Energy consumption prediction method and device for power utilization object, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a kind of energy consumption prediction method, device, electronic equipment and storage medium of electrical object, comprising: according to the preset period, the multiple historical energy consumptions of electrical object are collected;Set the clustering target function with weight to the historical energy consumption clustering is carried out to be granulated and obtain granulated data, in the clustering target function, the distance of historical energy consumption to cluster center is negatively correlated with the weight;The granulated data is degranulated, and the data after degranulation is obtained;Using the data after degranulation establishes fuzzy rule model to predict the energy consumption of the electrical object.The embodiments of the present application, since in the clustering target function, the distance of historical energy consumption to cluster center is negatively correlated with the weight, can be dynamically adjusted in the clustering process by weight to clustering target function, further refine the distance of different historical energy consumptions to each cluster center, improve the clustering effect of historical energy consumption, ultimately improve the accuracy of energy consumption prediction of electrical object.

Description

Technical Field

[0001] This invention relates to the field of power grid distribution technology, and in particular to a method, apparatus, electronic device, and storage medium for predicting the energy consumption of electricity users. Background Technology

[0002] Electricity, as a clean energy source, plays an important role in the national economy. In order to improve the utilization efficiency of electricity, avoid unnecessary waste, and ensure the rational distribution of electricity, it is crucial to predict the demand for electricity based on historical electricity consumption data of electricity users.

[0003] Currently, the main method for predicting electricity consumption is to granulate and degranulate historical electricity consumption data before building models. The accuracy of the prediction depends on the accuracy of the granulation. However, the current accuracy of data granulation is low, which reduces the accuracy of subsequent electricity consumption prediction and is not conducive to power distribution in the power grid. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for predicting the energy consumption of electricity users, in order to solve the problem that the accuracy of granularizing historical energy consumption in the prior art is low, thus reducing the accuracy of energy consumption prediction.

[0005] In a first aspect, embodiments of the present invention provide a method for predicting the energy consumption of an electricity user, comprising:

[0006] Collect multiple historical energy consumption data of electricity users according to a preset cycle;

[0007] A weighted clustering objective function is set to cluster the historical energy consumption to obtain granular data. In the clustering objective function, the distance from the historical energy consumption to the cluster center is negatively correlated with the weight.

[0008] The granulated data is degranulated to obtain degranulated data;

[0009] The degranulated data is used to establish a fuzzy rule model to predict the energy consumption of the electricity user.

[0010] Optionally, the step of collecting multiple historical energy consumption data of electricity users according to a preset period includes:

[0011] Energy consumption of electricity users is collected according to a preset cycle;

[0012] The preset number of energy consumption data collected before the current moment are defined as multiple historical energy consumption data.

[0013] Optionally, setting a weighted clustering objective function to cluster the historical energy consumption data to obtain granular data includes:

[0014] Set a weighted clustering objective function;

[0015] A new objective function is obtained by introducing the Lagrange operator into the clustering objective function.

[0016] The gradient is obtained by calculating the derivative of the new objective function with respect to the membership degree;

[0017] When the gradient is equal to 0, the membership degree and weight are calculated as the granular data.

[0018] Optionally, the clustering objective function is as follows:

[0019]

[0020] in, Historical energy consumption x j Belongs to prototype v i To what extent, Let C be the weight, N be the number of prototypes, m and τ be the fuzzy exponents, and v be the weight. i For the i-th prototype, Let be the standard deviation, and i, j, k, c, N, m, and τ be natural numbers.

[0021] Optionally, the membership degree is as follows:

[0022]

[0023] The weights are as follows:

[0024]

[0025] Where f and t are natural numbers.

[0026] Optionally, the step of degranulating the granulated data to obtain degranulated data includes:

[0027] The degranulation objective function is set as follows:

[0028]

[0029] For the degranulated objective function Solving the granulated data by finding the gradient and setting the gradient to 0. as follows:

[0030]

[0031] Optionally, the step of using the degranulated data to establish a fuzzy rule model to predict the energy consumption of the electricity user includes:

[0032] The following fuzzy rule model is established using the degranulated data:

[0033]

[0034] in, Based on historical energy consumption x j The predicted energy consumption, f(x), represents a function of the input energy consumption x.

[0035] Secondly, embodiments of the present invention provide an energy consumption prediction device for an electricity user, comprising:

[0036] The historical data acquisition module is used to collect multiple historical energy consumption data of electricity users according to a preset cycle.

[0037] The granulation module is used to set a weighted clustering objective function to cluster the historical energy consumption to obtain granulated data. In the clustering objective function, the distance from the historical energy consumption to the cluster center is negatively correlated with the weight.

[0038] The degranulation module is used to degranulate the granulated data to obtain degranulated data;

[0039] The prediction module is used to establish a fuzzy rule model using the degranulated data to predict the energy consumption of the electricity user.

[0040] Optionally, the historical data acquisition module includes:

[0041] The power acquisition submodule is used to collect the energy consumption of power-consuming objects according to a preset cycle;

[0042] The historical data determination submodule is used to determine a preset number of energy consumption data collected before the current moment as multiple historical energy consumption data.

[0043] Optionally, the granulation module includes:

[0044] The clustering objective function setting submodule is used to set the weighted clustering objective function;

[0045] The new function establishes a submodule, which is used to introduce the Lagrange operator into the clustering objective function to obtain a new objective function;

[0046] The gradient calculation submodule is used to calculate the gradient of the new objective function with respect to the membership degree.

[0047] The membership and weight calculation submodule is used to calculate the membership and weight as the granular data when the gradient is equal to 0.

[0048] Optionally, the clustering objective function is as follows:

[0049]

[0050] in, Historical energy consumption x j Belongs to prototype v i To what extent, Let C be the weight, N be the number of prototypes, m and τ be the fuzzy exponents, and v be the weight. i For the i-th prototype, Let be the standard deviation, and i, j, k, c, N, m, and τ be natural numbers.

[0051] Optionally, the membership degree is as follows:

[0052]

[0053] The weights are as follows:

[0054]

[0055] Where f and t are natural numbers.

[0056] Optionally, the degranulation module includes:

[0057] The degranulation objective function setting submodule is used to set the degranulation objective function as follows:

[0058]

[0059] Granulated data solving submodule, used to solve the granulated objective function. Solving the granulated data by finding the gradient and setting the gradient to 0. as follows:

[0060]

[0061] Optionally, the prediction module includes:

[0062] The model building submodule is used to build the following fuzzy rule model from the degranulated data:

[0063]

[0064] in, Based on historical energy consumption x j The predicted energy consumption, f(x), represents a function of the input energy consumption x.

[0065] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0066] One or more processors;

[0067] Storage device for storing one or more computer programs.

[0068] When the one or more computer programs are executed by the one or more processors, the one or more processors implement the energy consumption prediction method for electricity users as described in any of the first aspects of the present invention.

[0069] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the energy consumption prediction method for an electricity-consuming object as described in any of the first aspects of the present invention.

[0070] In this embodiment of the invention, after collecting multiple historical energy consumption data of electricity users, a weighted clustering objective function is set to evaluate the distance between historical energy consumption data to obtain granular data. After degranulating the granular data to obtain degranulated data, a fuzzy rule model is established using the degranulated data to predict the energy consumption of electricity users. Since the distance between historical energy consumption data and cluster centers is negatively correlated with the weight in the clustering objective function, the clustering objective function can be dynamically adjusted through weights during the clustering process to further refine the distance between different historical energy consumption data and each cluster center, thereby improving the clustering effect of historical energy consumption and ultimately improving the accuracy of energy consumption prediction for electricity users. Attached Figure Description

[0071] Figure 1 This is a flowchart of an energy consumption prediction method for an electricity user provided in Embodiment 1 of the present invention;

[0072] Figure 2 This is a flowchart of an energy consumption prediction method for an electricity user provided in Embodiment 2 of the present invention;

[0073] Figure 3 This is a structural block diagram of an energy consumption prediction device for an electricity user provided in Embodiment 3 of the present invention;

[0074] Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0075] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0076] Example 1

[0077] Figure 1This is a flowchart illustrating an energy consumption prediction method for an electricity user according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the energy demand of an electricity user is predicted based on its historical energy consumption. The method can be executed by the energy consumption prediction device for the electricity user as described in this invention. This energy consumption prediction device can be implemented in hardware or software and integrated into the electronic device provided in this embodiment. Specifically, as shown... Figure 1 As shown, the energy consumption prediction method for electricity users in this embodiment of the invention may include the following steps:

[0078] S101. Collect multiple historical energy consumption data of electricity users according to a preset cycle.

[0079] In this embodiment of the invention, the electricity user can be an electricity user, such as a household, shop, or enterprise. The electricity user can also be a building, a geographically defined area, such as an office building, an area, a city, or a province. Alternatively, the electricity user can be electrical equipment, such as household appliances like televisions, refrigerators, air conditioners, and water heaters for a household user, or machinery and equipment for an enterprise, or a transformer that transmits power to an area. This embodiment of the invention does not limit the electricity user.

[0080] Historical energy consumption can be the power consumption of an electrical object during use, or other data that can measure energy consumption, such as electricity consumption. In one example, when the electrical object is an electricity user, the real-time energy consumption of the electricity user can be collected according to a preset period. For example, the power data of a household user can be collected every hour, or the power data of each electrical device can be collected once a day, or the total power data of an office building can be collected every hour, or the total power data of an area can be collected every ten minutes, etc. In practical applications, different collection periods can be set according to different types of electrical objects to collect the historical energy consumption of the electrical object.

[0081] S102. Set a weighted clustering objective function to cluster historical energy consumption to obtain granular data. In the clustering objective function, the distance from historical energy consumption to the cluster center is negatively correlated with the weight.

[0082] In practical applications, granulation can be a process of clustering multiple data sets to obtain multiple prototypes. Each prototype is a data cluster within the cluster, and the distance from the data in each data cluster to the cluster center (prototype center) is within a certain range, meaning that the data in the data cluster are of the same type. Specifically, in this embodiment of the invention, the clustering objective function can be a weighted FCM (Fuzzy C-Means) clustering objective function. In this clustering objective function, the smaller the distance of a historical energy consumption to the cluster center, the greater its weight. This makes a historical energy consumption more likely to cluster into a prototype with a large weight during the clustering process, thereby improving the accuracy of the granularized data obtained from the clustering and enhancing the accuracy of subsequent energy consumption prediction.

[0083] It should be noted that the weighted clustering process can refer to the FCM clustering process in the prior art. The difference is that after the clustering in the embodiment of the present invention is granulated, the granulated data includes not only the membership degree of each historical energy consumption to each prototype, but also the weight of each historical energy consumption to each prototype.

[0084] In an alternative embodiment, a Lagrange operator can be introduced for the clustering objective function, and then the membership degree and weight expressions can be calculated as granular data when the gradient is set to 0.

[0085] S103. Degranulate the granulated data to obtain the degranulated data.

[0086] Degranulation can be the process of performing an inverse operation on the granulated data. Degranulation aims to make the distribution of the degranulated data close to that of the original data. Specifically, in this embodiment of the invention, the energy consumption after degranulation is obtained by degranulating the granulated data, so that the energy consumption after degranulation is close to the historical energy consumption.

[0087] In an optional embodiment, a degranulation objective function can be set, in which the energy consumption after degranulation is used as a variable. The gradient of the degranulation objective function is calculated, and when the gradient is equal to 0, the expression of the energy consumption after degranulation can be calculated as the degranulated data.

[0088] S104. Use the degranulated data to establish a fuzzy rule model to predict the energy consumption of electricity users.

[0089] This invention can employ the TS fuzzy rule model. The TS fuzzy rule model is a nonlinear system described by a set of If-then fuzzy rules, where each rule represents a subsystem. Its original form, the fuzzy implication conditional statement, is "If x is A, then y = f(x)", where f(x) is a linear function of x. In other words, the TS fuzzy rule can be understood as follows: when the input historical energy consumption x belongs to a prototype with a membership degree of A, the corresponding predicted energy consumption output data can be obtained. The rule referred to here is the membership degree of a historical power consumption to each prototype.

[0090] This fuzzy rule model can predict the energy consumption of electricity users at the next moment after inputting historical energy consumption data, thereby enabling power distribution in the power distribution network through this energy consumption data.

[0091] It should be noted that when the electricity user is a household, the electricity allocation can be achieved by analyzing the predicted energy consumption of multiple households. When the electricity user is a single electrical device in a household, the predicted energy consumption of all electrical devices in each household can be summed to obtain the predicted total energy consumption of the household.

[0092] In this embodiment of the invention, after collecting multiple historical energy consumption data of electricity users, a weighted clustering objective function is set to evaluate the distance between historical energy consumption data to obtain granular data. After degranulating the granular data to obtain degranulated data, a fuzzy rule model is established using the degranulated data to predict the energy consumption of electricity users. Since the distance between historical energy consumption data and cluster centers is negatively correlated with the weight in the clustering objective function, the clustering objective function can be dynamically adjusted through weights during the clustering process to further refine the distance between different historical energy consumption data and each cluster center, thereby improving the clustering effect of historical energy consumption and ultimately improving the accuracy of energy consumption prediction for electricity users.

[0093] Example 2

[0094] Figure 2 This is a flowchart of an energy consumption prediction method for an electricity user provided in Embodiment 2 of the present invention. This embodiment optimizes the aforementioned Embodiment 1. Specifically, as shown... Figure 2 As shown, the energy consumption prediction method for electricity users in this embodiment of the invention may include the following steps:

[0095] S201. Collect the energy consumption of electricity users according to the preset cycle.

[0096] In this embodiment of the invention, energy consumption prediction is illustrated using a single electrical device in a household as an example. This electrical device can be an air conditioner, an electric water heater, a refrigerator, a television, etc. Based on the user's usage habits of the air conditioner, electric water heater, refrigerator, and television, the power consumption of the electrical device can be collected on a daily basis. For example, the total power consumption of the air conditioner in a household can be collected in real time every day. Of course, the total electricity consumption of the air conditioner in a household can also be collected in a household.

[0097] S202. Determine the preset number of energy consumptions collected before the current moment as multiple historical energy consumptions.

[0098] In the above example, a one-day data collection period is used to predict the energy consumption of the electricity user on the next day. Therefore, multiple power consumption data collected before the current moment can be used as historical energy consumption. For example, at 24:00 every day, 30 power consumption data of the electricity user collected in the 30 days prior to that moment can be used as historical energy consumption. Of course, in practical applications, those skilled in the art can collect power consumption data from more periods as historical energy consumption. This embodiment of the invention does not limit the number of historical energy consumption data.

[0099] S203. Set the weighted clustering objective function.

[0100] In an optional embodiment of the present invention, the clustering objective function is as follows:

[0101]

[0102] in, Historical energy consumption x j Belongs to prototype v i To what extent, Let C be the weight of the k-th historical energy consumption relative to the i-th prototype, C be the number of prototypes, N be the number of historical energy consumptions, m and τ be the fuzzy exponents, and v be the weight of the k-th historical energy consumption relative to the i-th prototype. i For the i-th prototype, τ is the standard deviation, which is the standard deviation of the distance between each historical energy consumption and each prototype. i, j, k, c, N, n, m, and τ are all natural numbers. Among them, the values ​​of m and τ can usually be taken as empirical values ​​of 2.0, and k and j represent the first and second prototypes, respectively.

[0103] S204. Introducing Lagrange operators μ1 and μ2 into the clustering objective function yields a new objective function.

[0104] After introducing the Lagrange operator mentioned above into formula (1), the new objective function is obtained as follows:

[0105]

[0106] S205. Calculate the gradient of the new objective function with respect to the membership degree.

[0107] Specifically, the above formula (2) applies to the membership degree A respectively. ij and w ij The gradient is obtained by taking the derivative, and then set the gradient to 0 as follows:

[0108]

[0109] S206. Calculate membership degree and weight as granular data when the gradient is equal to 0.

[0110] Specifically,

[0111]

[0112]

[0113] Where f and t are natural numbers.

[0114] S207. Set the degranulation objective function.

[0115] In an optional embodiment of the present invention, the degranulation objective function can be set as follows:

[0116]

[0117] S208, regarding the degranulation objective function... Find the gradient and solve the granulated data by setting the gradient to 0.

[0118]

[0119] S209. Use the degranulated data to establish a fuzzy rule model to predict the energy consumption of electricity users.

[0120] In an optional embodiment of the present invention, the fuzzy rule model can be a TS fuzzy rule model. A TS fuzzy rule model is a nonlinear system described by a set of If-then fuzzy rules, where each rule represents a subsystem. Its original form, the fuzzy implication conditional statement, is "If x is A, then y = f(x)", where f(x) is a linear function of x. Specifically, v in the degranulated data can be... i (In Formula 7) is replaced with the conclusion part f. i (x j Thus, the expression for the fuzzy rule model can be obtained as follows:

[0121]

[0122] f(x) represents a function of the input energy consumption x.

[0123] In practical applications, the performance of fuzzy rule models can be evaluated using the function Q, the expression of which is as follows:

[0124]

[0125] In formula (9), y j For actual energy consumption, the smaller the Q value, the higher the accuracy of the model's energy consumption prediction.

[0126] In another alternative embodiment, the function f in the conclusion part of formula (8) can be set to... i (x j ) = wi If i = 1, 2, ..., c, then formula (8) can be rewritten as follows:

[0127]

[0128] When the model is a zero-order model, and the function in the conclusion part is set to a constant, the parameter w i The following can be estimated using formula (9):

[0129] W = (A T A) -1 A T Y (11)

[0130] Where W = [w1, w2, w3, ..., w c ], Y = [y1, y2, ..., y N [This refers to historical power consumption;]

[0131] In another alternative embodiment, the model can be a first-order model, where the function f in the conclusion of equation (8) is... i (x j ) is a polynomial, f i (x j The expression is as follows:

[0132] f i (x j )=b i +a 1i x j1 +a 2i x j2 +...+a ni x jn (12)

[0133] Then formula (8) can be transformed into:

[0134]

[0135] Among them, b i As constants, A = [a1, a2, a3, ..., a c ] represents f i (x j The coefficient of ).

[0136] Parameter A = [a1, a2, a3, ..., a c The performance index metric RMSE is obtained by minimizing the following function:

[0137]

[0138] That is, using the least squares method to apply f i(x j The coefficients of the predicted value are optimized to improve the predicted value. Compared with the true value y j The parameter A obtained when it is minimized is [a1, a2, a3, ..., a c ].

[0139] In practical applications, those skilled in the art can choose a zero-order or first-order model to predict the energy consumption of electricity users, depending on the actual situation.

[0140] In this embodiment of the invention, after collecting multiple historical energy consumption data of electricity users, a weighted clustering objective function is set to evaluate the distance between historical energy consumption data to obtain granular data. After degranulating the granular data to obtain degranulated data, a fuzzy rule model is established using the degranulated data to predict the energy consumption of electricity users. Since the distance between historical energy consumption data and cluster centers is negatively correlated with the weight in the clustering objective function, the clustering objective function can be dynamically adjusted through weights during the clustering process to further refine the distance between different historical energy consumption data and each cluster center, thereby improving the clustering effect of historical energy consumption and ultimately improving the accuracy of energy consumption prediction for electricity users.

[0141] Example 3

[0142] Figure 3 This is a structural block diagram of an energy consumption prediction device for an electricity user provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the energy consumption prediction device for electricity users in this embodiment of the invention may specifically include the following modules:

[0143] The historical data acquisition module 301 is used to collect multiple historical energy consumption data of electricity users according to a preset cycle.

[0144] Granulation module 302 is used to set a weighted clustering objective function to cluster the historical energy consumption to obtain granulated data. In the clustering objective function, the distance from the historical energy consumption to the cluster center is negatively correlated with the weight.

[0145] The degranulation module 303 is used to degranulate the granulated data to obtain degranulated data.

[0146] The prediction module 304 is used to establish a fuzzy rule model using the degranulated data to predict the energy consumption of the electricity user.

[0147] Optionally, the historical data acquisition module 301 includes:

[0148] The power acquisition submodule is used to collect the energy consumption of power-consuming objects according to a preset cycle;

[0149] The historical data determination submodule is used to determine a preset number of energy consumption data collected before the current moment as multiple historical energy consumption data.

[0150] Optionally, the granulation module 302 includes:

[0151] The clustering objective function setting submodule is used to set the weighted clustering objective function;

[0152] The new function establishes a submodule, which is used to introduce the Lagrange operator into the clustering objective function to obtain a new objective function;

[0153] The gradient calculation submodule is used to calculate the gradient of the new objective function with respect to the membership degree.

[0154] The membership and weight calculation submodule is used to calculate the membership and weight as the granular data when the gradient is equal to 0.

[0155] Optionally, the clustering objective function is as follows:

[0156]

[0157] in, Historical energy consumption x j Belongs to prototype v i To what extent, Let C be the weight, N be the number of prototypes, m and τ be the fuzzy exponents, and v be the weight. i For the i-th prototype, Let be the standard deviation, and i, j, k, c, N, m, and τ be natural numbers.

[0158] Optionally, the membership degree is as follows:

[0159]

[0160] The weights are as follows:

[0161]

[0162] Where f and t are natural numbers.

[0163] Optionally, the degranulation module 303 includes:

[0164] The degranulation objective function setting submodule is used to set the degranulation objective function as follows:

[0165]

[0166] The granulated data solving submodule is used to solve the granulated objective function. Find the gradient and solve the granulated data by setting the gradient to 0. as follows:

[0167]

[0168] Optionally, the prediction module 304 includes:

[0169] The model building submodule is used to build the following fuzzy rule model from the degranulated data:

[0170]

[0171] in, Based on historical energy consumption x j The predicted energy consumption, f(x), represents a function of the input energy consumption x.

[0172] The energy consumption prediction device for electricity users provided in this embodiment of the invention can execute the energy consumption prediction method for electricity users provided in Embodiment 1 and Embodiment 2 of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0173] Example 4

[0174] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0175] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0176] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0177] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the energy consumption prediction method for electrical objects described above.

[0178] In some embodiments, the energy consumption prediction method for an electrical object may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the energy consumption prediction method for an electrical object described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the energy consumption prediction method for an electrical object by any other suitable means (e.g., by means of firmware).

[0179] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0180] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0181] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0182] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0183] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0184] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0185] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0186] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A power consumption prediction method for an electric power utilization object, characterized by, Comprising: collecting a plurality of historical energy consumptions of the power consumption object according to a preset period; setting a clustering objective function with weights to cluster the historical energy consumptions to obtain granulated data, wherein a distance from the historical energy consumptions to a clustering center is negatively related to the weights in the clustering objective function; degranulating the granulated data to obtain degranulated data; establishing a fuzzy rule model using the degranulated data to predict the energy consumption of the power consumption object; the clustering objective function is as follows: ； Wherein, , , Indicates historical energy consumption Belongs to the prototype Degree, The weight of the kth historical energy consumption to the ith prototype, C is the number of prototypes, N is the number of historical energy consumption, m, The fuzzy index, The ith prototype, The standard deviation of the distance between the kth historical energy consumption and each prototype, i, j, k, c, N, n, m, All are natural numbers; the membership is as follows: ； the weights are as follows: ； wherein f and t are natural numbers.

2. The method of claim 1, wherein, The collecting a plurality of historical energy consumptions of the power consumption object according to a preset period comprises: collecting the energy consumption of the power consumption object according to a preset period; determining a preset number of energy consumptions collected before the current time as the plurality of historical energy consumptions.

3. The method of claim 1, wherein, The setting a clustering objective function with weights to cluster the historical energy consumptions to obtain granulated data comprises: setting a clustering objective function with weights; introducing a Lagrange operator into the clustering objective function to obtain a new objective function; calculating a derivative of the new objective function with respect to the membership to obtain a gradient; calculating the membership and the weights as the granulated data when the gradient is equal to 0.

4. The method of claim 1, wherein, The degranulating the granulated data to obtain degranulated data comprises: setting a degranulation objective function as follows: ； on the degranulated data in the degranulation objective function solving the degranulated data when the gradient is found and set equal to 0 as follows: 。 5. The method of claim 4, wherein, The establishing a fuzzy rule model using the degranulated data to predict the energy consumption of the power consumption object comprises: establishing a fuzzy rule model as follows using the degranulated data: ； wherein, is the predicted energy consumption according to the historical energy consumption f(x) represents a function of the input energy consumption x.

6. An electric energy consumption prediction device for an electric energy consuming object, characterized by comprising: Comprising: a historical data collection module configured to collect a plurality of historical energy consumptions of the power consumption object according to a preset period; a granulation module configured to set a clustering objective function with weights to cluster the historical energy consumptions to obtain granulated data, wherein a distance from the historical energy consumptions to a clustering center is negatively related to the weights in the clustering objective function; a degranulation module configured to degranulate the granulated data to obtain degranulated data; a prediction module configured to establish a fuzzy rule model using the degranulated data to predict the energy consumption of the power consumption object; the clustering objective function is as follows: ； Wherein, , , Indicates historical energy consumption Belongs to the prototype Degree, The weight of the kth historical energy consumption to the ith prototype, C is the number of prototypes, N is the number of historical energy consumption, m, The fuzzy index, The ith prototype, The standard deviation of the distance between the kth historical energy consumption and each prototype, i, j, k, c, N, n, m, Are natural numbers; the membership is as follows: ； the weights are as follows: ； wherein f and t are natural numbers.

7. An electronic device, comprising: The electronic device comprises: one or more processors; a storage device configured to store one or more computer programs, when the one or more computer programs are executed by the one or more processors, the one or more processors implement the energy consumption prediction method of the power consumption object according to any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the energy consumption prediction method of the power consumption object according to any one of claims 1-5.

Images