Power load control method based on multifunctional flexible adjusting unit

Abstract

The invention provides a power load control method based on a multifunctional flexible adjusting unit, and belongs to the technical field of power load control. The power load control method based on the multifunctional flexible adjusting unit comprises the following steps: collecting current data and voltage data, monitoring the load condition of a special transformer user, and carrying out load identification by utilizing edge calculation so as to distinguish the power load type and the power load working state; constructing a load prediction model; acquiring historical load data stored in the terminal and the master station software; generating a prediction result in the load prediction model based on the historical load data, the power load type and the power load working state; and dynamically adjusting the operation state of the electric equipment based on the prediction result. According to the power load control method based on the multifunctional flexible adjustment unit, the refinement degree of load management and the accuracy of load prediction can be improved, and dynamic optimization scheduling can be realized.

Description

Technical Field

[0001] The present application belongs to the technical field of power load control, and specifically relates to a power load control method, device and electronic equipment based on a multifunctional flexible adjustment unit. Background Art

[0002] The application of flexible regulation units in power systems is one of the important directions of energy Internet and power grid development in recent years. This type of technology integrates advanced sensing, communication, computing and control technologies to enable power systems to respond more flexibly and efficiently to various changes in power demand, ensuring the stability, reliability and economy of the system. With the rapid development and popularization of new energy power generation, especially distributed energy such as photovoltaic and wind power, and energy storage technology, the structure of the power system is undergoing profound changes, which poses unprecedented challenges to the system's regulation capabilities.

[0003] In this context, the flexible regulation unit needs to have higher comprehensive performance. However, the existing flexible regulation units have low refinement and load forecasting accuracy, and are difficult to achieve dynamic optimization scheduling, low efficiency and poor stability. Summary of the invention

[0004] In order to solve at least one of the technical problems existing in the background technology, the present application provides an electric load control method based on a multifunctional flexible adjustment unit, which can improve the refinement of load management, the accuracy of load forecasting, and realize dynamic optimization scheduling, and effectively solve the technical problems of high regulation pressure, low efficiency and poor stability faced by the power system in the face of distributed energy development, load diversification and demand growth.

[0005] The technical solution adopted in this application is: The first embodiment of the present application provides a method for controlling a power load based on a multifunctional flexible adjustment unit, including: Collect current and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify loads to distinguish the type of power loads and the working status of power loads; Build load forecasting models; Obtain historical load data stored in the terminal and master station software; Based on the historical load data, the power load type and the power load working state, generating a prediction result in the load prediction model; The operating status of the electrical equipment is dynamically adjusted based on the prediction result.

[0006] According to the power load control method based on the multifunctional flexible adjustment unit provided in the first aspect of the present application, by real-time monitoring of the load status of the dedicated transformer user and accurately identifying the load type and working status, it is possible to ensure that the power equipment operates in the most suitable state, reduce ineffective energy consumption, and improve the energy efficiency of the entire power grid. The load forecasting model combines historical data, load type and status to accurately predict future load changes. The power grid operator can pre-adjust the power supply plan according to these forecast results, effectively avoid problems such as overload and voltage fluctuations, and enhance the stability and reliability of the power grid. Dynamically adjust the operating status of the power equipment, which can increase the load consumption during the peak period of renewable energy generation and adjust and reduce it during the valley period, which helps to balance the supply and demand of the power grid, promote the efficient use of renewable energy such as wind energy and solar energy, and the green transformation of the power grid. It promotes the deep integration of information technology and power systems, provides key technical support for the development of smart grids, enhances the automation and information level of power grids, and lays the foundation for realizing flexible interaction, efficient operation and sustainable development of power grids. In summary, the power load control method based on a multifunctional flexible regulation unit provided in this application can improve the refinement of load management, the accuracy of load forecasting, and realize dynamic optimization scheduling, effectively solving the technical problems of high regulation pressure, low efficiency and poor stability faced by the power system in the face of distributed energy development, load diversification and demand growth.

[0007] According to an embodiment of the present application, the current data and voltage data are collected, the load status of the dedicated transformer user is monitored, and the load is identified by edge computing to distinguish the power load type and the power load working status, specifically: Filter and denoise the raw current and voltage data; Extracting load characteristic parameters from the processed current data and voltage data, wherein the load characteristic parameters include harmonic content parameters, current waveform parameters, and power factor parameters; Obtain load samples of known types, and establish mapping relationships between current characteristics and voltage characteristics and load types, and between current characteristics and voltage characteristics and working states of power loads; Clustering algorithms are used to identify patterns in load data, identify load groups, and analyze and confirm the type and working status of power loads.

[0008] According to an embodiment of the present application, the extracting of load characteristic parameters from the processed current data and voltage data is specifically: Use fast Fourier transform or wavelet transform to perform spectrum analysis on current data and voltage data, calculate the amplitude and phase of each harmonic, and generate total harmonic distortion and each harmonic content; Analyze the peak value, valley value, effective value and waveform distortion of the current waveform to determine the nature of the load.

[0009] According to an embodiment of the present application, the acquisition of historical load data stored in the terminal and the master station software is specifically: Establishing a communication connection between the terminal and the master station software; Control the main station software to construct a query instruction and send it to the terminal; After receiving the instruction, the terminal retrieves the historical data area stored locally based on the instruction content, generates a message and responds to the main station software; The master station software receives the response, parses the message and extracts the required historical load data.

[0010] According to an embodiment of the present application, the prediction result is generated in the load prediction model based on the historical load data, the power load type and the power load working state, specifically: Marking the power load types as industrial power load, commercial power load and residential power load, and marking the power load working states as peak, flat and valley; Converting the industrial power load, the commercial power load and the residential power load into numerical variables; A binary feature is created based on the classification of the power load operating state.

[0011] According to one embodiment of the present application, the method further includes: Control the master station software to send a time calibration instruction to the terminal; The terminal is controlled to update an internal clock according to the time data in the time calibration instruction.

[0012] According to an embodiment of the present application, dynamically adjusting the operating state of the electrical equipment based on the prediction result is specifically: Based on the prediction result, controlling the master station software to generate a load balancing strategy; The master station is controlled to monitor the operating status and load changes of the electrical equipment and to feed back data in real time.

[0013] According to one embodiment of the present application, the load balancing strategy includes load transfer and power generation forecast scheduling.

[0014] The second aspect of the present application provides a power load control device based on a multifunctional flexible adjustment unit, including: The differentiation module is suitable for collecting current data and voltage data, monitoring the load status of dedicated transformer users, and using edge computing for load identification to distinguish the type of power load and the working status of the power load; Model building module, suitable for building load forecasting models; A data acquisition module, suitable for acquiring historical load data stored in the terminal and the master station software; A prediction result generating module, adapted to generate a prediction result in the load prediction model based on the historical load data, the power load type and the power load working state; The adjustment module is adapted to dynamically adjust the operating state of the electrical equipment based on the prediction result.

[0015] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the power load control method based on the multifunctional flexible adjustment unit in any embodiment of the first aspect as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of a flow chart of a method for controlling a power load based on a multifunctional flexible regulating unit provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an electric load control device based on a multifunctional flexible adjustment unit provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0017] in, 110, distinguishing module; 120, model building module; 130, data acquisition module; 140, prediction result generation module; 150, adjustment module; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0018] In order to more clearly illustrate the overall concept of the present application, a detailed description is given below in an illustrative manner in conjunction with the accompanying drawings.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present application is not limited by the specific embodiments disclosed below. It should be noted that the embodiments of the present application and the features in each embodiment may be combined with each other without conflict.

[0020] In addition, in the description of the present application, it should be understood that the orientations or positional relationships indicated by the terms "top", "bottom", "inside", "outside", "axial", "radial", "circumferential", etc. are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0021] In this application, unless otherwise clearly specified and limited, the terms "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, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0022] In the present application, unless otherwise clearly specified and limited, a first feature "above" or "below" a second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0023] like Figure 1 As shown, the first embodiment of the present application provides a method for controlling a power load based on a multifunctional flexible adjustment unit, comprising: Step 100: Collect current data and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify the load to distinguish the type of power load and the working status of the power load.

[0024] In step 100, the current data and voltage data collection is the basis of the entire control process, which is usually achieved through devices such as smart meters, current transformers and voltage transformers installed at key nodes. These devices can monitor the current intensity and voltage level in the line in real time, and convert these data into digital signals to provide original information for subsequent processing. Monitoring the load status of special transformer users is through continuous collection of current and voltage data. The system can evaluate the changes in power demand of special transformer users in real time, including the size of the load, the trend of change, and possible abnormal conditions (such as voltage fluctuations, current mutations, etc.). This monitoring not only helps to diagnose faults immediately, but also lays a data foundation for subsequent intelligent regulation. In the process of load identification, edge computing plays a key role here. It refers to the technology of data analysis and processing close to the data source (such as smart gateways or edge servers at the user's site), instead of transmitting all data to the cloud for processing. This step involves the application of complex algorithms, which aims to identify different types of power loads (such as motors, lighting, air conditioners, etc.) based on the characteristics of current and voltage waveforms, and further judge the working status of each load (such as no load, full load or partial load). By analyzing electrical parameters such as the phase difference between current and voltage, harmonic components, power factor, and combining with specific algorithm models, the system can distinguish different types of loads (such as resistive, inductive or capacitive loads) and identify whether they are currently within the normal operating range and whether maintenance or adjustment is required. This is crucial for optimizing resource allocation, avoiding overload, and improving system efficiency.

[0025] Step 200: Construct a load forecasting model.

[0026] In step 200, accurate load forecasting can help power grid operators understand future power demand in advance, so as to reasonably arrange power generation plans, adjust power grid operation modes, and ensure the balance between power supply and demand. The past load records obtained from the terminal and master station software provide a time series data basis for the model, reflecting the law of load changes over time. In addition, the power load type and current working status identified in step 100 add additional dimensions to the model, making the prediction more detailed and accurate. By constructing a scientific and reasonable load forecasting model, the power system is provided with the ability to foresee future load changes, which is an important prerequisite for realizing intelligent scheduling, optimizing resource allocation, and improving system operation efficiency and reliability.

[0027] Step 300: Obtain historical load data stored in the terminal and the master station software.

[0028] In step 300, terminal data refers to the real-time or historical load data collected by various smart meters, sensors and data acquisition devices installed on the user side or at the edge of the power grid. These terminal devices measure electrical parameters such as current, voltage, and power to accumulate electricity consumption records of users or local areas.

[0029] The master station is the center of power system monitoring and data processing. Its software system is usually responsible for aggregating data from various terminals for centralized management and analysis. These data not only contain detailed load records, but may also include power grid operation status, fault alarm information, dispatch instructions, etc.

[0030] By analyzing past load change patterns, we can reveal the regularity of load changes over time, seasonal and periodic characteristics, and the impact of special events (such as holidays and extreme weather) on load.

[0031] Step 400: Generate a prediction result in a load prediction model based on historical load data, power load type and power load working status.

[0032] In step 400, the historical load data, as time series data, reflects the patterns and trends of past power consumption. By analyzing these data, the law of load fluctuation over time can be revealed, such as daily load curves, weekly load characteristics, and seasonal changes. There are various types of power loads, including industrial loads, commercial loads, and residential loads. Different types of loads have different power consumption characteristics and response patterns. For example, industrial loads may be greatly affected by production plans, while residential loads are closely related to living habits. Considering these types in the prediction model can improve the accuracy of the prediction. The working status of the load, such as operating efficiency, maintenance cycle, abnormal conditions, etc., will also affect the actual power consumption. Incorporating these status information into the model can help identify and quantify atypical load behaviors, making the prediction results closer to the actual situation. After integrating historical load data, load type information, and working status, a suitable prediction model is selected for training, and the trained model is used to predict the power load for a certain period of time in the future (hours, days, weeks, months, etc.). The prediction results usually include the predicted value and its confidence interval, providing data support for decision-making processes such as power dispatching, resource planning, and price setting.

[0033] Step 500: Dynamically adjust the operating status of the electrical equipment based on the prediction result.

[0034] In step 500, if the forecast shows that a high load will occur during a certain period, the system can automatically adjust the operating time of non-critical equipment to a low-load period (such as at night) to achieve load shifting and reduce the peak pressure on the power grid. Based on the forecast results, signals can also be sent to users participating in the demand response plan to encourage them to reduce electricity consumption or temporarily shut down some equipment during peak hours in exchange for economic compensation or other incentives. Step 500 is a key step in converting forecasts into actual actions. It achieves fine management of the operating status of power equipment and maximizes energy efficiency through a series of intelligent and automated means, promoting flexible scheduling of the power system and efficient allocation of resources.

[0035] According to the power load control method based on the multifunctional flexible adjustment unit provided in the first aspect of the present application, by real-time monitoring of the load status of the dedicated transformer user and accurately identifying the load type and working status, it is possible to ensure that the power equipment operates in the most suitable state, reduce ineffective energy consumption, and improve the energy efficiency of the entire power grid. The load forecasting model combines historical data, load type and status to accurately predict future load changes. The power grid operator can pre-adjust the power supply plan according to these forecast results, effectively avoid problems such as overload and voltage fluctuations, and enhance the stability and reliability of the power grid. Dynamically adjust the operating status of the power equipment, which can increase the load consumption during the peak period of renewable energy generation and adjust and reduce it during the valley period, which helps to balance the supply and demand of the power grid, promote the efficient use of renewable energy such as wind energy and solar energy, and the green transformation of the power grid. It promotes the deep integration of information technology and power systems, provides key technical support for the development of smart grids, enhances the automation and information level of power grids, and lays the foundation for realizing flexible interaction, efficient operation and sustainable development of power grids. In summary, the power load control method based on a multifunctional flexible regulation unit provided in this application can improve the refinement of load management, the accuracy of load forecasting, and realize dynamic optimization scheduling, effectively solving the technical problems of high regulation pressure, low efficiency and poor stability faced by the power system in the face of distributed energy development, load diversification and demand growth.

[0036] In some embodiments of the present application, current data and voltage data are collected, the load status of dedicated transformer users is monitored, and edge computing is used for load identification to distinguish the power load type and the power load working status, specifically: Filter and denoise the raw current and voltage data; Extracting load characteristic parameters from the processed current data and voltage data, wherein the load characteristic parameters include harmonic content parameters, current waveform parameters, and power factor parameters; Obtain load samples of known types, and establish mapping relationships between current characteristics and voltage characteristics and load types, and between current characteristics and voltage characteristics and working states of power loads; Clustering algorithms are used to identify patterns in load data, identify load groups, and analyze and confirm the type and working status of power loads.

[0037] First, the raw current and voltage data collected from the dedicated transformer users are filtered and denoised. This process is crucial because it can eliminate inaccurate data caused by factors such as noise in the measurement equipment and interference in the signal transmission process, ensuring the accuracy of subsequent analysis. Common filtering methods include low-pass filtering, high-pass filtering, band-pass filtering, etc., and denoising techniques may include wavelet transform, statistical methods, etc.

[0038] After preprocessing, characteristic parameters are extracted from the processed current and voltage data. These parameters are the key to identifying the type and state of the load. For example, the harmonic content parameter reflects the impact of nonlinear loads on the power grid; current waveform parameters (such as crest factor, zero-crossing characteristics) can reveal the nature of the load (such as motor starting, lighting equipment switching action, etc.); power factor parameters can reflect the energy utilization efficiency of the load.

[0039] By obtaining sample data of known load types, the relationship between current and voltage characteristics and load types and working conditions is studied. This means training models or establishing rules based on a large amount of classified load data so that when unknown data is input, it can be quickly matched to the corresponding load type or working condition based on its characteristic parameters. This involves supervised learning algorithms, such as support vector machines and decision trees, which are used to learn and establish mapping models.

[0040] Clustering algorithms are used to perform pattern recognition on the processed and feature-extracted data, and load data with similar characteristics are grouped together to form load groups. Cluster analysis helps to find natural groupings in the data, even without prior category information. Through in-depth analysis of these groups, the load type and working status represented by each group can be further confirmed, and the load can be finely identified.

[0041] In some embodiments of the present application, load characteristic parameters are extracted from the processed current data and voltage data, specifically: Use fast Fourier transform or wavelet transform to perform spectrum analysis on current data and voltage data, calculate the amplitude and phase of each harmonic, and generate total harmonic distortion and each harmonic content; Analyze the peak value, valley value, effective value and waveform distortion of the current waveform to determine the nature of the load.

[0042] Fast Fourier transform is a method for efficiently calculating the spectrum of discrete-time signals. By performing FFT on current and voltage signals, they can be decomposed into sinusoidal components of different frequencies, thereby obtaining the spectrum of the signal. In this way, the amplitude and phase angle of the fundamental wave (i.e., the power frequency 50Hz or 60Hz) and its harmonics can be calculated. Harmonic content is an important indicator for measuring power quality, reflecting the degree of nonlinear loads (such as inverters, rectifiers, etc.) in the system.

[0043] Wavelet transform provides local information of time and frequency, and is more suitable for analyzing current and voltage data containing transient characteristics and non-stationary signals. It can more accurately locate the time position of the occurrence of specific frequency components in the signal, and is very effective in capturing load mutations or short-term fluctuations.

[0044] The calculated amplitude of each harmonic can be used to calculate the total harmonic distortion (THD), which is the ratio of the square of the effective value of all harmonic components to the square of the effective value of the fundamental wave, usually expressed as a percentage. The higher the THD value, the worse the power quality, which may cause interference to other sensitive equipment.

[0045] Peak value, valley value, and effective value directly reflect the range and average level of current intensity. Peak value and valley value can be used to evaluate the instantaneous maximum and minimum demand of the load, while effective value (RMS) is a measure of the average power transmission capacity.

[0046] The degree of waveform distortion is usually measured by calculating the total harmonic distortion (THDi) of the current waveform or using other waveform quality indicators. A high distortion rate indicates that the current waveform deviates greatly from a sine wave, which may mean that there is a nonlinear load or circuit problem.

[0047] In summary, not only can the nature of the load be determined (such as whether it is a linear or nonlinear load, a power load or a lighting load, etc.), but its impact on grid stability and power quality can also be evaluated, providing a scientific basis for monitoring, fault diagnosis and optimal management of the power system.

[0048] In some embodiments of the present application, historical load data stored in the terminal and the master station software is obtained, specifically: Establish a communication connection between the terminal and the main station software; Control the main station software to construct query instructions and send them to the terminal; After receiving the command, the terminal retrieves the historical data area stored locally based on the command content, generates a message and responds to the main station software; The master station software receives the response, parses the message and extracts the required historical load data.

[0049] The communication connection between the terminal and the master software is usually established through power line carrier communication, wireless network (such as GPRS, 3G / 4G / 5G, LoRa, Wi-Fi) or wired network (such as Ethernet). The communication protocol may follow industry standards such as DLMS / COSEM (for meter communication) and IEC 61850 (substation automation) to ensure the compatibility and security of data transmission. The master software constructs a detailed query instruction according to the required data type (such as daily load curve, monthly maximum load, etc.) and time range. The instruction will contain the start time, end time, data type identification and other necessary control information of the query. This step ensures the clarity and pertinence of the request. The constructed query instruction is sent from the master software to the terminal device through the established communication link. This step requires both parties to follow the same communication protocol and data format standard to ensure that the instruction can be correctly identified and processed. After receiving the query command, the terminal searches the historical data area stored locally according to the command content. These data are usually stored in order in time series in advance to facilitate quick search. The retrieved data will be encapsulated into a message in a specific format (such as a data frame in accordance with the DLMS protocol) and then sent back to the master software through the original communication channel. After receiving the response message from the terminal, the master software parses it. The parsing process involves decoding the message header, verifying data integrity, extracting data fields, etc. Through this process, the master software can accurately extract the required historical load data from the message. After the parsing is completed, the master software will further process the extracted data, including data verification, statistical analysis, graphical display, or upload it to a higher-level management system for decision support, trend analysis, or load forecasting.

[0050] In some embodiments of the present application, based on historical load data, power load type and power load working status, a prediction result is generated in a load prediction model, specifically: The power load types are marked as industrial power load, commercial power load and residential power load, and the power load working status is marked as peak, flat peak and valley; Convert industrial power load, commercial power load and residential power load into numerical variables; Binary features are created based on the classification of the working status of the power load.

[0051] Industrial power load usually refers to the electricity consumption of heavy industry and light industry such as manufacturing and mining. This type of load is characterized by high power, relatively low stability, and is greatly affected by production cycles and economic activities.

[0052] Commercial power load involves electricity consumption in commercial activities such as offices, shopping malls, and hotels. It has the characteristics of higher load during the day and a significant drop at night, and is closely related to business hours and the intensity of commercial activities.

[0053] Residential electricity load refers to daily household electricity consumption, such as lighting and household appliances. It is characterized by obvious seasonal and diurnal variations, and is greatly affected by climate conditions and holidays.

[0054] Convert the above load type tags into a numerical form that the model can understand. For example, it can be simply coded as: Industrial power load = 1, commercial power load = 2, residential power load = 3. Or use One-Hot Encoding to convert each type into a vector, such as industry = [1,0,0], commercial = [0,1,0], residential = [0,0,1], which can better retain category information.

[0055] Peak, off-peak and off-peak are divided according to the electricity demand level at different times of the day or year. Peak hours generally refer to the hours with the highest electricity demand, off-peak hours are the hours between peak and off-peak, and off-peak hours are the hours with the lowest electricity demand.

[0056] Creating binary features means assigning a binary value to the working state at each moment. For example, peak = 1, flat peak = 0, trough = -1, or you can use one-hot encoding, peak = [1,0,0], flat peak = [0,1,0], trough = [0,0,1], this encoding method helps the model capture the differences in different states.

[0057] These preprocessing steps make the historical load data closely associated with the load type and working status, and express it in numerical form, which is convenient for use as input features in the load forecasting model. Forecasting models (such as time series analysis, neural networks, support vector machines, etc.) use these features to analyze historical trends and then predict future power load conditions, providing a scientific basis for the planning, scheduling and operation of the power system.

[0058] In some embodiments of the present application, the method further comprises: Control the master station software to send time calibration instructions to the terminal; The control terminal updates the internal clock according to the time data in the time calibration instruction.

[0059] The master station, usually the core of the power system supervisory control and data acquisition system (SCADA), is responsible for collecting data from each terminal and issuing control instructions. The master station software has built-in precise time service functions, which can obtain and maintain highly accurate time (usually synchronized with GPS time or other atomic clocks). When calibration is required, the master station software will generate a time calibration instruction containing the current accurate time data. This step ensures that the entire system has a unified and accurate time source. After receiving the time calibration instruction from the master station, the terminal equipment, such as remote terminal units (RTUs), smart meters, or any automation control equipment connected to the master station, will parse the time data in it. Then, the terminal will adjust its internal clock (real-time clock RTC) to the time specified by the time calibration instruction to achieve accurate time synchronization. Time synchronization is particularly important for power systems because it is directly related to the accuracy of event recording, the timeliness of fault analysis, and the coordination of system operations.

[0060] The advantages of this approach are: Improve system operation efficiency: All terminal devices have consistent time, reducing data misreading or operational errors caused by time deviation.

[0061] Enhanced data analysis accuracy: Event recording and data collection can be accurate to the same time base, facilitating data analysis and fault tracing.

[0062] Easy maintenance and management: Unified time management simplifies system maintenance, especially in cross-regional, large-scale distributed systems.

[0063] In some embodiments of the present application, the operating state of the electrical equipment is dynamically adjusted based on the prediction result, specifically: Based on the prediction results, the master station software is controlled to generate a load balancing strategy; The control master station monitors the operating status and load changes of electrical equipment and provides real-time data feedback.

[0064] First, the system conducts analysis based on the forecast results (such as the forecast of power demand in a certain period of time in the future, the forecast of renewable energy power generation, etc.). If the forecast results show that there may be a peak or trough of power at a certain point in the future, the master station software will automatically or after manual review generate the corresponding load balancing strategy. These strategies involve adjusting the power supply distribution in different areas, starting or shutting down the backup power supply, adjusting the working mode of the power-consuming equipment, etc., in order to achieve a balance between supply and demand and avoid overload or waste of resources. The master station continuously monitors the actual operating status of each power-consuming equipment in the power grid, including but not limited to parameters such as current, voltage, power factor and real-time load, which requires a highly integrated monitoring system and communication network to ensure real-time data collection and transmission. At the same time, the master station also needs to monitor the load change trend and identify abnormal situations, such as sudden load increase or decrease, which is crucial for rapid response and adjustment strategy. The collected real-time data is not only used for immediate monitoring and control, but also fed back to the prediction model and load balancing algorithm to form a closed-loop control system. This means that the actual operation data can be used to verify the accuracy of the prediction model and iteratively optimize the model accordingly. At the same time, these data can also be displayed to dispatchers in a timely manner to help them make more accurate decisions, such as whether resources need to be urgently deployed or strategies adjusted.

[0065] In some embodiments of the present application, the load balancing strategy includes load transfer and power generation forecasting scheduling.

[0066] Load shifting aims to reduce the pressure on high-load areas and make full use of the margin in low-load areas by adjusting the distribution of power demand in different areas or time periods within the power grid. Specific operations may include: Demand-side management: Encourage or force the reduction of non-critical load usage during certain periods (usually peak hours), such as by implementing a time-of-use electricity price policy to encourage users to use electricity during off-peak hours.

[0067] Smart grid technology: Utilize smart meters and automated control systems to automatically adjust the power consumption time or power of adjustable loads (such as energy storage equipment and some industrial loads) to achieve load redistribution in time and space.

[0068] Inter-regional electricity trading: transfer power loads between different power grids, use transmission lines to transmit surplus electricity to power-deficient areas, and balance power supply and demand between regions.

[0069] Power generation forecasting and dispatching is based on the accurate forecast of future output of various power generation resources (including traditional thermal power, hydropower, nuclear power and renewable energy power generation, etc.), to formulate reasonable power generation plans and dispatching schemes to meet the predicted power demand, while taking into account economic and environmental impacts. It mainly includes: Short-term and ultra-short-term forecasts: Using advanced data analysis and machine learning techniques, we conduct a comprehensive analysis of factors such as weather conditions, historical power generation data, maintenance plans, etc. in the next few hours to days to predict the power generation capacity of various power generation units.

[0070] Optimized dispatch: Based on the predicted load demand and power generation, the optimal output plan of each power plant is determined through complex optimization algorithms to ensure that costs, emissions and losses are minimized while ensuring power supply reliability.

[0071] Renewable energy integration: Pay special attention to the forecast of power generation from renewable energy sources with high volatility, such as wind and solar power, and smooth their impact on the power grid by coordinating operations with other power sources with good adjustability (such as hydropower and gas turbines) and deploying sufficient energy storage facilities.

[0072] like Figure 2 As shown, the second embodiment of the present application provides a power load control device based on a multifunctional flexible adjustment unit, comprising: The distinguishing module 110 is adapted to collect current data and voltage data, monitor the load status of the dedicated transformer user, and perform load identification using edge computing to distinguish the power load type and the power load working status; A model building module 120, adapted to build a load forecasting model; The data acquisition module 130 is adapted to acquire the historical load data stored in the terminal and the master station software; A prediction result generating module 140, adapted to generate prediction results in a load prediction model based on historical load data, power load type and power load working status; The adjustment module 150 is adapted to dynamically adjust the operating state of the electrical equipment based on the prediction result.

[0073] The power load control device based on the multifunctional flexible adjustment unit provided in the second aspect embodiment of the present application can implement the power load control method based on the multifunctional flexible adjustment unit in any embodiment of the first aspect mentioned above, and thus can achieve any technical effect in the power load control method based on the multifunctional flexible adjustment unit mentioned above, which will not be repeated here.

[0074] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the power load control method based on the multifunctional flexible adjustment unit in any embodiment of the first aspect is implemented.

[0075] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the power load control method based on the multifunctional flexible adjustment unit in any embodiment of the first aspect, the method comprising: Step 100: Collect current data and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify the load to distinguish the type of power load and the working status of the power load.

[0076] Step 200: Construct a load forecasting model.

[0077] Step 300: Obtain historical load data stored in the terminal and the master station software.

[0078] Step 400: Generate a prediction result in the load prediction model based on the historical load data, the power load type and the power load working status.

[0079] Step 500: Dynamically adjust the operating state of the electrical equipment based on the prediction result.

[0080] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0081] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the power load control method based on the multifunctional flexible adjustment unit provided by the above methods, the method includes: Step 100: Collect current data and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify the load to distinguish the type of power load and the working status of the power load.

[0082] Step 200: Construct a load forecasting model.

[0083] Step 300: Obtain historical load data stored in the terminal and the master station software.

[0084] Step 400: Generate a prediction result in the load prediction model based on the historical load data, the power load type and the power load working status.

[0085] Step 500: Dynamically adjust the operating state of the electrical equipment based on the prediction result.

[0086] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for controlling a power load based on a multifunctional flexible adjustment unit provided by the above methods is implemented, and the method comprises: Step 100: Collect current data and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify the load to distinguish the type of power load and the working status of the power load.

[0087] Step 200: Construct a load forecasting model.

[0088] Step 300: Obtain historical load data stored in the terminal and the master station software.

[0089] Step 400: Generate a prediction result in the load prediction model based on the historical load data, the power load type and the power load working status.

[0090] Step 500: Dynamically adjust the operating state of the electrical equipment based on the prediction result. The parts not described in this application can be implemented by adopting or drawing on existing technologies.

[0091] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0092] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for controlling electric load based on a multifunctional flexible regulating unit, characterized in that: include: Collect current and voltage data, monitor the load status of dedicated transformer users, and use edge computing to identify loads to distinguish the type of power loads and the working status of power loads; Build load forecasting models; Obtain historical load data stored in the terminal and master station software; Based on the historical load data, the power load type and the power load working state, generating a prediction result in the load prediction model; The operating status of the electrical equipment is dynamically adjusted based on the prediction result.

2. The power load control method based on the multifunctional flexible adjustment unit according to claim 1 is characterized in that: The current data and voltage data are collected, the load status of the dedicated transformer user is monitored, and the load is identified by edge computing to distinguish the power load type and the power load working status, specifically: Filter and denoise the raw current and voltage data; Extracting load characteristic parameters from the processed current data and voltage data, wherein the load characteristic parameters include harmonic content parameters, current waveform parameters, and power factor parameters; Obtain load samples of known types, and establish mapping relationships between current characteristics and voltage characteristics and load types, and between current characteristics and voltage characteristics and working states of power loads; Clustering algorithms are used to identify patterns in load data, identify load groups, and analyze and confirm the type and working status of power loads.

3. The power load control method based on the multifunctional flexible adjustment unit according to claim 2 is characterized in that: The load characteristic parameters are extracted from the processed current data and voltage data, specifically: Use fast Fourier transform or wavelet transform to perform spectrum analysis on current data and voltage data, calculate the amplitude and phase of each harmonic, and generate total harmonic distortion and each harmonic content; Analyze the peak value, valley value, effective value and waveform distortion of the current waveform to determine the nature of the load.

4. The power load control method based on the multifunctional flexible adjustment unit according to claim 1 is characterized in that: The acquisition of historical load data stored in the terminal and the master station software is specifically as follows: Establishing a communication connection between the terminal and the master station software; Control the main station software to construct a query instruction and send it to the terminal; After receiving the instruction, the terminal retrieves the historical data area stored locally based on the instruction content, generates a message and responds to the main station software; The master station software receives the response, parses the message and extracts the required historical load data.

5. The power load control method based on the multifunctional flexible adjustment unit according to claim 1 is characterized in that: The generating of prediction results in the load prediction model based on the historical load data, the power load type and the power load working state is specifically: Marking the power load types as industrial power load, commercial power load and residential power load, and marking the power load working states as peak, flat and valley; Converting the industrial power load, the commercial power load and the residential power load into numerical variables; A binary feature is created based on the classification of the power load operating state.

6. The power load control method based on the multifunctional flexible adjustment unit according to any one of claims 1 to 5, characterized in that: The method also includes: Control the master station software to send a time calibration instruction to the terminal; The terminal is controlled to update an internal clock according to the time data in the time calibration instruction.

7. The power load control method based on the multifunctional flexible adjustment unit according to any one of claims 1 to 5, characterized in that: The dynamically adjusting the operating state of the electrical equipment based on the prediction result is specifically: Based on the prediction result, controlling the master station software to generate a load balancing strategy; The master station is controlled to monitor the operating status and load changes of the electrical equipment and to feed back data in real time.

8. The electric load control method based on the multifunctional flexible adjustment unit according to claim 7 is characterized in that: The load balancing strategy includes load transfer and power generation forecasting and scheduling.

9. An electric load control device based on a multifunctional flexible adjustment unit, characterized in that: include: The differentiation module is suitable for collecting current data and voltage data, monitoring the load status of dedicated transformer users, and using edge computing for load identification to distinguish the type of power load and the working status of the power load; Model building module, suitable for building load forecasting models; A data acquisition module, suitable for acquiring historical load data stored in the terminal and the master station software; A prediction result generating module, adapted to generate a prediction result in the load prediction model based on the historical load data, the power load type and the power load working state; The adjustment module is adapted to dynamically adjust the operating state of the electrical equipment based on the prediction result.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the power load control method based on the multifunctional flexible adjustment unit as described in any one of claims 1 to 8 is implemented.

Images