Method for determining power demand response potential of industrial user in power grid dispatching

Abstract

The invention relates to the technical field of power grid regulation and control, and particularly provides a method for determining the power demand response potential of an industrial user in power grid dispatching, and the method comprises the steps: obtaining historical power load parameters of a target user under different power demands; performing transformation processing on the historical power load parameters to obtain corresponding load characteristic data; clustering is carried out according to the load characteristic data and preset clustering parameters, the response category of the target user is determined, the clustering parameters are obtained through clustering according to electric power related parameters of the investigation users, the clustering parameters comprise at least one of the clustering center and the clustering number, and the investigation users are users in the area where the target user is located; and calculating the power demand response potential of the target user according to the response category. Therefore, the problem of difficult management and scheduling caused by large power demand difference of industrial users in the prior art is solved.

Description

Technical Field

[0001] The invention relates to the technical field of power grid regulation, and in particular to a method for determining the power demand response potential of industrial users in power grid dispatching. Background Art

[0002] Power demand response is a method of power demand side management. When the reliability of the power system is threatened, including power system behaviors such as excessive peaks, power users change their habitual power consumption patterns to reduce or shift the power load in a certain period of time to meet the power supply stability requirements and ensure the stability of the power grid.

[0003] In the relevant technologies, only qualitative analysis is generally performed to determine the response actions of specific departments under specific response situations. The power load of industrial users in the power grid is greatly affected by the type of enterprise, production equipment, production process, etc. The load characteristics of power equipment are relatively complex, and the power demand varies greatly in different time periods, which makes management and scheduling difficult.

[0004] There is currently no effective solution to the problem that the power demand of industrial users in related technologies varies greatly, resulting in difficulties in management and scheduling. Summary of the invention

[0005] The invention provides a method for determining the power demand response potential of industrial users in power grid dispatching, which at least solves the problem in the related art that the power demand of industrial users varies greatly, leading to difficulties in management and dispatching.

[0006] The embodiment of the present invention provides a method for determining the power demand response potential of industrial users in power grid dispatching, including: obtaining historical power load parameters of target users under different power demands; transforming the historical power load parameters to obtain corresponding load characteristic data; clustering according to the load characteristic data and preset clustering parameters to determine the response category of the target user, wherein the clustering parameters are obtained by clustering power-related parameters of surveyed users, and the clustering parameters include at least one of the following: cluster center, number of clusters, and the surveyed users are users in the area where the target users are located; and calculating the power demand response potential of the target user according to the response category.

[0007] As an optional embodiment, before clustering is performed according to the load characteristic data and preset clustering parameters to determine the response category of the target user, the method also includes: obtaining power-related parameters of the surveyed user, wherein the power-related parameters include at least one of the following: response parameters, industry prosperity index, peak shaving and valley filling potential, and feeder response potential; performing transformation processing according to the power-related parameters to obtain corresponding characteristic data; performing clustering according to the characteristic data to obtain multiple response categories; and determining the clustering parameters according to the response category.

[0008] As an optional embodiment, obtaining the power-related parameters of the survey user in the current unit time includes: obtaining the response parameters of the survey user in the current unit time, wherein the response parameters are used to characterize the response type and response method of the survey user under different power demands; determining the industry prosperity index according to the load curve of the survey user in different historical unit times; determining the peak shaving and valley filling potential according to the industry type, flexible load ratio, and load curve of the survey user in the current unit time; superimposing the peak shaving and valley filling potentials of different survey users on the feeder of the power grid in the area where the survey user is located, and obtaining the feeder response potential at the feeder.

[0009] As an optional embodiment, the clustering parameters are determined according to the response category, including: determining the survey users corresponding to the response category; obtaining the historical power load parameters of the survey users of the response category in the historical unit time, and setting the number of clustering categories to one, clustering the historical power load parameters of the survey users of the same response category to obtain the cluster center of the response category; determining the cluster centers of multiple response categories by traversal, adding one to the number of determined cluster centers as the number of clusters; and determining the clustering parameters according to the cluster centers and the number of clusters.

[0010] As an optional embodiment, clustering is performed according to the feature data to obtain multiple response categories, including: determining the number of clustering categories according to the number of combinations of response types and response methods in the response parameters; and clustering the feature data using a clustering algorithm according to the number of categories to obtain multiple response categories with corresponding data.

[0011] As an optional embodiment, clustering is performed using a clustering algorithm according to the number of categories to obtain multiple response categories with corresponding data, including: calculating the probability that the survey user belongs to different response categories according to the clustering algorithm; determining the response category of the survey user according to whether the probability reaches a corresponding probability threshold, wherein the corresponding relationship between the survey user and the response category is one-to-one or one-to-many; and taking the response category with the corresponding survey user as the final response category.

[0012] As an optional embodiment, the historical power load parameters are transformed to obtain corresponding response characteristic data, including: quantitatively calculating each historical power load parameter at different times to determine the characteristic value corresponding to each historical image parameter; normalizing the characteristic values ​​of the historical power load parameters at different times to obtain corresponding response characteristic data.

[0013] As an optional embodiment, calculating the electricity demand response potential of the target user in the current unit time according to the response category includes: determining a potential calculation method for the response category, wherein the potential calculation method includes load parameters required for potential calculation, and a calculation method; using the potential calculation method as an objective function, obtaining preset constraints, and calculating the optimal solution of the electricity demand response potential according to the load parameters of the target user in the current unit time, wherein the constraints include at least one of the following: load minimization and electricity cost minimization.

[0014] The present invention also provides an electronic device, including: a processor, and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the above method.

[0015] The present invention also provides a non-transitory machine-readable medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the above method.

[0016] The present invention also provides a computer program product, including a computer program / instruction, wherein the computer program / instruction implements the above method when executed by a processor.

[0017] The invention provides a method for determining the power demand response potential of industrial users in power grid dispatching, which obtains clustering parameters by investigating the power-related parameters of users, and clusters the historical power load parameters of target users using the clustering parameters to determine the response category of the target users, and then determines the power demand response potential of the target users, so as to accurately reflect the response ability of the target users, support power dispatching, and manage the target users. The problem that the power demand of industrial users varies greatly, leading to difficulties in management and dispatching, is solved, and the technical effect of reducing the difficulty of managing industrial users is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other embodiments can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a flow chart of a method for determining the power demand response potential of industrial users in power grid dispatching according to an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of a response potential determination process of an industrial user according to an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of a device for determining the power demand response potential of industrial users in power grid dispatching according to an embodiment of the present invention.

[0022] Figure 4 It is a structural schematic diagram of the electronic device created by the present invention. DETAILED DESCRIPTION

[0023] The embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0024] Among the related technologies, under the new situation of new power system construction, higher requirements are put forward for power demand side management. With the gradual advancement of power market reform, demand response will play an increasingly important role in the future new power system.

[0025] For local power supply companies that provide power supply services directly to power users, accurately, quickly and effectively exploring users' demand response potential is an important measure to alleviate power supply pressure during peak periods and ensure the safe operation of the power grid. Identifying the demand response potential of user load characteristics is an important prerequisite for discovering demand response users and resources.

[0026] Existing methods for analyzing the potential for power demand response and identifying potential users are mostly based on the analysis of historical load data of power users. They explore the response potential of various industries or types of users in a data-driven manner. It is difficult to fully consider the actual willingness and potential of individual power users to participate in demand response, which ultimately affects the accuracy of power demand response decisions.

[0027] The load data of industrial enterprises is greatly affected by industry development trends (order volume), process characteristics, major production equipment, etc. The load characteristics of power equipment are related to actual production requirements. When flexible load adjustment cannot meet the response requirements of power demand, corporate users with strong response potential are needed to adjust the established production scheduling plans.

[0028] Due to different load data, industrial users have different capabilities to adjust their production scheduling plans and the effects of the adjustments. That is, their response potential under power demand varies greatly, leading to difficulties in management and scheduling. This requires accurate assessment of the response potential of different industrial users to power scheduling needs during the scheduling process.

[0029] In order to solve the above technical problems, an embodiment of the present invention provides a method for determining the power demand response potential of industrial users in power grid dispatching, comprising the following steps:

[0030] Step S101, obtaining historical power load parameters of a target user under different power demands;

[0031] Step S102, transforming the historical power load parameters to obtain corresponding load characteristic data;

[0032] Step S103, clustering is performed according to the load characteristic data and preset clustering parameters to determine the response category of the target user, wherein the clustering parameters are obtained by clustering the power-related parameters of the surveyed users, and the clustering parameters include at least one of the following: cluster center, number of clusters, and the surveyed users are users in the area where the target users are located;

[0033] Step S104: calculating the power demand response potential of the target user according to the response category.

[0034] The method for determining the power demand response potential of industrial users in the above-mentioned power grid dispatching provided by the embodiment of the invention obtains clustering parameters by investigating the power-related parameters of users, and clusters the historical power load parameters of target users using the clustering parameters to determine the response category of the target users, and then determine the power demand response potential of the target users, to accurately reflect the response ability of the target users, to support power dispatching, and to manage the target users. The problem that the power demand of industrial users varies greatly, leading to difficulties in management and dispatching, is solved, and the technical effect of reducing the difficulty of managing industrial users is achieved.

[0035] The execution subject of the above steps is the power grid dispatching terminal, which dispatches power to each user in the power grid, including but not limited to reducing the power supply, shortening the power supply time, etc. The above power grid dispatching terminal can be a terminal device such as a server, a calculator, a processor, a controller, etc. that can perform data storage and data processing.

[0036] The above target users are industrial users in the power grid. In other implementation scenarios, they can also be one or more types of users with common power characteristics, such as urban household users, agricultural users, and users of government agencies and institutions. The above power demand can be understood as the power dispatch demand of the power grid dispatch terminal for users, including but not limited to reducing the frequency of use, reducing the total amount of power consumption, changing the power consumption period, etc.

[0037] The above historical power load parameters can be understood as the power load data of the target user in the historical unit time. The historical unit time can be a historical year, a historical month, etc. The power load data can include the power load values ​​of the target user at different times, the load working mode and other data. The power load data can characterize the target user's demand for power use. The power load data of different historical unit time can reflect the target user's power use level, power use change, power use trend, etc., which can all be used as influencing factors for evaluating response potential.

[0038] Considering that different power load data may not exist in numerical form, in order to facilitate subsequent calculations, the historical power load parameters are transformed to obtain corresponding load characteristic data. The transformation processing method of different data items can be a preset fixed method.

[0039] According to the load characteristic data and the preset clustering parameters, a preset clustering algorithm is used for clustering to determine the response category of the target user. The above clustering algorithm can be an unsupervised clustering algorithm such as k-means clustering, agglomerative clustering, mean shift clustering, etc.

[0040] Taking the k-means clustering algorithm as an example, the clustering parameters include at least one of the following: cluster center, number of clusters k. The above clustering parameters are obtained by clustering the power-related parameters of the surveyed users. The surveyed users are users in the area where the target users are located. The difference between the surveyed users and other surveyed users is that the surveyed users obtain more accurate power-related parameters through actual data collection to ensure the accuracy of the power response capability.

[0041] The power load parameters mainly include the existing load-related parameters of industrial users. The power-related parameters not only include the power load parameters that can be directly and quickly obtained, but also combine the load response behavior of actual surveys to obtain relevant power parameters, which also include some parameters obtained by analyzing and processing the power load parameters.

[0042] Specifically, the power-related parameters include power load parameters, and may also include response parameters, industry prosperity index, peak shaving and valley filling potential, feeder response potential and other parameters in multiple dimensions, which will be described in detail later.

[0043] Compared with power load parameters, power-related parameters have the performance of more accurate response capability, but they are more difficult to obtain and require more work, which is not conducive to the rapid needs of power dispatch.

[0044] Therefore, we use the more detailed multi-dimensional power-related parameters of the surveyed users to cluster and determine the clustering parameters, so that the clustering model can more quickly form a more accurate clustering capability for response potential classification, and cluster the power load parameters of the target users that are easily obtained to determine the response potential category corresponding to the target users. This makes the clustering results of the target users more accurate and closer to the actual response capabilities or levels.

[0045] By clustering surveyed users, the clustering results and clustering models have more accurate clustering capabilities that are closer to the actual situation. In particular, clustering the historical power load data of target users that have not been surveyed can make the clustering effect of target users better and more accurate based on the clustering parameters obtained by clustering surveyed users.

[0046] The above calculation of the target user's power demand response potential based on the response category can be understood as after determining the category of the target user, the target user's power demand response potential can be calculated based on the response category to which the target user belongs and in combination with other data. The specific method will be described later.

[0047] The power demand response potential can be a ranking table of different users, or a numerical value, or different levels to characterize the levels of different power demand response potentials.

[0048] As an optional embodiment, before clustering is performed according to load characteristic data and preset clustering parameters and determining the response category of the target user, the method also includes: obtaining power-related parameters of the surveyed user, wherein the power-related parameters include at least one of the following: response parameters, industry prosperity index, peak shaving and valley filling potential, and feeder response potential; performing transformation processing according to the power-related parameters to obtain corresponding characteristic data; performing clustering according to the characteristic data to obtain multiple response categories; and determining clustering parameters according to the response categories.

[0049] The electricity-related parameters may also include response parameters, that is, parameters that respond under different electricity demands, including but not limited to whether the production load can be shifted, how much the shift can be, how long the time is, how much the non-production load can be reduced, the auxiliary production load, whether the main production load can be reduced, and how much it can be reduced.

[0050] The response parameters can be reflected by various data. In this embodiment, the response parameters may include: production mode, process type, distributed energy parameters, and load parameters.

[0051] The production mode can include production shifts and work calendars. Production shifts include: single shift, double shift, triple shift, and others. Work calendars include: open all year round, single day off, double day off, and others.

[0052] The process type includes: whether it is a process or a coexistence of non-process and process. And whether there is a special process (process with large energy loss and long preparation time, such as high temperature treatment, electroplating, etc.), and parameter transformation is performed according to the special process load ratio.

[0053] Distributed energy parameters include: photovoltaic installed capacity, which is converted by the ratio of photovoltaic installed capacity to maximum demand capacity. And energy storage installed capacity, which is converted by the ratio of energy storage capacity (kW) to maximum load;

[0054] Load parameters include: power load rate, which is the ratio of maximum load to contract capacity. Safety load, which is the ratio of safety load. Main production load, which is the ratio of main production load. Non-production load, which is the ratio of non-production load. Whether the user is an orderly power user, etc.

[0055] Electricity-related parameters may also include an industry prosperity index, which is an index that characterizes the industry development level of the target users, including the level of the industry to which the target users belong, production priority, etc.

[0056] Power-related parameters may also include peak-shaving and valley-filling potential, that is, the ability to shift loads by reducing loads or increasing loads, including but not limited to flexible composite ratios, load curves, etc.

[0057] The power-related parameters may also include feeder response potential, which is the superposition value of the peak-shaving and valley-filling potential for different users at the feeder on the topological structure of the power grid in the target user's area.

[0058] According to the power-related parameters, the corresponding characteristic data is obtained by transformation processing. Similar to the way the power load data is transformed, certain transformation rules can be set for non-parametric data to perform numerical conversion. Generally speaking, the numerical values ​​of the final conversion of each power-related parameter are consistent in the performance of characterizing the response potential. For example, the larger the value, the higher the response potential of the parameter, and the smaller the value, the lower the response potential of the parameter.

[0059] By investigating the power-related parameters of the above-mentioned multiple dimensions of users and clustering them, the determined clustering parameters can make the clustering model more accurate and have a clustering capability that is closer to the actual situation. This can improve the clustering accuracy of the historical power load of the target user, that is, improve the accuracy of the target user's power demand response potential.

[0060] As an optional embodiment, obtaining power-related parameters of the surveyed user in the current unit time includes: obtaining response parameters of the surveyed user in the current unit time, wherein the response parameters are used to characterize the response type and response method of the surveyed user to different power demands; determining the industry prosperity index according to the load curve of the surveyed user in different historical unit times; determining the peak shaving and valley filling potential according to the industry type, flexible load ratio, and load curve of the surveyed user in the current unit time; and superimposing the peak shaving and valley filling potentials of different surveyed users on the feeder of the power grid in the area where the surveyed users are located to obtain the feeder response potential at the feeder.

[0061] The response parameters are used to characterize the response type and response method of the surveyed users under different power demands. Among them, the response type may include: day-ahead response, intra-day response (within 8 hours, 4 hours, 2 hours, etc.), and the response method may include: adjusting flexible loads, shutting down some rigid loads, adjusting holidays and stopping production, etc.

[0062] The industry prosperity index is determined based on the load curves of surveyed users at different historical unit times. The primary and secondary classifications of each enterprise can be clarified according to the national industry classification standards, and parameter transformation can be performed according to hot industries (for example, the increase exceeds 10%, the economic volume exceeds 5%), hot industry-related industries, mature industries, and industries with overcapacity. The growth rate of the overall load curve of industrial users in a certain industry at different historical unit times can be combined to characterize the prosperity index of the industry.

[0063] Generally speaking, the more popular the industry, the higher the corresponding industry prosperity index, and the higher the growth rate, the higher the corresponding industry prosperity index.

[0064] The peak-shaving and valley-filling potential is determined based on the industry type, flexible load ratio, and load curve of the surveyed user in the current unit time. The industry type can characterize the priority of the surveyed user's electricity demand, and then reflect the response potential of the load shift, that is, the peak-shaving and valley-filling potential. The flexible load ratio is the ratio of the non-essential load to the necessary load of the surveyed user. The non-essential load can be adjusted according to demand. The load curve is the change in the load curve of the surveyed user. Combining the above parameters, the peak-shaving and valley-filling potential of the surveyed user can be evaluated.

[0065] As an optional embodiment, clustering parameters are determined according to the response category, including: determining the survey users corresponding to the response category; obtaining the historical power load parameters of the survey users of the response category in the historical unit time, and setting the number of cluster categories to one, clustering the historical power load parameters of the survey users of the same response category to obtain the cluster center of the response category; determining the cluster centers of multiple response categories by traversal, adding one to the number of determined cluster centers as the number of clusters; and determining the clustering parameters according to the cluster centers and the number of clusters.

[0066] After obtaining the clustered response categories, the clustering parameters of the clustering model / algorithm are obtained by performing unsupervised clustering on the power-related parameters of the surveyed users. In particular, the selection of the cluster center will have certain errors. In this embodiment, for each response category, the historical power load parameters of the surveyed users of the response category are obtained, and the number of cluster categories is set to 1, and clustering is performed to obtain the cluster center of the response category. This cluster center can accurately cluster the performance of whether the target user belongs to the response category based on the historical power load.

[0067] Theoretically, one response category can correspond to one cluster number. Considering that there is an extreme case where none of the target users belong to the existing response categories, the number of clusters is calculated by adding one to the number of response categories, that is, the number of cluster centers mentioned above, so that the final clustering result is more accurate and avoids the classification of target users with low similarity or difficult to cluster with low accuracy. Thus, the final classification result has higher accuracy.

[0068] As an optional embodiment, clustering is performed based on the feature data to obtain multiple response categories, including: determining the number of clustering categories based on the number of combinations of response types and response methods in the response parameters; and clustering the feature data using a clustering algorithm based on the number of categories to obtain multiple response categories.

[0069] When clustering according to the response characteristics of power-related parameters, taking into account that the response types and response methods have been clearly defined and divided, in order to improve the efficiency and accuracy of unsupervised clustering of power-related parameters, the number of combinations of response types and response methods is used as the number of clustering categories, and clustering is performed using a clustering algorithm.

[0070] As an optional embodiment, clustering is performed using a clustering algorithm according to the number of categories to obtain multiple response categories with corresponding data, including: calculating the probability that the survey user belongs to different response categories according to the clustering algorithm; determining the response category of the survey user according to whether the probability reaches a corresponding probability threshold, wherein the correspondence between the survey user and the response category is one-to-one or one-to-many; and taking the response category with the corresponding survey user as the final response category.

[0071] The response categories of the surveyed users obtained by clustering the power-related parameters can be expressed in the form of probability, so it is necessary to use the probability to further accurately divide the response categories to which the surveyed users belong.

[0072] For example, when more than 60% of the samples of a survey user in a cluster belong to the first cluster type, the survey user is defined as the corresponding first cluster type; when more than 60% of the samples of a survey user in a cluster belong to the first cluster type, but the response behavior obviously belongs to the second cluster type, the survey user is defined as the second cluster type; when the proportion of the survey user's samples belonging to the first cluster type is between 40% and 60%, it is defined as other types, that is, other cluster types with higher proportions; when the proportion of the survey user's samples belonging to the first cluster type is less than 40%, it is defined as non-first cluster type. The classification standard can be redefined according to the accuracy requirements.

[0073] Therefore, the correspondence between the above survey users and response categories is one-to-one or one-to-many.

[0074] In addition, considering that the surveyed users and the target users belong to the same regional power grid, in order to improve the clustering accuracy, the response category with the corresponding surveyed user can be used as the final response category, and the response category without parameters can be discarded. It can be understood that the probability that the target user belongs to this response category is almost zero.

[0075] As an optional embodiment, the historical power load parameters are transformed to obtain corresponding response characteristic data, including: quantitatively calculating each historical power load parameter at different times to determine the characteristic value corresponding to each historical image parameter; normalizing the characteristic values ​​of the historical power load parameters at different times to obtain corresponding response characteristic data.

[0076] For example, load types may include productive load, non-production load, auxiliary production load, safety compliance, etc., and their values ​​can be transformed by proportion.

[0077] For another example, production types may include single shift, double shift, triple shift, etc., and different scores may be set according to corresponding levels.

[0078] For example, load behavior may include conducting main production while ensuring safety; during holidays, only ensuring power consumption of safety equipment, etc. This can be scored according to preset scoring rules to evaluate the impact of load behavior on response potential.

[0079] As an optional embodiment, the target user's electricity demand response potential in the current unit time is calculated according to the response category, including: determining a potential calculation method for the response category, wherein the potential calculation method includes load parameters required for potential calculation, and a calculation method; using the potential calculation method as an objective function, obtaining preset constraints, and calculating the optimal solution for the electricity demand response potential according to the target user's load parameters in the current unit time, wherein the constraints include at least one of the following: load minimization, electricity cost minimization.

[0080] Demand response potential is evaluated according to the response category, so as to establish the calculation formula of load variance and electricity cost according to the load parameters, and the optimization goal is to minimize both load variance and electricity cost. Set constraints: technical restrictions such as load response amount, response period, response duration, energy balance, etc.; economic constraints that participate in response can save electricity costs, perform iterative optimization, sort the final optimization results, and confirm the demand response potential level of the industrial user. Different response potential levels can also set corresponding response potential indexes as indicators for subsequent power dispatch.

[0081] There are many ways to dispatch electricity. One common way is to restrict the power consumption of industrial users with high response potential in the case of power shortage, including but not limited to load shifting, reducing power supply, reducing power supply frequency, etc. Another dispatching method is to predict the subsequent changes of the power grid through the power fluctuation of the power grid. If regulation is needed, the regulation notification will be issued in advance to avoid the suspension of power consumption of users after adjustment in the event of power shortage.

[0082] It should be noted that this embodiment also provides an optional implementation, which is described in detail below.

[0083] This implementation method proposes a method of identifying potential users of power demand response by integrating multi-dimensional power load data of industrial users and factors such as industry development prosperity. Taking into account the constraints of uncertain influencing factors such as market and technology on response potential in actual situations, a more accurate portrait of industrial users of power demand response and power load characteristics is obtained, so as to locate potential power demand response users of different types or characteristics, and provide an effective basis for the formulation of regional power demand response policies.

[0084] For industrial users, production always comes first, which means that under the current power demand response, it is difficult for industrial enterprises to actively implement power demand response measures during normal operation. In order to solve the low enthusiasm for power demand response under existing technologies and management mechanisms, and to meet the higher requirements for power demand side management in new power systems. This implementation method provides a method for identifying potential users of power demand response and response potential. Through the method of this implementation method, the resource richness of the demand response system is greatly improved, the accuracy of power dispatch is improved, and the impact of invalid dispatch plans on power grid stability is reduced.

[0085] A method for identifying industrial users with potential for power demand response is proposed. Based on large-scale survey information related to power demand response of industrial enterprises, a K-means clustering model of industrial users with potential for power demand response is constructed. Cluster groups are classified and defined according to the way in which each industrial enterprise participates in demand response, and k cluster centers are recorded. A large number of power load characteristic samples of non-surveyed enterprises are added, and the k cluster centers are used as initial cluster centers to re-cluster a large number of samples. According to the clustering results, whether each non-surveyed enterprise is a potential industrial user for power demand response is identified.

[0086] Figure 2 Schematic diagram of the response potential determination process of an industrial user according to an embodiment of the present invention, Figure 2 As shown, the specific steps are as follows:

[0087] Step 1: Based on the electricity-related parameters of industrial survey users, classify and define the ways and types of industrial users' participation in electricity demand response. The response types may include: day-ahead response, intra-day response (within 8 hours, 4 hours, 2 hours, etc.), and the response methods may include: adjusting flexible loads, shutting down some rigid loads, adjusting holidays and stopping production, etc.

[0088] Step 2: Perform feature transformation (quantification or standardization) on the power-related parameters of the surveyed users, and use the k-means clustering method to perform cluster analysis after normalizing all the transformation parameters. The k value of the K-means clustering algorithm is equal to the number of combinations of response types and response methods defined in step 1 plus 1, where "1" represents the user type that does not participate in demand response.

[0089] The main power-related parameters and characteristic change parameters are as follows:

[0090] a) Production mode: a.1 Production shift system: single shift, double shift, triple shift, other; a.2 Working calendar: all year round, single day off, double day off, other;

[0091] b) Process type: b.1 Is it a process technology, or is it a coexistence of non-process technology and process technology? b.2 Is there a special process (process with large energy loss and long preparation time, such as high temperature treatment, electroplating, etc.), and parameter transformation is performed according to the special process load ratio;

[0092] c) Distributed energy parameters: c.1 Photovoltaic installed capacity, parameter transformation is performed based on the ratio of photovoltaic installed capacity to maximum demand capacity; c.2 Energy storage installed capacity, parameter transformation is performed based on the ratio of energy storage capacity (kW) to maximum load;

[0093] d) Load parameters: d.1 Power load rate, parameter transformation is performed based on the ratio of maximum load to contract capacity; d.2 Safety load, parameter transformation is performed based on the proportion of safety load; d.3 Main production load, parameter transformation is performed based on the proportion of main production load; d.4 Non-production load, parameter transformation is performed based on the proportion of non-production load; d.5 Whether the user is an orderly power user;

[0094] e) Industry prosperity index: clarify the primary and secondary classification of each enterprise in accordance with the national industry classification standards, and transform the parameters according to popular industries (for example, the increase exceeds 10%, the economic size exceeds 5%), hot industry-related industries, mature industries, and industries with overcapacity.

[0095] Step 3: Perform statistical analysis on the cluster samples in step 2, classify the cluster samples according to the power demand response classification method in step 1, and count the proportion of participating response enterprises, the proportion of each response type, and the average response volume ratio (the average of the response capacity of each enterprise and the proportion of the highest load), etc. When more than 60% of the samples of a certain class in the cluster belong to a certain response type described in step 1, the class is defined as the response type defined in step 1; when the proportion of participating response samples in a certain class in the cluster exceeds 60%, but it clearly belongs to a certain type described in step 1, the class is defined as an indefinite response type; when the proportion of participating response samples is between 40% and 60%, it is defined as other types; when the proportion of participating response samples is less than 40%, it is defined as a non-response type. The classification standard can be redefined according to the accuracy requirements.

[0096] Step 4: Obtain the power load data of all the above-mentioned surveyed enterprises in the past three years (the data time span is within 1 hour), and perform feature changes on the power load data. The feature changes include but are not limited to the following parameters: average maximum load rate, maximum load increase or decrease ratio, daily peak load and duration, daily valley load and duration, holiday load days, daytime and nighttime load difference, peak-valley load difference during peak power hours, etc.; then, perform secondary K-means clustering on each cluster clustered in step 2 based on the normalized power load characteristic parameters, with the k value set to 1. Finally, each cluster forms a cluster center based on the power load characteristic parameters.

[0097] Step 5: Obtain the historical power load data of other industrial users in the survey area that did not participate in the survey, transform and normalize the characteristic parameters according to the same power load data characteristic change method as in step 4, and perform k-means re-clustering, using the cluster center obtained in step 4 as the initial cluster center, and finally forming the same number of clusters as in step 2.

[0098] Step 6: Define each type of cluster sample based on the above type classification and response ratio statistics, and clarify whether each type of cluster sample is a potential user participating in electricity demand response and the corresponding response potential, so as to determine the response potential of industrial users who did not participate in the survey based on the clustering results obtained in step 5, and provide a decision-making basis for the formulation of electricity demand response plans or policies for the entire region.

[0099] When clustering is performed in the above step 1, the peak shaving and valley filling potential and the feeder response potential can also be combined for clustering. That is, before clustering, the user's peak shaving and valley filling potential is evaluated based on the type of industrial users and the proportion of flexible loads, combined with the typical load curve; according to the selected regional power grid topology, the peak shaving and valley filling potential of different user demand responses is superimposed on the feeder to obtain the total response potential at the feeder.

[0100] After the clustering in step 5 is completed, the demand response potential can also be evaluated based on the clustering results, with the minimization of load variance and electricity cost as the optimization goal: a) Constraints: technical restrictions such as load response amount, response period, response duration, energy balance, etc.; b) Economic constraints that participating in the response can save electricity costs; c) Sort the optimization results and confirm the demand response potential level of the industrial user.

[0101] Figure 3 Schematic diagram of a device for determining the power demand response potential of industrial users in power grid dispatching according to an embodiment of the present invention, such as Figure 3As shown, based on the method for determining the power demand response potential of industrial users in the above-mentioned power grid dispatching provided by the embodiment of the invention, the embodiment of the invention also provides a device for determining the power demand response potential of industrial users in power grid dispatching, which is applied to determine and calculate the power demand response potential of industrial users in the power grid dispatching process, and the device includes:

[0102] An acquisition module 31 is used to obtain historical power load parameters of the target user under different power demands; a transformation module 32 is connected to the above acquisition module 31, and is used to transform the historical power load parameters to obtain corresponding load characteristic data; a clustering module 33 is connected to the above transformation module 32, and is used to perform clustering according to the load characteristic data and preset clustering parameters to determine the response category of the target user, wherein the clustering parameters are obtained by clustering the power-related parameters of the surveyed users, and the clustering parameters include at least one of the following: cluster center, number of clusters, and the surveyed users are users in the area where the target users are located; a calculation module 34 is connected to the above clustering module 33, and is used to calculate the power demand response potential of the target user according to the response category, wherein the power demand response potential is used to support different regulation strategies to control the target user.

[0103] The above-mentioned device provided by the embodiment of the invention obtains clustering parameters by investigating the power-related parameters of users, and clusters the historical power load parameters of target users using the clustering parameters to determine the response category of the target users, and then determine the power demand response potential of the target users, so as to accurately reflect the response ability of the target users, support power dispatching, and manage the target users. The problem that the power demand of industrial users varies greatly, resulting in difficulties in management and dispatching is solved, and the technical effect of reducing the difficulty of managing industrial users is achieved.

[0104] The embodiments of the present invention also provide a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiments of the present invention.

[0105] The embodiments of the present invention further provide a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiments of the present invention.

[0106] The embodiment of the invention also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to enable the electronic device to perform the method of the embodiment of the invention when executed by the at least one processor.

[0107] refer to Figure 4 , a block diagram of an electronic device that can be used as a server or client of an embodiment of the invention will now be described, which is an example of hardware devices that can be applied to various aspects of the invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or required herein.

[0108] like Figure 4 As shown, the electronic device includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 to a random access memory (RAM) 403. In RAM 403, various programs and data required for the operation of the electronic device can also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0109] Multiple components in the electronic device are connected to the I / O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 can be any type of device that can input information to the electronic device, and the input unit 406 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device. The output unit 407 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 408 can include but is not limited to a disk, an optical disk. The communication unit 409 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, and / or a wireless communication transceiver, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0110] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU, a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing units, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above. For example, in some embodiments, the method embodiments created by the present invention may be implemented as a computer program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via ROM 402 and / or communication unit 409. In some embodiments, the computing unit 401 may be configured to perform the above-described method in any other appropriate manner (e.g., by means of firmware).

[0111] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the computer program, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable signal medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, or infrared systems, devices, or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] It should be noted that the term "including" and its variations used in the embodiments of the present invention are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present invention are illustrative and not restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0114] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0115] The various steps described in the method implementation methods provided by the embodiments of the present invention can be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0116] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same and similar parts between the various embodiments refer to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0117] The above-described embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of protection. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the attached claims.

Claims

1. A method for determining the power demand response potential of industrial users in power grid dispatching, characterized in that: include: Obtain historical power load parameters of target users under different power demands; Transforming the historical power load parameters to obtain corresponding load characteristic data; Clustering is performed according to the load characteristic data and preset clustering parameters to determine the response category of the target user, wherein the clustering parameters are obtained by clustering power-related parameters of the surveyed users, and the clustering parameters include at least one of the following: cluster center, number of clusters, and the surveyed users are users in the area where the target users are located; The power demand response potential of the target user is calculated according to the response category, wherein the power demand response potential is used to support different regulation strategies to control the target user.

2. The method according to claim 1, characterized in that Before clustering the load characteristic data and the preset clustering parameters to determine the response category of the target user, the method further includes: Obtaining power-related parameters of the surveyed user, wherein the power-related parameters include at least one of the following: response parameters, industry prosperity index, peak shaving and valley filling potential, and feeder response potential; Perform transformation processing according to the power-related parameters to obtain corresponding characteristic data; Clustering is performed according to the characteristic data to obtain multiple response categories; The clustering parameter is determined according to the response category.

3. The method according to claim 2, characterized in that Obtaining the power-related parameters of the surveyed user in the current unit time, including: Acquire the response parameter of the survey user in the current unit time, wherein the response parameter is used to characterize the response type and response mode of the survey user under different power demands; Determine the industry prosperity index based on the load curves of the surveyed users at different historical unit times; Determine the peak shaving and valley filling potential according to the industry type, flexible load ratio, and load curve of the surveyed user in the current unit time; The peak shaving and valley filling potentials of different surveyed users on the feeder of the power grid in the area where the surveyed user is located are superimposed to obtain the feeder response potential at the feeder.

4. The method according to claim 2, characterized in that: Determining the clustering parameter according to the response category includes: Determine survey users corresponding to the response category; Obtaining historical power load parameters of survey users of the response category in historical unit time, setting the number of cluster categories to one, clustering the historical power load parameters of survey users of the same response category, and obtaining the cluster center of the response category; Determine the cluster centers of the multiple response categories by traversing, and add one to the number of the determined cluster centers to obtain the number of clusters; The clustering parameters are determined according to the cluster centers and the number of clusters.

5. The method according to claim 2, characterized in that: Clustering is performed based on the characteristic data to obtain multiple response categories, including: Determining the number of categories of the clustering according to the number of combinations of response types and response modes in the response parameters; According to the number of categories, the characteristic data is clustered using a clustering algorithm to obtain a plurality of response categories.

6. The method according to claim 5, characterized in that According to the number of categories, clustering is performed using a clustering algorithm to obtain multiple response categories with corresponding data, including: Calculating the probability that the surveyed user belongs to different response categories according to a clustering algorithm; Determining the response category of the survey user according to whether the probability reaches a corresponding probability threshold, wherein the corresponding relationship between the survey user and the response category is one-to-one or one-to-many; The response category with the corresponding survey user is taken as the final response category.

7. The method according to claim 1, characterized in that The historical power load parameters are transformed to obtain corresponding response characteristic data, including: Quantitatively calculate each historical power load parameter at different times and determine the characteristic value corresponding to each historical image parameter; The characteristic values ​​of historical power load parameters at different times are normalized to obtain the corresponding response characteristic data.

8. The method according to any one of claims 1 to 7, characterized in that Calculating the power demand response potential of the target user at the current unit time according to the response category includes: Determining a potential calculation method for the response category, wherein the potential calculation method includes load parameters required for potential calculation and a calculation method; The potential calculation method is used as the objective function, the preset constraints are obtained, and the optimal solution of the power demand response potential is calculated according to the load parameters of the target user in the current unit time, wherein the constraints include at least one of the following: load minimization and electricity cost minimization.

9. An electronic device, comprising: A processor and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 8.

10. A non-transitory machine-readable medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images