A Distribution Network Regulation Method Based on a Multi-Objective Optimization Dynamic Aggregation Strategy

Abstract

The present invention provides a distribution network regulation method based on a multi-objective optimization dynamic aggregation strategy, which relates to the technical field of power system automation and control. The method includes: collecting in real time the voltage, current, power, active and reactive power, and harmonic operation data of each key node of the distribution network, and preprocessing the operation data to obtain processed data; constructing an initial optimization model including multiple optimization objectives according to the processed data; adjusting and determining the weights and priorities of each optimization objective according to the current operation state of the distribution network and each optimization objective to obtain a multi-objective optimization model optimized by weights. The present invention comprehensively improves the voltage quality of the distribution network, reduces network losses, promotes the consumption of renewable energy, enhances power supply reliability, and effectively reduces carbon emissions by dynamically constructing a multi-objective model optimized by weights, generating and executing precise regulation instructions, and real-time evaluation and closed-loop adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation and control, and particularly to a distribution network regulation method based on a multi-objective optimization dynamic aggregation strategy. Background Art

[0002] Traditional regulation strategies strive to reduce the energy loss of the power grid during the process of power transmission and distribution by means of adjusting the voltage level, optimizing the power flow distribution, etc., so as to improve the overall energy efficiency. In order to ensure the power supply quality and system safety, traditional methods will closely monitor the voltage fluctuations and ensure that the voltage level is stable within the allowable range by adjusting the reactive power compensation, transformer tap position, etc. For fault recovery and power supply reliability, traditional strategies focus on quickly locating the fault point, isolating the fault area and restoring power supply to reduce the time affected by users.

[0003] However, in the actual operation of the distribution network, the optimization of these single objectives has been difficult to meet the increasingly complex and changeable challenges, specifically including:

[0004] With the changes in users' electricity consumption behaviors, the influence of seasonal climates, and the fluctuations in industrial production, the load of the distribution network shows a high degree of uncertainty and dynamics, which puts higher requirements on the flexibility and response speed of the power grid. Some equipment in the distribution network gradually ages due to long-term use, which not only affects the power supply reliability, but also may increase the failure rate and maintenance cost, posing a threat to the overall performance and safety of the power grid. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a distribution network regulation method based on a multi-objective optimization dynamic aggregation strategy, which improves the comprehensive benefit of the distribution network operation by dynamically adjusting and optimizing the weights and relationships between multiple regulation objectives.

[0006] To solve the above technical problem, the technical solution of the present invention is as follows:

[0007] In a first aspect, a distribution network regulation method based on a multi-objective optimization dynamic aggregation strategy, the method includes:

[0008] Real-time collect the voltage, current, power, active and reactive power, harmonic operation data of each key node of the distribution network, and preprocess the operation data to obtain processed data;

[0009] According to the processed data, construct an initial optimization model including multiple optimization objectives; according to the current operation state of the distribution network and each optimization objective, adjust and determine the weights and priorities of each optimization objective to obtain a multi-objective optimization model optimized by weights;

[0010] Solve the multi-objective optimization model to obtain a distribution network regulation plan;

[0011] Generate control commands according to the distribution network control plan and send the control commands to the corresponding control devices; wherein, the control commands include adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer tap changers, and optimizing load distribution.

[0012] Conduct real-time evaluation on the distribution network after executing the control commands, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions, and obtain the evaluation results.

[0013] Adjust the parameters and weights of the multi-objective optimization model according to the evaluation results to match the current operating state of the distribution network.

[0014] Furthermore, construct an initial optimization model including multiple optimization objectives based on the processed data, including:

[0015] Integrate the processed electrical parameter data with relevant data to form a data set; wherein, the relevant data includes load forecasting, equipment status, and environmental factors.

[0016] Analyze the data set, identify key indicators and influencing factors related to the optimization objectives, and determine multiple optimization objectives.

[0017] Optimize multiple objectives through the initial optimization model and set constraint conditions, where the constraint conditions include voltage range, current limit, and equipment capacity.

[0018] Furthermore, adjust and determine the weights and priorities of each optimization objective according to the current operating state of the distribution network and each optimization objective to obtain a multi-objective optimization model optimized by weights, including:

[0019] For each optimization objective, define a corresponding objective function to quantify the implementation effect of each optimization objective.

[0020] Evaluate the urgency and importance of each optimization objective according to the current operating state of the distribution network to obtain the evaluation results.

[0021] Adjust the weights of each optimization objective according to the evaluation results, and rank the priorities of each optimization objective according to the adjusted weights to obtain a multi-objective optimization model optimized by weights.

[0022] Furthermore, solve the multi-objective optimization model optimized by weights to obtain the distribution network control plan, including:

[0023] Convert the format of the multi-objective optimization model optimized by weights and configure the parameters of the linear programming solver, where the parameters of the linear programming solver include solution accuracy, iteration number limit, and time limit.

[0024] The linear programming solver iteratively solves the transformed multi-objective optimization model, traverses the feasible solution space until the preset number of iterations is reached, and obtains the solution result.

[0025] Further, solving the multi-objective optimization model after weight optimization to obtain a distribution network control scheme further includes:

[0026] The linear programming solver outputs the solution result, analyzes the solution result, extracts the final values of the optimization variables, and corresponds the final values to the operation instructions in the distribution network control scheme;

[0027] According to the final values, a distribution network control scheme is generated, and the distribution network control scheme includes adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer tap positions, and optimizing load distribution.

[0028] Further, the distribution network after executing the control instructions is evaluated in real time, and the changes of key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions are monitored and analyzed to obtain the evaluation result, including:

[0029] Using smart meters and voltage monitoring systems, the voltage level data of each node in the distribution network is monitored in real time, and it is judged whether the voltage is within the range to identify whether there is overvoltage or undervoltage;

[0030] Based on the voltage level data and relevant parameters, the power loss of the distribution network is calculated to evaluate the impact of the control instructions on the network loss; the relevant parameters include current data, line parameters, transformer parameters, and load data; based on the renewable energy and its consumption in the distribution network, the utilization rate and grid connection performance of renewable energy are evaluated, where the renewable energy includes the power generation of solar energy and wind energy; the key indicators such as the number of power outages and the duration of power outages are counted to evaluate the reliability and stability of the power supply system; according to the operation data and energy consumption of the distribution network, the carbon emissions are calculated to evaluate the impact of the distribution network operation on the environment, so as to obtain the monitoring and analysis results of the distribution network performance, renewable energy utilization, power supply reliability, and environmental impact.

[0031] In a second aspect, a distribution network control system based on a multi-objective optimization dynamic aggregation strategy is applied to the distribution network control method based on the multi-objective optimization dynamic aggregation strategy, and includes:

[0032] An acquisition module, configured to collect in real time the voltage, current, power, active and reactive power, and harmonic operation data of each key node of the distribution network, and preprocess the operation data to obtain processed data; construct an initial optimization model including multiple optimization objectives according to the processed data; adjust and determine the weights and priorities of each optimization objective according to the current operation state of the distribution network and each optimization objective to obtain a multi-objective optimization model optimized by weights; solve the multi-objective optimization model to obtain a distribution network control scheme;

[0033] A processing module, configured to generate a control instruction according to the distribution network control scheme and send the control instruction to the corresponding control device; wherein, the control instruction includes adjusting the output power of the distributed power source, switching the capacitor bank, adjusting the transformer tap, and optimizing the load distribution; perform real-time evaluation on the distribution network after executing the control instruction, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions to obtain an evaluation result; adjust the parameters and weights of the multi-objective optimization model according to the evaluation result to match the current operation state of the distribution network.

[0034] In a third aspect, a computing device includes:

[0035] One or more processors;

[0036] A storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the one or more processors to implement the method described above.

[0037] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described above is implemented.

[0038] The above solution of the present invention has at least the following beneficial effects:

[0039] By collecting and processing in real time the operation data of each key node of the distribution network, the real-time state of the power grid can be accurately grasped, and then a multi-objective optimization model can be constructed and solved to generate a targeted control scheme. This helps to quickly respond to challenges such as load fluctuations and equipment aging, maintain voltage stability, reduce power outage time, and thus improve power supply quality and user satisfaction.

[0040] Considering the renewable energy consumption rate as one of the optimization objectives in the optimization model and dynamically adjusting its weight according to the current operating state can effectively promote the access and consumption of renewable energy. This helps reduce the dependence on fossil energy, lower carbon emissions, and drive the development of the distribution network towards green and low-carbon directions. By constructing a multi-objective optimization model that includes minimizing network losses, this method can effectively reduce the energy losses in the power grid during the process of transmitting and distributing electrical energy while ensuring power supply quality. This helps improve overall energy efficiency, reduce energy waste, and provide strong support for energy conservation and consumption reduction in the distribution network.

[0041] Adopt a dynamic aggregation strategy to flexibly adjust the weights and priorities of each objective according to the current operating state of the distribution network and the importance of each optimization objective. This enables the control scheme to better meet the actual operating requirements and enhances the adaptability and flexibility of the distribution network to changes such as load fluctuations and renewable energy access. By conducting real-time evaluation of the distribution network after executing the control instructions and adjusting the optimization model and aggregation strategy according to the evaluation results, this method can form a closed-loop optimization mechanism. This helps continuously improve the control effect and enhance the overall performance and optimization level of the distribution network. Brief Description of the Drawings

[0042] Figure 1 is a schematic flow chart of a distribution network control method based on a multi-objective optimization dynamic aggregation strategy provided by an embodiment of the present invention.

[0043] Figure 2 is a schematic diagram of a distribution network control system based on a multi-objective optimization dynamic aggregation strategy provided by an embodiment of the present invention. Detailed Embodiments

[0044] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0045] As Figure 1 shown, an embodiment of the present invention proposes a distribution network control method based on a multi-objective optimization dynamic aggregation strategy, and the method includes the following steps:

[0046] Step 11, collect the voltage, current, power, active and reactive power, and harmonic operation data of each key node of the distribution network in real time, and preprocess the operation data to obtain processed data;

[0047] Step 12: Construct an initial optimization model with multiple optimization objectives based on the processed data; adjust and determine the weights and priorities of each optimization objective according to the current operating state of the distribution network and each optimization objective, so as to obtain a multi-objective optimization model with optimized weights.

[0048] Step 13: Solve the multi-objective optimization model to obtain a distribution network control scheme.

[0049] Step 14: Generate control instructions according to the distribution network control scheme and send the control instructions to the corresponding control devices; wherein, the control instructions include adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer tap positions, and optimizing load distribution.

[0050] Step 15: Conduct real-time evaluation on the distribution network after executing the control instructions, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions to obtain an evaluation result.

[0051] Step 16: Adjust the parameters and weights of the multi-objective optimization model according to the evaluation result to match the current operating state of the distribution network.

[0052] In the embodiment of the present invention, by collecting data in real time, constructing an optimization model and solving it, the operating state of the distribution network can be accurately controlled, the voltage stability can be improved, the network loss can be reduced, and the overall operating efficiency can be enhanced. Promote the consumption of renewable energy: The optimization model considers the renewable energy consumption rate as one of the optimization objectives, which helps to maximize the utilization of renewable energy and reduce the dependence on traditional energy. By monitoring and analyzing key indicators in real time, potential problems can be discovered and solved in a timely manner to ensure the stable operation and reliable power supply of the distribution network. The optimization model considers the carbon emissions as one of the optimization objectives, which helps to reduce the carbon emissions during the operation of the distribution network and achieve the environmental protection and sustainable development goals. By real-time evaluating and adjusting the model parameters and weights, the changes in the operating state of the distribution network can be dynamically adapted to ensure the continuous effectiveness and accuracy of the optimized control strategy.

[0053] In a preferred embodiment of the present invention, the above Step 11 of collecting the voltage, current, power, active and reactive power, and harmonic operation data of each key node of the distribution network in real time and preprocessing the operation data to obtain the processed data may include:

[0054] Install high-precision and highly reliable sensors and measurement devices at each key node of the distribution network (such as substations, feeder ends, important users, etc.). These devices can collect electrical parameters such as voltage, current, power, as well as power quality indicators such as harmonics in real time. The collected data is transmitted to the data center via wired or wireless means. Encryption and compression technologies are adopted during the transmission process to ensure data security and transmission efficiency. The database has high concurrent read and write capabilities and can support real-time storage and query of a large amount of data. Clean the collected data to remove outliers, duplicate values, and missing values. Outliers are generated due to reasons such as equipment failures and data transmission errors and need to be identified and removed through statistical methods or machine learning algorithms.

[0055] Calibrate the cleaned data to ensure data accuracy and consistency. The calibration process includes operations such as time synchronization and value correction to eliminate measurement differences between different devices. For example, convert analog signals to digital signals or uniformly format the data of different devices. Extract useful feature information from the converted data, such as voltage fluctuations and current harmonic content. The data collection and preprocessing process need to be carried out in real time to ensure that the control center can timely obtain the current state of the distribution network.

[0056] When specifically applied, the above content specifically includes:

[0057] At key positions in the substation, such as incoming and outgoing lines, busbars, transformers, etc., install equipment such as voltage sensors, current sensors, power factor meters, etc. to collect electrical parameters such as voltage, current, and power in real time. At the end of the feeder, install equipment such as voltage monitors and current monitors to monitor the voltage and current conditions at the end of the feeder. At the incoming line of important users, install power quality monitors to monitor power quality indicators such as voltage fluctuations and harmonics in real time. These devices should all use products with high precision and high reliability to ensure the accuracy of the collected data. Set appropriate collection frequencies according to actual needs, such as collecting once per minute or multiple times per second, including electrical parameters such as voltage, current, power, active and reactive power, harmonics, and power quality indicators. The collected data is stored in the memory of the device or transmitted to the data center in real time via wired or wireless means. Use wired (such as optical fiber) or wireless (such as wireless private network) means to transmit data to the data center. Optical fiber transmission has the characteristics of high speed, stability, and strong anti-interference ability, and is suitable for long-distance and large-data-volume transmission; wireless private networks are suitable for occasions where it is difficult to lay optical fibers, such as remote areas or mobile devices. During the data transmission process, use encryption technology (such as the AES encryption algorithm) to encrypt the data to ensure that the data is not stolen or tampered with during transmission. Specifically, group the plaintext data in 128-bit (16-byte) blocks. If the length of the plaintext is not an integer multiple of 16, padding operations are required. Expand the initial key into multiple round keys for encryption together with the plaintext. The AES algorithm supports three key lengths: 128 bits, 192 bits, and 256 bits. For different key lengths, the 128-bit key requires 10 rounds of expansion, the 192-bit key requires 12 rounds of expansion, and the 256-bit key requires 14 rounds of expansion. Each round of encryption contains four operations: SubBytes, ShiftRows, MixColumns, and AddRoundKey.

[0058] SubBytes (Byte Substitution), replaces the input 16 bytes with new 16 bytes by looking up a table. The table used is called the S-box, which is a fixed-size table consisting of 256 bytes. ShiftRows (Row Shifting), divides the plaintext into four rows and then performs a circular shift on each row. The first row remains unchanged, the second row is circularly shifted left by one byte, the third row is circularly shifted left by two bytes, and the fourth row is circularly shifted left by three bytes. MixColumns (Column Mixing), performs a confusion operation on each column to change the structure of the plaintext. A fixed matrix is used for the transformation to replace each column with another column. AddRoundKey (Round Key Addition), performs an exclusive OR operation between the expanded round key and the plaintext to obtain the encrypted intermediate result. After multiple rounds of encryption, the final encrypted result (ciphertext) is obtained. If the plaintext has undergone a padding operation, the padding part needs to be removed during decryption to restore the original plaintext. The use of encryption technology should follow relevant security standards and specifications to ensure the security of data transmission. To improve transmission efficiency, compression technology can be used to compress the data. Compression technology can reduce the amount of data, reduce transmission latency and bandwidth occupancy, and improve the real-time performance and reliability of data transmission.

[0059] In the data center, preprocess the received data, including data cleaning, format conversion, etc. Data cleaning refers to removing noise and irrelevant information from the data and retaining useful information; during the data preprocessing process, outliers need to be identified and removed. Outliers may be caused by equipment failures, data transmission errors, etc. Statistical methods (such as the 3σ principle) are used to identify and remove outliers. Specifically, for a given data set, first calculate its mean and standard deviation. According to the 3σ principle, the range of outliers is determined to be data values outside [μ - 3σ, μ + 3σ], where μ represents the mean. That is, if a data value is less than μ - 3σ or greater than μ + 3σ, it is considered an outlier. Traverse the data set and for each data value, determine whether it belongs to the outlier range. If it belongs to the outlier range, remove the data value from the data set. After removing the outliers, update the data set.

[0060] Suppose there is a data set containing 10 data values:

[0061] [10, 12, 13, 13, 12, 10, 104, 11, 12, 15].

[0062] Mean = (10 + 12 + 13 + 13 + 12 + 10 + 104 + 11 + 12 + 15) / 10 = 19.6;

[0063] (rounded to two decimal places);

[0064] Outlier range = [19.6 - 329.96, 19.6 + 329.96] ≈ [-70.28, 119.56] (rounded to two decimal places). It can be seen that 104 is not within this range. However, since we are in an example, it is obvious that 104 is far from the data values, so it should be regarded as an outlier. Traversing the data set, it is found that 104 is an outlier and is removed. The updated data set is: [10, 12, 13, 13, 12, 10, 11, 12, 15].

[0065] For example, when the voltage data of a certain node suddenly deviates from the normal range, it can be judged as an outlier and removed.

[0066] Taking a certain urban distribution network as an example, high-precision and high-reliability sensors and measurement devices are installed at positions such as substations, the ends of feeders, and important users in this distribution network. These devices collect electrical parameters such as voltage, current, power, and power quality indicators such as harmonics in real time, and transmit the data to the data center through optical fibers and wireless private networks. During the data transmission process, the AES encryption algorithm is used to encrypt the data to ensure the security of data transmission. At the same time, in order to improve the transmission efficiency, compression technology is used to compress the data. In the data center, after preprocessing and outlier removal of the received data, accurate and reliable data support is obtained. These data are used for aspects such as optimization decision-making, fault diagnosis, energy efficiency evaluation, and load forecasting, providing strong guarantee for the intelligent management of the distribution network.

[0067] Calibrate the cleaned data to ensure the accuracy and consistency of the data. The calibration process includes operations such as time synchronization and value correction to eliminate measurement differences between different devices. Convert the calibrated data into a format suitable for subsequent processing and analysis. For example, convert analog signals into digital signals, or uniformly format the data of different devices. Extract useful feature information from the converted data, such as voltage fluctuations and current harmonic contents.

[0068] In a preferred embodiment of the present invention, step 12, constructing an initial optimization model including multiple optimization targets according to the processed data, may include:

[0069] Step 121, integrating the processed electrical parameter data with relevant data to form a data set; wherein, the relevant data includes load forecasting, equipment status, and environmental factors;

[0070] Step 122, analyzing the data set, identifying key indicators and influencing factors related to the optimization targets, and determining multiple optimization targets;

[0071] Step 123, optimizing multiple targets through the initial optimization model and setting constraint conditions, where the constraint conditions include voltage range, current limit, and equipment capacity.

[0072] In the embodiments of the present invention, the processed electrical parameter data includes operation data such as voltage, current, power, active power, reactive power, and harmonics. It is collected in real time by sensors and undergoes cleaning and calibration processes. Based on historical load data and weather forecasts, a time series analysis method is used for load forecasting to obtain the load demand for a period of time in the future, including the states (such as operation, fault, and maintenance states) of equipment such as transformers, switches, and lines, as well as their historical performance records. Environmental factor data, such as meteorological data like temperature, humidity, and wind speed, which affect the load and equipment performance of the distribution network.

[0073] Specifically, collect the power load data for a past period of time, recorded in hours or minutes, including the total load, sub-region loads, etc. Collect weather data related to the load, such as temperature, humidity, precipitation, wind speed, etc., from meteorological stations or weather APIs. Use chart tools to plot the time series graphs of the load and weather data, and observe the trend, seasonal, and periodic characteristics of the data. Calculate the correlation coefficients between the load and weather variables (such as temperature, humidity, etc.) to identify the key weather factors affecting the load.

[0074] According to the data characteristics, determine the autoregressive integrated moving average model, divide the data set into a training set and a test set, and divide them in chronological order (for example, the first 80% of the data is used as the training set, and the last 20% is used as the test set). Determine the model input features, including historical load values and relevant weather data. Use the autoregressive integrated moving average model and the training set data for model fitting, and adjust the model parameters to optimize the prediction effect. Use the trained model to predict the load demand for the test set. Calculate the prediction performance indicators of the model, including the root mean square error. The calculation formula for the mean square error is: where MSE represents the mean square error; n represents the number of samples; represents the predicted value; y i represents the actual value.

[0075] For each sample point i, calculate the difference between the predicted value and the actual value y i , that is This difference represents the prediction error of the model at this sample point. Square each error, that is The purpose of squaring is to eliminate the influence of negative errors on the sum, and make the contribution of large errors to the sum greater, so as to more prominently show the performance of the model on large errors. Sum the squared errors of all sample points, that is This step obtains the sum of the squared errors at all sample points. Divide the sum of the squared errors by the number of samples n, that is This step is to obtain the squared error at each sample point on average, so as to more objectively evaluate the overall prediction performance of the model. According to the evaluation results, the model is tuned, such as adjusting model parameters, adding features, changing the model structure, etc.

[0076] Train and evaluate repeatedly until the final model is found. Deploy the trained model to actual applications for load forecasting. Monitor the prediction effect of the model and update the model in a timely manner to adapt to data changes. Use the final model combined with the latest weather prediction data to predict the load demand for a period of time in the future. Use charts to show the comparison between the actual load and the predicted load for easy observation of the prediction effect of the model. Apply the load forecasting results to power dispatching, load management, demand response and other fields to optimize the allocation of power resources. Horizontally integrate the processed electrical parameter data with load forecasting, equipment status and environmental factor data to form a multi-dimensional data set. Conduct preliminary analysis on the data to observe the relationships between various parameters, identify trends and patterns. Determine the correlations between electrical parameters, load demand, equipment status and environmental factors, and identify the important factors affecting the operation of the power grid.

[0077] According to the analysis results, clarify multiple optimization objectives, such as: maximizing the renewable energy consumption rate, minimizing voltage fluctuations, minimizing network losses, improving power supply reliability, reducing carbon emissions. Prioritize the optimization objectives according to the actual application scenarios and business requirements. Build an initial optimization model according to multiple optimization objectives. For example: f(x) = w1f1(x) + w2f2(x) + w3f3(x) + w4f4(x) + w5f5(x); where, f(x) represents the objective of the entire optimization model; w1 represents the weight coefficient of the renewable energy power generation; f1(x) represents the renewable energy power generation; w2 represents the weight coefficient of the voltage fluctuation range; f2(x) represents the voltage fluctuation range; w3 represents the weight coefficient of the transmission loss; f3(x) represents the transmission loss; w4 represents the weight coefficient of the number of power supply interruptions; f4(x) represents the number of power supply interruptions; w5 represents the weight coefficient of the system carbon emissions; f5(x) represents the system carbon emissions. Ensure that the voltage at each node in the distribution network is within the specified range. For example, set the voltage range to [0.95, 1.05] p.u. Ensure that the current in each line does not exceed the rated capacity. Set the current upper limit for each line, such as I ≤ I max . Consider the capacity limitations of equipment such as transformers and switches to ensure that the regulation plan is within the equipment's carrying capacity, that is: where, V min represents the minimum constraint value of the node voltage; V c represents the voltage value of the c-th node in the distribution network; V max represents the maximum constraint value of the node voltage; I represents the current value of any line in the distribution network; I maxrepresents the maximum current value of the line; P represents the power value transmitted through devices (such as transformers, switches, etc.); P y represents the maximum capacity constraint of the device.

[0078] By integrating the processed electrical parameter data with relevant data (such as load forecasting, device status, environmental factors), a dataset containing multi-dimensional information is formed. This data integration enables the optimization model to comprehensively consider the operating status and external conditions of the distribution network, thereby improving the accuracy and practicality of the optimization results. After in-depth analysis of the dataset, the problems existing in the operation of the distribution network and potential optimization spaces can be more clearly identified. This helps to determine multiple optimization targets with clear directions, such as improving voltage stability, reducing network losses, increasing the renewable energy consumption rate, etc. These clear targets provide a clear direction for the construction of the optimization model. The initial optimization model constructed according to multiple optimization targets comprehensively considers various aspects and requirements of the distribution network. This scientific model construction method can ensure that the optimization scheme can achieve the optimization of multiple targets as much as possible while meeting the constraint conditions, thereby improving the overall performance of the distribution network. The constraint conditions (such as voltage range, current limit, device capacity, etc.) set in the optimization process ensure the feasibility and practicality of the optimization scheme. By optimizing multiple targets through the initial optimization model, the operation efficiency, stability and sustainability of the distribution network can be improved. For example, the voltage stability after optimization is improved, the network losses are reduced, the renewable energy consumption rate is increased, the power supply reliability is enhanced, the carbon emissions are reduced, etc. These optimization effects contribute to the efficient and stable operation of the distribution network.

[0079] In another preferred embodiment of the present invention, in step 12 above, according to the operating status of the current distribution network and each optimization target, adjusting and determining the weights and priorities of each optimization target to obtain a multi-objective optimization model optimized by weights may further include:

[0080] Step 124, for each optimization target, defining a corresponding objective function to quantify the implementation effect of each optimization target;

[0081] Step 125, according to the operating status of the current distribution network, evaluating the urgency and importance of each optimization target to obtain an evaluation result;

[0082] Step 126, according to the evaluation result, adjusting the weights of each optimization target, and sorting the priorities of each optimization target according to the adjusted weights to obtain a multi-objective optimization model optimized by weights.

[0083] In the embodiments of the present invention, a quantitative objective function is established for each optimization target so that it can be analyzed and optimized through a mathematical model. These objective functions can effectively reflect the implementation effects of each target. For example: Among them, f1(x) represents the power generation of renewable energy; P r represents the total power generated by renewable energy (such as solar energy, wind energy, water energy, etc.); P t represents the power that the distribution network can provide within a specific time period. f2(x) = max(V c ) - min(V c ); among them, f2(x) represents the voltage fluctuation range; min(V c ) represents the minimum constraint value of the node voltage; V c represents the voltage value of the c-th node in the distribution network; max(V c ) represents the maximum constraint value of the node voltage. f3(x) = ∑P s ; among them, f3(x) represents the transmission loss; P s represents the loss power. f4(x) = R; where f4(x) represents the number of power supply interruptions; R represents the power outage frequency, average power outage duration, and number of power supply interruptions. f5(x) = ∑CO2; where f5(x) represents the system carbon emissions; ∑CO2 represents the total amount of carbon dioxide emitted by each power generation source in the distribution network during the power generation process. According to the actual operation status of the distribution network, analyze and evaluate the urgency and importance of each optimization objective. According to the evaluation method, score each optimization objective to form an evaluation result. For example, adopt a scoring system of 1 - 5, where 5 represents very important and 1 represents unimportant:

[0084] The optimization objectives are: maximizing the renewable energy consumption rate, minimizing the voltage fluctuation, minimizing the network loss, and improving the power supply reliability. The corresponding importance scores are: 4, 5, 3, 5, 4. According to the evaluation result, adjust the weights of each optimization objective. The setting of the weights should reflect the importance and urgency of each objective. The adjustment steps include: normalizing the evaluation result to ensure that all weights are compared under the same standard. According to the importance of each objective, assign corresponding weights to each objective to ensure that the sum of the overall weights is 1. After the weight adjustment is completed, sort the optimization objectives by priority. It can be sorted from high to low according to the weights to form a priority list. For example: the weight of minimizing the voltage fluctuation is 0.25, so the priority is 1; the weight of improving the power supply reliability is 0.25, so the priority is 2. The weight of maximizing the renewable energy consumption rate is 0.20; so the priority is 3. The weight of reducing carbon emissions is 0.15, so the priority is 4. The weight of minimizing the network loss is 0.15, so the priority is 5. Integrate the objective function optimized by weights into a unified multi-objective optimization model. This model needs to consider the mutual influence of each objective and the comprehensive objective after the weight assignment.

[0085] By obtaining a multi-objective optimization model with optimized weights, renewable energy can be utilized more efficiently, dependence on traditional energy can be reduced, and environmental impact can be minimized. The stability of the grid voltage can be improved, voltage fluctuations can be reduced, and power quality can be ensured. The power loss of the grid can be reduced, energy efficiency can be increased, and operating costs can be lowered. By optimizing with priority given to power supply reliability, the frequency and duration of power outages can be reduced, and continuous and stable power supply to users can be guaranteed. Carbon dioxide emissions can be reduced, helping the distribution network to develop in a green and low-carbon direction, meeting environmental protection and energy conservation goals. According to the current operating state of the distribution network, the optimization objectives can be adjusted in a timely manner, and the most urgent problems (such as voltage instability or load overload) can be solved first, improving the emergency response ability of the system.

[0086] In a preferred embodiment of the present invention, step 13 of solving the multi-objective optimization model with optimized weights to obtain a distribution network regulation plan may include:

[0087] Step 131, convert the format of the multi-objective optimization model with optimized weights and configure the parameters of the linear programming solver. The parameters of the linear programming solver include the solution accuracy, the iteration number limit, and the time limit.

[0088] Step 132, the linear programming solver performs iterative solution on the converted multi-objective optimization model, traverses the feasible solution space until the preset number of iterations is reached, and obtains the solution result.

[0089] In the embodiment of the present invention, it is ensured that both the objective function and the constraint conditions can be adapted to the form of linear programming. All objective functions are converted into linear forms. It is ensured that all constraint conditions are linear expressions. Nonlinear constraints are linearized. The meaning, unit, and upper and lower bounds of each decision variable are defined. All variables must be within the feasible range. Appropriate parameters are configured in the solver to ensure the efficiency and accuracy of the solution process. The convergence criterion of the solution is determined, for example, the tolerances of the relative error and the absolute error are set. Set to 10 -6, to ensure the accuracy of the solution results. Set the upper limit of the number of iterations. For example, the maximum number of iterations can be set to 1000 times, or an appropriate value can be set according to historical solution experience. To prevent excessive solution time, the maximum allowable solution time (such as 300 seconds) can be set to ensure that the solution can be completed within a reasonable time. Input the transformed multi-objective optimization model into the linear programming solver and initialize all variables. The solver starts iterative solution and traverses the feasible solution space. In each iteration, the solver optimizes the objective function based on the current solution state and verifies the feasibility according to the constraint conditions. In each iteration, the solver needs to check whether the current solution meets the accuracy requirements. If the maximum number of iterations is reached, stop the iteration. During the iteration process, the solver needs to record the solution and the objective function value at each step and monitor the optimization progress. After the solution is completed, extract the final optimization results, including the optimal values of each decision variable and the corresponding objective function values. Check whether the solution results meet all constraint conditions. If not, analysis is required to determine whether the model needs to be adjusted or the parameters need to be reset. Based on the solution results, specific distribution network control measures are proposed. For example, adjust the access amount of renewable energy, optimize the load distribution, improve the voltage control strategy, etc. Organize the solution process, results and the corresponding distribution network control plan into a report for decision-makers to refer to.

[0090] By configuring power output, load distribution and equipment regulation, effectively improve the operation efficiency and reliability of the distribution network. An accurate control plan can reduce unnecessary energy losses, lower operating costs and bring economic benefits. By increasing the utilization rate of renewable energy, reduce dependence on fossil fuels and support the goal of sustainable development. Effective control measures help to stabilize the grid operation, reduce the risk of faults and improve the security of power supply. Through the analysis of the solution results, data-driven decision-making basis can be formed to improve the scientificity and effectiveness of the control strategy.

[0091] In another preferred embodiment of the present invention, step 13 of solving the multi-objective optimization model after weight optimization to obtain a distribution network control plan may further include:

[0092] Step 133, the linear programming solver outputs the solution results, analyzes the solution results, extracts the final values of the optimization variables, and corresponds the final values to the operation instructions in the distribution network control plan;

[0093] Step 134, generate a distribution network control plan according to the final values, and the distribution network control plan includes adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer tap positions, and optimizing load distribution.

[0094] In the embodiment of the present invention, after the solution is completed, the solver will generate the solution results, including the final values of each decision variable and the optimal value of the objective function (such as minimum loss or maximum economic benefit). Extract the final values of each decision variable from the solution results, and these values will directly affect the regulation operations of the distribution network. For example: the output power of distributed power sources, the quantity and type of switched capacitor banks, the tap position of transformers, and the specific strategy of load distribution. Organize the extracted optimization variables into an understandable format. Record the status and final results during the solution process. Generate specific operation instructions according to the optimization results. The instructions should clearly specify the specific output power value of each distributed power source, adjust the switching state of capacitor banks according to requirements to ensure the optimization of the system power factor, indicate the specific tap position and adjustment range to adapt to load changes, and formulate a specific load distribution strategy to ensure the reasonable distribution of load at each node. Organize the operation instructions into a distribution network regulation plan document, which includes regulation objectives and expected effects, operation steps and execution schedules, and the expected effects and monitoring indicators of each regulation measure. Implement the distribution network regulation measures according to the generated operation instructions, and continuously monitor the operation status of the distribution network to evaluate the effects of the regulation measures, including voltage stability, changes in system losses, and improvement in economic benefits.

[0095] By optimizing power output and load distribution, energy losses can be reduced. Adjusting the transformer taps and switching capacitor banks can effectively improve the voltage stability of the system and prevent the impact of too high or too low voltage on equipment. By adjusting the output power of distributed power sources, the utilization of renewable energy can be maximized, the dependence on fossil fuels can be reduced, and environmental protection goals can be supported. Use the optimization results to form a data-driven regulation plan to enhance the scientificity and effectiveness of regulation strategies. After implementing the regulation plan, continuously monitor the operation of the distribution network and collect data to evaluate the regulation effects. According to the gap between the actual operation results and the expected effects, timely adjust the parameters of the optimization model to improve the solution accuracy and practicality.

[0096] In a preferred embodiment of the present invention, in step 14 above, according to the distribution network regulation plan, generate regulation instructions and send the regulation instructions to the corresponding control devices; wherein, the regulation instructions include adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer taps, and optimizing load distribution, and may include:

[0097] The regulation plan includes adjusting the output power of distributed power sources, switching capacitor banks, and adjusting transformer taps. Collect parameters from the solution results of the multi-objective optimization model. These parameters include the target output power of distributed power sources, the state of capacitor banks (on or off), the tap position of transformers, and the specific situation of load distribution. For example, the optimization results may indicate:

[0098] The output power of the wind farm is set to 150 kw;

[0099] Switch on and off the capacitor bank 1, and turn off the capacitor bank 2;

[0100] Adjust transformer A to tap position 2.

[0101] Transfer a 20 - kw load from node 1 to node 2. Compile the control and regulation instructions according to the optimization results. The instructions should clearly indicate the type of distributed power source to be adjusted and the specific output power. For example, the instruction content is "Adjust the output power of the wind farm to 150 kW". For the switching state of the capacitor bank, the instruction should specify the number and state (on or off) of the specific capacitor bank. For example, the instruction content is "Switch on capacitor bank 1 and turn off capacitor bank 2". The instruction should include the specific transformer identification and the new tap position. For example, the instruction content is "Adjust the tap of transformer A to position 2". For the re - distribution of the load, the instruction should clearly state the source node, target node, and the amount of load transferred. For example, the instruction content is "Transfer the 20 - kW load at node 1 to node 2".

[0102] Collate the control and regulation instructions into a complete control and regulation instruction package to ensure that it contains all necessary instructions. The format of this package should be easy to parse and can be executed immediately after being sent. Determine the way to send the control and regulation instructions according to the architecture of the distribution network control system. Send the assembled control and regulation instructions to the corresponding control equipment through the determined method. After receiving the control and regulation instructions, the control equipment will return feedback information to confirm the execution status of the instructions. The feedback information includes whether the instruction execution is successful. If it fails, return the specific error information. If the feedback information shows that the instruction execution is successful, record the execution result and update the system status. If the instruction execution fails, analyze the failure reason and take corresponding measures, such as retrying to send the instruction or adjusting the strategy. After the instruction is executed, obtain the status information of each node and device in the distribution network in real - time through the monitoring system of the distribution network to ensure the normal operation of the system, including the monitoring of key parameters such as voltage, power, and load. According to the monitoring data, adjust the original control and regulation strategy and instructions when necessary to cope with possible emergencies and ensure the stability and efficiency of the system. Save the execution process of the control and regulation instructions, including the sending time, execution status, feedback information, etc.

[0103] In a preferred embodiment of the present invention, in step 15 above, perform a real - time evaluation on the distribution network after executing the control and regulation instructions, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions, and obtain the evaluation results, which may include:

[0104] Step 151, use smart meters and voltage monitoring systems to real - time monitor the voltage level data of each node in the distribution network, judge whether the voltage is within the range, and identify whether there is over - voltage or under - voltage conditions;

[0105] Step 152: Calculate the power loss of the distribution network based on the voltage level data and relevant parameters, and evaluate the impact of the regulation instructions on the network loss; the relevant parameters include current data, line parameters, transformer parameters, and load data; evaluate the utilization rate and grid connection performance of renewable energy based on the renewable energy and its consumption in the distribution network, where the renewable energy includes the power generation of solar energy and wind energy; count key indicators such as the number of power outages and the duration of power outages, and evaluate the reliability and stability of the power supply system; calculate the carbon emissions according to the operation data and energy consumption of the distribution network, and evaluate the impact of the distribution network operation on the environment, so as to obtain the monitoring and analysis results of the distribution network performance, renewable energy utilization, power supply reliability, and environmental impact.

[0106] In the embodiment of the present invention, intelligent meters and voltage monitoring systems are installed at the key nodes and user terminals of the distribution network to ensure that voltage level data can be obtained in real time. The distribution network monitoring system regularly collects the voltage data of each node from the intelligent meters. This includes measuring parameters such as instantaneous voltage and average voltage. Set the voltage range (such as ±10% of the rated voltage range). The monitoring system compares the current voltage data with the standard range in real time to identify whether there is overvoltage or undervoltage. The system records the time, duration, and severity of each voltage anomaly. Collect relevant parameters, including real-time current data from intelligent meters and transformers, line parameters such as the resistance and length of the line, and transformer parameters, such as the efficiency and capacity of the transformer.

[0107] The load conditions of each part of the system. Calculate the power loss as: P loss = I 2 ·R; where I represents the current; R represents the line resistance. Summarize the power losses of different nodes and evaluate the change in network loss before and after the execution of the regulation instructions. Collect the power generation data of solar energy and wind energy. These data are obtained through the intelligent monitoring systems of the photovoltaic power generation system and the wind turbine. Calculate the utilization rate of renewable energy as: where P represents the actual power generation; M represents the maximum power generation. Evaluate the grid connection performance of renewable energy in the distribution network according to the utilization rate of renewable energy, and analyze whether the grid connection of renewable energy causes voltage fluctuations or load imbalance. Count the number of power outage events and the duration of each power outage. Obtained through the fault recording function of the intelligent meter and the monitoring system. Collect the energy consumption data of the distribution network through the monitoring system, including the usage of various types of energy. Integrate all the data into a comprehensive monitoring platform, and conduct a comparative analysis of the voltage level, network loss, utilization rate of renewable energy, and power supply reliability. Generate an evaluation report according to the monitoring and analysis results, including the change of each index, the analysis of influencing factors, and corresponding suggestions and improvement measures.

[0108] Through real-time monitoring, overvoltage or undervoltage conditions can be detected in a timely manner, and corresponding measures can be taken for adjustment to ensure the stability of the voltage level. By comparing the power losses before and after the execution of the regulation instructions, the impact of the regulation instructions on network losses can be evaluated. If the network losses are reduced, it indicates that the regulation instructions have effectively optimized the operation of the distribution network. Evaluate the accommodation of renewable energy in the distribution network. By collecting the power generation data of solar energy and wind energy, the utilization rate and grid connection performance of renewable energy can be calculated. If the utilization rate of renewable energy increases, it indicates that the regulation instructions have promoted the accommodation of renewable energy, which helps to reduce the use of fossil energy and lower carbon emissions. Evaluate the reliability and stability of the power supply system by counting the number of power outages and the duration of power outages. If the number of power outages decreases and the duration of power outages shortens, it indicates that the regulation instructions have improved the power supply reliability and reduced the power outage time of users.

[0109] In another preferred embodiment of the present invention, according to the monitoring and analysis results of the distribution network performance, renewable energy utilization, power supply reliability and environmental impact, an evaluation result is generated. The evaluation result includes the change situation of each key index, the comparison with the expected target, the existing problems and improvement measures, and may include:

[0110] The distribution network performance data includes voltage level, power loss, network loss, etc. The renewable energy utilization data includes the actual power generation and grid connection situation of solar energy and wind energy, etc. The power supply reliability data includes the number of power outages, the duration of power outages, user complaints, etc. Judge the frequency and degree of voltage abnormalities. Generate a voltage fluctuation chart to show whether the voltage is within the expected range. Analyze the reasons for the reduction or increase of network losses. Compare the actual power generation with the expected power generation, and evaluate the grid connection performance of renewable energy in different time periods (such as peak periods and off-peak periods). Count the number of power outages and the duration of power outages. Analyze the root causes of power supply reliability problems through user feedback and complaint records. Set the expected targets for each key index. For example:

[0111] The voltage stability rate ≥ 95%;

[0112] The network loss rate ≤ 5%;

[0113] The utilization rate of renewable energy ≥ 30%.

[0114] The average power outage duration ≤ 1 hour. Compare the monitored key indexes with the expected targets to identify the gaps. Make a comparison chart to show the achievement of each index. Based on the comparison results, the reasons for the non-compliance of each index may be: voltage abnormalities may be caused by load fluctuations or line aging, the increase in network losses may be related to insufficient line maintenance or equipment failures, the low utilization rate of renewable energy may be affected by weather conditions, technical problems or grid connection policy restrictions, and the increase in power outage events may be related to equipment aging, insufficient maintenance or emergencies.

[0115] Regarding the voltage level issue, inspect and maintain the equipment at abnormal voltage nodes, and perform system upgrades if necessary. Adopt intelligent scheduling technology to optimize load distribution and ensure voltage stability. Regarding the network loss issue, regularly inspect and maintain the distribution network lines, and promptly replace aging equipment. Optimize the line design to reduce the line length and resistance and improve efficiency. Regarding the utilization of renewable energy, introduce new technologies to improve the grid connection capacity and power generation efficiency of renewable energy. Seek policy support to encourage the development and utilization of renewable energy and promote a higher proportion of renewable energy access. Regarding the power supply reliability issue, strengthen emergency management, formulate an emergency response plan, and improve the ability to respond to emergencies. Strengthen the communication and feedback mechanism with users and promptly solve the problems reflected by users.

[0116] In a preferred embodiment of the present invention, step 16 above, adjusting the parameters and weights of the multi-objective optimization model according to the evaluation results to match the current operating state of the distribution network may include:

[0117] Adjust the parameters of each objective function according to the evaluation results. For example: If the power loss is high, increase the weight of the power loss. If the utilization rate of renewable energy is insufficient, increase the weight of the utilization rate of renewable energy. Allocate the weights of each objective according to the actual operating conditions. Establish a feedback mechanism to monitor the operating state of the distribution network after the optimization is implemented to ensure that the optimization objectives are achieved. Regularly re-evaluate and adjust the model parameters and weights according to the new operating data and evaluation results to maintain the timeliness and effectiveness of the model.

[0118] As Figure 2 shown, an embodiment of the present invention further provides a distribution network regulation system 20 based on a multi-objective optimization dynamic aggregation strategy, including:

[0119] An acquisition module 21, configured to collect in real time the voltage, current, power, active and reactive power, and harmonic operation data of each key node of the distribution network, preprocess the operation data to obtain processed data; construct an initial optimization model including multiple optimization objectives according to the processed data; adjust and determine the weights and priorities of each optimization objective according to the current operating state of the distribution network and each optimization objective to obtain a multi-objective optimization model optimized by weights; solve the multi-objective optimization model to obtain a distribution network regulation plan;

[0120] A processing module 22, configured to generate control instructions according to the distribution network regulation scheme and send the control instructions to corresponding control devices; wherein, the control instructions include adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer tap changers, and optimizing load distribution; performing real-time evaluation on the distribution network after executing the control instructions, monitoring and analyzing the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions to obtain an evaluation result; adjusting the parameters and weights of the multi-objective optimization model according to the evaluation result to match the current operating state of the distribution network.

[0121] The system corresponds to the above method, and all implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0122] An embodiment of the present invention further provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0123] An embodiment of the present invention further provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is caused to execute the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0124] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A distribution network control method based on multi-objective optimization dynamic aggregation strategy, characterized in that: The method comprises: Collect voltage, current, power and harmonic operation data of key nodes of distribution network in real time, and pre-process the operation data to obtain processed data; Based on the processed data, an initial optimization model including multiple optimization objectives is constructed; based on the current operating status of the distribution network and each optimization objective, the weight and priority of each optimization objective are adjusted and determined to obtain a multi-objective optimization model with weight optimization; Solving the multi-objective optimization model to obtain a distribution network control plan includes: converting the format of the weight-optimized multi-objective optimization model and configuring the parameters of the linear programming solver, wherein the parameters of the linear programming solver include solution accuracy, iteration number limit, and time limit; solving the converted multi-objective optimization model by the linear programming solver, traversing the feasible solution space until a preset iteration number is reached to obtain a solution result; Generate control instructions according to the distribution network control plan, and send the control instructions to the corresponding control device; wherein the control instructions include adjusting the output power of the distributed power source, switching capacitor banks, adjusting transformer taps, and optimizing load distribution; Conduct real-time evaluation of the distribution network after executing the control instructions, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions, and obtain evaluation results; According to the evaluation results, the parameters and weights of the multi-objective optimization model are adjusted to match the current operating status of the distribution network. The adjustments to the parameters and weights of the multi-objective optimization model include increasing the weight of power loss, increasing the weight of renewable energy utilization, and allocating weights to each objective.

2. The distribution network control method based on multi-objective optimization dynamic aggregation strategy according to claim 1 is characterized in that: Based on the processed data, an initial optimization model with multiple optimization objectives is constructed, including: Integrate the processed electrical parameter data with related data to form a data set; wherein the related data includes load forecast, equipment status, and environmental factors; Analyze the data set, identify key indicators and influencing factors related to the optimization objectives, and determine multiple optimization objectives; Multiple objectives are optimized through a linear programming model, and constraints are set, including voltage range, current limit, and equipment capacity.

3. The distribution network control method based on multi-objective optimization dynamic aggregation strategy according to claim 2 is characterized in that: According to the current operating status of the distribution network and various optimization objectives, the weights and priorities of various optimization objectives are adjusted and determined to obtain a multi-objective optimization model with weight optimization, including: For each optimization goal, define the corresponding objective function to quantify the effect of achieving each optimization goal; According to the current operating status of the distribution network, the urgency and importance of each optimization target are evaluated to obtain the evaluation results; According to the evaluation results, the weight of each optimization objective is adjusted, and the optimization objectives are prioritized according to the adjusted weights to obtain a multi-objective optimization model with weight optimization.

4. The distribution network control method based on multi-objective optimization dynamic aggregation strategy according to claim 3 is characterized in that: Solve the weighted multi-objective optimization model to obtain the distribution network control plan, which also includes: The solver outputs the solution result, analyzes the solution result, extracts the final value of the optimization variable, and corresponds the final value to the operation instruction in the distribution network control scheme; A distribution network control scheme is generated according to the final value, wherein the distribution network control scheme includes adjusting the output power of distributed power sources, switching capacitor banks, adjusting transformer taps, and optimizing load distribution.

5. The distribution network control method based on multi-objective optimization dynamic aggregation strategy according to claim 4 is characterized in that: Conduct real-time evaluation of the distribution network after executing the control instructions, monitor and analyze the changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions, to obtain evaluation results, including: Using smart meters and voltage monitoring systems, the voltage level data of each node in the distribution network is monitored in real time, and it is determined whether the voltage is within the range and whether there is overvoltage or undervoltage. The power loss of the distribution network is calculated based on the voltage level data and related parameters, and the impact of the control instructions on the network loss is evaluated; the related parameters include current data, line parameters, transformer parameters, and load data; based on renewable energy and its absorption in the distribution network, the utilization rate and grid-connected performance of renewable energy are evaluated, wherein the renewable energy includes the power generation of solar energy and wind energy; the key indicators of the number of power outages and the duration of power outages are counted to evaluate the reliability and stability of the power supply system; according to the operating data and energy consumption of the distribution network, the carbon emissions are calculated, and the impact of the distribution network operation on the environment is evaluated, so as to obtain the monitoring and analysis results of the distribution network performance, renewable energy utilization, power supply reliability and environmental impact.

6. The distribution network control method based on multi-objective optimization dynamic aggregation strategy according to claim 5 is characterized in that: Based on the monitoring and analysis results of distribution network performance, renewable energy utilization, power supply reliability and environmental impact, an evaluation result is generated, which includes the changes in key indicators, comparison with expected goals, existing problems and improvement measures.

7. A distribution network control system based on a multi-objective optimization dynamic aggregation strategy, the system implementing the method as described in any one of claims 1 to 6, characterized in that: include: The acquisition module is used to collect the voltage, current, power and harmonic operation data of each key node of the distribution network in real time, and pre-process the operation data to obtain processed data; Based on the processed data, an initial optimization model including multiple optimization objectives is constructed; According to the current operating status of the distribution network and various optimization objectives, the weights and priorities of various optimization objectives are adjusted and determined to obtain a multi-objective optimization model with weight optimization; Solve the multi-objective optimization model to obtain the distribution network control plan; The processing module is used to generate control instructions according to the distribution network control plan, and send the control instructions to the corresponding control device; wherein the control instructions include adjusting the output power of distributed power sources, switching capacitor groups, adjusting transformer taps, and optimizing load distribution; performing real-time evaluation of the distribution network after executing the control instructions, monitoring and analyzing changes in key indicators such as voltage level, network loss, renewable energy consumption rate, power supply reliability, and carbon emissions, and obtaining evaluation results; according to the evaluation results, adjusting the parameters and weights of the multi-objective optimization model to match the current operating status of the distribution network.

8. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images