A power demand over-limit early warning method and device based on user power consumption behavior

Abstract

This specification discloses a method and device for early warning of excessive electricity demand based on user electricity consumption behavior. The method includes collecting user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment, and the power corresponding to the electrical equipment. A subsequent load curve for the user is calculated based on an electricity consumption behavior prediction model to obtain a demand verification value. An early warning threshold curve is calculated based on the subsequent load curve and the demand verification value. The user's electricity demand at the current moment is obtained. An early warning threshold is selected based on the early warning threshold curve. If the user's electricity demand at the current moment is greater than the early warning threshold, an early warning message is sent. This method adapts to the personalized needs of users in different industries and with different electricity consumption characteristics, reduces the number of false and missed early warnings, and improves the accuracy and precision of early warning of excessive electricity demand.

Description

Technical Field

[0001] This invention relates to the field of power system electricity consumption monitoring and intelligent management technology, and in particular to a method, device, electronic device and storage medium for early warning of excessive electricity demand based on user electricity consumption behavior. Background Technology

[0002] In existing technologies, methods for issuing early warnings for exceeding electricity demand (Maximum Demand, MD: refers to the average maximum power consumption of a user within an electricity billing cycle (usually 15 or 30 minutes). If the actual maximum demand exceeds the declared contracted demand (contract capacity), the excess portion is typically subject to a punitive electricity price that is double or even higher. These methods often employ a universal threshold setting model, where a fixed demand warning threshold is set based on unified power industry standards or regional average electricity consumption levels, and the same form of warning information is pushed to all users. The warning threshold is a static, fixed value, simply set based on the total electricity load limit. However, this method lacks detailed classification for high-energy-consuming industrial users, time-of-use commercial users, and large residential electricity users, and is not highly targeted. Using the same threshold or a roughly estimated threshold easily leads to false or missed warnings. Summary of the Invention

[0003] To address the problems existing in the prior art, this specification describes a method, device, electronic device, and storage medium for early warning of excessive power demand based on user electricity consumption behavior through one or more embodiments.

[0004] According to the first aspect, a method for early warning of excessive electricity demand based on user electricity consumption behavior is provided, the method comprising:

[0005] Collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. A predictive model for electricity consumption behavior is trained based on the attribute data and electricity consumption data.

[0006] The user's subsequent load curve is calculated based on the electricity consumption behavior prediction model, and the demand verification value is obtained. The warning threshold curve is calculated based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the warning threshold curve over time is opposite.

[0007] Obtain the user's electricity demand at the current moment, select the warning threshold at the current moment based on the warning threshold curve, and send a warning message if the user's electricity demand at the current moment is greater than the warning threshold at the current moment.

[0008] Preferably, the method further includes: when the user's electricity demand at the current time is greater than the warning threshold at the current time, reasoning the cause of the demand exceeding the limit based on the electricity consumption behavior prediction model, generating at least one user optimization scheme based on the cause of the demand exceeding the limit, and sending the user optimization scheme to the user, so that the user's electricity demand at the current time is less than the warning threshold at the current time.

[0009] Preferably, the user optimization scheme includes emergency response suggestions based on device start-up and shutdown, and short-term optimization suggestions based on device start-up and shutdown time.

[0010] Preferably, the method further includes: acquiring newly added attribute data and electricity consumption data corresponding to the user, and updating the electricity consumption behavior prediction model based on the newly added attribute data and electricity consumption data.

[0011] Preferably, the warning threshold curve includes at least one warning threshold and the time or time period corresponding to each warning threshold.

[0012] Preferably, each of the aforementioned warning thresholds is less than the required quantity verification value.

[0013] Preferably, the early warning information includes the over-limit risk level, current demand, over-limit trigger time, and over-limit duration. The method further includes: classifying the over-limit risk level based on each of the early warning thresholds; when the user's electricity demand at the current time is greater than the early warning threshold at the current time, selecting the corresponding over-limit risk level based on the early warning threshold; and calculating the over-limit duration based on the electricity consumption behavior prediction model.

[0014] According to the second aspect, a power demand exceeding warning device based on user electricity consumption behavior is provided, the device comprising:

[0015] The model training module is used to collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. Based on the attribute data and the electricity consumption data, an electricity consumption behavior prediction model is trained.

[0016] The threshold prediction module is used to calculate the user's subsequent load curve based on the electricity consumption behavior prediction model, obtain the demand verification value, and calculate the warning threshold curve based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the warning threshold curve over time is opposite.

[0017] The over-limit early warning module is used to obtain the user's electricity demand at the current moment, select the early warning threshold at the current moment based on the early warning threshold curve, and send an early warning information if the user's electricity demand at the current moment is greater than the early warning threshold at the current moment.

[0018] According to a third aspect, an electronic device is provided, including a processor and a memory;

[0019] The processor is connected to the memory;

[0020] The memory is used to store executable program code;

[0021] The processor runs a program corresponding to the executable program code stored in the memory to perform the steps of the method provided as in the first aspect or any possible implementation thereof.

[0022] According to a fourth aspect, a computer-readable storage medium is provided having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the method provided as in the first aspect or any possible implementation thereof.

[0023] The beneficial effects of this invention are as follows:

[0024] 1. The method and apparatus provided in the embodiments of this specification train the user's attribute data and electricity consumption data to obtain the electricity consumption behavior prediction model corresponding to the user. The electricity consumption behavior prediction model is used to predict the user's possible electricity consumption in the future. Based on the predicted electricity consumption, the warning threshold for the user in the future is obtained, thereby adapting to the personalized needs of users in different industries and with different electricity consumption characteristics, reducing the number of false warnings and missed warnings, and improving the accuracy and precision of the electricity demand over-limit warning.

[0025] 2. The method and apparatus provided in the embodiments of this specification, when a user triggers an over-limit power demand warning, infers the cause of the over-limit demand based on the power consumption behavior prediction model, generates a user optimization plan, and sends the user optimization plan to the user so that the user can quickly identify the cause of the over-limit demand and take effective countermeasures in a timely manner to save electricity costs;

[0026] 3. The methods and apparatus provided in the embodiments of this specification provide warning information including the risk level of exceeding limits, the current demand value, the trigger time of exceeding limits, and the predicted duration of the risk, so as to enable users to quickly locate the cause of exceeding limits and achieve high warning response efficiency;

[0027] 4. The method and apparatus provided in the embodiments of this specification update the electricity behavior prediction model after obtaining the user's newly added attribute data and electricity consumption data to obtain an iterative electricity behavior prediction model. This allows the electricity behavior prediction model to adapt to changes in the user's electricity consumption behavior in real time without the need for manual parameter resetting, reducing system operation and maintenance costs. It is applicable to various users in different industries and with different electricity consumption scales. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart illustrating a method for early warning of excessive electricity demand based on user electricity consumption behavior in a specific implementation of this manual.

[0030] Figure 2 This is a schematic diagram of the structure of an over-limit power demand early warning device based on user electricity consumption behavior in a specific implementation of this specification;

[0031] Figure 3 This is a schematic diagram of the structure of an electronic device used in a specific implementation of this specification. Detailed Implementation

[0032] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0033] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.

[0034] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0035] See Figure 1 , Figure 1 This is a flowchart illustrating a method for early warning of excessive electricity demand based on user electricity consumption behavior, provided in an embodiment of this application. In this embodiment, the method includes:

[0036] S101. Collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. Train an electricity consumption behavior prediction model based on the attribute data and the electricity consumption data.

[0037] S102. Calculate the user's subsequent load curve based on the electricity consumption behavior prediction model, obtain the demand verification value, and calculate the early warning threshold curve based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the early warning threshold curve changing with time is opposite.

[0038] S103. Obtain the user's electricity demand at the current moment, select the warning threshold at the current moment based on the warning threshold curve, and send a warning message if the user's electricity demand at the current moment is greater than the warning threshold at the current moment.

[0039] The entity executing this application may be a cloud server.

[0040] In the embodiments of this specification, user attribute data and electricity consumption data are collected based on a set data collection frequency. The attribute data includes user industry classification, production mode, electrical equipment, and the power corresponding to the electrical equipment. The user industry classification includes labels such as industrial, commercial, and residential corresponding to the user. The production mode includes labels such as 24-hour continuous production, part-time operation, and residential electricity corresponding to the user. The electrical equipment refers to all the equipment required for the user's life and production. Electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio, equipment start-up and shutdown electricity consumption patterns, monthly electricity consumption fluctuations, quarterly electricity consumption fluctuations, and annual electricity consumption fluctuations. Using collected user attribute data and electricity consumption data as samples, and user industry classification and production mode as basic features, and historical electricity load, peak-valley-flat electricity consumption ratio, equipment start-up and shutdown electricity consumption patterns, monthly electricity consumption fluctuations, quarterly electricity consumption fluctuations, and annual electricity consumption fluctuations as deep features, a neural network (such as LSTM, GRU, Transformer, etc.) is used for training to obtain a corresponding electricity consumption behavior prediction model for that user. This model describes the user's electricity consumption habits, jointly represented by parameters such as the start-up time, duration, and environmental conditions of each electrical device used by that user. For example, for residential users: weekday and weekend work schedules, daily peak electricity consumption, the correlation between electricity load and weather, and the temperature at which electricity consumption begins to increase; for industrial and commercial users: electricity consumption during workers' work and rest periods. The system can predict the user's future load curve based on the user's corresponding electricity consumption behavior prediction model. The future load curve represents the user's potential electricity consumption in the future, i.e., the electrical equipment the user will be using and its power consumption over a future period. The system obtains the user's demand assessment value published by the power company and calculates a warning threshold curve based on the future load curve and the demand assessment value. The warning threshold curve represents the user's warning threshold for the future, i.e., the warning threshold corresponding to each moment or time period within a future period. The monotonicity of the future load curve and the warning threshold curve over time is opposite; that is, during periods of high electricity load, the warning threshold is lower to remind the user in advance, while during periods of low electricity load, the warning threshold is higher to avoid disturbing the user. The system monitors the user's current electricity demand in real time and selects the warning threshold corresponding to that moment from the warning threshold curve. If the user's current electricity demand exceeds the warning threshold at that moment, a warning message is sent according to the user's selected push channel (platform pop-up, SMS, or APP notification, etc.).This application trains a predictive model of electricity consumption behavior for a user based on the user's attribute data and electricity consumption data. The predictive model is then used to predict the user's possible electricity consumption in the future. Based on the predicted electricity consumption, a warning threshold for the user in the future is obtained. This adapts to the personalized needs of users in different industries and with different electricity consumption characteristics, reduces the number of false and missed warnings, and improves the accuracy and precision of warnings for exceeding electricity demand limits.

[0041] In one possible implementation, the method further includes: when the user's electricity demand at the current time is greater than the warning threshold at the current time, reasoning the cause of the demand exceeding the limit based on the electricity consumption behavior prediction model, generating at least one user optimization scheme based on the cause of the demand exceeding the limit, and sending the user optimization scheme to the user, so that the user's electricity demand at the current time is less than the warning threshold at the current time.

[0042] In this embodiment, when a user triggers a power demand exceedance warning, the system collects the user's current attribute data, including the user's industry classification, production mode, electrical equipment, and the power of the corresponding equipment. The collected data on the activated electrical equipment is compared with the predicted activated electrical equipment in the subsequent load curve based on the user's corresponding electricity consumption behavior prediction model. This comparison helps deduce the cause of the demand exceedance, identifying electrical equipment not predicted to be activated. Then, at least one user optimization plan is generated based on the cause of the demand exceedance. This optimization plan is sent to the user via a push channel selected by the user (platform pop-up, SMS, or APP notification, etc.) to ensure that the user's current demand is less than the warning threshold at that moment. For example, if the subsequent load curve predicts that the user will turn on the air conditioner at 8 PM, but the user triggers a power demand exceedance warning at 8 PM, and the system detects that the user has turned on high-power appliances such as the air conditioner and water heater, a user optimization plan will be generated based on the additional high-power appliances such as the water heater that were activated. In this application, when a user triggers an over-limit power demand warning, the cause of the over-limit demand is inferred based on the power consumption behavior prediction model, and an optimization plan for the user is generated and sent to the user so that the user can quickly identify the cause of the over-limit demand and take effective countermeasures in a timely manner to save electricity costs.

[0043] In one possible implementation, the user optimization scheme includes emergency response suggestions based on device start-up and shutdown, and short-term optimization suggestions based on device start-up and shutdown time.

[0044] In this embodiment, as described above, the collected data on activated electrical equipment is compared with the predicted activated electrical equipment in the subsequent load curve based on the user's corresponding electricity consumption behavior prediction model to deduce the reasons for demand exceeding limits, i.e., electrical equipment not predicted to be activated. Then, at least one user optimization plan is generated based on the reasons for demand exceeding limits. The generated user optimization plan includes emergency response suggestions based on equipment start / stop, short-term optimization suggestions based on equipment start / stop time, and long-term suggestions based on equipment modification. For example, the user optimization plan generated based on additional activated high-power appliances such as water heaters could specifically include: emergency response suggestion: immediately turn off high-power appliances such as water heaters; short-term optimization suggestion: adjust the on-time of high-power appliances such as water heaters so that their on-time does not overlap with the on-time of air conditioners; long-term suggestion: energy-saving equipment modification and electricity consumption process restructuring. The customized multi-level electricity consumption optimization suggestions in this application are closely aligned with users' actual production / life situations, highly implementable, and help users gradually optimize their electricity consumption behavior from emergency response and short-term adjustments to long-term modifications.

[0045] In one possible implementation, newly added attribute data and electricity consumption data corresponding to the user are obtained, and the electricity consumption behavior prediction model is updated based on the newly added attribute data and electricity consumption data.

[0046] In this embodiment, after obtaining the user's newly added attribute data and electricity consumption data, the user's industry classification and production mode are used as basic features, and historical electricity load, peak-valley-flat electricity consumption ratio, equipment start-up and shutdown electricity consumption patterns, monthly electricity consumption fluctuations, quarterly electricity consumption fluctuations, and annual electricity consumption fluctuations are used as deep features. The data is then updated through neural networks (such as LSTM long short-term memory network, GRU, Transformer, etc.) to obtain an iterative electricity consumption behavior prediction model. This allows the electricity consumption behavior prediction model to adapt to changes in user electricity consumption behavior in real time without the need for manual parameter resetting, reducing system operation and maintenance costs. It is applicable to various users in different industries and with different electricity consumption scales.

[0047] In one possible implementation, the warning threshold curve includes at least one warning threshold and the time or time period corresponding to each warning threshold.

[0048] In this embodiment of the application, the warning threshold curve is used to represent the warning threshold of the user in the future time, that is, the warning threshold corresponding to each moment or time period in the future.

[0049] In one possible implementation, each of the aforementioned warning thresholds is less than the required quantity verification value.

[0050] In this embodiment of the application, each warning threshold is less than the demand set value to ensure that users receive a reminder before the demand set value is reached, thereby saving electricity costs.

[0051] In one possible implementation, the early warning information includes an over-limit risk level, current demand, over-limit trigger time, and over-limit duration. The method further includes: classifying over-limit risk levels based on each of the early warning thresholds; when the user's electricity demand at the current time is greater than the early warning threshold at the current time, selecting the corresponding over-limit risk level based on the early warning threshold; and calculating the over-limit duration based on the electricity consumption behavior prediction model.

[0052] In this embodiment, the warning information includes targeted content such as the over-limit risk level, current demand value, over-limit trigger time, and risk duration prediction. The power demand over-limit warning method based on user electricity consumption behavior includes: classifying risk levels according to multiple warning thresholds, such as: Level 1 warning threshold, Level 2 warning threshold, and Level 3 warning threshold; when the user's electricity demand at the current time is greater than the warning threshold at that time, selecting the over-limit risk level corresponding to that time based on the relationship between the user's electricity demand at the current time and the approved value; and calculating the duration prediction based on the electricity consumption behavior prediction model and the inferred cause of the demand over-limit. For example, if the inferred cause of the demand over-limit is the operation of high-power appliances such as water heaters, and the electricity consumption behavior prediction model fits the operation time of high-power appliances such as water heaters as 1 hour, then the duration prediction is 1 hour. In this application, the warning information includes targeted content such as the over-limit risk level, current demand value, over-limit trigger time, and risk duration prediction, so that users can quickly locate the cause of the over-limit, and the warning response efficiency is high.

[0053] The following will be combined with the appendix Figure 2 This application provides a detailed description of the power demand over-limit early warning device based on user electricity consumption behavior provided in the embodiments of this application. It should be noted that the appendix... Figure 2 The power demand over-limit early warning device shown is based on user electricity consumption behavior and is used to perform the functions described in this application. Figure 1 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figure 1 The example shown.

[0054] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the power demand over-limit early warning device based on user electricity consumption behavior provided in an embodiment of this application. Figure 2 As shown, the device includes:

[0055] The model training module 201 is used to collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. Based on the attribute data and the electricity consumption data, an electricity consumption behavior prediction model is trained.

[0056] The threshold prediction module 202 is used to calculate the user's subsequent load curve based on the electricity consumption behavior prediction model, obtain the demand verification value, and calculate the warning threshold curve based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the warning threshold curve changing with time is opposite.

[0057] The over-limit early warning module 203 is used to obtain the user's electricity demand at the current time, select the early warning threshold at the current time based on the early warning threshold curve, and send an early warning information if the user's electricity demand at the current time is greater than the early warning threshold at the current time.

[0058] In one possible implementation, the over-limit warning module 203 is specifically used for:

[0059] When the user's electricity demand at the current time is greater than the warning threshold at the current time, the cause of the demand exceeding the limit is inferred based on the electricity behavior prediction model, and at least one user optimization scheme is generated based on the cause of the demand exceeding the limit and the user optimization scheme is sent to the user so that the user's electricity demand at the current time is less than the warning threshold at the current time.

[0060] In one possible implementation, the over-limit warning module 203 is specifically used for:

[0061] The user optimization scheme includes emergency response suggestions based on device start-up and shutdown, as well as short-term optimization suggestions based on device start-up and shutdown time.

[0062] In one possible implementation, the model training module 201 is specifically used for:

[0063] Obtain newly added attribute data and electricity consumption data corresponding to the user, and update the electricity consumption behavior prediction model based on the newly added attribute data and electricity consumption data.

[0064] In one possible implementation, the threshold prediction module 202 is specifically used for:

[0065] The warning threshold curve includes at least one warning threshold and the time or time period corresponding to each warning threshold.

[0066] In one possible implementation, the threshold prediction module 202 is specifically used for:

[0067] All of the aforementioned warning thresholds are less than the required quantity verification value.

[0068] In one possible implementation, the threshold prediction module 202 is specifically used for:

[0069] The warning information includes the over-limit risk level, current demand, over-limit trigger time, and over-limit duration. The method further includes: classifying the over-limit risk level based on each of the warning thresholds; when the user's electricity demand at the current time is greater than the warning threshold at the current time, selecting the corresponding over-limit risk level based on the warning threshold; and calculating the over-limit duration based on the electricity consumption behavior prediction model.

[0070] Those skilled in the art will clearly understand that the technical solutions of the embodiments of this application can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit (IC), etc.

[0071] Each processing unit and / or module in the embodiments of this application can be implemented by an analog circuit that implements the functions described in the embodiments of this application, or by software that executes the functions described in the embodiments of this application.

[0072] See Figure 3 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this application, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 3 As shown, the electronic device 300 may include: at least one central processing unit 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0073] The communication bus 302 is used to enable communication between these components.

[0074] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0075] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0076] The central processing unit 301 may include one or more processing cores. The central processing unit 301 connects to various parts within the electronic device 300 using various interfaces and lines. It executes various functions of the terminal 300 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the central processing unit 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The central processing unit 301 may integrate one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the central processing unit 301.

[0077] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned central processing unit 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0078] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the central processing unit 301 can be used to call the application program stored in the memory 305 and specifically perform the following operations:

[0079] S101. Collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. Train an electricity consumption behavior prediction model based on the attribute data and the electricity consumption data.

[0080] S102. Calculate the user's subsequent load curve based on the electricity consumption behavior prediction model, obtain the demand verification value, and calculate the early warning threshold curve based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the early warning threshold curve changing with time is opposite.

[0081] S103. Obtain the user's electricity demand at the current moment, select the warning threshold at the current moment based on the warning threshold curve, and send a warning message if the user's electricity demand at the current moment is greater than the warning threshold at the current moment.

[0082] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0083] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0084] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0086] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0088] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0089] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0090] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for early warning of excessive electricity demand based on user electricity consumption behavior, characterized in that, The method includes: Collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. A predictive model for electricity consumption behavior is trained based on the attribute data and electricity consumption data. The user's subsequent load curve is calculated based on the electricity consumption behavior prediction model, and the demand verification value is obtained. The warning threshold curve is calculated based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the warning threshold curve over time is opposite. Obtain the user's electricity demand at the current moment, select the warning threshold at the current moment based on the warning threshold curve, and send a warning message if the user's electricity demand at the current moment is greater than the warning threshold at the current moment.

2. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 1, characterized in that, The method further includes: when the user's electricity demand at the current time is greater than the warning threshold at the current time, reasoning the cause of the demand exceeding the limit based on the electricity behavior prediction model, generating at least one user optimization scheme based on the cause of the demand exceeding the limit, and sending the user optimization scheme to the user so that the user's electricity demand at the current time is less than the warning threshold at the current time.

3. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 2, characterized in that, The user optimization scheme includes emergency response suggestions based on device start-up and shutdown, as well as short-term optimization suggestions based on device start-up and shutdown time.

4. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 1, characterized in that, The method further includes: acquiring newly added attribute data and electricity consumption data corresponding to the user, and updating the electricity consumption behavior prediction model based on the newly added attribute data and electricity consumption data.

5. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 1, characterized in that, The warning threshold curve includes at least one warning threshold and the time or time period corresponding to each warning threshold.

6. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 5, characterized in that, All of the aforementioned warning thresholds are less than the required quantity verification value.

7. The method for early warning of excessive electricity demand based on user electricity consumption behavior according to claim 5, characterized in that, The warning information includes the over-limit risk level, current demand, over-limit trigger time, and over-limit duration. The method further includes: classifying the over-limit risk level based on each of the warning thresholds; when the user's electricity demand at the current time is greater than the warning threshold at the current time, selecting the corresponding over-limit risk level based on the warning threshold; and calculating the over-limit duration based on the electricity consumption behavior prediction model.

8. A power demand over-limit early warning device based on user electricity consumption behavior, characterized in that, The apparatus implements the steps of the method as described in any one of claims 1-7, the apparatus comprising: The model training module is used to collect user attribute data and electricity consumption data. The attribute data includes user industry classification, production mode, electrical equipment and the power corresponding to the electrical equipment. The electricity consumption data includes historical electricity load, peak-valley-flat electricity consumption ratio and historical equipment start-up and shutdown time. Based on the attribute data and the electricity consumption data, an electricity consumption behavior prediction model is trained. The threshold prediction module is used to calculate the user's subsequent load curve based on the electricity consumption behavior prediction model, obtain the demand verification value, and calculate the warning threshold curve based on the subsequent load curve and the demand verification value. The monotonicity of the subsequent load curve and the warning threshold curve over time is opposite. The over-limit early warning module is used to obtain the user's electricity demand at the current moment, select the early warning threshold at the current moment based on the early warning threshold curve, and send an early warning information if the user's electricity demand at the current moment is greater than the early warning threshold at the current moment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-7.

Images