Data-driven power retail package pushing method and device considering individual rationality

Abstract

The invention provides a data-driven power retail package pushing method and device considering individual rationality, and relates to the technical field of power system operation. The method comprises the following steps: clustering historical load curve data of a plurality of power consumers, and determining the classification of each power consumer and the center load curve of each classification; based on a data driving method, utilizing the center load curve of each classification to construct a utility function of the power users under each classification, and based on the utility function, constructing individual rational constraints of the power users under each classification; establishing a package optimization model by taking benefit maximization of a power retailer as a target and considering individual rational constraints; and solving the package optimization model to obtain recommended packages corresponding to the plurality of classifications. According to the method, the rational selection behavior of the user is fully considered by constructing the individual rational constraint, the reasonable package is pushed to optimize the user experience, the selection of the user for the new package is accurately predicted, and the effective utilization of resources is facilitated.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power system operation, and in particular to a data-driven power retail package push method and device that considers individual rationality. Background Art

[0002] As the main entity in the electricity sales market, how to push reasonable electricity retail packages to electricity users is an important consideration in its operation. A reasonable package push mechanism can improve market vitality, promote interaction between users and power grids, and promote the efficient use of resources.

[0003] Since most electricity users lack relevant professional knowledge and capabilities, they tend to choose from given retail packages. Most existing technologies design retail packages for electricity users from the perspective of analytical mechanism models. There are solutions in related technologies that use user satisfaction functions to design electricity retail packages. However, in practical applications, it is difficult for retailers to directly obtain private information such as electricity users' satisfaction functions. Therefore, how to make full use of existing electricity user data to deeply explore the behavioral trends of electricity users and improve electricity users' satisfaction with push packages is one of the problems that need to be solved in this field. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first embodiment of the present disclosure proposes a data-driven electricity retail package push method that takes individual rationality into consideration, including:

[0006] Obtain historical load curve data for multiple power users;

[0007] Clustering the historical load curve data, and determining the category to which each of the power users belongs and the central load curve of each category according to the clustering result;

[0008] Based on a data-driven approach, a utility function of the power users in each category is constructed using the central load curve of each category, and individual rational constraints of the power users in each category are constructed based on the utility function;

[0009] Taking the maximization of the profit of the electricity retailer as the goal, taking the recommended packages designed for each category as the optimization variable, considering the power consumption-purchase power balance constraint, the risk loss constraint of the electricity retailer, the individual rationality constraint of the electricity user and the limit constraint of the number of retail package changes, a package optimization model is constructed;

[0010] Solving the package optimization model to obtain recommended packages corresponding to multiple categories;

[0011] The recommended packages corresponding to each of the multiple categories are pushed to the user.

[0012] In some embodiments of the present disclosure, clustering the historical load curve data and determining the category to which each of the electricity users belongs based on the clustering results include: clustering the historical load curve data respectively by multiple clustering methods to obtain first clustering results corresponding to each of the clustering methods, wherein the first clustering results include the number of clustering categories and the corresponding classification of the multiple electricity users; determining the optimal number of clustering categories from the multiple numbers of clustering categories by an optimal number of clustering category determination method, and determining the category to which each of the electricity users belongs based on the first clustering result corresponding to the optimal number of clustering categories.

[0013] In some embodiments of the present disclosure, the optimal clustering category number determination method is any one of the following: silhouette method, DBI (Davies Boudlin Index) method, VRC (Variance Ratio Criterion) method.

[0014] In some embodiments of the present disclosure, the utility function of the power user under each category is expressed by the following formula:

[0015]

[0016] in, It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is the recommended package p designed for the rth category r , and the central load curve is The electricity usage at Represents the central load curve of the rth category The power load in the tth time period, p r，t Indicates recommended set meal p r The recommended package price for the tth time period, p r，t(0) Indicates the original retail package p r(0) is the original retail package price for the t-th time period, T is the total number of time periods considered in the package, and is the power elasticity parameter.

[0017] In some embodiments of the present disclosure, the individual rational constraints of the power users under each category are constructed based on the utility function and are expressed as follows:

[0018]

[0019] Among them, p r′ Indicates the recommended packages designed for all the categories except the rth category; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r′ , and the central load curve is The electricity usage at that time; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r(0) , and the central load curve is The electricity usage at that time.

[0020] In some embodiments of the present disclosure, the package optimization model is expressed by the following formula:

[0021]

[0022] Among them, p r，t represents the recommended package designed for the electricity user belonging to the rth category in the tth time period, For electricity users belonging to category r, in the recommended package p r，t The predicted power load for the next time period t is: represents the total electricity sales revenue obtained by the electricity retailer from the multiple electricity users, p r，t(0) represents the original retail package p of the electricity user belonging to the rth category r(0) The original retail package price in the tth time period, α is the power elasticity parameter, Represents the central load curve of the rth category The power load in the tth time period is {k|k∈r} represents the set of electricity users belonging to the rth category, card({k|k∈r}) represents the total number of electricity users belonging to the rth category, q k,t(0) Represents the historical load curve data q of power user k k(0) The power load in the tth time period, q k(0) =(q k，1(0) ,…,q k，t(0) , ..., q k，T(0) ), Represents the historical load curve data q k(0) After normalization, the average power load of power user k in the tth time period is: represents the maximum power load of power user k within the total time T considered in the package, is the average daily electricity purchase price of the electricity retailer in the t period, L t is the electricity retailer’s purchase amount in the tth time period, is the total electricity purchase cost of the electricity retailer, and C is the risk loss of the electricity retailer.

[0023] In some embodiments of the present disclosure, the retail package change number limit constraint is expressed by the following formula:

[0024]

[0025] Where M is the total number of time periods of the package, m = 1, 2, ..., M, represents the upper limit of the number of times the package price changes, represents the recommended package p designed for the rth category r The price of the mth time period; is a 01 variable, for the recommended package p r , if time period t belongs to the mth time-sharing time period, then τ min The minimum duration for each time-sharing period.

[0026] The second aspect of the present disclosure provides a data-driven electricity retail package push device that takes individual rationality into consideration, including:

[0027] An acquisition module, used to acquire historical load curve data of multiple power users;

[0028] A clustering module, used for clustering the historical load curve data, determining the category to which each of the power users belongs according to the clustering result, and determining the central load curve of each category according to the historical load curve data of the power users under each category;

[0029] A first building module is used to build a utility function of the power users in each category by using the central load curve of each category based on a data-driven method, and to build a personal rational constraint of the power users in each category based on the utility function;

[0030] The second construction module is used to maximize the profit of the power retailer, take the recommended packages designed for each category as the optimization variable, consider the power consumption-purchase power balance constraint, the power retailer risk loss constraint, the individual rationality constraint of the power user, the power user's power consumption response law constraint and the retail package change segment limit constraint, and construct a package optimization model;

[0031] A determination module, used to solve the package optimization model to obtain recommended packages corresponding to multiple categories;

[0032] The push module is used to push the recommended packages corresponding to the multiple categories to the user.

[0033] A third aspect of the present disclosure provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0036] The fourth aspect of the present disclosure provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0037] The data-driven power retail package push method considering individual rationality provided by the present disclosure deeply mines the data of power users by implementing the embodiments of the present disclosure, fully considers the rational choice behavior of power users by constructing individual rational constraints, and designs retail packages for power users under each category to better meet the actual needs and personalized wishes of users. At the same time, retailers can also accurately predict the behavioral trends of power users under each category, accurately predict the choice of power users for new packages, and be more conducive to promoting the effective use of resources. In addition, the present disclosure pushes all packages designed for all categories to users for individual selection, without mandatory push, to ensure the right of users to freely choose and improve user experience.

[0038] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0040] Figure 1 A flow chart of a data-driven electricity retail package push method considering individual rationality provided by an embodiment of the present disclosure;

[0041] Figure 2 A schematic diagram of a data-driven electricity retail package push device that takes individual rationality into consideration provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0043] Specifically, the data-driven electricity retail package push method and device considering individual rationality according to an embodiment of the present disclosure will be described below with reference to the accompanying drawings.

[0044] Figure 1 This is a flow chart of a data-driven electricity retail package push method considering individual rationality provided by an embodiment of the present disclosure. Figure 1 As shown, the data-driven electricity retail package push method considering individual rationality may include the following steps:

[0045] Step 101: Obtain historical load curve data of multiple power users.

[0046] In some embodiments of the present disclosure, the set of power users may be defined as 1, ..., k, ..., K, where K is the number of power users, the number of days of historical load curve data is recorded as 1, ..., d, ..., D, D is the total number of days considered in the historical load curve data, and the time period of the historical load curve data is defined as 1, ..., t, ..., T, T is the total number of time periods considered in one day in the historical load curve data. It should be noted that the historical load curve data is the load curve data in the past period of time, and can be the average daily load curve of the power user in the past month. The historical load curve data is recorded as q k(0) =(q k，1(0) , ..., q k,t(0) , ..., q k，T(0) ), where q k,t(0) is the average power load of power user k in time period t over the past period of time (such as one month), q k(0) It is a vector formed by stacking the average power load of power user k at each moment in a period of time.

[0047] Step 102: cluster the historical load curve data, and determine the category to which each power user belongs and the central load curve of each category according to the clustering result.

[0048] Optionally, various clustering methods such as K-means clustering, hierarchical clustering, fuzzy clustering, Gaussian mixture clustering, etc. can be used to cluster the historical load curve data. In one implementation, before clustering the historical load curve data, the historical load curve data of each power user can be normalized and preprocessed, and the reference formula is as follows:

[0049]

[0050] in, Represents the historical load curve data q k(0) After normalization, the average power load of power user k in the tth time period is: It represents the maximum value of the electricity load of electricity user k within the total time T considered in the package.

[0051] Optionally, in some embodiments of the present disclosure, in order to push the simplification of retail packages later, the number of clustered categories can be reduced. In one implementation, the historical load curve data can be clustered by multiple clustering methods to obtain the first clustering results corresponding to each clustering method. The first clustering results include the number of clustering categories and the classification of multiple corresponding power users (i.e., the classification of each power user in different clustering methods). The optimal number of clustering categories is determined from multiple clustering category numbers by the optimal clustering category number determination method, and the classification of each power user is determined according to the first clustering result corresponding to the optimal number of clustering categories. Among them, any of the following optimal clustering category number determination methods can be used: silhouette method, DBI (Davies Boudlin Index) method, VRC (Variance Ratio Criterion) method. Taking the DBI method as an example, the DBI index is calculated under multiple clustering category numbers. If the DBI index under a certain category number is the smallest, the clustering category number can be determined as the optimal clustering category number.

[0052] As an example, the divided categories are marked as 1, ..., r, ..., R, where R is the optimal number of clustering categories. For the center load curve of the rth category The calculation rules are:

[0053]

[0054] in, Represents the central load curve of the rth category The power load in the tth time period is {k|k∈r} represents the set of power users belonging to the rth category, and card({k|k∈r}) represents the total number of users in the set of power users belonging to the rth category.

[0055] Step 103, based on a data-driven approach, the utility function of the power users in each category is constructed using the central load curve of each category, and the individual rational constraints of the power users in each category are constructed based on the utility function.

[0056] It should be noted that the utility function of electricity users is used to mine deeper information about electricity users from load curves and electricity consumption information, and to describe the behavior of electricity users under each category. Among them, the utility function can be understood as using the historical load curves and electricity consumption information (original retail package prices, electricity load, etc.) of electricity users to predict the possibility that users will choose new retail packages, or their satisfaction with new packages. When promoting packages, the rational choice behavior of users is fully considered from the user's perspective, and the specific strategic behavior of users in electricity consumption is accurately portrayed. In one implementation method, the present disclosure proposes the following formula expression of the utility function of electricity users under each category:

[0057]

[0058] in, It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is the recommended package p designed for the rth category r , and the central load curve is The electricity usage at Represents the central load curve of the rth category The power load in the tth time period, p r，t Indicates recommended set meal p r The recommended package price for the tth time period, p r，t(0) Indicates the original retail package p r(0) The original retail package price of the tth time period in the package, T is the total number of time periods considered in the package, and is the power elasticity parameter. The original retail package can be the current package used by the power user. In some embodiments of the present disclosure, the original retail package of the power user in each category can be assumed to be the same package.

[0059] Based on the utility function, the individual rational constraints of power users in each category are constructed so that the power user's electricity utility (satisfaction) for the new package corresponding to the category is greater than or equal to the electricity utility (satisfaction) of the original retail package. From the perspective of power retailers, accurately predicting the choice of power users for new packages is more conducive to promoting the efficient use of resources. Therefore, based on the retailer side, the individual rational constraints can also increase the power user's electricity utility (satisfaction) for the new package corresponding to the category to be greater than or equal to the electricity utility (satisfaction) of the packages corresponding to other categories except the user's category. It ensures that the personalized wishes and preferences of power users are fully respected, and while improving user satisfaction, the overall optimization of social welfare is achieved. Among them, the individual rational constraints of power users in each category constructed based on the utility function are expressed as follows:

[0060]

[0061] in, It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is the recommended package p designed for the rth category r , and the central load curve is The electricity usage at the time r′ It represents the recommended packages designed for all categories except the rth category; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r′, and the central load curve is The electricity usage at that time; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r(0) , and the central load curve is The electricity usage at that time.

[0062] Step 104, with the goal of maximizing the profit of electricity retailers, taking the recommended packages designed for each category as the optimization variable, considering the electricity consumption-purchase electricity balance constraint, the risk loss constraint of electricity retailers, the personal rationality constraint of electricity users and the limit constraint on the number of retail package changes, a package optimization model is constructed.

[0063] In addition to individual rational constraints, other data constraints need to be considered. Among them, the power consumption-power purchase balance constraint means that the total power consumption of multiple power users under the new package should be equal to the power purchase amount L of the power retailer. t The mutual balance can be expressed as follows:

[0064]

[0065] in, Represents the central load curve of the rth category The power load in the tth time period, α is the power elasticity parameter, p r，t Indicates the recommended package p corresponding to the rth category r The recommended package price for the tth time period, p r，t(0) Indicates the original retail package p r(0) The original retail package price in the tth time period, It indicates that the power users in the predicted rth category are in the corresponding recommended package p r The power load in the next time period t.

[0066] The risk loss constraint of power retailers expresses the size of the risk loss that may be incurred if the power purchase price fluctuates and causes losses to the retailers according to the power purchase price data within a recent period of time (such as a month) within D days. It can be expressed as follows:

[0067]

[0068] Where C is the loss of the electricity retailer, A is the indirect decision variable; ε CVaR is the confidence level, generally 0.9-0.98; [·] + represents max{·,0}.

[0069] In some embodiments of the present disclosure, a package optimization model can be constructed based on the power consumption-purchase power balance constraint, the power retailer risk loss constraint, and the power user's personal rationality constraint. However, considering the operability of practical applications, it is also necessary to limit the number of changes in the retail package. Otherwise, if there are too many package changes, the package price will change at every moment, which is not suitable for practical application scenarios.

[0070] The structure of the time-of-use electricity price package is more easily accepted by users due to its fewer changes and lower risks, so the basic structure of the time-of-use structure is adopted for different packages of different users. Therefore, the present disclosure limits the number of change segments of the package by adding a restriction on the number of change segments of the retail package. The restriction on the number of change segments of the retail package can be expressed by the following formula:

[0071]

[0072] Where M is the total number of time periods of the package, m = 1, 2, ..., M, and M represents the upper limit of the number of times the package price changes. represents the recommended package p designed for the rth category r The price of the mth time period; is a 01 variable, for the recommended package p r , if time period t belongs to the mth time-sharing time period, then τ min The shortest duration of each time-sharing period. The first equation of formula (8) means that each time period can only belong to one time-sharing period. The shortest duration of each time-sharing period in formula (8) is τ min The third equation of formula (8) represents that the maintenance time of each time-sharing period must be continuous. The fourth equation of formula (8) represents the mapping relationship between the electricity price of each time-sharing period and the package electricity price.

[0073] In some embodiments of the present disclosure, the goal is to maximize the profit of power retailers, and the recommended packages designed for each category are used as optimization variables. Considering the power consumption-purchase power balance constraint, the power retailer risk loss constraint, the power user's personal rationality constraint, and the retail package change segment limit constraint, a package optimization model is constructed. The package optimization model can be expressed by the following formula:

[0074]

[0075] in, represents the total electricity sales revenue obtained by the electricity retailer from the multiple electricity users, is the average daily electricity purchase price of the retailer in the t period, D is the total number of days considered by the historical load curve data, and the daily electricity purchase price curve on the dth day is recorded as η d =(η d，1, ..., η d，t , .., η d，T ), η d is the vector formed by stacking the electricity purchase price on the dth day in time period t, η d，t is the electricity purchase price on the dth day in time period t, L t is the electricity retailer’s purchase amount in the tth time period, is the total electricity purchase cost of the electricity retailer, and C is the risk loss of the electricity retailer.

[0076] Step 105, solving the package optimization model to obtain recommended packages corresponding to multiple categories.

[0077] In some embodiments of the present disclosure, the package optimization model can be adapted and transformed. In the step of solving the package optimization model, the package optimization model needs to be adapted and transformed first. The specific transformation process includes converting the bilinear term Perform piecewise linear approximation to eliminate constraints equivalently; transform the product and absolute value terms of the 01 variable and continuous variable constrained by formula (8) using the big M method; finally, linearize the risk loss of formula (7). The specific transformation steps are omitted. After the transformation is completed, the package optimization model formula (4)-formula (9) can be transformed into a mixed linear integer optimization model, which can be effectively solved by a commercial solver to obtain the recommended package corresponding to each category. Due to the existence of personal rational constraints, the recommended package corresponding to the user's category is the best for power users.

[0078] Step 106: Push the recommended packages corresponding to the multiple categories to the user.

[0079] In some embodiments of the present disclosure, when pushing packages to electricity users, only the recommended packages of the category to which the electricity user belongs may be pushed to the user. However, the method of pushing different packages to users of different categories is often more like forcibly dividing the users and forcibly setting multiple types of electricity prices, which results in a poor user experience. To this end, the present disclosure proposes to push all the recommended packages corresponding to all the categories obtained by solving to the user for selection, respect the user's right to choose independently, and optimize the user experience. Optionally, the recommended packages of the category to which the user belongs may be marked, such as marking the package of the category to which the user belongs as a "recommended package" among multiple recommended packages to facilitate user selection.

[0080] By implementing the embodiments of the present disclosure, the data of power users is deeply mined, and the rational choice behavior of power users is fully considered by constructing individual rational constraints. While the retail packages designed for power users in each category better meet the actual needs and personalized wishes of users, retailers can also accurately predict the behavioral trends of power users in each category and accurately predict the choice of power users for new packages, which is more conducive to promoting the effective use of resources. In addition, the present disclosure pushes all packages designed for all categories to users for selection, without forced push, to ensure the right of users to freely choose and improve user experience.

[0081] The disclosed embodiments contribute valuable technical resources and reference blueprints to the power retail market management framework, and provide accurate technical support and decision-making references in predicting retailer and user behavior trends. In addition, the disclosed embodiments also inspire the enthusiasm of diversified user entities such as small and medium-sized enterprises to actively participate in the retail electricity price competition, promote the formation of a fair, transparent, and orderly competitive retail market environment, and inject new vitality into the healthy development of the power market.

[0082] Figure 2 This is a schematic diagram of a data-driven electricity retail package push device that takes into account individual rationality provided by an embodiment of the present disclosure. Figure 2 As shown, the data-driven electricity retail package push device considering individual rationality includes: an acquisition module 201, a clustering module 202, a first construction module 203, a second construction module 204, a determination module 205 and a push module 206.

[0083] The acquisition module 201 is used to acquire historical load curve data of multiple power users.

[0084] The clustering module 202 is used to cluster the historical load curve data, determine the category to which each power user belongs according to the clustering result, and determine the central load curve of each category according to the historical load curve data of the power users in each category.

[0085] The first construction module 203 is used to construct the utility function of the power users in each category based on the data-driven method by using the central load curve of each category, and to construct the individual rational constraints of the power users in each category based on the utility function.

[0086] The second construction module 204 is used to maximize the profit of electricity retailers, take the recommended packages designed for each category as the optimization variable, consider the power consumption-purchase balance constraint, the risk loss constraint of electricity retailers, the personal rationality constraint of electricity users, the power consumption response law constraint of electricity users and the limit constraint on the number of retail package change segments, and construct a package optimization model.

[0087] The determination module 205 is used to solve the package optimization model to obtain recommended packages corresponding to multiple categories.

[0088] The push module 206 is used to push the recommended packages corresponding to the multiple categories to the user.

[0089] In some embodiments of the present disclosure, the clustering module 202 is specifically used to: cluster the historical load curve data respectively by multiple clustering methods to obtain the first clustering results corresponding to each clustering method, wherein the first clustering results include the number of clustering categories and the classification of the corresponding multiple power users; determine the optimal number of clustering categories from multiple numbers of clustering categories by the optimal number of clustering categories judgment method, and determine the category to which each power user belongs according to the first clustering result corresponding to the optimal number of clustering categories.

[0090] In some embodiments of the present disclosure, the optimal method for determining the number of clustering categories is any one of the following: silhouette method, DBI (Davies Boudlin Index) method, VRC (Variance Ratio Criterion) method.

[0091] In some embodiments of the present disclosure, the utility function of each power user under each category is expressed by the following formula:

[0092]

[0093] in, It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is the recommended package p designed for the rth category r , and the central load curve is The electricity usage at Represents the central load curve of the rth category The power load in the tth time period, p r，t Indicates recommended set meal p r The recommended package price for the tth time period, p r，t(0) Indicates the original retail package p r(0) is the original retail package price for the t-th time period, T is the total number of time periods considered in the package, and is the power elasticity parameter.

[0094] In some embodiments of the present disclosure, the individual rational constraints of each power user under each category are constructed based on the utility function and are expressed as follows:

[0095]

[0096] Among them, p r′ It represents the recommended packages designed for all categories except the rth category; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r′ , and the central load curve is The electricity usage at that time; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r(0) , and the central load curve is The electricity usage at that time.

[0097] In some embodiments of the present disclosure, the package optimization model is expressed by the following formula:

[0098]

[0099] Among them, p r，t represents the recommended package designed for the electricity user belonging to the rth category in the tth time period, For electricity users belonging to category r, in the recommended package p r，t The predicted power load for the next time period t is: represents the total electricity sales revenue obtained by the electricity retailer from multiple electricity users, p r，t(0) represents the original retail package p of the electricity user belonging to the rth category r(0) The original retail package price in the tth time period, α is the power elasticity parameter, Represents the central load curve of the rth category The power load in the tth time period is {k|k∈r} represents the set of electricity users belonging to the rth category, card({k|k∈r}) represents the total number of electricity users belonging to the rth category, q k,t(0) Represents the historical load curve data q of power user k k(0) The power load in the tth time period, q k(0) =(q k，1(0) ,…,q k，t(0) ,…,q k，T(0) ), Represents the historical load curve data q k(0) After normalization, the average power load of power user k in the tth time period is: represents the maximum power load of power user k within the total time T considered in the package, is the average daily electricity purchase price of the electricity retailer in the t period, L t is the electricity retailer’s purchase amount in the tth time period, is the total electricity purchase cost of the electricity retailer, and C is the risk loss of the electricity retailer.

[0100] In some embodiments of the present disclosure, the retail package change limit constraint is expressed by the following formula:

[0101]

[0102] Where M is the total number of time periods of the package, m = 1, 2, ..., M, represents the upper limit of the number of times the package price changes, represents the recommended package p designed for the rth category r The price of the mth time period; is a 01 variable, for the recommended package p r , if time period t belongs to the mth time-sharing time period, then τ min The minimum duration for each time-sharing period.

[0103] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0105] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0106] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0107] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this disclosure shall comply with the relevant laws and regulations and shall not violate public order and good morals.

[0108] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0109] The present disclosure anticipates providing implementation schemes for users to selectively block the use or access of personal information data. That is, the present disclosure anticipates providing hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0110] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0111] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0112] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0114] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0115] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0116] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0117] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A data-driven electricity retail package push method considering individual rationality, characterized in that: The following steps are involved: Obtain historical load curve data for multiple power users; Clustering the historical load curve data, and determining the category to which each of the power users belongs and the central load curve of each category according to the clustering result; Based on a data-driven approach, a utility function of the power users in each category is constructed using the central load curve of each category, and individual rational constraints of the power users in each category are constructed based on the utility function; Taking the maximization of the profit of the power retailer as the goal, taking the recommended packages designed for each category as the optimization variable, considering the power consumption-purchase power balance constraint, the power retailer risk loss constraint, the individual rationality constraint of the power user and the limit constraint on the number of retail package changes, a package optimization model is constructed; Solving the package optimization model to obtain recommended packages corresponding to multiple categories; The recommended packages corresponding to each of the multiple categories are pushed to the user.

2. The method according to claim 1, characterized in that The clustering of the historical load curve data and determining the category to which each of the power users belongs according to the clustering result includes: Clustering the historical load curve data respectively by using a plurality of clustering methods, and obtaining a first clustering result corresponding to each of the clustering methods, wherein the first clustering result includes the number of clustering categories and the corresponding classification of the plurality of power users; An optimal clustering category number is determined from a plurality of clustering category numbers by using an optimal clustering category number determination method, and a category to which each of the power users belongs is determined according to a first clustering result corresponding to the optimal clustering category number.

3. The method according to claim 2, characterized in that The optimal clustering category number determination method is any one of the following: silhouette method, DBI (Davies Boudlin Index) method, VRC (Variance Ratio Criterion) method.

4. The method according to claim 1, characterized in that: The utility function of each electricity user under the classification is expressed by the following formula: in, It means that for the electricity user k belonging to the rth category, in the original retail package of P r(0) , the new package is the recommended package P designed for the rth category r , and the central load curve is The electricity usage at Represents the central load curve of the rth category The power load in the tth time period, P r，t Indicates recommended set meal P r The recommended package price for the tth time period, p r，t(0) Indicates the original retail package P r(0) Where is the original retail package price for the t-th time period, T is the total number of time periods considered in the package, and α is the power elasticity parameter.

5. The method according to claim 4, characterized in that The individual rational constraints of the power users under each category constructed based on the utility function are expressed as follows: Among them, P r′ Indicates the recommended packages designed for all the categories except the rth category; It means that for the electricity user k belonging to the rth category, in the original retail package of p r(0) , the new package is p r′ , and the central load curve is The electricity usage at that time; It means that for the electricity user k belonging to the rth category, in the original retail package of P r(0) , the new package is P r(0) , and the central load curve is The electricity usage at that time.

6. The method according to claim 1, characterized in that The package optimization model is expressed by the following formula: Among them, p r，t represents the recommended package designed for the electricity user belonging to the rth category in the tth time period, For electricity users belonging to category r, in the recommended package p r，t The predicted power load for the next time period t is: represents the total electricity sales revenue obtained by the electricity retailer from the multiple electricity users, p r，t(0) represents the original retail package p of the electricity user belonging to the rth category r(0) The original retail package price in the tth time period, α is the power elasticity parameter, Represents the central load curve of the rth category The power load in the tth time period is {k|k∈r} represents the set of electricity users belonging to the rth category, card({k|k∈r}) represents the total number of electricity users belonging to the rth category, q k，t(0) Represents the historical load curve data q of power user k k(0) The power load in the tth time period, q k(0) =(q k，1(0) , ..., q k，t(0) , ..., q k，T(0) ), Represents the historical load curve data q k(0) After normalization, the average power load of power user k in the tth time period is: represents the maximum power load of power user k within the total time T considered in the package, is the average daily electricity purchase price of the electricity retailer in the t period, L t is the electricity retailer’s purchase amount in the tth time period, is the total electricity purchase cost of the electricity retailer, and C is the risk loss of the electricity retailer.

7. The method according to claim 1, characterized in that The retail package change limit constraint is expressed by the following formula: Among them, M is the total number of time periods of the package, m = 1, 2, ..., M, represents the upper limit of the number of times the package price changes, represents the recommended package p designed for the rth category r The price of the mth time period; is a 01 variable, for the recommended package p r , if time period t belongs to the mth time-sharing time period, then τ min The minimum duration for each time-sharing period.

8. A data-driven electricity retail package push device that takes individual rationality into consideration, characterized in that: include: An acquisition module, used to acquire historical load curve data of multiple power users; A clustering module, used for clustering the historical load curve data, determining the category to which each of the power users belongs according to the clustering result, and determining the central load curve of each category according to the historical load curve data of the power users under each category; A first building module is used to build a utility function of the power users in each category by using the central load curve of each category based on a data-driven method, and to build a personal rational constraint of the power users in each category based on the utility function; The second construction module is used to maximize the profit of the power retailer, take the recommended packages designed for each category as the optimization variable, consider the power consumption-purchase power balance constraint, the power retailer risk loss constraint, the individual rationality constraint of the power user, the power user's power consumption response law constraint and the retail package change segment limit constraint, and construct a package optimization model; A determination module, used to solve the package optimization model to obtain recommended packages corresponding to multiple categories; The push module is used to push the recommended packages corresponding to the multiple categories to the user.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 10.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 10 when executed by a processor.

Images