the discharge time of the electrical device for discharging at the target swapping station.

15. A prediction device, wherein, comprising: a determining unit, configured to determine the market retention amount of electrical devices within a preset time period according to a first parameter, where the first parameter includes at least one parameter of the price of the electrical device within the preset time period and the policy for the electrical device; a prediction unit, configured to predict the discharging behavior of the electrical device according to the market retention amount.

16. The device according to claim 15, wherein, the determining unit is specifically configured to: Determine the market retention amount according to at least one of a first policy strength, a second policy strength, a first acceptance degree, and a second acceptance degree; Wherein, the first policy strength is the policy strength for users who spontaneously purchase the electric device, the second policy strength is the policy strength for users who follow the trend to purchase the electric device, the first acceptance degree is the acceptance degree of the users who spontaneously purchase the electric device for the policy, and the second acceptance degree is the acceptance degree of the users who follow the trend to purchase the electric device for the policy.

17. The device according to claim 15 or 16, characterized in that the first parameter includes the price, and the determining unit is specifically configured to: determine the market retention based on the difference between the price of the electric device and the price of the fuel device.

18. The device according to any one of claims 15 to 17, characterized in that the price of the electric device is determined based on the purchase price of the electric device and the maintenance cost of the electric device.

19. The device according to claim 18, characterized in that the determining unit is further configured to: determine the purchase price of the electric device according to at least one of the service life of the electric device, the depreciation rate of the electric device, the selling price of the electric device, and the subsidy amount of the electric device.

20. The device according to claim 18 or 19, characterized in that the determining unit is further configured to: determine the maintenance cost of the electric device according to at least one of the cost per unit mileage fuel consumption of the electric device, the annual maintenance cost of the electric device, the annual mileage of the electric device, and the depreciation rate of the electric device.

21. The device according to any one of claims 15 to 20, characterized in that the determining unit is specifically configured to: determine the market retention according to the first parameter and the first model, and the first model is the Bass model.

22. The device according to any one of claims 15 to 21, characterized in that the first parameter further includes the discharge amount of the electric device within the preset time period; the prediction unit is specifically configured to: predict the discharge behavior of the electric device according to the market retention and the discharge amount of the electric device.

23. The device according to claim 22, characterized in that the determining unit is further configured to: determine the discharge amount of each electric device based on the subjective factors of the users of each electric device in the electric device.

24. The device according to claim 23, characterized in that the determining unit is specifically configured to: determine the discharge amount of each electric device based on the preference degree of the user for the subjective factor and the satisfaction degree of the swapping station for the subjective factor.

25. The device according to claim 24, characterized in that the determining unit is further configured to: determine the preference degree of the user for the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy set; wherein, the electric device includes a first electric device, the user of the first electric device is a first user, the subjective factor of the first user includes a first subjective factor, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the preference degree of the first user for the first subjective factor.

26. The device according to claim 24 or 25, wherein, the determining unit is further configured to: determine the degree of satisfaction of the swapping station with respect to the subjective factor based on the subjective factor of the user and the intuitionistic fuzzy decision matrix; wherein the i-th row of the intuitionistic fuzzy decision matrix represents the intuitionistic fuzzy set of swapping station i, and the membership degree and non-membership degree of the intuitionistic fuzzy set are used to characterize the degree of satisfaction of swapping station g with respect to the subjective factor, and i and g are positive integers.

27. The device according to any one of claims 24 to 26, wherein, the determining unit is specifically configured to: obtain an approximation matrix based on the preference degree of the subjective factor and the degree of satisfaction of the swapping station with respect to the subjective factor, where the element in the m-th row and n-th column of the approximation matrix represents the preference degree of user m for swapping station n; determine a target swapping station among the swapping stations according to the approximation matrix; determine the discharge amount based on the target swapping station.

28. The device according to claim 27, wherein, the determining unit is specifically configured to: determine the discharge amount based on the distance of the power-consuming device from the target swapping station at the current moment and / or the discharge time of the power-consuming device when discharging at the target swapping station.

29. A prediction device, wherein, it includes: a memory for storing a program; a processor for executing the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to execute the prediction method according to any one of claims 1 to 14.

30. A computer-readable storage medium, wherein, it is used to store a computer program, and the computer program causes a computer to execute the prediction method according to any one of claims 1 to 14.

Images