Distribution transformer voltage gear shifting method, system and equipment based on seasonal regional characteristics and medium

Abstract

The invention belongs to the technical field of transformer distribution transformer voltage gear shifting, and discloses a distribution transformer voltage gear shifting method, system and device based on seasonal regional characteristics and a medium so as to meet the requirements of a modern power grid for high precision, real-time performance and reliability of voltage regulation. The method comprises the following steps: based on obtained distribution transformer voltage historical data and real-time meteorological data, analyzing typical power consumption characteristics of each season and constructing a seasonal characteristic vector; based on the acquired geographic information system data and load distribution data, dividing the power distribution network into a plurality of regions and analyzing typical power consumption characteristics to construct region characteristic vectors; constructing a distribution transformer operation feature vector based on the obtained distribution transformer equipment operation data and equipment environment data; and based on the seasonal feature vector, the regional feature vector and the distribution transformer operation feature vector, calculating a voltage adjustment value and setting a corresponding gear shifting instruction to perform distribution transformer voltage gear shifting. According to the invention, the prediction of the voltage change trend is more accurate, and the accuracy and pertinence of voltage regulation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of transformer distribution voltage regulation, and specifically relates to a distribution transformer voltage regulation method, system, device and medium based on seasonal and regional characteristics. Background Art

[0002] With the rapid development of the power system, the stability and regulation accuracy of distribution transformer voltage have an increasingly significant impact on the grid operation efficiency and power quality. The existing distribution transformer voltage regulation technologies mainly include regulation technologies based on data monitoring and analysis, regulation technologies based on model prediction, regulation technologies based on intelligent algorithms, remote control regulation technologies, and regulation technologies based on online monitoring and verification. Although these technologies can achieve the regulation of distribution transformer voltage to a certain extent, there are still many defects.

[0003] The regulation technology based on data monitoring and analysis relies on real-time data collected by sensors and monitoring devices. However, due to problems such as insufficient sensor accuracy and data transmission interference, it is difficult to ensure the accuracy of the data, which in turn affects the accuracy of the regulation decision. In addition, the processing capacity of the data processing system is limited. Especially during peak power consumption periods, the data volume increases sharply, and the system may not be able to process the data in time, resulting in a delay in the regulation decision.

[0004] The regulation technology based on model prediction predicts the future power consumption load and voltage change trend through a load prediction model and a voltage stability model. However, the accuracy of the load prediction model is greatly affected by factors such as meteorological conditions and user behavior, and it is difficult to accurately predict sudden load changes. When considering the complex topology structure and equipment characteristics of the power grid, the voltage stability model may ignore some key factors, resulting in a deviation between the model analysis results and the actual power grid operation situation.

[0005] Although the regulation technology based on intelligent algorithms (such as genetic algorithms and neural network algorithms) has strong optimization capabilities, in practical applications, there are problems such as slow convergence speed and easy to fall into local optimal solutions. Moreover, the adaptability and interpretability of the algorithms are poor, and it is difficult to cope with the dynamic changes of the power grid operation environment.

[0006] The remote control regulation technology depends on the stability of the communication network. However, in remote areas or places with poor communication infrastructure, the communication signal may be weak or unstable, resulting in a delay or loss of the regulation instruction transmission. In addition, the long-term operation of the automatic regulation device may malfunction, affecting the normal progress of the regulation. Even, it may cause misregulation or malicious regulation due to control logic loopholes or network attacks, threatening the safety of the power grid.

[0007] Although the tap-changing technology based on online monitoring and calibration can monitor the distribution transformer voltage and tap position in real time, the accuracy and real-time performance of the monitoring equipment may not meet the requirements of rapid voltage changes. Offline calibration requires power outage operations, which affect the normal power consumption of users. Online calibration may lead to inaccurate calibration results due to the influence of the power grid operating environment and measurement errors.

[0008] In summary, the existing distribution transformer voltage tap-changing technologies have obvious defects in terms of data accuracy, model prediction accuracy, algorithm adaptability, communication reliability, and monitoring and calibration accuracy, and it is difficult to meet the requirements of high precision, real-time performance, and reliability of voltage regulation in modern power grids. Summary of the Invention

[0009] Based on the above-mentioned disadvantages and deficiencies in the prior art, one of the objectives of the present invention is to at least solve one or more of the above problems existing in the prior art. In other words, one of the objectives of the present invention is to provide a distribution transformer voltage tap-changing method, system, device, and medium based on seasonal regional characteristics that meet one or more of the foregoing requirements, so as to achieve the purpose of improving the accuracy, real-time performance, and reliability of distribution transformer voltage tap-changing.

[0010] To achieve the above-mentioned invention objective, the present invention adopts the following technical solutions:

[0011] In the first aspect, the present invention provides a distribution transformer voltage tap-changing method based on seasonal regional characteristics, including the steps of: S1. Obtain the historical data of the distribution transformer voltage and the real-time meteorological data, and analyze the typical electricity consumption characteristics of each season based on this to construct a seasonal feature vector S2. Obtain the geographic information system data and the load distribution data, and divide the distribution network into multiple regions based on this, and then analyze the typical electricity consumption characteristics of each region to construct a regional feature vector S3. Obtain the operation data of the distribution transformer equipment and the equipment environment data to construct a distribution transformer operation feature vector S4. Based on the seasonal feature vector the regional feature vector and the distribution transformer operation feature vector calculate the voltage adjustment value y and set the corresponding tap-changing instruction y(t) to perform the distribution transformer voltage tap-changing.

[0012] As a preferred solution, the seasonal feature vector where j represents the season number, and n represents the total number of feature parameters in the seasonal feature vector; the feature parameters in the seasonal feature vector include the average temperature, the duration of high temperature, and the daily load peak.

[0013] As a preferred solution, the regional feature vector i represents the region type serial number, m represents the total number of characteristic parameters in the region characteristic vector; the regions include urban areas, rural areas, coastal areas, and mountainous areas; the characteristic parameters in the region characteristic vector include terrain height h, terrain slope α, and vegetation coverage β.

[0014] As a preferred solution, the distribution transformer operation characteristic vector k represents the total number of characteristic parameters in the distribution transformer operation characteristic vector; the characteristic parameters in the distribution transformer operation characteristic vector include the three-phase voltage amplitude U, the phase difference θ between the three-phase voltages, the three-phase current I, and the total harmonic distortion rate THD of the current 1 , active power P, reactive power Q, apparent power S, power factor Transformer winding temperature T winding , Transformer oil level L oil , vibration amplitude A vibration .

[0015] As a preferred solution, the calculation of the voltage adjustment value y includes the steps of: obtaining a preset neural network, and inputting the seasonal characteristic vector into the neural network. The regional feature vector and the distribution transformer operation characteristic vector Adjust the predicted value with output voltage Obtain a preset error function E and adjust the voltage prediction value based on it Correction is performed to obtain the actual voltage adjustment value y i ; The error function

[0016] As a preferred solution, the shift instruction y(t)=x(t)*h(t)+n(t), h(t) represents the transmitted signal, n(t) represents the channel impulse response, and x(t) represents additive noise.

[0017] As a preferred solution, after step S4, the following step is further included: obtaining the expected voltage value U e and the feedback voltage value U after the gear adjustment based on the gear adjustment instruction y(t) f Based on the expected voltage value U e and the feedback voltage value U f Calculate the gear adjustment effect evaluation index value Q. If the gear adjustment effect evaluation index value Q is greater than a preset threshold, optimize the voltage adjustment value y, and re-allocate the gear adjustment based on the optimized voltage adjustment value y to achieve the expected gear adjustment effect.

[0018] In a second aspect, the present invention provides a distribution transformer voltage gear adjustment system based on seasonal regional characteristics, which is used to implement the distribution transformer voltage gear adjustment method as described in the first aspect.

[0019] In a third aspect, the present invention provides an electronic device, wherein the computer device includes a memory, a processor, and a computer program, and when the computer program is executed by the processor, the distribution transformer voltage adjustment method as described in the first aspect is implemented.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the distribution transformer voltage adjustment method as described in the first aspect is implemented.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. The present invention constructs seasonal characteristic vectors by deeply analyzing typical electricity consumption characteristics in different seasons, and constructs regional characteristic vectors by combining geographic information system data and load distribution data, fully considering the complex impact of seasonal and regional changes on distribution transformer voltage. This innovative method makes the prediction of voltage change trends more accurate, and can then formulate a gear adjustment strategy that is highly matched with seasonal and regional characteristics, significantly improving the accuracy and pertinence of voltage regulation.

[0023] 2. The present invention introduces a real-time data collection and dynamic gear adjustment decision-making mechanism, which can instantly capture key information such as seasonal changes, sudden weather changes, and instantaneous changes in load. This mechanism ensures the rapid execution of gear adjustment operations and effectively responds to various voltage fluctuations, thereby greatly reducing the adverse effects of voltage fluctuations on user power consumption experience and stable operation of the power grid.

[0024] 3. By integrating the remote control and feedback module, the present invention not only realizes the remote and precise control of the distribution transformer gear adjustment, but also establishes a closed loop of strategy optimization based on actual feedback data. This closed loop system can continuously collect the effect data after gear adjustment, and continuously iterate and optimize the gear adjustment strategy based on it, so as to ensure the stability of power grid operation and the continuous improvement of power quality.

[0025] Further or more detailed beneficial effects will be described in detail in conjunction with specific examples in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 It is a flow chart of the voltage adjustment method of the distribution transformer described in an embodiment of the present invention.

[0028] Figure 2 is a structural diagram of the electronic device provided in an embodiment of the present invention.

[0029] Reference numerals:

[0030] 200. Electronic equipment;

[0031] 201, processor; 202, communication bus; 203, user interface; 204, network interface; 205, memory. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0033] In the following description, multiple embodiments of the present invention are provided, and different embodiments may be replaced or combined, so the present invention may also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present invention should also be considered to include embodiments containing one or more of A, B, C, and D, all other possible combinations, even though the embodiment may not be clearly described in the following text.

[0034] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present invention. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the described order, and various steps may be added, omitted or combined. In addition, the features described in some examples may be combined in other examples.

[0035] In order to facilitate a better understanding of the embodiments of the present invention, before explaining the specific implementation modes of the present invention in detail, its application scenarios are first described.

[0036] The distribution transformer voltage adjustment method described in the embodiments of this specification is applied in a variety of actual power management and distribution processes, including but not limited to power management systems of urban power grids, rural power grids, industrial park power grids, and specific large-scale power-consuming facilities (such as data centers, hospitals, etc.). In these scenarios, the application of the distribution transformer voltage adjustment method aims to improve the stability and efficiency of power grid operation through intelligent voltage management and regulation, achieve dual improvements in energy conservation and emission reduction and economic benefits, and at the same time improve users' power consumption experience and satisfaction.

[0037] Embodiment 1:

[0038] like Figure 1As shown, this embodiment provides a distribution transformer voltage adjustment method based on seasonal regional characteristics, which realizes the intelligence and precision of voltage regulation through a series of fine steps. First, this embodiment performs comprehensive data collection and preprocessing to ensure the accuracy and reliability of the data. Subsequently, based on these processed data, this implementation deeply analyzes seasonal characteristics and regional characteristics to accurately capture the complex relationship between them and voltage changes. In order to further improve the accuracy and adaptability of voltage regulation, this implementation combines the analysis results of seasonal and regional characteristics to establish a distribution transformer voltage simulation adjustment model based on advanced artificial intelligence algorithms (such as neural networks, support vector machines, etc.). This model can comprehensively consider multiple factors, including seasonal changes, regional power consumption characteristics, and the operating status of distribution transformer equipment, so as to formulate the optimal adjustment strategy. In the execution stage of the adjustment instruction, this implementation uses wireless communication networks (such as 5G, GPRS, etc.) to quickly send accurate adjustment instructions to the automatic adjustment device of the distribution transformer, realizing the immediacy and efficiency of remote control. This step ensures the rapid response and accurate execution of the adjustment operation, effectively reducing the impact of voltage fluctuations on the power grid and users. After the gear adjustment is completed, the high-precision sensors on the distribution transformer continue to collect key data such as voltage and current, and feed back these adjusted operating data to the control center in real time. The control center conducts a comprehensive evaluation of the gear adjustment effect based on these feedback data to ensure that the voltage regulation has achieved the expected goal. If the evaluation results show that the gear adjustment effect does not meet expectations, the control center will immediately re-analyze and adjust to ensure the continuous optimization and accuracy of voltage regulation. In summary, the distribution transformer voltage gear adjustment method provided in this embodiment realizes the precision, intelligence and efficiency of voltage regulation through intelligent data collection, analysis, simulated gear adjustment and feedback evaluation, which provides a strong guarantee for the stable operation of the power grid and the user's high-quality electricity experience. The specific steps are as follows:

[0039] The first step is data collection and preprocessing:

[0040] Install multiple types of sensors on the distribution transformer, which may include at least high-precision voltage sensors, current sensors, temperature sensors, humidity sensors and meteorological data acquisition devices (share data with local meteorological departments to obtain more extensive meteorological information). These sensors are conducive to real-time collection of distribution transformer-related data, which may include at least voltage value U, current value I, transformer temperature T, ambient humidity H, local temperature t, wind speed v, and precipitation p.

[0041] The collected data is preprocessed, which may include at least filtering, denoising and standardization of the data. Digital filtering technology is used to remove high-frequency noise and outliers in the data, and the data of different magnitudes are unified into a standard range through normalization method for subsequent analysis and processing. Let the original data be x, and the normalized data x nThe calculation formula is where x min and x max are the minimum and maximum values ​​of data x respectively. In addition, for noise removal, the prediction equation in the Kalman filter algorithm is in is the prior state estimate at time k, A is the state transfer matrix, is the posterior state estimate at time k-1, B is the control input matrix, u k-1 is the control input at time k-1. This embodiment improves the prediction equation in the Kalman filter algorithm to obtain a new equation: in is the posterior state estimate at time k, K k is the Kalman gain, z k is the measurement value at the moment, and H is the measurement matrix.

[0042] The second step is seasonal and regional characteristics analysis:

[0043] In terms of seasonal characteristic analysis, the typical electricity consumption characteristics of each season are analyzed based on historical data and real-time meteorological data. For each season, a seasonal characteristic vector is constructed. Wherein, j represents the season number, and n represents the total number of characteristic parameters in the seasonal characteristic vector. j1 It can be the average temperature, s j2 It can be the duration of high temperature, s j3 It can be the peak load of a typical day in summer, etc. Through statistical analysis of many years of summer data, it is assumed that there is a certain functional relationship between the average temperature t and the voltage fluctuation ΔU ΔU = f 1 (t), f can be determined by polynomial fitting method 1 , assuming f 1 (t) = a 0 +a 1 t+a 2 t 2 +…+a m t m , where a i is the fitting coefficient, and min∑ is solved by the least squares method k (ΔU k -f 1 (t k )) 2 Get a i The value of .

[0044] In terms of regional characteristics analysis, the distribution network is divided into different regions based on geographic information system (GIS) data and load distribution data. The regions can be divided into at least urban areas, rural areas, coastal areas, and mountainous areas. Analyze the impact of the load density ρ and geographical environment characteristics on the distribution transformer voltage in each region. Assume that the geographical environment impact factor G is a function of factors such as terrain height h, slope α, and vegetation coverage β, that is, G = g(h, α, β, ...). Determine the expression of g through geographic information analysis and field measurements. For mountainous areas, the terrain height h has an impact on the line resistance R. According to the physical formula where ρ 0 is the material resistivity, α is the height coefficient, l is the line length, S is the conductor cross-sectional area, which in turn affects the voltage U. There is a relationship between the voltage U and the load density ρ and the geographical environment influencing factor G. U=f(ρ,G). The specific form of the function f is determined by multiple regression analysis and other methods. Let f(ρ,G)=b 0 +b 1 ρ+b 2 G+b 3 ρG+…, using a large amount of regional data to determine the coefficient b by the least squares method i .

[0045] The third step is voltage simulation gear adjustment decision:

[0046] Combined with the results of seasonal and regional characteristic analysis, a distribution transformer voltage simulation gear adjustment model based on artificial intelligence algorithms such as neural networks and support vector machines is established. The input parameters of the distribution transformer voltage simulation gear adjustment model include seasonal information, regional information, real-time distribution transformer operating parameters and environmental data, and the output is the optimal gear adjustment value of the distribution transformer.

[0047] Based on real-time data and the gear-shifting model, the optimal gear position of the distribution transformer is calculated dynamically in real time, and the gear-shifting strategy is adjusted in time in situations such as seasonal changes, sudden weather changes, or large changes in load.

[0048] In addition, the seasonal feature vector and the regional feature vector Based on this, this embodiment also constructs the distribution transformer operation characteristic vector k represents the total number of characteristic parameters in the distribution transformer operation characteristic vector. More specifically, in this embodiment, the number of characteristic parameters in the distribution transformer operation characteristic vector is preferably 17. Since the stability of the distribution transformer output voltage is directly related to the power quality at the user end, the three-phase voltage amplitude U A , U B , U C is the key indicator, so x 1 =U A , x 2 =U B , x3 =U C As a vector The first three elements of can accurately describe the voltage amplitude information. In addition to the amplitude, the phase information of the voltage is also crucial. The phase difference between the three-phase voltages should usually be 120°, otherwise the phase abnormality will affect the normal operation of the motor and other equipment. In this embodiment, the phase difference θ AB ,θ BC ,θ CA Incorporate the vector, that is, x 4 =θ AB , x 5 =θ BC 、x 6 =θ CA . Three-phase current I A ,I B ,I C It reflects the load size carried by the distribution transformer. When the current of a phase is too large, it may mean that the user load connected to the phase is too heavy or there is a potential fault such as a short circuit. Therefore, in this embodiment, x 7 =I A 、x 8 =I B 、x 9 =I C , which directly shows the current amplitude. The harmonic content of the current is also an important consideration. With the widespread application of power electronic equipment at the user end, current harmonics will increase line losses and affect the normal operation of distribution transformers. 10 Set to the total harmonic distortion rate THD of the current 1 , used to measure the severity of harmonic components in current. Active power P, reactive power Q, apparent power S and power factor are used as As vector element x 11 -x 14 . Transformer winding temperature T winding It is a key indicator to measure the safety of transformer operation. Excessive winding temperature will accelerate the aging of insulation materials and shorten the life of the transformer. 15 =T winding , to monitor the winding temperature changes in real time. Transformer oil level L oil It is also an important equipment status parameter. If the oil level is too low, it may cause poor heat dissipation of the transformer. If the oil level is too high, it may cause dangers such as oil spraying when the oil temperature rises. Therefore, in this embodiment, x 16 =L oil To ensure that the transformer oil level is within the normal range. The vibration signal of the transformer can also reflect the health of its internal structure. An abnormal increase in the vibration amplitude may mean that there are problems such as looseness inside the transformer. In this embodiment, the vibration amplitude A vibration As vector element x 17,The vibration signal of the transformer can be obtained by installing a vibration sensor.

[0049] The relationship between the gear adjustment value y of the distribution transformer and these factors is expressed by the function Indicates that the parameters of function g are determined by using a large amount of historical data and experimental data and optimization algorithms such as the least squares method. When using a neural network, assume that the number of input layer nodes of the neural network is n+m+k, the number of output layer nodes is 1, the number of hidden layer nodes is l, and the activation function of the neuron is σ(x) (the commonly used Sigmoid function Or ReLU function σ(x)=max(0,x)). The output of the neural network It can be expressed as where w i 、v ij is the weight, b i , c is the bias. The weight of the neural network is adjusted by the back propagation algorithm to minimize the sum of square errors between the predicted gear adjustment value and the actual optimal value. The error function where y i is the actual gear adjustment value, is the predicted gear adjustment value. During the training process, the weights are updated according to the gradient descent method. For the weight ω, this embodiment is optimized based on the existing formula. The optimized formula is where η is the learning rate.

[0050] Step 4: Remote control and feedback:

[0051] The gear adjustment instruction is sent to the automatic gear adjustment device of the distribution transformer through a wireless communication network (such as 5G, GPRS, etc.) to realize remote control gear adjustment. The automatic gear adjustment device accurately adjusts the gear of the distribution transformer according to the instruction. Assume that the transmission model of the communication signal is y(t)=x(t)*h(t)+n(t), where y(t) is the received signal, x(t) is the transmitted signal, h(t) is the channel impulse response, and n(t) is the additive noise. The reliability of communication is ensured by adopting appropriate modulation and demodulation technology and channel coding schemes, such as using orthogonal frequency division multiplexing (OFDM) technology to divide the high-speed data signal into multiple low-speed sub-signals for parallel transmission on different sub-carriers, thereby improving spectrum utilization and anti-multipath fading capabilities.

[0052] After the gear adjustment is completed, the sensors on the distribution transformer continue to collect data such as voltage and current, and feed back the adjusted operating data to the control center. The control center evaluates the gear adjustment effect based on the feedback data. If the expected effect is not achieved, it will re-analyze and adjust. Assume that the feedback voltage value is U f , the expected voltage value is U e , define the evaluation index of the gear adjustment effect N is the total number of evaluation data, represents the feedback voltage value of the ith data point, represents the expected voltage value of the ith data point. When Q is greater than a certain threshold, the gear adjustment strategy needs to be optimized. At the same time, the confidence interval concept in probability theory is used to evaluate the reliability of the feedback data. Assuming that the voltage value U f Subordinate to the normal distribution N(μ,σ 2 ), then the confidence interval at the confidence level 1-α is where z α / 2 is the quantile of the standard normal distribution, and n is the number of samples. If the feedback data exceeds the confidence interval, it is necessary to further check the accuracy of the data and whether there are problems in the adjustment process.

[0053] Embodiment 2:

[0054] This embodiment provides a distribution transformer voltage adjustment system based on seasonal regional characteristics, which is used to implement the distribution transformer voltage adjustment method as described in the first embodiment.

[0055] Embodiment three:

[0056] like Figure 2 As shown, this embodiment provides an electronic device, which may include: at least one processor, at least one network interface, a user interface, a memory, and at least one communication bus.

[0057] The communication bus can be used to realize the connection and communication among the above-mentioned components.

[0058] The user interface may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0059] The network interface may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0060] Among them, the processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a chip.

[0061] Among them, the memory may include RAM or ROM. Optionally, the memory includes a non-transitory computer-readable medium. The memory can be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory may also be optionally at least one storage device located away from the aforementioned processor. The memory as a computer storage medium may include an operating system, a network communication module, a user interface module and a gear adjustment application. The processor may be used to call the gear adjustment application stored in the memory and execute the steps of the distribution transformer voltage gear adjustment method mentioned in the above-mentioned embodiment.

[0062] Embodiment 4:

[0063] This embodiment provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a computer or a processor, the computer or the processor executes the above-mentioned Figure 1 One or more steps in the illustrated embodiment. If the components of the electronic device described above are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0064] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0065] A person of ordinary skill in the art can understand that all or part of the processes in the method of the first embodiment can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0066] Embodiment five:

[0067] In order to verify the effectiveness of the distribution transformer voltage adjustment method and system based on seasonal regional characteristics described in this specification, this embodiment performs distribution transformer voltage adjustment based on the actual application scenario of the distribution transformer voltage adjustment method based on seasonal regional characteristics. The specific process is as follows:

[0068] 1. Initial setup and data collection start

[0069] Deploy the distribution transformer voltage adjustment system based on seasonal regional characteristics described in this manual in the distribution network, and complete the installation and commissioning of the sensors. The installation location of the sensors needs to be optimized according to the structure and operating characteristics of the distribution transformer to ensure the accuracy and representativeness of the collected data. The voltage sensors are installed on different phase lines on the output side of the distribution transformer. According to Kirchhoff's voltage law, the three-phase voltage should meet ∪i represents the three-phase voltage value, which is used to calibrate the installation position and measurement accuracy of the voltage sensor. The temperature sensor is installed in the key heating parts such as the transformer core, winding and heat sink. According to the law of heat conduction

[0070] Where Q is the heat flow, k is the thermal conductivity, and A is the heat transfer area. The temperature gradient is ensured to accurately reflect the temperature distribution inside the transformer. At the same time, a data sharing channel with the meteorological department is established to ensure timely acquisition of comprehensive and accurate meteorological data, and to complete the connection and configuration of wireless communication networks such as 5G and GPRS.

[0071] Start the data acquisition system and start collecting the operating parameters and environmental data of the distribution transformer in real time. The acquisition frequency should be set reasonably to ensure the timeliness of the data and avoid the storage and processing burden caused by excessive data volume. For key parameters such as voltage and current, the acquisition frequency can be set to once per second, and the acquisition values ​​can be expressed as U(t) and I(t), where t is time and Ohm's law U(t)=I(t)R(t) is satisfied. R(t) is the resistance value that changes with time. The influence of factors such as temperature is considered in the distribution transformer. For parameters that change relatively slowly, such as temperature and humidity, the acquisition frequency can be set to once per minute. At the same time, meteorological data is synchronously acquired according to the update frequency of the meteorological department. Parameters such as temperature t, wind speed v, and precipitation p in the meteorological data can serve as an important basis for subsequent analysis.

[0072] 2. Analysis of seasonal regional characteristics

[0073] (1) Implementation in spring

[0074] In the suburbs of the city, the impact of irrigation equipment power consumption on the distribution transformer voltage during the spring plowing period is analyzed. By analyzing the historical spring data and real-time collected data, the voltage fluctuation pattern during the irrigation equipment startup period is determined. Assuming the number of irrigation equipment startups is n, the power of a single device is P, and the distribution transformer capacity is S, a relationship model between the voltage fluctuation ΔU and n, P, and S is established. c 1 、c 2 is the coefficient obtained based on data analysis. At the same time, considering the impact of spring rain on line insulation, according to the relationship between humidity sensor data and line insulation resistance, the insulation resistance R ins There is a functional relationship with humidity H d1 d 2 As a constant, analyze the voltage change caused by leakage. Combined with these factors, determine the voltage fluctuation range and typical change trend in the suburbs of the city in spring.

[0075] In rural areas, in addition to the impact of irrigation equipment, the use of other electrical equipment such as spring sowing needs to be considered. By counting the usage time and power of different types of electrical equipment, their comprehensive impact on the distribution transformer voltage is analyzed. For example, for equipment such as seed drills, the voltage changes are analyzed based on their start-up times and operating time, combined with the load characteristics of the distribution transformer, to further improve the voltage characteristic model in rural areas in spring.

[0076] (2) Implementation in summer

[0077] For the central commercial area of ​​the city, the focus is on the impact of air conditioning load on voltage during high temperature periods. Collect temperature sensor data and operating parameters of each air conditioning system in the commercial area, such as power, number of units in operation, etc., and establish a relationship between temperature and air conditioning load L ac The relationship model between e 1 、e 2 is the fitting coefficient. According to the relationship between the voltage and load of the distribution transformer, U=∪0-f 2 (L ac ), ∪0 is the no-load voltage, f 2 The voltage variation model of the commercial area in different temperature ranges in summer is determined based on the function determined by the experimental and historical data. At the same time, considering the impact of the flow of people in the commercial area on the power load, the voltage variation model is further optimized by analyzing the correlation between the flow monitoring data and the power load in the commercial area.

[0078] In coastal areas, the possible damage to the line and the impact on voltage during the typhoon season are considered. The intensity and path of the typhoon are obtained through meteorological data, and the probability of line damage under the influence of the typhoon is analyzed in combination with the Geographic Information System (GIS). Assume that the typhoon intensity is I and the line damage probability P is d There is a functional relationship P with I d =g 1 (I) can be obtained by statistical analysis of historical typhoon disaster data. 1 When the line is damaged, the impact on the voltage is analyzed according to the line fault type, such as line break, short circuit, etc., and the corresponding risk assessment model is established. For example, for a line break fault, the abnormal voltage variation range is calculated based on the topological structure of the line and the connection method of the distribution transformer.

[0079] (3) Implementation in autumn

[0080] In rural areas, analyze the impact of autumn harvest electrical equipment such as harvesters and threshers on voltage. Statistically count the usage quantity, power, and usage time of autumn harvest equipment, and establish a relationship model with the change in distribution transformer voltage. Let the number of harvesters be m, the power be P h , the usage time be t h , and the change in distribution transformer voltage be ΔU fall There is a relationship ΔU fall = h 1 mP h t h + h 2 , where h 1 , h 2 are coefficients obtained from data analysis. At the same time, consider the potential threat of dry autumn weather to the line, such as the impact of fire risk on line insulation and voltage. According to the relationship between humidity data and the dryness degree of vegetation, let there be a functional relationship between the vegetation dryness index D and humidity H as D = k 1 - k 2 H, where k 1 , k 2 are constants. Combining with the fire risk model, let the probability of fire occurrence P fire have a functional relationship with D l 1 , l 2 are coefficients, and analyze the indirect impact of fire hazards on line voltage.

[0081] For areas such as mountainous regions that are vulnerable to natural disasters, consider the impact of geological disasters such as landslides that may occur in autumn on the distribution transformer lines. Through the Geographic Information System (GIS), monitor the stability indicators of the mountain such as the slope change rate and the change in groundwater level. Let the mountain stability indicator be S m , and the probability of line damage have a functional relationship with S m where m 1 , m 2 are constants. When the line is damaged due to a landslide, analyze the impact on voltage, such as calculating the abnormal change range of voltage and the chain reaction on the surrounding distribution transformer voltage according to the degree and location of line damage.

[0082] (4) Implementation in winter

[0083] In cold northern regions, study the characteristics of the electricity load of heating equipment. Statistically count the installation quantity, power, and usage time of different types of heating equipment such as electric heaters and wall-mounted boilers, and establish a heating load model. Let the number of electric heaters be n e , the power be P e , the usage time be t e , the number of wall-mounted boilers be n b , the power be P b, the usage time is t b , the total heating load L hrat = n e P e t e + n b P b t b + …. Analyze the influence of low temperature on line resistance and transformer performance. According to the relationship between temperature sensor data and line resistance as described above In winter, considering the influence of temperature, assume is the resistivity at the reference temperature t 0 , γ is the temperature coefficient. Combining the relationship between the voltage, resistance, and load of the distribution transformer, determine the increase in line resistance and voltage drop caused by low temperature in the northern region

[0084] In the southern humid and cold regions, in addition to the influence of heating equipment, the influence of humidity on the insulation and voltage of electrical equipment also needs to be considered. According to the relationship between humidity sensor data and the insulation resistance of electrical equipment, analyze the voltage change caused by leakage. At the same time, consider the influence of weather such as freezing rain that may occur in winter on the line. Monitor the occurrence of freezing rain through meteorological data, and analyze the influence of the ice layer formed by freezing rain on the line weight, tension, and resistance, and then determine the influence on the distribution transformer voltage. For mountainous areas, establish a correlation model between winter line icing and voltage drop. Assume the icing thickness is d, and there is a functional relationship between the voltage drop amount Δ∪ice and d n 1 、n 2 are coefficients obtained through experiment and data analysis. Obtain the icing thickness data through icing monitoring sensors installed on the line, and evaluate the voltage change trend in real time

[0085] III. Voltage simulation gear shifting decision-making and implementation

[0086] According to the analysis results of seasonal regional characteristics, train and optimize the distribution transformer voltage simulation gear shifting model. During the training process, divide the historical data into a training set, a validation set, and a test set according to a certain ratio. 70% of the data is used for training, 20% for validation, and 10% for testing. Use the training set data to train the gear shifting model, and adjust the parameters of the model such as the number of hidden layer nodes and learning rate of the neural network through the validation set to prevent overfitting. Finally, use the test set to evaluate the performance of the model to ensure that the model has good generalization ability on new data

[0087] (1) Implementation in urban commercial areas in summer

[0088] When the temperature exceeds 30°C and the load increases beyond a certain threshold, the gear shifting model calculates the specific value by which the distribution transformer gear position needs to be raised based on real-time voltage data. Let the real-time voltage be ∪real, and the expected normal voltage range be [∪min, ∪max]. When ∪real < ∪min and the temperature and load meet the conditions, the gear shifting value Δy is calculated according to the gear shifting model. The gear shifting instruction is sent to the automatic gear shifting device of the distribution transformer through remote control, and the automatic gear shifting device accurately adjusts the gear position of the distribution transformer according to the instruction. During the gear shifting process, the signal quality of the communication network is monitored to ensure the accurate transmission of the instruction. At the same time, when the automatic gear shifting device of the distribution transformer executes the instruction, parameters such as the motor speed and torque are monitored to ensure the smoothness and accuracy of the gear position adjustment.

[0089] (2) Implementation in winter in mountainous areas:

[0090] When it is monitored that the ice thickness on the line reaches a certain value such as d ≥ d 0 , d 0 is the set threshold and the voltage drops significantly such as ΔU ice ≥ ΔU 0 , ΔU 0 is the voltage drop threshold, the gear shifting model determines the strategy of reducing the distribution transformer gear position to increase the voltage and implements remote gear shifting. During the gear shifting process, data such as voltage and current are continuously monitored, and the concept of confidence interval in probability theory is used to evaluate the reliability of the data. For example, for voltage data, if it exceeds the confidence interval, the gear shifting operation is suspended and the sensor and data acquisition system are checked for normality. At the same time, the voltage recovery situation after gear shifting is monitored. If the voltage fails to return to the normal range within the set time, the reason is re-analyzed, such as considering whether there are other unmonitored factors affecting the voltage, such as the impact of tower deformation caused by icing on line parameters.

[0091] IV. Feedback and Optimization

[0092] After the gear shifting is completed, the operating data fed back by the distribution transformer is received. If it is found that the voltage still does not reach the expected stable range, the reason is analyzed, which may be inaccurate model parameters or unconsidered factors. If the voltage fluctuates abnormally in a certain area after a summer rainstorm, it may be necessary to further consider the impact of rain on line leakage, and the seasonal area characteristics analysis and gear shifting model are optimized and adjusted accordingly. By adding new characteristic parameters such as rain conductivity to the model, the model is retrained and verified. At the same time, the accuracy of the data acquisition system is checked, such as whether the sensor fails due to being soaked by rain, and the faulty sensor is repaired or replaced.

[0093] Regularly evaluate and optimize the entire system, and adjust the data acquisition frequency, model parameters, etc. according to the actual operating conditions in different seasons and regions. After several winters of operation, it is found that some parameters in the mountain icing model in winter need to be fine-tuned according to the actual icing situation. By collecting more on-site data and experimental data, update the model parameters of the relationship between icing thickness and voltage drop to improve the accuracy of the next gear shift. At the same time, optimize the communication protocol and network configuration according to the operating conditions of the communication network, such as the number of signal interruptions and data transmission delays, to ensure the reliability of remote control and data feedback.

[0094] Through this embodiment, efficient and accurate transformer voltage regulation is achieved, that is, this embodiment verifies the effectiveness of the transformer voltage regulation method and system based on seasonal and regional characteristics described in this specification.

[0095] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0096] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] The above are only exemplary embodiments of the present invention, and the scope of the present invention cannot be limited thereby. That is, all equivalent changes and modifications made according to the teachings of the present invention still fall within the scope covered by the present invention. Those skilled in the art will easily think of other implementation schemes of the present invention after considering the specification and practicing the disclosure herein. The present invention aims to cover any variations, uses or adaptive changes of the present invention, and these variations, uses or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not recorded in the present invention. The specification and embodiments are only regarded as exemplary, and the scope and spirit of the present invention are defined by the claims.

Claims

1. A distribution transformer voltage adjustment method based on seasonal regional characteristics, characterized in that: Includes steps: S1. Obtain the historical data of distribution transformer voltage and real-time meteorological data, and analyze the typical power consumption characteristics of each season based on this to construct the seasonal characteristic vector S2. Obtain geographic information system data and load distribution data, and divide the distribution network into multiple regions based on this data. Then analyze the typical power consumption characteristics of each region to construct a regional feature vector S3. Obtaining distribution transformer equipment operation data and equipment environment data to construct a distribution transformer operation feature vector S4, based on the seasonal feature vector The regional feature vector and the distribution transformer operation characteristic vector Calculate the voltage adjustment value y and set the corresponding adjustment command y(t) to perform distribution transformer voltage adjustment.

2. A method for voltage adjustment of distribution transformers based on seasonal regional characteristics according to claim 1, characterized in that: The seasonal eigenvector Wherein, j represents the season number, and n represents the total number of characteristic parameters in the seasonal characteristic vector; The characteristic parameters in the seasonal characteristic vector include average temperature, high temperature duration, and daily load peak.

3. The method for voltage adjustment of distribution transformer based on seasonal regional characteristics according to claim 1 is characterized in that: The regional feature vector i represents the region type number, and m represents the total number of feature parameters in the region feature vector; The areas include urban areas, rural areas, coastal areas, and mountainous areas; The characteristic parameters in the regional characteristic vector include terrain height h, terrain slope α, and vegetation coverage β.

4. The method for voltage adjustment of distribution transformer based on seasonal regional characteristics according to claim 1 is characterized in that: The distribution transformer operation characteristic vector k represents the total number of characteristic parameters in the distribution transformer operation characteristic vector; The characteristic parameters in the distribution transformer operation characteristic vector include the three-phase voltage amplitude U, the phase difference θ between the three-phase voltages, the three-phase current I, the total harmonic distortion rate THD1 of the current, the active power P, the reactive power Q, the apparent power S, and the power factor Transformer winding temperature T winding , Transformer oil level L oil , vibration amplitude A vibration .

5. The method for voltage adjustment of distribution transformer based on seasonal regional characteristics according to claim 1 is characterized in that: The calculation of the voltage adjustment value y comprises the steps of: Obtain a preset neural network and input the seasonal feature vector into the neural network The regional feature vector and the distribution transformer operation characteristic vector Adjust the predicted value with output voltage Obtain a preset error function E and adjust the voltage prediction value based on it Correction is performed to obtain the actual voltage adjustment value y i ; The error function 6. A method for voltage adjustment of distribution transformers based on seasonal regional characteristics according to claim 5, characterized in that: The shift instruction y(t)=x(t)*h(t)+n(t), h(t) represents the transmitted signal, n(t) represents the channel impulse response, and x(t) represents the additive noise.

7. A method for voltage adjustment of distribution transformers based on seasonal regional characteristics according to claim 6, characterized in that: Step S4 further includes the following steps: Get the expected voltage value U e and the feedback voltage value U after the gear adjustment based on the gear adjustment instruction y(t) f ; Based on the expected voltage value U e and the feedback voltage value U f Calculate the gear adjustment effect evaluation index value Q. If the gear adjustment effect evaluation index value Q is greater than a preset threshold, optimize the voltage adjustment value y, and re-allocate the gear adjustment based on the optimized voltage adjustment value y to achieve the expected gear adjustment effect.

8. A distribution transformer voltage adjustment system based on seasonal regional characteristics, characterized in that: Used to implement the distribution transformer voltage adjustment method as described in any one of claims 1 to 7.

9. A computer device, comprising a memory, a processor and a computer program, characterized in that: When the computer program is executed by a processor, the distribution transformer voltage adjustment method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the distribution transformer voltage adjustment method according to any one of claims 1 to 7 is implemented.

Images