Regional load sudden drop prediction method and device, terminal equipment and storage medium

Abstract

The invention discloses a regional load sudden drop prediction method and device, terminal equipment and a storage medium, and the method comprises the steps: inputting load prediction data, which is generated through the coding of the load change characteristics, market economic data, weather data and special event information of each industry in a monitoring region, into a preset load sudden drop recognition model; and according to the load prediction data, the load sudden drop identification model calculates and outputs the probability of abnormal load fluctuation of each industry in the monitoring area in the future and a load prediction result of whether a load sudden drop event occurs in the monitoring area in the future. Therefore, multi-dimensional analysis is carried out on load change, market economy, weather and special events of each industry in the area through the load sudden drop identification model so as to accurately predict whether a load sudden drop event occurs in the future, so that related workers can execute a treatment scheme in time, the load sudden drop event is avoided, and the working efficiency is improved. And the social economy and the life of people are severely influenced.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, device, terminal equipment and storage medium for predicting regional load drop. Background Art

[0002] With the rapid development of social economy, people's demand for electricity is increasing, and the scale of power system is also expanding. The continuous development of new power systems has made complex power grids the mainstream. Complex power grids refer to power systems composed of many interacting and interdependent components, which are highly complex, uncertain and fragile. In the context of complex power grids, regional load drops frequently occur, which has a serious impact on the stable operation of power systems.

[0003] Regional load sag refers to a sudden drop in load in a certain area of ​​the power system, which leads to system instability and even power outages. This phenomenon may be caused by many factors, such as weather changes, equipment failures, human errors, etc. Regional load sag will have a significant impact on the social economy and people's lives.

[0004] However, traditional load sag prevention and control technology is mainly based on statistical methods and expert experience. Although this method can deal with some common problems to a certain extent, it is often not comprehensive enough for users with complex energy consumption characteristics. Due to production processes, operating characteristics or other factors, the power demand of some users may fluctuate greatly in a short period of time. For example, among industrial users, enterprises in basic raw material industries such as chemical and metallurgical industries tend to have relatively stable and continuous power demand; while the load curves of textile and mechanical processing industries in the manufacturing industry fluctuate significantly with work and rest time; the load characteristics of commercial users are closely related to business hours, generally showing the characteristics of peaks during the day and valleys at night. Due to the large changes in power demand, these users have high requirements for the stability and reliability of the power supply system. Therefore, how to predict regional load sag based on the current complex energy consumption characteristics has become an urgent problem to be solved. Summary of the invention

[0005] The present invention discloses a method, device, terminal equipment and storage medium for predicting regional load sag. Through a load sag identification model, the load changes of various industries in the region, market economy, weather, and special events are analyzed in multiple dimensions to accurately predict whether a load sag event will occur in the future, so that relevant staff can implement the governance plan in time to avoid the occurrence of load sag events, which will cause serious impact on social economy and people's lives.

[0006] An embodiment of the present invention discloses a method for predicting a regional load drop, comprising:

[0007] During each monitoring period, obtain weather data in the monitoring area, electricity consumption data of several users in each industry, market economic data of each industry, and special event information;

[0008] Generate a load change curve for each user in the current monitoring period according to the power consumption data;

[0009] According to the load change curve, the load change characteristics of each type of industry in the current monitoring period are generated;

[0010] According to the load change characteristics of each industry, the market economic data, weather data, and special event information of each industry, the load forecast data of each industry in the monitoring area during the current monitoring period are generated;

[0011] The load forecast data is input into a preset load sag identification model so that the load sag identification model calculates and outputs the probability of abnormal load fluctuation in each industry in the monitoring area in the future period according to each load forecast data, as well as the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

[0012] Furthermore, the method for predicting a regional load drop further includes:

[0013] Obtaining historical electricity consumption data and electrical equipment information of each user in the monitoring area;

[0014] Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user;

[0015] According to the preset industry classification rules, each user in the monitoring area is classified into the corresponding industry;

[0016] Determine the risk level of each user in the industry to which they belong based on each user's power equipment information, power usage behavior patterns, and the industry to which they belong;

[0017] A user information database within the monitoring area is constructed based on each user's power equipment information, power usage behavior patterns, industry, and risk level.

[0018] Furthermore, in each monitoring period, after obtaining weather data in the monitoring area, electricity consumption data of several users in each type of industry, market economic data of each type of industry, and special event information, it also includes:

[0019] Re-determine the electricity usage behavior pattern of each user in the user information database based on the electricity usage data and historical electricity usage data of each user;

[0020] Based on each user's re-determined electricity usage behavior patterns, electricity equipment information, and industry, the risk level of each user in the industry to which he or she belongs is updated.

[0021] Furthermore, according to the load change curve, the load change characteristics of each type of industry in the current monitoring period are generated, including:

[0022] Obtaining the risk level of each user in the user information database;

[0023] Based on the risk level of each user and the load change curve, the load change characteristics of each industry during the current monitoring period are generated.

[0024] Furthermore, the method for predicting a regional load drop further includes:

[0025] When it is determined that the load forecast result indicates that a load drop event will occur in the monitoring area in the future period, several main reasons causing the load drop event to occur in the monitoring area in the future period are determined according to the probability of abnormal load fluctuations in various industries in the monitoring area in the future period;

[0026] According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database;

[0027] According to the main causes and the prevention and control strategies, load drop warning information is generated and issued.

[0028] Another embodiment of the present invention discloses a device for predicting a sudden drop in regional load, comprising:

[0029] The data acquisition module is used to obtain weather data in the monitoring area, electricity consumption data of several users in each type of industry, market economic data of each type of industry, and special event information during each monitoring period;

[0030] A load curve generating module, used to generate a load change curve of each user in a current monitoring period according to the power consumption data;

[0031] A feature generation module, used to generate the load change characteristics of each type of industry in the current monitoring period according to the load change curve;

[0032] The forecast data generation module is used to encode the load change characteristics of each industry, the market economic data of each industry, weather data, and special event information to generate the load forecast data of each industry in the monitoring area during the current monitoring period;

[0033] The model prediction module is used to input the load forecast data into a preset load sag identification model so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to each load forecast data, as well as the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

[0034] Furthermore, the device for predicting a sudden drop in regional load further includes: an information base construction module;

[0035] The information base construction module is used to obtain the historical electricity consumption data and power equipment information of each user in the monitoring area;

[0036] Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user;

[0037] According to the preset industry classification rules, each user in the monitoring area is classified into the corresponding industry;

[0038] Determine the risk level of each user in the industry to which they belong based on each user's power equipment information, power usage behavior patterns, and the industry to which they belong;

[0039] A user information database within the monitoring area is constructed based on each user's power equipment information, power usage behavior patterns, industry, and risk level.

[0040] Furthermore, the device for predicting a sudden drop in regional load further includes: an early warning release module;

[0041] The warning issuing module is used to determine several main reasons causing the load drop event to occur in the monitoring area in the future period according to the probability of abnormal load fluctuation in each industry in the monitoring area in the future period when it is determined that the load forecast result indicates that the monitoring area will experience a load drop event in the future period;

[0042] According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database;

[0043] According to the main causes and the prevention and control strategies, load drop warning information is generated and issued.

[0044] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for predicting a regional load drop as described in any one of the embodiments is implemented.

[0045] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a method for predicting a regional load drop as described in any one of the above embodiments.

[0046] The following beneficial effects are achieved by implementing the present invention:

[0047] The present invention discloses a method, device, terminal equipment and storage medium for predicting regional load sag, by inputting load forecast data generated by encoding the load change characteristics of each type of industry, market economic data, weather data, and special event information into a preset load sag identification model, so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to the load forecast data, and the load forecast result of whether a load sag event will occur in the monitoring area in the future period. Therefore, the present invention uses the load sag identification model to analyze the load change characteristics, market economic data, weather data, and special event information of each type of industry in the region, to accurately predict whether a load sag event will occur in the future period, so that relevant staff can timely implement the governance plan according to the load forecast results, and avoid the serious impact of the load sag event on the social economy and people's lives. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of a method for predicting a regional load drop provided by an embodiment of the present invention.

[0049] Figure 2 It is a structural schematic diagram of a device for predicting regional load drop provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0052] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0053] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0056] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0057] See also Figure 1 , is a flow chart of a method for predicting a regional load drop provided by an embodiment of the present invention, comprising:

[0058] S1. During each monitoring period, obtain weather data in the monitoring area, electricity consumption data of several users in each industry, market economic data of each industry, and special event information;

[0059] In a preferred embodiment of the present invention, the electricity consumption data includes: electricity consumption and electricity consumption time distribution; market economic data includes: industry economic growth rate and market trend; special event information includes: whether the monitoring period is within the time of large-scale activities and holidays. It should be noted that weather, industry economic conditions, large-scale activities and holidays are all factors that affect users' electricity consumption.

[0060] Preferably, the method for predicting a regional load drop described in the above embodiment further includes:

[0061] S01, obtaining historical electricity consumption data and electrical equipment information of each user in the monitoring area;

[0062] S02. Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user;

[0063] S03. Classify each user in the monitoring area into a corresponding industry according to a preset industry classification rule;

[0064] S04. Determine the risk level of each user in the industry to which they belong based on the power equipment information, power usage behavior patterns, and industry to which each user belongs;

[0065] S05. Construct a user information database in the monitoring area according to each user's power equipment information, power usage behavior pattern, industry, and risk level.

[0066] In a preferred embodiment of the present invention, the historical electricity consumption data includes: the user's historical electricity consumption and historical electricity consumption time distribution, and the power equipment information includes: the operating stability of the user's power equipment;

[0067] The preset industry classification rules include: manufacturing, service industry, public institutions, and high-tech industry; it can be understood that the manufacturing industry includes: machinery manufacturing, electronic manufacturing, automobile manufacturing and other industries; the service industry includes: hotels, catering, commercial complexes and other industries; public institutions include: schools, hospitals and other public institutions; high-tech industries include: Internet, information technology, artificial intelligence and other industries.

[0068] It should be noted that, in this embodiment, the risk level includes: high risk level, medium risk level, and low risk level;

[0069] Determining the risk level of each user in the industry to which he belongs based on the power equipment information, power usage behavior patterns, and industry to which each user belongs includes:

[0070] Users whose electric equipment has poor operating stability and irregular electricity usage behavior are identified as high-risk users in their industry; users whose electric equipment has poor operating stability and regular electricity usage behavior, as well as users whose electric equipment has high operating stability and irregular electricity usage behavior, are identified as medium-risk users in their industry; users whose electric equipment has high operating stability and regular electricity usage behavior are identified as low-risk users in their industry.

[0071] It is understandable that high-risk users have frequent historical load drop events, serious equipment aging, extremely high power stability requirements, and load changes are easily affected by external factors. Medium-risk users occasionally have load drop events, their equipment is aged to a certain extent, and their power stability requirements are high, but they have not yet reached the high-risk level. Low-risk users have stable historical loads, newer equipment, average power stability requirements, and relatively stable load changes.

[0072] Preferably, in each monitoring period, after obtaining weather data in the monitoring area, electricity consumption data of several users in each type of industry, market economic data of each type of industry, and special event information, the method further includes:

[0073] S11, re-determining the electricity usage behavior pattern of each user in the user information database according to the electricity usage data and historical electricity usage data of each user;

[0074] S12. Update the risk level of each user in the industry to which they belong based on the re-determined electricity usage behavior pattern, electricity equipment information, and industry to which each user belongs.

[0075] In a preferred embodiment of the present invention, when new electricity usage data of a user is obtained, the new electricity usage data is saved in a user database, the electricity usage behavior pattern of the user is re-evaluated, and the risk level of the user is re-determined.

[0076] It is understandable that the data contained in the user information database, namely each user's electricity consumption behavior, electricity equipment information, industry, and risk level, is crucial for the model to accurately identify load drop events. These data have the following key features, which enable the model to learn and predict effectively:

[0077] Diversity: Different industries and load devices have different electricity consumption characteristics and patterns. This diversity provides the model with rich training samples, enabling the model to learn the load change patterns under different circumstances. Causality: There is a direct causal relationship between the cause of the sag and the load sag event. By analyzing the cause of the sag, the model can learn the key factors that lead to the load sag, thereby more accurately predicting the load sag events that may occur in the future. Relevance: The main hazards and impacts are closely related to the load sag event. These data can help the model understand the impact of the load sag event on users and the power grid system, thereby improving the accuracy and reliability of the model in identifying load sag events. Historicity: The data in the information database usually includes records of historical load sag events. These historical data provide valuable experience for the model, enabling the model to learn the laws and trends of past events, so as to better predict future events. Structured: Through reasonable data organization and preprocessing, the data in the information database is convenient for the model to extract features and learn. This structured data enables the model to extract useful information from it more effectively and improve the accuracy of identifying load sag events.

[0078] S2. generating a load change curve for each user in the current monitoring period according to the power consumption data;

[0079] In a preferred embodiment of the present invention, the horizontal axis is generated at a preset time interval, the vertical axis is generated by the power load, and the load change curve of each user in the current monitoring period is generated according to the power consumption data. It can be understood that the load change curve can be an image such as a line graph and a step graph.

[0080] S3. Generate load change characteristics of each type of industry in the current monitoring period according to the load change curve;

[0081] Preferably, generating the load change characteristics of each type of industry in the current monitoring period according to the load change curve includes:

[0082] S31, obtaining the risk level of each user in the user information database;

[0083] S32. Generate the load change characteristics of each type of industry during the current monitoring period based on the risk level of each user and the load change curve.

[0084] In a preferred embodiment of the present invention, based on the load change curve, the characteristic information of the load change curve of each user is determined: peak value, valley value, volatility, and stability. The user's current risk level is combined with the characteristic information of the user's load change curve to generate a load change characteristic for each industry in the current period.

[0085] It can be understood that high-risk users are users whose electrical equipment has poor operating stability and irregular electricity consumption behavior. If the load change curve characteristic information of high-risk users indicates that the high-risk users have strong stability in the current period, it indicates that the load change fluctuation of the industry where the high-risk users are located in the current period is extremely small. If the load change curve characteristic information of low-risk users indicates that the low-risk users have abnormal fluctuations in the current period, it indicates that the load change fluctuation of the industry where the low-risk users are located in the current period is extremely large.

[0086] S4. Encode the load change characteristics of each industry, the market economic data, weather data, and special event information of each industry to generate load forecast data for each industry in the monitoring area during the current monitoring period;

[0087] S5. Input the load forecast data into a preset load sag identification model, so that the load sag identification model calculates and outputs the probability of abnormal load fluctuation in each industry in the monitoring area in the future period according to each load forecast data, and the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

[0088] In a preferred embodiment of the present invention, a CNN network is used to construct the load sag identification model, and the industry load change characteristics, industry market economic data, weather data, and special event information in the time period before the historical load sag event are used for training, so that the CNN network can output the probability of abnormal load fluctuations in various industries in the region in the future period based on these data, as well as the load forecast results of whether a load sag event will occur in the monitoring area in the future period.

[0089] It is understandable that the output of the model is usually a probability value or score, indicating the possibility that the input data belongs to a load drop event. Specifically, when the output of the model exceeds a preset threshold, the event discriminator predicts it as a load drop event. This threshold is usually determined based on the performance evaluation during the model training process. During the model training phase, a portion of data with known labels (i.e., it is known which are load drop events and which are not) is used to evaluate the performance of the model. By adjusting the threshold, a balance point can be found so that the model can maintain a high accuracy rate while avoiding too many false alarms when identifying load drop events. In general, the selection of the threshold needs to comprehensively consider the model's accuracy, recall rate, F1 score and other indicators. The accuracy rate indicates the proportion of load drop events that the model correctly identifies, the recall rate indicates the proportion of load drop events that actually occur that are correctly identified by the model, and the F1 score is the harmonic mean of the accuracy rate and the recall rate, which is used to comprehensively evaluate the performance of the model.

[0090] Preferably, the method for predicting a regional load drop described in the above embodiment further includes:

[0091] S6. When it is determined that the load forecast result indicates that a load drop event will occur in the monitoring area in the future period, several main reasons causing the load drop event to occur in the monitoring area in the future period are determined according to the probability of abnormal load fluctuations in various industries in the monitoring area in the future period;

[0092] S7. According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database;

[0093] S8. Generate and issue load drop warning information based on the several main causes and the several prevention and control strategies.

[0094] In a preferred embodiment of the present invention, the main reasons include: equipment failure: such as generator, transformer or transmission line failure. Human operation error: such as circuit breaker tripping caused by misoperation. Natural disasters: such as power system failures caused by weather factors such as lightning and storms. Sudden changes in electricity demand: such as sudden power outages for large industrial users or sudden drops in electricity demand caused by the end of large-scale activities. Power system scheduling problems: such as imbalance between supply and demand caused by improper scheduling.

[0095] The control strategies for each major cause in the preset control strategy database include:

[0096] For equipment failure, the prevention and control strategies include: 1. Strengthen equipment inspection and maintenance to prevent potential failures; 2. Equip spare equipment to ensure rapid replacement when failure occurs. For human operation errors, the prevention and control strategies include: 1. Improve the professional skills and safety awareness of operators. 2. Introduce automation and intelligent systems to reduce human intervention. For natural disasters, the prevention and control strategies include: 1. Strengthen the disaster resistance of the power system, such as using more weather-resistant materials and equipment. 2. Establish emergency plans to ensure rapid response when disasters occur. For sudden changes in electricity demand, the prevention and control strategies include: 1. Strengthen communication with users to understand changes in electricity demand in advance. 2. Optimize power dispatch to ensure supply and demand balance. For power system dispatch problems, the prevention and control strategies include: 1. Improve the intelligence level of the dispatch system to achieve accurate prediction and dispatch. 2. Strengthen coordination with other power systems to achieve resource sharing and complementarity. It is understandable that when the main cause is a specific situation, the output prevention and control strategy will be specific measures for that situation. For example, if the main cause is only equipment failure, the output prevention and control strategies may include immediately starting the backup equipment, notifying maintenance personnel to quickly arrive at the site for maintenance, and adjusting the power dispatch strategy to alleviate the impact of the sudden load drop.

[0097] The present invention discloses a method for predicting regional load sag, by inputting load forecast data generated by encoding the load change characteristics of each type of industry, market economic data, weather data, and special event information into a preset load sag identification model, so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to the load forecast data, and the load forecast result of whether a load sag event will occur in the monitoring area in the future period. Therefore, the present invention uses the load sag identification model to analyze the load change characteristics, market economic data, weather data, and special event information of each type of industry in the region, to accurately predict whether a load sag event will occur in the future period, so that relevant staff can timely implement the governance plan according to the load forecast results, and avoid the serious impact of the load sag event on the social economy and people's lives.

[0098] See also Figure 2 , is a schematic diagram of a regional load drop prediction device provided by an embodiment of the present invention, comprising:

[0099] The data acquisition module is used to obtain weather data in the monitoring area, electricity consumption data of several users in each type of industry, market economic data of each type of industry, and special event information during each monitoring period;

[0100] A load curve generating module, used to generate a load change curve of each user in a current monitoring period according to the power consumption data;

[0101] A feature generation module, used to generate the load change characteristics of each type of industry in the current monitoring period according to the load change curve;

[0102] The forecast data generation module is used to encode the load change characteristics of each industry, the market economic data of each industry, weather data, and special event information to generate the load forecast data of each industry in the monitoring area during the current monitoring period;

[0103] The model prediction module is used to input the load forecast data into a preset load sag identification model so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to each load forecast data, as well as the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

[0104] Preferably, the device for predicting a sudden drop in regional load described in the above embodiment further includes: an information base construction module;

[0105] The information base construction module is used to obtain the historical electricity consumption data and power equipment information of each user in the monitoring area;

[0106] Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user;

[0107] According to the preset industry classification rules, each user in the monitoring area is classified into the corresponding industry;

[0108] Determine the risk level of each user in the industry to which they belong based on each user's power equipment information, power usage behavior patterns, and the industry to which they belong;

[0109] A user information database within the monitoring area is constructed based on each user's power equipment information, power usage behavior patterns, industry, and risk level.

[0110] Preferably, the device for predicting a sudden drop in regional load described in the above embodiment further includes: an early warning issuing module;

[0111] The warning issuing module is used to determine several main reasons causing the load drop event to occur in the monitoring area in the future period according to the probability of abnormal load fluctuation in each industry in the monitoring area in the future period when it is determined that the load forecast result indicates that the monitoring area will experience a load drop event in the future period;

[0112] According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database;

[0113] According to the main causes and the prevention and control strategies, load drop warning information is generated and issued.

[0114] The present invention discloses a regional load sag prediction device, which inputs load prediction data generated by encoding the load change characteristics of each type of industry, market economic data, weather data, and special event information into a preset load sag identification model, so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to the load prediction data, and the load prediction result of whether a load sag event will occur in the monitoring area in the future period. Therefore, the present invention uses the load sag identification model to analyze the load change characteristics, market economic data, weather data, and special event information of each type of industry in the region to accurately predict whether a load sag event will occur in the future period, so that relevant staff can implement the governance plan according to the load prediction results in time, and avoid the serious impact of the load sag event on the social economy and people's lives.

[0115] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0116] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0117] Another preferred embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for predicting a regional load drop as described in any one of the above embodiments is implemented.

[0118] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0119] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0120] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0121] Another preferred embodiment of the present invention provides a storage medium, the storage medium is a computer-readable storage medium, the computer program is stored in the computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0122] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for predicting regional load drop, characterized in that: include: During each monitoring period, obtain weather data in the monitoring area, electricity consumption data of several users in each industry, market economic data of each industry, and special event information; Generate a load change curve for each user in the current monitoring period according to the power consumption data; According to the load change curve, the load change characteristics of each type of industry in the current monitoring period are generated; According to the load change characteristics of each industry, the market economic data, weather data, and special event information of each industry, the load forecast data of each industry in the monitoring area during the current monitoring period are generated; The load forecast data is input into a preset load sag identification model so that the load sag identification model calculates and outputs the probability of abnormal load fluctuation in each industry in the monitoring area in the future period according to each load forecast data, as well as the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

2. A method for predicting regional load drop according to claim 1, characterized in that: Also includes: Obtaining historical electricity consumption data and electrical equipment information of each user in the monitoring area; Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user; According to the preset industry classification rules, each user in the monitoring area is classified into the corresponding industry; Determine the risk level of each user in the industry to which they belong based on each user's power equipment information, power usage behavior patterns, and the industry to which they belong; A user information database within the monitoring area is constructed based on each user's power equipment information, power usage behavior patterns, industry, and risk level.

3. A method for predicting regional load drop according to claim 2, characterized in that: In each monitoring period, after obtaining weather data in the monitoring area, electricity consumption data of several users in each industry, market economic data of each industry, and special event information, it also includes: Re-determine the electricity usage behavior pattern of each user in the user information database based on the electricity usage data and historical electricity usage data of each user; Based on each user's re-determined electricity usage behavior patterns, electricity equipment information, and industry, the risk level of each user in the industry to which he or she belongs is updated.

4. A method for predicting regional load drop according to claim 3, characterized in that: The load change characteristics of each type of industry in the current monitoring period are generated according to the load change curve, including: Obtaining the risk level of each user in the user information database; Based on the risk level of each user and the load change curve, the load change characteristics of each industry during the current monitoring period are generated.

5. A method for predicting regional load drop according to claim 1, characterized in that: Also includes: When it is determined that the load forecast result indicates that a load drop event will occur in the monitoring area in the future period, several main reasons causing the load drop event to occur in the monitoring area in the future period are determined according to the probability of abnormal load fluctuations in various industries in the monitoring area in the future period; According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database; According to the main causes and the prevention and control strategies, load drop warning information is generated and issued.

6. A device for predicting regional load drop, characterized in that: include: The data acquisition module is used to obtain weather data in the monitoring area, electricity consumption data of several users in each type of industry, market economic data of each type of industry, and special event information during each monitoring period; A load curve generating module, used to generate a load change curve of each user in a current monitoring period according to the power consumption data; A feature generation module, used to generate the load change characteristics of each type of industry in the current monitoring period according to the load change curve; The forecast data generation module is used to encode the load change characteristics of each industry, the market economic data of each industry, weather data, and special event information to generate the load forecast data of each industry in the monitoring area during the current monitoring period; The model prediction module is used to input the load forecast data into a preset load sag identification model so that the load sag identification model calculates and outputs the probability of abnormal load fluctuations in each industry in the monitoring area in the future period according to each load forecast data, as well as the load forecast result of whether a load sag event will occur in the monitoring area in the future period.

7. A regional load drop prediction device as claimed in claim 6, characterized in that: Also includes: Information base building blocks; The information base construction module is used to obtain the historical electricity consumption data and power equipment information of each user in the monitoring area; Determine the electricity usage behavior pattern of each user based on the historical electricity usage data of each user; According to the preset industry classification rules, each user in the monitoring area is classified into the corresponding industry; Determine the risk level of each user in the industry to which they belong based on each user's power equipment information, power usage behavior patterns, and the industry to which they belong; A user information database within the monitoring area is constructed based on each user's power equipment information, power usage behavior patterns, industry, and risk level.

8. The device for predicting regional load drop according to claim 6, characterized in that: Also includes: early warning release module; The warning issuing module is used to determine several main reasons causing the load drop event to occur in the monitoring area in the future period according to the probability of abnormal load fluctuation in each industry in the monitoring area in the future period when it is determined that the load forecast result indicates that the monitoring area will experience a load drop event in the future period; According to the main reasons, a plurality of prevention and control strategies are matched in a preset prevention and control strategy database; According to the main causes and the prevention and control strategies, load drop warning information is generated and issued.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for predicting a regional load drop according to any one of claims 1 to 5 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a method for predicting a regional load drop according to any one of claims 1 to 5.

Images