An intelligent load scheduling method, device and storage medium for a ring main unit

Abstract

The present invention relates to the technical field of load scheduling, and discloses an intelligent load scheduling method, device and storage medium for a ring main unit. The method includes: obtaining fault location information and historical power consumption data of surrounding users; according to the historical power consumption data, using a pre-configured power consumption data analysis model for processing and analysis to obtain user power consumption behavior characteristics; based on a preset weight allocation model, performing weight matching on the user power consumption behavior characteristics to obtain the scheduling priority of the users, and restoring the faults from low to high according to the scheduling priority. This method improves the reliability of power grid fault recovery and enhances the intelligent level of power resource management.

Description

Technical Field

[0001] The present invention relates to the technical field of load scheduling, and in particular to an intelligent scheduling method, device, and storage medium for load management of ring main units. Background Art

[0002] Currently, against the backdrop of the continuous growth of global energy consumption, as the core hub for power distribution, the load intelligence of ring main units has become the key to improving energy efficiency and ensuring power supply stability.

[0003] In the prior art, the load management of electricity lacks intelligent scheduling means when dealing with load faults. When handling faults, in the face of the complex and changeable power grid operation environment, the existing scheduling methods mainly schedule according to the power consumption of the load, which is prone to inaccurate scheduling problems. Moreover, the complexity and diversity of user electricity consumption behaviors are not fully considered, lacking data-driven optimization algorithm support, and unable to handle according to the current scenario status during power resource scheduling to achieve fault recovery.

[0004] The above-mentioned technology fails to fully consider the complexity and diversity of user electricity consumption behaviors when dealing with the recovery of power grid emergencies, resulting in low reliability of fault recovery. Summary of the Invention

[0005] The present invention provides an intelligent scheduling method, device, and storage medium for load management of ring main units to address the problem that the above-mentioned technology fails to fully consider the complexity and diversity of user electricity consumption behaviors when dealing with the recovery of power grid emergencies, resulting in low reliability of fault recovery.

[0006] In a first aspect, to solve the above technical problem, the present invention provides an intelligent scheduling method for load management of ring main units, including:

[0007] Obtain the fault location information and the historical electricity consumption data of surrounding users;

[0008] According to the historical electricity consumption data, use a pre-configured electricity consumption data analysis model for processing and analysis to obtain user electricity consumption behavior characteristics;

[0009] Based on a preset weight assignment model, perform weight matching on the user electricity consumption behavior characteristics to obtain the scheduling priority of the user, and recover the fault from low to high according to the scheduling priority.

[0010] Optionally, the historical electricity consumption data is the electricity consumption data of surrounding users within a preset time period before the occurrence of the fault;

[0011] Optionally, based on the historical power consumption data, using a pre-configured power consumption data analysis model for processing and analysis to obtain user power consumption behavior characteristics, including:

[0012] Using a power consumption habit analysis model to analyze the historical power consumption data to obtain user power consumption habit characteristics; wherein, the user power consumption habit characteristics include the user's power consumption frequency, power consumption amount, and peak-valley power consumption period within the time period;

[0013] Inputting the power consumption habit characteristics into a power consumption behavior analysis model for analysis to obtain user power consumption behavior characteristics; wherein, the user power consumption behavior characteristics include the user's failure rate, user importance value, and user power consumption probability prediction value;

[0014] Among them, the power consumption data analysis model includes a power consumption habit analysis model and a power consumption behavior analysis model.

[0015] Optionally, after obtaining the user power consumption behavior characteristics, the method further includes:

[0016] Updating the original user power consumption behavior characteristics stored in the memory to obtain the updated user power consumption behavior characteristics.

[0017] Optionally, the method further includes:

[0018] When it is detected that the failure rate of a certain user is higher than a preset failure rate threshold, generating a warning message and sending it to the user.

[0019] Optionally, the method further includes:

[0020] Obtaining the real-time power consumption of all surrounding users, and when the real-time power consumption of any user is less than a preset user power consumption threshold, invoking the power surplus of the user for fault recovery.

[0021] Optionally, the weight allocation model includes:

[0022]

[0023] Among them, N is the priority value of the user in power resource scheduling, N1 is the user importance value, N2 is the user failure rate, N3 is the user power consumption frequency, and N4 is the user power consumption probability prediction value;

[0024] Among them and are preset coefficients, and their value ranges are both from 0 to 1.

[0025] Optionally, the method further includes:

[0026] When at least two fault areas exist, analyze the historical power consumption data of users in each fault area respectively, obtain the fault recovery priorities corresponding to each fault area, and perform fault recovery in descending order according to the fault recovery priorities;

[0027] Among them, the historical power consumption data is the power consumption data of fault users within a preset time period before the fault occurs.

[0028] In a second aspect, the present invention provides a load intelligent scheduling device for a ring main unit, including:

[0029] A power consumption monitoring unit for obtaining fault location information and the historical power consumption data of surrounding users;

[0030] A weight determination unit for processing and analyzing using a pre-configured power consumption data analysis model to obtain user power consumption behavior characteristics; and performing weight matching on the user power consumption behavior characteristics based on a preset weight allocation model to obtain the scheduling priorities of users, and processing according to the historical power consumption data to obtain the scheduling priorities;

[0031] A resource scheduling unit for scheduling power resources to recover at the fault location in ascending order according to the scheduling priorities.

[0032] In a third aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the ring main unit load intelligent scheduling method described in any one of the above.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention provides a ring main unit load intelligent scheduling method, including: obtaining fault location information and the historical power consumption data of surrounding users; according to the historical power consumption data, using a pre-configured power consumption data analysis model for processing and analysis to obtain user power consumption behavior characteristics; performing weight matching on the user power consumption behavior characteristics based on a preset weight allocation model to obtain the scheduling priorities of users, and recovering the fault in ascending order according to the scheduling priorities. When dealing with sudden power grid faults, by analyzing user power consumption data, using the power consumption data analysis model for analysis to obtain user power consumption behavior characteristics, and then processing the user power consumption behavior characteristics using the weight allocation algorithm to obtain the scheduling priorities of users, so that the system schedules power resources according to the scheduling priorities of users for fault recovery, thereby improving the reliability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flowchart of the ring main unit load intelligent scheduling method provided by an embodiment of the present invention;

[0036] Figure 2 It is a schematic structural diagram of the intelligent load scheduling device for the ring main unit provided by the embodiment of the present invention. Detailed implementation manners

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0038] Referring to Figure 1 , the first embodiment of the present invention provides an intelligent load scheduling method for a ring main unit, including the following steps:

[0039] S1, obtaining the fault location information and the historical power consumption data of surrounding users.

[0040] S2, according to the historical power consumption data, using a pre-configured power consumption data analysis model for processing and analysis to obtain user power consumption behavior characteristics.

[0041] S3, performing weight matching on the user power consumption behavior characteristics based on a preset weight distribution model to obtain the scheduling priority of the user, and restoring the fault from low to high according to the scheduling priority.

[0042] It should be noted that in the context of the continuous growth of global energy consumption, the role of the ring main unit, the core hub of power distribution, has become particularly important. The intelligence of the ring main unit not only concerns the improvement of energy efficiency, but also directly affects the stability and reliability of power supply. However, there are obvious deficiencies in the existing power load management in terms of intelligence, especially in the emergency handling ability in the face of power grid failures.

[0043] When dealing with power grid failures, traditional methods often rely on simple power consumption data for scheduling decisions. This single consideration criterion cannot comprehensively reflect the complexity of user power consumption behavior. For example, the power consumption patterns of different users may vary greatly at different times. Industrial users may have production peaks at night, while residential users may have power consumption peaks in the evening. In addition, factors such as the type of user's electrical equipment, the requirements for power consumption stability, and the sensitivity to power quality are all important dimensions affecting power grid scheduling decisions. However, the existing technologies have not comprehensively considered these factors and lack a data-driven optimization algorithm to support more accurate and reliable scheduling. When a sudden power grid failure occurs, if it is impossible to quickly respond and adjust according to real-time data and the power consumption characteristics of users, it is difficult to achieve effective resource allocation and fault recovery, which directly affects the reliability of the power grid and the power consumption experience of users.

[0044] The present invention provides an intelligent load scheduling method for ring main units. When dealing with sudden power grid failures, by analyzing user power consumption data, using a power consumption data analysis model for analysis, obtaining user power consumption behavior characteristics, and using a weight allocation algorithm for processing, obtaining the scheduling priorities of users, enabling the system to schedule power resources according to the scheduling priorities of users for fault recovery, thereby improving the reliability of power supply.

[0045] To facilitate the understanding of the present invention, some preferred embodiments of the present invention will be further described below.

[0046] In step S1, obtain the fault location information and the historical power consumption data of surrounding users.

[0047] It should be noted that the fault location information refers to the detailed information of the specific fault occurrence location that the system can determine when a power grid failure occurs. To determine the specific location of the fault in the power system, this information is usually obtained through power grid monitoring devices, such as sensor networks, smart meters, or anomaly detection algorithms in the power grid management system for real-time monitoring and identification, so as to obtain fault signals. Once a power grid anomaly is detected, the system can accurately locate the fault location through means such as GPS. After determining the fault location, the system needs to collect the historical power consumption data of surrounding users.

[0048] Specifically, the historical power consumption data in step S1 is the power consumption data of surrounding users within a preset time period before the fault occurs.

[0049] Among them, the preset time period is a specific time range set in the power grid management system for analyzing and predicting power consumption behavior. This time period is usually selected for a period of time before the power grid failure, which can be a time range such as one month or half a year. The preset time period is set by power grid staff based on the understanding of the power grid operation mode, statistical analysis of historical fault data, or characteristics of user power consumption patterns. The power consumption data refers to the user power consumption information collected by power consumption monitoring devices within the preset time period. These information include, but are not limited to, electrical parameters such as voltage, current, power factor, and frequency. The collection of power consumption data is usually achieved through devices such as smart meters, sensors, and data acquisition systems, which can monitor and record the power consumption situation of users in real time.

[0050] In step S2, according to the historical power consumption data, use a pre-configured power consumption data analysis model for processing and analysis to obtain user power consumption behavior characteristics.

[0051] It should be noted that the power consumption data analysis model includes a power consumption habit analysis model and a power consumption behavior analysis model;

[0052] The electricity consumption habit analysis model is a pre-configured data analysis model that uses statistical analysis methods to identify electricity consumption patterns and applies machine learning algorithms to improve the accuracy and efficiency of identification. By analyzing the input user electricity consumption data, it can obtain the user's daily electricity consumption curve, seasonal electricity consumption changes, electricity consumption behavior under special events, etc. By identifying these features, the model can classify and label the user's electricity consumption behavior, providing basic data for further analysis of electricity consumption behavior characteristics.

[0053] Among them, the user electricity consumption habit features include the user's electricity consumption frequency, electricity consumption volume, peak and valley electricity consumption periods of the user within the time period, and other features.

[0054] The electricity consumption behavior analysis model is a data analysis tool pre-trained using big data algorithms. First, it preprocesses and analyzes the data based on the k-means clustering algorithm to obtain the target user electricity consumption behavior feature parameter set. Then, it further applies the neural network algorithm to the feature parameter set, draws dynamic curve graphs, predicts the user's behavior, and evaluates the potential risks under the user's electricity consumption behavior pattern. Finally, it outputs the user's electricity consumption behavior features.

[0055] Exemplarily, the applied neural network algorithms include:

[0056] The multi-layer perceptron (MLP) is a feedforward neural network composed of multiple neuron layers. It receives data through the input layer, performs weighted and nonlinear transformations through one or more hidden layers, and finally generates prediction results in the output layer. It uses the backpropagation algorithm and gradient descent method to train the network weights so that it can learn complex function mappings. In electricity consumption behavior analysis, the MLP can be used to identify and predict the user's electricity consumption patterns. The input layer receives the user's electricity consumption data, the hidden layer processes and extracts features, and the output layer generates prediction results.

[0057] The recurrent neural network (RNN) is a neural network for processing sequential data that can capture the temporal dependencies in time series data. Its internal recurrent mechanism enables the network to pass the information from the previous time step (i.e., historical data) to the current time step through the state of the hidden layer, realizing the dynamic processing of sequential data. Specifically, the RNN receives an input vector at each time step, combines it with the hidden state of the previous time step, performs a linear transformation through a weight matrix, and then performs a nonlinear transformation through an activation function (such as Sigmoid or Tanh) to generate the output and a new hidden state at the current time step. This process is repeated continuously until the entire sequence is processed. In electricity consumption behavior analysis, the RNN can be used to predict the user's electricity consumption behavior at different time periods, especially in cases where time dependencies need to be considered.

[0058] Among them, the user's electricity consumption behavior characteristics include the user's failure rate, the user's importance value, and the predicted value of the user's electricity consumption probability.

[0059] In one implementation, the specific modules of the electricity consumption behavior analysis model include:

[0060] Habits acquisition unit: used to identify and acquire electricity consumption habit data such as the user's electricity consumption frequency, electricity consumption amount, and peak-valley periods of the user's electricity consumption.

[0061] Data preprocessing unit: cleans, formats, and converts the collected electricity consumption habit data to meet the input requirements of the analysis model.

[0062] Behavior recognition unit: by statistically analyzing the user's electricity consumption habit characteristics and applying advanced algorithms such as machine learning and data mining technologies, identifies the significant characteristics and potential patterns of the user's electricity consumption behavior.

[0063] Prediction analysis unit: using technologies such as the fuzzy neural network algorithm, this unit predicts the user's future electricity consumption behavior and provides forward-looking guidance for the allocation of power resources and the planning of the power grid.

[0064] Feature output unit: outputs the user's electricity consumption behavior characteristics obtained from the processed historical electricity consumption data in a structured form.

[0065] In an alternative implementation, in step S2, the processing and analysis of the historical electricity consumption data using a pre-configured electricity consumption data analysis model to obtain the user's electricity consumption behavior characteristics includes:

[0066] Analyze the historical electricity consumption data using the electricity consumption habit analysis model to obtain the user's electricity consumption habit characteristics; input the electricity consumption habit characteristics into the electricity consumption behavior analysis model for analysis to obtain the user's electricity consumption behavior characteristics.

[0067] It should be noted that after obtaining the user's electricity consumption behavior characteristics, the method further includes:

[0068] Update the original user's electricity consumption behavior characteristics stored in the memory to obtain the updated user's electricity consumption behavior characteristics. Exemplarily, the updated user's electricity consumption behavior characteristics can be stored as an external file and output. This output can adopt a standardized data format, such as CSV, JSON, or XML, etc., to facilitate reading and processing by different systems and applications. In this way, the updated user's electricity consumption behavior characteristics can be applied within the power system and at the same time provide data support for external researchers and developers.

[0069] Among them, the user failure rate is a parameter used to evaluate the potential risk of power supply interruption or failure encountered by users during the process of being called for power resources. This parameter is represented by a numerical range from 0 to 1, where the higher the value, the higher the probability of power supply interruption faced by the user, and a higher value means that the user is more likely to encounter a failure situation during the power call process.

[0070] The user importance value is a parameter in the power system used to measure the user's demand for power supply stability and the priority of power grid resource allocation. By comprehensively considering the user's social and economic value, dependence on continuous power supply, and role in power grid operation, it ensures that critical infrastructure and services are given priority during power shortages. This parameter is represented by a numerical range from 0 to 1, and a higher value means that the user has a higher demand for power supply stability and a higher priority for power grid resource allocation.

[0071] The predicted value of the user's power consumption probability is a quantitative indicator used to predict the probability of a user consuming power during a specific time period of a day. This indicator is represented by a numerical range from 0 to 1, where the smaller the value, the smaller the probability of the user consuming power during the specific time period; the larger the value, the greater the probability of the user consuming power during the specific time period. Among them, the specific time period starts from the time when the power grid fails and ends until the time when the failure is predicted to be fully restored.

[0072] It should also be noted that when the user failure rate of a certain user is detected to be higher than the preset failure rate threshold, a warning message is generated and sent to the user.

[0073] Among them, the failure rate threshold is a key parameter used to evaluate and define the critical level of the risk of power supply interruption encountered by users. This threshold is set based on the analysis of historical failure data and statistical methods. When it is monitored that the failure rate of a user exceeds this preset threshold, the warning notification mechanism for the user is triggered, and a warning message is generated and sent to the user.

[0074] In addition, the generated warning message will be sent to the user through an appropriate communication channel to ensure that the user can receive this important information in a timely manner. This can be achieved through text messages, emails, mobile application push notifications, or any communication method agreed upon between the user and the power grid operator.

[0075] In another alternative implementation, the method further includes:

[0076] Obtain the real-time power consumption of all surrounding users. When the real-time power consumption of any user is less than the preset user power consumption threshold, call the power margin of this user for fault recovery.

[0077] The user power consumption threshold is set by power system staff based on historical experience and grid load conditions, etc. When the real-time power consumption of any user is monitored to be lower than this preset threshold, the system will identify that the user has unused power surplus, and the system will automatically give priority to calling the power surplus of these users below the threshold to support the power demand for fault recovery.

[0078] In step S3, based on a preset weight allocation model, weight matching is performed on the user power consumption behavior characteristics to obtain the scheduling priority of the user, and the faults are recovered from low to high according to the scheduling priority.

[0079] The weight allocation model includes:

[0080]

[0081] Among them, is the priority value of the user in power resource scheduling, is the user importance value, N2 is the user failure rate, N3 is the user power consumption frequency, and N4 is the predicted user power consumption probability value.

[0082] Among them, the priority value of the user in power resource scheduling is a decisive parameter, which is obtained through comprehensive calculation and reflects the priority of the user to obtain power resources. The larger the value, the higher the importance of the user in power resource allocation. Therefore, when power resources are in short supply or during fault recovery, the system will give priority to meeting the needs of these high-priority users. At the same time, this also means that in the case of a power grid fault, the system will tend to first call the power resources of those users with lower priority values to achieve the rapid recovery of the power grid and the optimal allocation of resources. This scheduling mechanism ensures that critical users can obtain stable and reliable power supply, and at the same time improves the overall operation efficiency and reliability of the power grid.

[0083] is the user importance value. In terms of numerical representation, the user importance value is in the range of 0 to 1. Within this range, the higher the value, the more urgent the user's demand for power supply stability, and the relatively higher its priority in power grid resource allocation.

[0084] is the user failure rate, which is represented by a numerical range of 0 to 1. When the numerical value of the user failure rate is low, it indicates that the user faces a small risk of power supply interruption during the process of using power resources; relatively, when this numerical value is high, it indicates an increase in the probability of the user encountering a fault during power consumption.

[0085] is the user's power consumption frequency, which measures how frequently the user connects to the power grid and consumes electricity within a certain period. The value range of this indicator is from 0 to 1, where 0 means the user has no power consumption during the investigated time period, and 1 indicates that the user is continuously consuming electricity, close to or equal to the full-time usage.

[0086] is the predicted value of the user's power consumption probability, measured in the value range of 0 to 1. The higher or lower the value is directly related to the size of the power consumption probability: when the value is lower, it means that the user has a lower possibility of consuming electricity during this specific time period; on the contrary, a higher value indicates a greater power consumption probability of the user during this specific time period.

[0087] and are two core preset coefficients, which respectively represent the weight adjustment factors of different parameters in the model. Their values are between 0 and 1, and the power system staff set their specific values according to the actual operation strategies and goals. is mainly used to balance the user's power consumption frequency. affects the proportion of the user's failure rate in the weight calculation.

[0088] In implementation, according to the user's power consumption frequency and the user importance value, user failure rate, predicted value of the user's power consumption probability in the above user power consumption habit characteristics, and set corresponding coefficients for the user's power consumption frequency and predicted value of the user's power consumption probability, the user weight value can be calculated. At the same time, it is also necessary to ensure the primary and secondary relationships among the four weights of the user importance value, user failure rate, user power consumption frequency, and predicted value of the user's power consumption probability under certain circumstances. Therefore, the user's scheduling priority is a function of the user importance value, user failure rate, user power consumption frequency, and predicted value of the user's power consumption probability.

[0089] It should be noted that, first of all, the user importance value is the principle of priority consideration. That is, among two users with different importance values, if the importance value of the first user is higher than that of the second user, the scheduling priority of the first user should be higher than that of the second user, and the power resources of the second user should be preferentially called to restore the fault. Secondly, the influence degree of the weight of the user failure rate should be second only to the weight of the user importance value. The higher the user failure rate, the greater the possibility of failure during the process of restoring the power resources of this user. Then, the weights of the user failure rate and the predicted value of the user's power consumption probability should be considered comprehensively, and specifically can be adjusted through the coefficients and Finally, the user's power consumption frequency is an auxiliary consideration factor, and has the lowest impact on the user's scheduling priority.

[0090] Meanwhile, monitor and obtain the real-time power consumption of all surrounding users. When the real-time power consumption of any user is less than the preset user power consumption threshold, the scheduling priority of this user will be automatically reduced to the lowest, and the power resources of this user will be called to perform fault recovery. If the real-time power consumption of at least two users is less than the preset user power consumption threshold, then calculate the scheduling priorities of all users according to the formula, and call the power resources of users with lower priorities in turn according to the calculated scheduling priorities to perform fault recovery.

[0091] In an alternative embodiment, when there are at least two faulty users, analyze the historical power consumption data of each faulty user respectively to obtain the fault recovery priority corresponding to each faulty user, and perform fault recovery in descending order according to the fault recovery priority.

[0092] Wherein, the historical power consumption data is the power consumption data of the faulty user within a preset time period before the fault occurs.

[0093] Specifically, the system will analyze the historical power consumption data of each faulty user respectively. The historical power consumption data is processed and analyzed using a pre-configured power consumption data analysis model to obtain the user power consumption behavior characteristics. Further combined with the weight allocation algorithm, these characteristics are converted into the scheduling priorities of each faulty user. Through the analysis of these data, the system can calculate the fault recovery priority corresponding to each faulty user, ensuring that key areas and users can obtain the restoration of power resources first. Then, the system will perform fault recovery operations in descending order according to these priorities, optimize the allocation of power resources, and improve the efficiency and effect of power grid fault recovery.

[0094] In summary, the present invention relates to an intelligent load scheduling method for a ring main unit. When a power grid fault occurs, this method obtains the fault location information and the historical power consumption data of surrounding users. And according to the historical power consumption data, it is processed and analyzed using a pre-configured power consumption data analysis model to obtain the user power consumption behavior characteristics. Further combined with the weight allocation algorithm, these characteristics are converted into the scheduling priorities of each user. Finally, the system dynamically adjusts and optimizes the allocation of power resources based on these priorities to ensure rapid and effective power restoration when a fault occurs. This method not only improves the response speed and recovery ability of the power grid, but also enhances the reliability and intelligence level of power resource management, providing a solid guarantee for the stable operation of the power grid and the power consumption safety of users.

[0095] Refer to Figure 2 , the second embodiment of the present invention provides an intelligent load scheduling device for a ring main unit, including:

[0096] A power consumption monitoring unit, configured to obtain the fault location information and the historical power consumption data of surrounding users;

[0097] A weight determination unit, configured to process and analyze by using a pre-configured power consumption data analysis model to obtain user power consumption behavior characteristics; and perform weight matching on the user power consumption behavior characteristics based on a preset weight allocation model to obtain the scheduling priority of the user, and process the historical power consumption data to obtain the scheduling priority;

[0098] A resource scheduling unit, configured to schedule power resources to the fault location for restoration in ascending order of the scheduling priority.

[0099] Specifically, the power consumption monitoring unit: responsible for real-time monitoring and recording of the user's power consumption situation. By connecting to data acquisition devices such as smart meters and sensors, the power consumption monitoring unit can obtain the historical power consumption data of the user within a specific time period. This data not only includes the magnitude of the power consumption, but also covers detailed information such as the power consumption frequency and peak-valley periods. Through this data, the system can comprehensively understand the user's power consumption habits and power consumption behavior characteristics.

[0100] The weight determination unit: receives the historical power consumption data provided by the power consumption monitoring unit and performs in-depth analysis by using a preset weight allocation model. The weight allocation model comprehensively considers multiple factors such as the user's power consumption frequency, power consumption amount, power consumption peak-valley period, failure rate, importance value, and power consumption probability prediction value, and calculates the scheduling priority of each user through a scientific algorithm. This priority reflects the relative importance of the user in power resource scheduling and provides a decision basis for subsequent resource scheduling.

[0101] The resource scheduling unit: This unit is a key part of the system for performing operations. It intelligently schedules the power resources at the fault location according to the scheduling priority calculated by the weight determination unit. The resource scheduling unit dynamically adjusts the allocation of power resources through an optimization algorithm to give priority to ensuring the power supply of high-priority users. When a power grid failure occurs, this unit can quickly respond, reasonably allocate power resources according to the user's power consumption behavior characteristics and priority, and achieve rapid recovery of the failure. At the same time, the resource scheduling unit can also dynamically adjust the scheduling strategy according to the real-time operating conditions of the power grid and the changes in the user's power consumption demand to ensure the stable operation of the power grid and the power consumption quality of the user.

[0102] The aforementioned power consumption behavior characteristic analysis module includes:

[0103] A habit characteristic analysis unit, configured to analyze the historical power consumption data by using a power consumption habit analysis model to obtain user power consumption habit characteristics; wherein, the user power consumption habit characteristics include the user's power consumption frequency, user's power consumption amount, and user's power consumption peak-valley period within the preset time period;

[0104] A behavior feature analysis unit is configured to input the electricity consumption habit features into an electricity consumption behavior analysis model for analysis to obtain user electricity consumption behavior features. Among them, the user electricity consumption behavior features include user failure rates, user importance values, and user electricity consumption probability prediction values.

[0105] It should be noted that a ring main unit load intelligent scheduling device provided in an embodiment of the present invention is used to execute all process steps of a ring main unit load intelligent scheduling method in the above embodiment. The working principles and beneficial effects of the two correspond one by one, and thus will not be elaborated here.

[0106] An embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a ring main unit load intelligent scheduling program. When the processor executes the computer program, the steps in the above embodiments of various ring main unit load intelligent scheduling methods are implemented, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiments are implemented, such as the weight determination module.

[0107] Exemplarily, the computer program may be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0108] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0109] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device, connecting all parts of the entire electronic device through various interfaces and circuits.

[0110] The memory can be used to store the computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0111] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0112] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached 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 can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0113] The above-described specific embodiments have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligently dispatching loads of a ring main unit, characterized in that: include: Obtain fault location information and historical electricity consumption data of surrounding users; Based on the historical electricity consumption data, a pre-configured electricity consumption data analysis model is used to process and analyze the data to obtain the user's electricity consumption behavior characteristics; Based on the preset weight allocation model, the user's electricity consumption behavior characteristics are weighted and matched to obtain the user's scheduling priority, and the user resources with low to high scheduling priority are scheduled to achieve recovery from other user failures; Wherein, the weight distribution model includes: Wherein, N is the priority value of the user in the power resource scheduling, N1 is the importance value of the user, N2 is the failure rate of the user, N3 is the power consumption frequency of the user, and N4 is the power consumption probability prediction value of the user; in and is the preset coefficient, and its value range is 0 to 1; The user power consumption behavior characteristics include user failure rate, user importance value, and user power consumption probability prediction value.

2. The method for intelligently dispatching loads of a ring main unit according to claim 1, characterized in that: The historical power consumption data is the power consumption data of surrounding users within a preset time period before the fault occurs.

3. The method for intelligently dispatching loads of ring main units according to claim 2, characterized in that: The method of processing and analyzing the historical electricity consumption data using a pre-configured electricity consumption data analysis model to obtain the user's electricity consumption behavior characteristics includes: The historical electricity usage data is analyzed using an electricity usage habit analysis model to obtain the user's electricity usage habit characteristics; wherein the user's electricity usage habit characteristics include the user's electricity usage frequency, the user's electricity usage, and the user's electricity usage peak and valley time periods within the preset time period; Inputting the electricity usage habit characteristics into the electricity usage behavior analysis model for analysis to obtain the user's electricity usage behavior characteristics; wherein the user's electricity usage behavior characteristics include user failure rate, user importance value, and user electricity usage probability prediction value; Among them, the electricity consumption data analysis model includes the electricity consumption habit analysis model and the electricity consumption behavior analysis model.

4. The method for intelligently dispatching loads of a ring main unit according to claim 3, characterized in that: After obtaining the user's electricity usage behavior characteristics, the method further includes: The original user power usage behavior characteristics stored in the memory are updated to obtain the updated user power usage behavior characteristics.

5. The method for intelligently dispatching loads of a ring main unit according to claim 3, characterized in that: include: When it is detected that the user failure rate of a certain user is higher than a preset failure rate threshold, a warning message is generated and sent to the user.

6. The method for intelligently dispatching loads of a ring main unit according to claim 3, characterized in that: The method further comprises: The real-time power consumption of all surrounding users is obtained. When the real-time power consumption of any user is less than a preset user power consumption threshold, the power reserve of the user is called to perform fault recovery.

7. The method for intelligently dispatching loads of a ring main unit according to any one of claims 1 to 6, characterized in that: Also includes: When at least two fault areas exist, historical power consumption data of users in each fault area are analyzed respectively to obtain the fault recovery priority corresponding to each fault area, and fault recovery is performed in order from high to low according to the fault recovery priority; The historical electricity consumption data is the electricity consumption data of the faulty user within a preset time period before the fault occurs.

8. A ring main unit load intelligent dispatching device, used to implement the ring main unit load intelligent dispatching method according to any one of claims 1 to 7, characterized in that: include: The power consumption monitoring unit is used to obtain the fault location information and the historical power consumption data of surrounding users; A weight determination unit, used to process and analyze the power consumption data using a pre-configured power consumption data analysis model to obtain the user's power consumption behavior characteristics; And based on a preset weight allocation model, weight matching is performed on the user's electricity consumption behavior characteristics to obtain the user's scheduling priority. The historical electricity consumption data is processed to obtain the scheduling priority; The resource scheduling unit is used to schedule the power resources at the fault location for recovery according to the scheduling priority from low to high.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the intelligent scheduling method for ring main unit load according to any one of claims 1 to 7.

Images